STARD 2015: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies

Best Practice for MRI Diagnostic Accuracy Research With Lessons and Examples from the LI-RADS Individual Participant Data Group

Medical imaging diagnostic test accuracy research is strengthened by adhering to best practices for study design, data collection, data documentation, and study reporting. In this review, key elements of such research are discussed, and specific recommendations provided for optimizing diagnostic accuracy study execution to improve uniformity, minimize common sources of bias and avoid potential pitfalls. Examples are provided regarding study methodology and data collection practices based on insights gained by the liver imaging reporting and data system (LI-RADS) individual participant data group, who have evaluated raw data from numerous MRI diagnostic accuracy studies for risk of bias and data integrity. The goal of this review is to outline strategies for investigators to improve research practices, and to help reviewers and readers better contextualize a study's findings while understanding its limitations. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 3.

Doug Altman, medical statistician par excellence: What can radiologists learn from his legacy?

This narrative review describes our experience of working with Doug Altman, the most highly cited medical statistician in the world. Doug was particularly interested in diagnostics, and imaging studies in particular. We describe how his insights helped improve our own radiological research studies and we provide advice for other researchers hoping to improve their own research practice.

Population-wide evaluation of artificial intelligence and radiologist assessment of screening mammograms

OBJECTIVES

To validate an AI system for standalone breast cancer detection on an entire screening population in comparison to first-reading breast radiologists.

MATERIALS AND METHODS

All mammography screenings performed between August 4, 2014, and August 15, 2018, in the Region of Southern Denmark with follow-up within 24 months were eligible. Screenings were assessed as normal or abnormal by breast radiologists through double reading with arbitration. For an AI decision of normal or abnormal, two AI-score cut-off points were applied by matching at mean sensitivity (AIsens) and specificity (AIspec) of first readers. Accuracy measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and recall rate (RR).

RESULTS

The sample included 249,402 screenings (149,495 women) and 2033 breast cancers (72.6% screen-detected cancers, 27.4% interval cancers). AIsens had lower specificity (97.5% vs 97.7%; p < 0.0001) and PPV (17.5% vs 18.7%; p = 0.01) and a higher RR (3.0% vs 2.8%; p < 0.0001) than first readers. AIspec was comparable to first readers in terms of all accuracy measures. Both AIsens and AIspec detected significantly fewer screen-detected cancers (1166 (AIsens), 1156 (AIspec) vs 1252; p < 0.0001) but found more interval cancers compared to first readers (126 (AIsens), 117 (AIspec) vs 39; p < 0.0001) with varying types of cancers detected across multiple subgroups.

CONCLUSION

Standalone AI can detect breast cancer at an accuracy level equivalent to the standard of first readers when the AI threshold point was matched at first reader specificity. However, AI and first readers detected a different composition of cancers.

CLINICAL RELEVANCE STATEMENT

Replacing first readers with AI with an appropriate cut-off score could be feasible. AI-detected cancers not detected by radiologists suggest a potential increase in the number of cancers detected if AI is implemented to support double reading within screening, although the clinicopathological characteristics of detected cancers would not change significantly.

KEY POINTS

• Standalone AI cancer detection was compared to first readers in a double-read mammography screening population. • Standalone AI matched at first reader specificity showed no statistically significant difference in overall accuracy but detected different cancers. • With an appropriate threshold, AI-integrated screening can increase the number of detected cancers with similar clinicopathological characteristics.

Nonaneurysmal perimesencephalic subarachnoid hemorrhage on noncontrast head CT: An accuracy, inter-rater, and intra-rater reliability study

BACKGROUND AND PURPOSE

To evaluate the reliability and accuracy of nonaneurysmal perimesencephalic subarachnoid hemorrhage (NAPSAH) on Noncontrast Head CT (NCCT) between numerous raters.

MATERIALS AND METHODS

45 NCCT of adult patients with SAH who also had a catheter angiography (CA) were independently evaluated by 48 diverse raters; 45 raters performed a second assessment one month later. For each case, raters were asked: 1) whether they judged the bleeding pattern to be perimesencephalic; 2) whether there was blood anterior to brainstem; 3) complete filling of the anterior interhemispheric fissure (AIF); 4) extension to the lateral part of the sylvian fissure (LSF); 5) frank intraventricular hemorrhage; 6) whether in the hypothetical presence of a negative CT angiogram they would still recommend CA. An automatic NAPSAH diagnosis was also generated by combining responses to questions 2-5. Reliability was estimated using Gwet's AC1 (κG), and the relationship between the NCCT diagnosis of NAPSAH and the recommendation to perform CA using Cramer's V test. Multi-rater accuracy of NCCT in predicting negative CA was explored.

RESULTS

Inter-rater reliability for the presence of NAPSAH was moderate (κG = 0.58; 95%CI: 0.47, 0.69), but improved to substantial when automatically generated (κG = 0.70; 95%CI: 0.59, 0.81). The most reliable criteria were the absence of AIF filling (κG = 0.79) and extension to LSF (κG = 0.79). Mean intra-rater reliability was substantial (κG = 0.65). NAPSAH weakly correlated with CA decision (V = 0.50). Mean sensitivity and specificity were 58% (95%CI: 44%, 71%) and 83 % (95%CI: 72 %, 94%), respectively.

CONCLUSION

NAPSAH remains a diagnosis of exclusion. The NCCT diagnosis was moderately reliable and its impact on clinical decisions modest.

Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography

BACKGROUND

Early identification of large vessel occlusion (LVO) in patients with ischemic stroke is crucial for timely interventions. We propose a machine learning-based algorithm (JLK-CTL) that uses handcrafted features from noncontrast computed tomography to predict LVO.

METHODS

We included patients with ischemic stroke who underwent concurrent noncontrast computed tomography and computed tomography angiography in seven hospitals. Patients from 5 of these hospitals, admitted between May 2011 and March 2015, were randomly divided into training and internal validation (9:1 ratio). Those from the remaining 2 hospitals, admitted between March 2021 and September 2021, were designated for external validation. From each noncontrast computed tomography scan, we extracted differences in volume, tissue density, and Hounsfield unit distribution between bihemispheric regions (striatocapsular, insula, M1-M3, and M4-M6, modified from the Alberta Stroke Program Early Computed Tomography Score). A deep learning algorithm was used to incorporate clot signs as an additional feature. Machine learning models, including ExtraTrees, random forest, extreme gradient boosting, support vector machine, and multilayer perceptron, as well as a deep learning model, were trained and evaluated. Additionally, we assessed the models' performance after incorporating the National Institutes of Health Stroke Scale scores as an additional feature.

RESULTS

Among 2919 patients, 83 were excluded. Across the training (n=2463), internal validation (n=275), and external validation (n=95) datasets, the mean ages were 68.5±12.4, 67.6±13.8, and 67.9±13.6 years, respectively. The proportions of men were 57%, 53%, and 59%, with LVO prevalences of 17.0%, 16.4%, and 26.3%, respectively. In the external validation, the ExtraTrees model achieved a robust area under the curve of 0.888 (95% CI, 0.850-0.925), with a sensitivity of 80.1% (95% CI, 72.0-88.1) and a specificity of 88.6% (95% CI, 84.7-92.5). Adding the National Institutes of Health Stroke Scale score to the ExtraTrees model increased sensitivity (from 80.1% to 92.1%) while maintaining specificity.

CONCLUSIONS

Our algorithm provides reliable predictions of LVO using noncontrast computed tomography. By enabling early LVO identification, our algorithm has the potential to expedite the stroke workflow.

Predicting autism traits from baby wellness records: A machine learning approach

LAY ABSTRACT

Timely identification of autism spectrum conditions is a necessity to enable children to receive the most benefit from early interventions. Emerging technological advancements provide avenues for detecting subtle, early indicators of autism from routinely collected health information. This study tested a model that provides a likelihood score for autism diagnosis from baby wellness visit records collected during the first 2 years of life. It included records of 591,989 non-autistic children and 12,846 children with autism. The model identified two-thirds of the autism spectrum condition group (boys 63% and girls 66%). Sex-specific models had several predictive features in common. These included language development, fine motor skills, and social milestones from visits at 12-24 months, mother's age, and lower initial growth but higher last growth measurements. Parental concerns about development or hearing impairment were other predictors. The models differed in other growth measurements and birth parameters. These models can support the detection of early signs of autism in girls and boys by using information routinely recorded during the first 2 years of life.

Evaluation of postoperative pancreatic fistula prediction scales following pancreatoduodenectomies based on magnetic resonance imaging: A diagnostic test study

BACKGROUND

Postoperative pancreatic fistula (POPF) is one of the most feared and common complications following pancreatoduodenectomies. This study aims to evaluate the performance of different scales in predicting POPF using magnetic resonance imaging (MRI), including estimation of the pancreatic duct diameter, pancreatic texture, main duct index, relation to the portal vein, and intra-abdominal fat thickness.

MATERIALS AND METHODS

A retrospective diagnostic test study was designed. Between January 2017 and December 2021, 133 pancreatoduodenectomies were performed at our institution. The performance for predicting overall POPF and clinically relevant POPF (CR-POPF) was evaluated using a receiver operating characteristic (ROC) curve.

RESULTS

A total of 96 patients were included in the study, of whom 26 patients experienced overall POPF, and 8 patients had CR-POPF. When analyzing the predictive value of each of the different scores applied, the Birmingham score showed the highest performance for predicting overall POPF and CR-POPF with an AUC (area under the curve) of 0.815 (95 % CI 0.725-0.906) and 0.813 (0.679-0.947), respectively.

CONCLUSION

The Birmingham scale demonstrated the highest predictive performance for POPF. It is a simple scale with only two variables that can be obtained preoperatively using MRI. Based on these results, we recommend its use in patients undergoing pancreatoduodenectomy.

Comparing the Diagnostic Performance of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and Radiologists in Challenging Neuroradiology Cases

PURPOSE

To compare the diagnostic performance among Generative Pre-trained Transformer (GPT)-4-based ChatGPT, GPT‑4 with vision (GPT-4V) based ChatGPT, and radiologists in challenging neuroradiology cases.

METHODS

We collected 32 consecutive "Freiburg Neuropathology Case Conference" cases from the journal Clinical Neuroradiology between March 2016 and December 2023. We input the medical history and imaging findings into GPT-4-based ChatGPT and the medical history and images into GPT-4V-based ChatGPT, then both generated a diagnosis for each case. Six radiologists (three radiology residents and three board-certified radiologists) independently reviewed all cases and provided diagnoses. ChatGPT and radiologists' diagnostic accuracy rates were evaluated based on the published ground truth. Chi-square tests were performed to compare the diagnostic accuracy of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and radiologists.

RESULTS

GPT‑4 and GPT-4V-based ChatGPTs achieved accuracy rates of 22% (7/32) and 16% (5/32), respectively. Radiologists achieved the following accuracy rates: three radiology residents 28% (9/32), 31% (10/32), and 28% (9/32); and three board-certified radiologists 38% (12/32), 47% (15/32), and 44% (14/32). GPT-4-based ChatGPT's diagnostic accuracy was lower than each radiologist, although not significantly (all p > 0.07). GPT-4V-based ChatGPT's diagnostic accuracy was also lower than each radiologist and significantly lower than two board-certified radiologists (p = 0.02 and 0.03) (not significant for radiology residents and one board-certified radiologist [all p > 0.09]).

CONCLUSION

While GPT-4-based ChatGPT demonstrated relatively higher diagnostic performance than GPT-4V-based ChatGPT, the diagnostic performance of GPT‑4 and GPT-4V-based ChatGPTs did not reach the performance level of either radiology residents or board-certified radiologists in challenging neuroradiology cases.

Machine learning-based response assessment in patients with rectal cancer after neoadjuvant chemoradiotherapy: radiomics analysis for assessing tumor regression grade using T2-weighted magnetic resonance images

PURPOSE

This study aimed to assess tumor regression grade (TRG) in patients with rectal cancer after neoadjuvant chemoradiotherapy (NCRT) through a machine learning-based radiomics analysis using baseline T2-weighted magnetic resonance (MR) images.

MATERIALS AND METHODS

In total, 148 patients with locally advanced rectal cancer(T2-4 or N+) who underwent MR imaging at baseline and after chemoradiotherapy between January 2010 and May 2021 were included. A region of interest for each tumor mass was drawn by a radiologist on oblique axial T2-weighted images, and main features were selected using principal component analysis after dimension reduction among 116 radiomics and three clinical features. Among eight learning models that were used for prediction model development, the model showing best performance was selected. Treatment responses were classified as either good or poor based on the MR-assessed TRG (mrTRG) and pathologic TRG (pTRG). The model performance was assessed using the area under the receiver operating curve (AUROC) to classify the response group.

RESULTS

Approximately 49% of the patients were in the good response (GR) group based on mrTRG (73/148) and 26.9% based on pTRG (28/104). The AUCs of clinical data, radiomics models, and combined radiomics with clinical data model for predicting mrTRG were 0.80 (95% confidence interval [CI] 0.73, 0.87), 0.74 (95% CI 0.66, 0.81), and 0.75(95% CI 0.68, 0.82), and those for predicting pTRG was 0.62 (95% CI 0.52, 0.71), 0.74 (95% CI 0.65, 0.82), and 0.79 (95% CI 0.71, 0.87).

CONCLUSION

Radiomics combined with clinical data model using baseline T2-weighted MR images demonstrated feasible diagnostic performance in predicting both MR-assessed and pathologic treatment response in patients with rectal cancer after NCRT.

Performance of AI to exclude normal chest radiographs to reduce radiologists' workload

INTRODUCTION

This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest radiographs and its potential to reduce radiologist workload.

METHODS

Retrospective analysis included consecutive chest radiographs from two medical centers between Oct 1, 2016 and Oct 14, 2016. Exclusions comprised follow-up exams within the inclusion period, bedside radiographs, incomplete images, imported radiographs, and pediatric radiographs. Three chest radiologists categorized findings into normal, clinically irrelevant, clinically relevant, urgent, and critical. A commercial AI system processed all radiographs, scoring 10 chest abnormalities on a 0-100 confidence scale. AI system performance was evaluated using the area under the ROC curve (AUC), assessing the detection of normal radiographs. Sensitivity was calculated for the default and a conservative operating point. the detection of negative predictive value (NPV) for urgent and critical findings, as well as the potential workload reduction, was calculated.

RESULTS

A total of 2603 radiographs were acquired in 2141 unique patients. Post-exclusion, 1670 radiographs were analyzed. Categories included 479 normal, 332 clinically irrelevant, 339 clinically relevant, 501 urgent, and 19 critical findings. The AI system achieved an AUC of 0.92. Sensitivity for normal radiographs was 92% at default and 53% at the conservative operating point. At the conservative operating point, NPV was 98% for urgent and critical findings, and could result in a 15% workload reduction.

CONCLUSION

A commercially available AI system effectively identifies normal chest radiographs and holds the potential to lessen radiologists' workload by omitting half of the normal exams from reporting.

CLINICAL RELEVANCE STATEMENT

The AI system is able to detect half of all normal chest radiographs at a clinically acceptable operating point, thereby potentially reducing the workload for the radiologists by 15%.

KEY POINTS

The AI system reached an AUC of 0.92 for the detection of normal chest radiographs. Fifty-three percent of normal chest radiographs were identified with a NPV of 98% for urgent findings. AI can reduce the workload of chest radiography reporting by 15%.

A Real-World Assessment of Stage I Lung Cancer Through Electronic Nose Technology

INTRODUCTION

Electronic nose (E-nose) technology has reported excellent sensitivity and specificity in the setting of lung cancer screening. However, the performance of E-nose specifically for early-stage tumors remains unclear. Therefore, the aim of our study was to assess the diagnostic performance of E-nose technology in clinical stage I lung cancer.

METHODS

This phase IIc trial (NCT04734145) included patients diagnosed with a single greater than or equal to 50% solid stage I nodule. Exhalates were prospectively collected from January 2020 to August 2023. Blinded bioengineers analyzed the exhalates, using E-nose technology to determine the probability of malignancy. Patients were stratified into three risk groups (low-risk, [<0.2]; moderate-risk, [≥0.2-0.7]; high-risk, [≥0.7]). The primary outcome was the diagnostic performance of E-nose versus histopathology (accuracy and F1 score). The secondary outcome was the clinical performance of the E-nose versus clinicoradiological prediction models.

RESULTS

Based on the predefined cutoff (<0.20), E-nose agreed with histopathologic results in 86% of cases, achieving an F1 score of 92.5%, based on 86 true positives, two false negatives, and 12 false positives (n = 100). E-nose would refer fewer patients with malignant nodules to observation (low-risk: 2 versus 9 and 11, respectively; p = 0.028 and p = 0.011) than would the Swensen and Brock models and more patients with malignant nodules to treatment without biopsy (high-risk: 27 versus 19 and 6, respectively; p = 0.057 and p < 0.001).

CONCLUSIONS

In the setting of clinical stage I lung cancer, E-nose agrees well with histopathology. Accordingly, E-nose technology can be used in addition to imaging or as part of a "multiomics" platform.

MR Imaging of Adverse Effects and Ocular Growth Decline after Selective Intra-Arterial Chemotherapy for Retinoblastoma

This retrospective multicenter study examines therapy-induced orbital and ocular MRI findings in retinoblastoma patients following selective intra-arterial chemotherapy (SIAC) and quantifies the impact of SIAC on ocular and optic nerve growth. Patients were selected based on medical chart review, with inclusion criteria requiring the availability of posttreatment MR imaging encompassing T2-weighted and T1-weighted images (pre- and post-intravenous gadolinium administration). Qualitative features and quantitative measurements were independently scored by experienced radiologists, with deep learning segmentation aiding total eye volume assessment. Eyes were categorized into three groups: eyes receiving SIAC (Rb-SIAC), eyes treated with other eye-saving methods (Rb-control), and healthy eyes. The most prevalent adverse effects post-SIAC were inflammatory and vascular features, with therapy-induced contrast enhancement observed in the intraorbital optic nerve segment in 6% of patients. Quantitative analysis revealed significant growth arrest in Rb-SIAC eyes, particularly when treatment commenced ≤ 12 months of age. Optic nerve atrophy was a significant complication in Rb-SIAC eyes. In conclusion, this study highlights the vascular and inflammatory adverse effects observed post-SIAC in retinoblastoma patients and demonstrates a negative impact on eye and optic nerve growth, particularly in children treated ≤ 12 months of age, providing crucial insights for clinical management and future research.

Development and Validation of a Diagnostic Histopathological Scoring System for Capsular Contracture Based on 720 Breast Implant Capsules

BACKGROUND

Capsular contracture is traditionally evaluated with the Baker classification, but this has notable limitations regarding reproducibility and objectivity.

OBJECTIVES

The aim of this study was to develop and validate procedure-specific histopathological scoring systems to assess capsular contracture severity.

METHODS

Biopsies of breast implant capsules were used to develop histopathological scoring systems for patients following breast augmentation and breast reconstruction. Ten histological parameters were evaluated by multivariable logistic regression to identify those most associated with capsular contracture. Significant parameters (P < .05) were selected for the scoring systems and assigned weighted scores (1-10). Validation was assessed from the area under the curve (AUC) and the mean absolute error (MAE).

RESULTS

A total of 720 biopsies from 542 patients were included. Four parameters were selected for the augmentation scoring system, namely, collagen layer thickness, fiber organization, inflammatory infiltration, and calcification, providing a combined maximum score of 26. The AUC and MAE for the augmentation scoring system were 81% and 0.8%, which is considered strong. Three parameters were selected for the reconstruction scoring system, namely, fiber organization, collagen layer cellularity, and inflammatory infiltration, providing a combined maximum score of 19. The AUC and MAE of the reconstruction scoring system were 72% and 7.1%, which is considered good.

CONCLUSIONS

The new histopathological scoring systems provide an objective, reproducible, and accurate assessment of capsular contracture severity. We propose these novel scoring systems as a valuable tool for confirming capsular contracture diagnosis in the clinical setting, for research, and for implant manufacturers and insurance providers in need of a confirmed capsular contracture diagnosis.

LEVEL OF EVIDENCE: 3

AI-assisted Analysis to Facilitate Detection of Humeral Lesions on Chest Radiographs

Purpose To develop an artificial intelligence (AI) system for humeral tumor detection on chest radiographs (CRs) and evaluate the impact on reader performance. Materials and Methods In this retrospective study, 14 709 CRs (January 2000 to December 2021) were collected from 13 468 patients, including CT-proven normal (n = 13 116) and humeral tumor (n = 1593) cases. The data were divided into training and test groups. A novel training method called false-positive activation area reduction (FPAR) was introduced to enhance the diagnostic performance by focusing on the humeral region. The AI program and 10 radiologists were assessed using holdout test set 1, wherein the radiologists were tested twice (with and without AI test results). The performance of the AI system was evaluated using holdout test set 2, comprising 10 497 normal images. Receiver operating characteristic analyses were conducted for evaluating model performance. Results FPAR application in the AI program improved its performance compared with a conventional model based on the area under the receiver operating characteristic curve (0.87 vs 0.82, P = .04). The proposed AI system also demonstrated improved tumor localization accuracy (80% vs 57%, P < .001). In holdout test set 2, the proposed AI system exhibited a false-positive rate of 2%. AI assistance improved the radiologists' sensitivity, specificity, and accuracy by 8.9%, 1.2%, and 3.5%, respectively (P < .05 for all). Conclusion The proposed AI tool incorporating FPAR improved humeral tumor detection on CRs and reduced false-positive results in tumor visualization. It may serve as a supportive diagnostic tool to alert radiologists about humeral abnormalities. Keywords: Artificial Intelligence, Conventional Radiography, Humerus, Machine Learning, Shoulder, Tumor Supplemental material is available for this article. © RSNA, 2024.

Diagnostic accuracy of apple watch ECG outputs in identifying dysrhythmias: A comparison with 12-Lead ECG in emergency department

BACKGROUND

Wearable devices, particularly smartwatches like the Apple Watch (AW), can record important cardiac information, such as single‑lead electrocardiograms (ECGs). Although they are increasingly used to detect conditions such as atrial fibrillation (AF), research on their effectiveness in detecting a wider range of dysrhythmias and abnormal ECG findings remains limited. The primary objective of this study is to evaluate the accuracy of the AW in detecting various cardiac rhythms by comparing it with standard ECG's lead-I.

METHODS

This single-center prospective observational study was conducted in a tertiary care emergency department (ED) between 1.10.2023 and 31.10.2023. The study population consisted of all patients assessed in the critical care areas of the ED, all of whom underwent standard 12‑lead ECGs for various clinical reasons. Participants in the study were included consecutively. An AW was attached to patients' wrists and an ECG lead-I printout was obtained. Heart rate, rhythm and abnormal findings were evaluated and compared with the lead-I of standard ECG. Two emergency medicine specialists performed the ECG evaluations. Rhythms were categorized as normal sinus rhythm and abnormal rhythms, while ECG findings were categorized as the presence or absence of abnormal findings. AW and 12‑lead ECG outputs were compared using the McNemar test. Predictive performance analyses were also performed for subgroups. Bland-Altman analysis using absolute mean differences and concordance correlation coefficients was used to assess the level of heart rate agreement between devices.

RESULTS

The study was carried out on 721 patients. When analyzing ECG rhythms and abnormal findings in lead-I, the effectiveness of AW in distinguishing between normal and abnormal rhythms was similar to standard ECGs (p = 0.52). However, there was a significant difference between AW and standard ECGs in identifying abnormal findings in lead-I (p < 0.05). Using Bland-Altman analysis for heart rate assessment, the absolute mean difference for heart rate was 0.81 ± 6.12 bpm (r = 0.94). There was strong agreement in 658 out of 700 (94%) heart rate measurements.

CONCLUSION

Our study indicates that the AW has the potential to detect cardiac rhythms beyond AF. ECG tracings obtained from the AW may help evaluate cardiac rhythms prior to the patient's arrival in the ED. However, further research with a larger patient cohort is essential, especially for specific diagnoses.

Novel 3D morphological characteristics for congenital biliary dilatation diagnosis: a case-control study

BACKGROUND

Congenital biliary dilatation (CBD) necessitates the timely removal of dilated bile ducts. Accurate differentiation between CBD and secondary biliary dilatation (SBD) is crucial for treatment decisions, and identification of CBD with intrahepatic involvement is vital for surgical planning and supportive care. This study aimed to develop quantitative models based on bile duct morphology to distinguish CBD from SBD and further identify CBD with intrahepatic involvement.

MATERIALS AND METHODS

The retrospective study included 131 CBD and 209 SBD patients between December 2014 and December 2021 for model development, internal validation, and testing. A separate cohort of 15 CBD and 34 SBD patients between January 2022 and December 2022 was recruited for temporally-independent validation. Quantitative shape-based (Shape) and diameter-based (Diam) morphological characteristics of bile ducts were extracted to build a CBD diagnosis model to distinguish CBD from SBD and an intrahepatic involvement identification model to classify CBD with/without intrahepatic involvement. The diagnostic performance of the models was compared with that of experienced hepatobiliary surgeons.

RESULTS

The CBD diagnosis model using clinical, Shape, and Diam characteristics showed good performance with an AUROC of 0.942 (95% CI: 0.890-0.994), AUPRC of 0.917 (0.855-0.979), accuracy of 0.891, sensitivity of 0.950, and F1-score of 0.864. The model outperformed two experienced surgeons in accuracy, sensitivity, and F1-score. The intrahepatic involvement identification model using clinical, Shape, and Diam characteristics yielded outstanding performance with an AUROC of 0.944 (0.879-1.000), AUPRC of 0.982 (0.947-1.000), accuracy of 0.932, sensitivity of 0.971, and F1-score of 0.957. The models demonstrated generalizable performance on the temporally-independent validation cohort.

CONCLUSIONS

This study developed two robust quantitative models for distinguishing CBD from SBD and identifying CBD with intrahepatic involvement, respectively, based on morphological characteristics of the bile ducts, showing great potential in risk stratification and surgical planning of CBD.

Nodal staging with MRI after neoadjuvant chemo-radiotherapy for locally advanced rectal cancer: a fast and reliable method

OBJECTIVES

In patients with locally advanced rectal carcinoma (LARC), negative nodal status after neoadjuvant chemoradiotherapy (nCRT) may allow for rectum-sparing protocols rather than total mesorectal excision; however, current MRI criteria for nodal staging have suboptimal accuracy. The aim of this study was to compare the diagnostic accuracy of different MRI dimensional criteria for nodal staging after nCRT in patients with LARC.

MATERIALS AND METHODS

Patients who underwent MRI after nCRT for LARC followed by surgery were retrospectively included and divided into a training and a validation cohort of 100 and 39 patients, respectively. Short-, long-, and cranial-caudal axes and volume of the largest mesorectal node and nodal status based on European Society of Gastrointestinal Radiology consensus guidelines (i.e., ESGAR method) were assessed by two radiologists independently. Inter-reader agreement was assessed in the training cohort. Histopathology was the reference standard. ROC curves and the best cut-off were calculated, and accuracies compared with the McNemar test.

RESULTS

The study population included 139 patients (median age 62 years [IQR 55-72], 94 men). Inter-reader agreement was high for long axis (κ = 0.81), volume (κ = 0.85), and ESGAR method (κ = 0.88) and low for short axis (κ = 0.11). Accuracy was similar (p > 0.05) for long axis, volume, and ESGAR method both in the training (71%, 74%, and 65%, respectively) and in the validation (83%, 78%, and 75%, respectively) cohorts.

CONCLUSION

Accuracy of the measurement of long axis and volume of the largest lymph node is not inferior to the ESGAR method for nodal staging after nCRT in LARC.

CLINICAL RELEVANCE STATEMENT

In MRI restaging of rectal cancer, measurement of the long axis or volume of largest mesorectal lymph node after preoperative chemoradiotherapy is a faster and reliable alternative to ESGAR criteria for nodal staging.

KEY POINTS

• Current MRI criteria for nodal staging in locally advanced rectal cancer after chemo-radiotherapy have suboptimal accuracy and are time-consuming. • Measurement of long axis or volume of the largest mesorectal lymph node on MRI showed good accuracy for assessment of loco-regional nodal status in locally advanced rectal cancer. • MRI measurement of the long axis and volume of largest mesorectal lymph node after chemo-radiotherapy could be a faster and reliable alternative to ESGAR criteria for nodal staging.

Optimizing Diagnostic Performance of ChatGPT: The Impact of Prompt Engineering on Thoracic Radiology Cases

Background Recent studies have highlighted the diagnostic performance of ChatGPT 3.5 and GPT-4 in a text-based format, demonstrating their radiological knowledge across different areas. Our objective is to investigate the impact of prompt engineering on the diagnostic performance of ChatGPT 3.5 and GPT-4 in diagnosing thoracic radiology cases, highlighting how the complexity of prompts influences model performance. Methodology We conducted a retrospective cross-sectional study using 124 publicly available Case of the Month examples from the Thoracic Society of Radiology website. We initially input the cases into the ChatGPT versions without prompting. Then, we employed five different prompts, ranging from basic task-oriented to complex role-specific formulations to measure the diagnostic accuracy of ChatGPT versions. The differential diagnosis lists generated by the models were compared against the radiological diagnoses listed on the Thoracic Society of Radiology website, with a scoring system in place to comprehensively assess the accuracy. Diagnostic accuracy and differential diagnosis scores were analyzed using the McNemar, Chi-square, Kruskal-Wallis, and Mann-Whitney U tests. Results Without any prompts, ChatGPT 3.5's accuracy was 25% (31/124), which increased to 56.5% (70/124) with the most complex prompt (P < 0.001). GPT-4 showed a high baseline accuracy at 53.2% (66/124) without prompting. This accuracy increased to 59.7% (74/124) with complex prompts (P = 0.09). Notably, there was no statistical difference in peak performance between ChatGPT 3.5 (70/124) and GPT-4 (74/124) (P = 0.55). Conclusions This study emphasizes the critical influence of prompt engineering on enhancing the diagnostic performance of ChatGPT versions, especially ChatGPT 3.5.

PRIDASE 2024 guidelines for reporting diagnostic accuracy studies in endodontics: A consensus-based development

Studies investigating the accuracy of diagnostic tests should provide data on how effectively they identify or exclude disease in order to inform clinicians responsible for managing patients. This consensus-based project was undertaken to develop reporting guidelines for authors submitting manuscripts, which describe studies that have evaluated the accuracy of diagnostic tests in endodontics. These guidelines are known as the Preferred Reporting Items for Diagnostic Accuracy Studies in Endodontics (PRIDASE) 2024 guidelines. A nine-member steering committee created an initial checklist by integrating and modifying items from the Standards for Reporting of Diagnostic Accuracy (STARD) 2015 checklist and the Clinical and Laboratory Images in Publications (CLIP) principles, as well as adding a number of new items specific to the specialty of endodontics. Thereafter, the steering committee formed the PRIDASE Delphi Group (PDG) and the PRIDASE Online Meeting Group (POMG) in order to collect expert feedback on the preliminary draft checklist. Members of the Delphi group engaged in an online Delphi process to reach consensus on the clarity and suitability of the items in the checklist. The online meeting group then held an in-depth discussion on the online Delphi-generated items via the Zoom platform on 20 October 2023. According to the feedback obtained, the steering committee revised the PRIDASE checklist, which was then piloted by several authors when preparing manuscripts describing diagnostic accuracy studies in endodontics. Feedback from this process resulted in the final version of the PRIDASE 2024 checklist, which has 11 sections and 66 items. Authors are encouraged to use the PRIDASE 2024 guidelines when developing manuscripts on diagnostic accuracy in endodontics in order to improve the quality of reporting in this area. Editors of relevant journals will be invited to include these guidelines in their instructions to authors.

Common challenges and suggestions for risk of bias tool development: a systematic review of methodological studies

OBJECTIVES

To review the findings of studies that have evaluated the design and/or usability of key risk of bias (RoB) tools for the assessment of RoB in primary studies, as categorized by the Library of Assessment Tools and InsTruments Used to assess Data validity in Evidence Synthesis Network (a searchable library of RoB tools for evidence synthesis): Prediction model Risk Of Bias ASessment Tool (PROBAST) , Risk of Bias-2 (RoB2), Risk Of Bias In Non-randomised Studies of Interventions (ROBINS-I), Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), Quality Assessment of Diagnostic Accuracy Studies-Comparative (QUADAS-C), Quality Assessment of Prognostic Accuracy Studies (QUAPAS), Risk Of Bias in Non-randomised Studies of Exposures (ROBINS-E), and the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) RoB checklist.

STUDY DESIGN AND SETTING

Systematic review of methodological studies. We conducted a forward citation search from the primary report of each tool, to identify primary studies that aimed to evaluate the design and/or usability of the tool. Two reviewers assessed studies for inclusion. We extracted tool features into Microsoft Word and used NVivo for document analysis, comprising a mix of deductive and inductive approaches. We summarized findings within each tool and explored common findings across tools.

RESULTS

We identified 13 tool evaluations meeting our inclusion criteria: PROBAST (3), RoB2 (3), ROBINS-I (4), and QUADAS-2 (3). We identified no evaluations for the other tools. Evaluations varied in clinical topic area, methodology, approach to bias assessment, and tool user background. Some had limitations affecting generalizability. We identified common findings across tools for 6/14 themes: (1) challenging items (eg, RoB2/ROBINS-I "deviations from intended interventions" domain), (2) overall RoB judgment (concerns with overall risk calculation in PROBAST/ROBINS-I), (3) tool usability (concerns about complexity), (4) time to complete tool (varying demands on time, eg, depending on number of outcomes assessed), (5) user agreement (varied across tools), and (6) recommendations for future use (eg, piloting) and development (add intermediate domain answer to QUADAS-2/PROBAST; provide clearer guidance for all tools). Of the other eight themes, seven only had findings for the QUADAS-2 tool, limiting comparison across tools, and one ("reorganization of questions") had no findings.

CONCLUSION

Evaluations of key RoB tools have posited common challenges and recommendations for tool use and development. These findings may be helpful to people who use or develop RoB tools. Guidance is necessary to support the design and implementation of future RoB tool evaluations.

Prostate-specific membrane antigen positron emission tomography in addition to multiparametric magnetic resonance imaging and biopsies to select prostate cancer patients for focal therapy

OBJECTIVE

To evaluate the additional value of prostate-specific membrane antigen positron emission tomography (PSMA-PET) to conventional diagnostic tools to select patients for hemi-ablative focal therapy (FT).

PATIENTS AND METHODS

We performed a retrospective analysis on a multicentre cohort (private and institutional) of 138 patients who underwent multiparametric magnetic resonance imaging (mpMRI), PSMA-PET, and systematic biopsies prior to radical prostatectomy between January 2011 and July 2021. Patients were eligible when they met the consensus criteria for FT: PSA <15 ng/mL, clinical/radiological T stage ≤T2b, and International Society of Urological Pathology (ISUP) grade 2-3. Clinically significant prostate cancer (csPCa) was defined as ISUP grade ≥2, extracapsular extension >0.5 mm or seminal vesicle involvement at final histopathology. The diagnostic accuracy of mpMRI, systematic biopsies and PSMA-PET for csPCa (separate and combined) was calculated within a four-quadrant prostate model by receiver-operating characteristic and 2 × 2 contingency analysis. Additionally, we assessed whether the diagnostic tools correctly identified patients suitable for hemi-ablative FT.

RESULTS

In total 552 prostate quadrants were analysed and 272 (49%) contained csPCa on final histopathology. The area under the curve, sensitivity, specificity, positive predictive value and negative predictive value for csPCa were 0.79, 75%, 83%, 81% and 77%, respectively, for combined mpMRI and systematic biopsies, and improved after addition of PSMA-PET to 0.84, 87%, 80%, 81% and 86%, respectively (P < 0.001). On final histopathology 46/138 patients (33%) were not suitable for hemi-ablative FT. Addition of PSMA-PET correctly identified 26/46 (57%) non-suitable patients and resulted in 4/138 (3%) false-positive exclusions.

CONCLUSIONS

Addition of PSMA-PET to the conventional work-up by mpMRI and systematic biopsies could improve selection for hemi-ablative FT and guide exclusion of patients for whom whole-gland treatments might be a more suitable treatment option.

Reproducible Reporting of the Collection and Evaluation of Annotations for Artificial Intelligence Models

This work puts forth and demonstrates the utility of a reporting framework for collecting and evaluating annotations of medical images used for training and testing artificial intelligence (AI) models in assisting detection and diagnosis. AI has unique reporting requirements, as shown by the AI extensions to the Consolidated Standards of Reporting Trials (CONSORT) and Standard Protocol Items: Recommendations for Interventional Trials (SPIRIT) checklists and the proposed AI extensions to the Standards for Reporting Diagnostic Accuracy (STARD) and Transparent Reporting of a Multivariable Prediction model for Individual Prognosis or Diagnosis (TRIPOD) checklists. AI for detection and/or diagnostic image analysis requires complete, reproducible, and transparent reporting of the annotations and metadata used in training and testing data sets. In an earlier work by other researchers, an annotation workflow and quality checklist for computational pathology annotations were proposed. In this manuscript, we operationalize this workflow into an evaluable quality checklist that applies to any reader-interpreted medical images, and we demonstrate its use for an annotation effort in digital pathology. We refer to this quality framework as the Collection and Evaluation of Annotations for Reproducible Reporting of Artificial Intelligence (CLEARR-AI).

Comparison of Ultra-High-Resolution and Normal-Resolution CT-Angiography for Intracranial Aneurysm Detection in Patients with Subarachnoid Hemorrhage

RATIONALE AND OBJECTIVES

Ruptured intracranial aneurysms (IAs) are the leading cause for atraumatic subarachnoid hemorrhage. In case of aneurysm rupture, patients may face life-threatening complications and require aneurysm occlusion. Detection of the aneurysm in computed tomography (CT) imaging is therefore essential for patient outcome. This study provides an evaluation of the diagnostic accuracy of Ultra-High-Resolution Computed Tomography Angiography (UHR-CTA) and Normal-Resolution Computed Tomography Angiography (NR-CTA) concerning IA detection and characterization.

MATERIALS AND METHODS

Consecutive patients with atraumatic subarachnoid hemorrhage who received Digital Subtraction Angiography (DSA) and either UHR-CTA or NR-CTA were retrospectively included. Three readers evaluated CT-Angiography regarding image quality, diagnostic confidence and presence of IAs. Sensitivity and specificity were calculated on patient-level and segment-level with reference standard DSA-imaging. CTA patient radiation exposure (effective dose) was compared.

RESULTS

One hundred and eight patients were identified (mean age = 57.8 ± 14.1 years, 65 women). UHR-CTA revealed significantly higher image quality and diagnostic confidence (P < 0.001) for all readers and significantly lower effective dose (P < 0.001). Readers correctly classified ≥55/56 patients on UHR-CTA and ≥44/52 patients on NR-CTA. We noted significantly higher patient-level sensitivity for UHR-CTA compared to NR-CTA for all three readers (reader 1: 41/41 [100%] vs. 28/34 [82%], reader 2: 41/41 [100%] vs. 30/34 [88%], reader 3: 41/41 [100%] vs. 30/34 [88%], P ≤ 0.04). Segment-level analysis also revealed significantly higher sensitivity for UHR-CTA compared to NR-CTA for all three readers (reader 1: 47/49 [96%] vs. 34/45 [76%], reader 2: 47/49 [96%] vs. 37/45 [82%], reader 3: 48/49 [98%] vs. 37/45 [82%], P ≤ 0.04). Specificity was comparable for both techniques.

CONCLUSION

We found Ultra-High-Resolution CT-Angiography to provide higher sensitivity than Normal-Resolution CT-Angiography for the detection of intracranial aneurysms in patients with aneurysmal subarachnoid hemorrhage while improving image quality and reducing patient radiation exposure.

Towards clinical implementation of an AI-algorithm for detection of cervical spine fractures on computed tomography

BACKGROUND

Artificial intelligence (AI) applications can facilitate detection of cervical spine fractures on CT and reduce time to diagnosis by prioritizing suspected cases.

PURPOSE

To assess the effect on time to diagnose cervical spine fractures on CT and diagnostic accuracy of a commercially available AI application.

MATERIALS AND METHODS

In this study (June 2020 - March 2022) with historic controls and prospective evaluation, we evaluated regulatory-cleared AI-software to prioritize cervical spine fractures on CT. All patients underwent non-contrast CT of the cervical spine. The time between CT acquisition and the moment the scan was first opened (DNT) was compared between the retrospective and prospective cohorts. The reference standard for determining diagnostic accuracy was the radiology report created in routine clinical workflow and adjusted by a senior radiologist. Discrepant cases were reviewed and clinical relevance of missed fractures was determined.

RESULTS

2973 (mean age, 55.4 ± 19.7 [standard deviation]; 1857 men) patients were analyzed by AI, including 2036 retrospective and 938 prospective cases. Overall prevalence of cervical spine fractures was 7.6 %. The DNT was 18 % (5 min) shorter in the prospective cohort. In scans positive for cervical spine fracture according to the reference standard, DNT was 46 % (16 min) shorter in the prospective cohort. Overall sensitivity of the AI application was 89.8 % (95 % CI: 84.2-94.0 %), specificity was 95.3 % (95 % CI: 94.2-96.2 %), and diagnostic accuracy was 94.8 % (95 % CI: 93.8-95.8 %). Negative predictive value was 99.1 % (95 % CI: 98.5-99.4 %) and positive predictive value was 63.0 % (95 % CI: 58.0-67.8 %). 22 fractures were missed by AI of which 5 required stabilizing therapy.

CONCLUSION

A time gain of 16 min to diagnosis for fractured cases was observed after introducing AI. Although AI-assisted workflow prioritization of cervical spine fractures on CT shows high diagnostic accuracy, clinically relevant cases were missed.

COVID-19 Stroke Apical Lung Examination Study 2: a national prospective CTA biomarker study of the lung apices, in patients presenting with suspected acute stroke (COVID SALES 2)

BACKGROUND

Apical ground-glass opacification (GGO) identified on CT angiography (CTA) performed for suspected acute stroke was developed in 2020 as a coronavirus-disease-2019 (COVID-19) diagnostic and prognostic biomarker in a retrospective study during the first wave of COVID-19.

OBJECTIVE

To prospectively validate whether GGO on CTA performed for suspected acute stroke is a reliable COVID-19 diagnostic and prognostic biomarker and whether it is reliable for COVID-19 vaccinated patients.

METHODS

In this prospective, pragmatic, national, multi-center validation study performed at 13 sites, we captured study data consecutively in patients undergoing CTA for suspected acute stroke from January-March 2021. Demographic and clinical features associated with stroke and COVID-19 were incorporated. The primary outcome was the likelihood of reverse-transcriptase-polymerase-chain-reaction swab-test-confirmed COVID-19 using the GGO biomarker. Secondary outcomes investigated were functional status at discharge and survival analyses at 30 and 90 days. Univariate and multivariable statistical analyses were employed.

RESULTS

CTAs from 1,111 patients were analyzed, with apical GGO identified in 8.5 % during a period of high COVID-19 prevalence. GGO showed good inter-rater reliability (Fleiss κ = 0.77); and high COVID-19 specificity (93.7 %, 91.8-95.2) and negative predictive value (NPV; 97.8 %, 96.5-98.6). In subgroup analysis of vaccinated patients, GGO remained a good diagnostic biomarker (specificity 93.1 %, 89.8-95.5; NPV 99.7 %, 98.3-100.0). Patients with COVID-19 were more likely to have higher stroke score (NIHSS (mean +/- SD) 6.9 +/- 6.9, COVID-19 negative, 9.7 +/- 9.0, COVID-19 positive; p = 0.01), carotid occlusions (6.2 % negative, 14.9 % positive; p = 0.02), and larger infarcts on presentation CT (ASPECTS 9.4 +/- 1.5, COVID-19 negative, 8.6 +/- 2.4, COVID-19 positive; p = 0.00). After multivariable logistic regression, GGO (odds ratio 15.7, 6.2-40.1), myalgia (8.9, 2.1-38.2) and higher core body temperature (1.9, 1.1-3.2) were independent COVID-19 predictors. GGO was associated with worse functional outcome on discharge and worse survival after univariate analysis. However, after adjustment for factors including stroke severity, GGO was not independently predictive of functional outcome or mortality.

CONCLUSION

Apical GGO on CTA performed for patients with suspected acute stroke is a reliable diagnostic biomarker for COVID-19, which in combination with clinical features may be useful in COVID-19 triage.

Validating the efficacy and value proposition of mental fitness vocal biomarkers in a psychiatric population: prospective cohort study

Background

The utility of vocal biomarkers for mental health assessment has gained increasing attention. This study aims to further this line of research by introducing a novel vocal scoring system designed to provide mental fitness tracking insights to users in real-world settings.

Methods

A prospective cohort study with 104 outpatient psychiatric participants was conducted to validate the "Mental Fitness Vocal Biomarker" (MFVB) score. The MFVB score was derived from eight vocal features, selected based on literature review. Participants' mental health symptom severity was assessed using the M3 Checklist, which serves as a transdiagnostic tool for measuring depression, anxiety, post-traumatic stress disorder, and bipolar symptoms.

Results

The MFVB demonstrated an ability to stratify individuals by their risk of elevated mental health symptom severity. Continuous observation enhanced the MFVB's efficacy, with risk ratios improving from 1.53 (1.09-2.14, p=0.0138) for single 30-second voice samples to 2.00 (1.21-3.30, p=0.0068) for data aggregated over two weeks. A higher risk ratio of 8.50 (2.31-31.25, p=0.0013) was observed in participants who used the MFVB 5-6 times per week, underscoring the utility of frequent and continuous observation. Participant feedback confirmed the user-friendliness of the application and its perceived benefits.

Conclusions

The MFVB is a promising tool for objective mental health tracking in real-world conditions, with potential to be a cost-effective, scalable, and privacy-preserving adjunct to traditional psychiatric assessments. User feedback suggests that vocal biomarkers can offer personalized insights and support clinical therapy and other beneficial activities that are associated with improved mental health risks and outcomes.

Incidence and Risk Factors for the Development of Axial Symptoms Following Posterior Single-Door Laminoplasty: A Retrospective Analysis

OBJECTIVE

Posterior single-door laminoplasty is a widely practiced clinical procedure, but the occurrence of postoperative axial syndrome (AS) remains a significant concern. The aim of this study was to identify risk factors associated with AS and develop a risk prediction model.

METHODS

Clinical data from 226 patients who underwent posterior single-door laminoplasty between June 2017 and June 2022 were collected. Through Logistic model analysis, the risk factors of AS are clarified and the intensity of each risk factor is explained in the form of forest plot. Subsequently, we constructed a predictive model and plotted receiver operating characteristic curves to assess the model's predictive value.

RESULTS

In the end, 87 cases were diagnosed with AS, resulting in an incidence rate of 38.5%. Logistic regression analysis revealed that preoperative encroachment rate of anterior spinal canal (pre-op ERASC), intraoperative facet joints destruction, intraoperative open-door angle, postoperative loss of cervical curvature, and postoperative loss of cervical range of motion were independent risk factors for AS. Conversely, preoperative cervical curvature (pre-op CC) and postoperation early function training were protective factors against AS. The Youden index indicated that the cutoff values for pre-op ERASC and pre-op CC were 26.6°and 16.5, respectively. The risk prediction model for AS was constructed and a nomogram was plotted. The model has high clinical value.

CONCLUSIONS

Pre-op ERASC, pre-op CC, intraoperative facet joints destruction, intraoperative open-door angle, postoperative loss of cervical curvature, postoperative loss of cervical range of motion, and postoperation early function training are independent influencing factors for AS occurrence. The risk model has good practicability.

Diagnostic accuracy of CT and Doppler US for hepatic outflow obstruction after pediatric liver transplantation using left lobe or left lateral section grafts

PURPOSE

The aim of this study was to evaluate diagnostic accuracy and to establish computed tomography (CT) and Doppler ultrasonography (US) criteria for hepatic outflow obstruction after pediatric liver transplantation (LT) using left lobe (LL) or left lateral section (LLS) grafts.

METHODS

Pediatric patients who underwent LT using LL or LLS grafts between January 1999 and December 2021 were retrospectively included. The diagnostic performance of Doppler US and CT parameters for hepatic outflow obstruction was calculated using receiver operating characteristic (ROC) curve analysis. A diagnostic decision tree model combining the imaging parameters was developed.

RESULTS

In total, 288 patients (150 girls; median age at LT, 1.8 years [interquartile range, 0.9 to 3.6 years]) were included. Among the Doppler US parameters, venous pulsatility index (VPI) showed excellent diagnostic performance (area under the ROC curve [AUROC], 0.90; 95% confidence interval [CI], 0.86 to 0.93; Youden cut-off value, 0.40). Among the CT parameters, anastomotic site diameter (AUROC, 0.92; 95% CI, 0.88 to 0.95; Youden cut-off, 4.2 mm) and percentage of anastomotic site stenosis (AUROC, 0.88; 95% CI, 0.84 to 0.92; Youden cut-off, 35%) showed excellent and good diagnostic performance, respectively. A decision tree model combining the VPI, peak systolic velocity, and percentage of anastomotic site stenosis stratified patients according to the risk of hepatic outflow obstruction.

CONCLUSION

VPI, anastomotic site diameter, and percentage of anastomotic site stenosis were reliable imaging parameters for diagnosing hepatic outflow obstruction after pediatric LT using LL or LLS grafts.

High diagnostic accuracy of T2FLAIR at 3 T in the detection of optic nerve head edema in acute optic neuritis

OBJECTIVES

Optic nerve head edema (ONHE) detected by fundoscopy is observed in one-third of patients presenting optic neuritis (ON). While ONHE is an important semiological feature, the correlation between ONHE and optic nerve head MRI abnormalities (ONHMA), sometimes called "optic nerve head swelling," remains unknown. Our study aimed to assess the diagnostic accuracy of T2 fluid-attenuated inversion recovery (FLAIR) MRI sequence in detecting ONHE in patients with acute ON.

METHODS

In the present single-center study, data were extracted from two prospective cohort studies that consecutively included adults with a first episode of acute ON treated between 2015 and 2020. Two experienced readers blinded to study data independently analyzed imaging. A senior neuroradiologist resolved any discrepancies. The primary judgment criterion of ONHMA was assessed as optic nerve head high signal intensity on gadolinium-enhanced T2FLAIR MRI sequence. Its diagnostic accuracy was evaluated with both the gold standard of ONHE on fundus photography (FP) and peripapillary retinal nerve fiber layer thickening on optic coherence tomography (OCT).

RESULTS

A total of 102 patients were included, providing 110 affected and 94 unaffected optic nerves. Agreement was high between the different modalities: 92% between MRI and FP (k = 0.77, 95% CI: 0.67-0.88) and 93% between MRI and OCT (k = 0.77, 95% CI: 0.67-0.87). MRI sensitivity was 0.84 (95% CI: 0.70-0.93) and specificity was 0.94 (95% CI: 0.89-0.97) when compared with the FP.

CONCLUSION

Optic nerve head high T2FLAIR signal intensity corresponds indeed to the optic nerve head edema diagnosed by the ophthalmologists. MRI is a sensitive tool for detecting ONHE in patients presenting acute ON.

CLINICAL RELEVANCE STATEMENT

In patients with optic neuritis the high T2FLAIR (fluid-attenuated inversion recovery) signal intensity of the optic nerve head corresponds indeed to optic nerve head edema, which is a useful feature in optic neuritis etiological evaluation and treatment.

KEY POINTS

Optic nerve head edema is a prominent clinical feature of acute optic neuritis and is usually diagnosed during dilated or non-dilated eye fundus examination. Agreement was high between magnetic resonance imaging, fundus photography, and optical coherence tomography. Optic nerve head high T2 fluid attenuation inversion recovery signal intensity is a promising detection tool for optic nerve head edema in patients presenting acute optic neuritis.

X-rays radiomics-based machine learning classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones

BACKGROUND

Atypical cartilaginous tumour (ACT) and high-grade chondrosarcoma (CS) of long bones are respectively managed with active surveillance or curettage and wide resection. Our aim was to determine diagnostic performance of X-rays radiomics-based machine learning for classification of ACT and high-grade CS of long bones.

METHODS

This retrospective, IRB-approved study included 150 patients with surgically treated and histology-proven lesions at two tertiary bone sarcoma centres. At centre 1, the dataset was split into training (n = 71 ACT, n = 24 high-grade CS) and internal test (n = 19 ACT, n = 6 high-grade CS) cohorts, respectively, based on the date of surgery. At centre 2, the dataset constituted the external test cohort (n = 12 ACT, n = 18 high-grade CS). Manual segmentation was performed on frontal view X-rays, using MRI or CT for preliminary identification of lesion margins. After image pre-processing, radiomic features were extracted. Dimensionality reduction included stability, coefficient of variation, and mutual information analyses. In the training cohort, after class balancing, a machine learning classifier (Support Vector Machine) was automatically tuned using nested 10-fold cross-validation. Then, it was tested on both the test cohorts and compared to two musculoskeletal radiologists' performance using McNemar's test.

FINDINGS

Five radiomic features (3 morphology, 2 texture) passed dimensionality reduction. After tuning on the training cohort (AUC = 0.75), the classifier had 80%, 83%, 79% and 80%, 89%, 67% accuracy, sensitivity, and specificity in the internal (temporally independent) and external (geographically independent) test cohorts, respectively, with no difference compared to the radiologists (p ≥ 0.617).

INTERPRETATION

X-rays radiomics-based machine learning accurately differentiates between ACT and high-grade CS of long bones.

FUNDING

AIRC Investigator Grant.

Diagnostic performance and image quality of an image-based denoising algorithm applied to radiation dose-reduced CT in diagnosing acute appendicitis

PURPOSE

To evaluate diagnostic performance and image quality of ultralow-dose CT (ULDCT) in diagnosing acute appendicitis with an image-based deep-learning denoising algorithm (IDLDA).

METHODS

This retrospective multicenter study included 180 patients (mean ± standard deviation, 29 ± 9 years; 91 female) who underwent contrast-enhanced 2-mSv CT for suspected appendicitis from February 2014 to August 2016. We simulated ULDCT from 2-mSv CT, reducing the dose by at least 50%. Then we applied an IDLDA on ULDCT to produce denoised ULDCT (D-ULDCT). Six radiologists with different experience levels (three board-certified radiologists and three residents) independently reviewed the ULDCT and D-ULDCT. They rated the likelihood of appendicitis and subjective image qualities (subjective image noise, diagnostic acceptability, and artificial sensation). One radiologist measured image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). We used the receiver operating characteristic (ROC) analyses, Wilcoxon's signed-rank tests, and paired t-tests.

RESULTS

The area under the ROC curves (AUC) for diagnosing appendicitis ranged 0.90-0.97 for ULDCT and 0.94-0.97 for D-ULDCT. The AUCs of two residents were significantly higher on D-ULDCT (AUC difference = 0.06 [95% confidence interval, 0.01-0.11; p = .022] and 0.05 [0.00-0.10; p = .046], respectively). D-ULDCT provided better subjective image noise and diagnostic acceptability to all six readers. However, the response of board-certified radiologists and residents differed in artificial sensation (all p ≤ .003). D-ULDCT showed significantly lower image noise, higher SNR, and higher CNR (all p < .001).

CONCLUSION

An IDLDA can provide better ULDCT image quality and enhance diagnostic performance for less-experienced radiologists.

Bone age assessment based on three-dimensional ultrasound and artificial intelligence compared with paediatrician-read radiographic bone age: protocol for a prospective, diagnostic accuracy study

INTRODUCTION

Radiographic bone age (BA) assessment is widely used to evaluate children's growth disorders and predict their future height. Moreover, children are more sensitive and vulnerable to X-ray radiation exposure than adults. The purpose of this study is to develop a new, safer, radiation-free BA assessment method for children by using three-dimensional ultrasound (3D-US) and artificial intelligence (AI), and to test the diagnostic accuracy and reliability of this method.

METHODS AND ANALYSIS

This is a prospective, observational study. All participants will be recruited through Paediatric Growth and Development Clinic. All participants will receive left hand 3D-US and X-ray examination at the Shanghai Sixth People's Hospital on the same day, all images will be recorded. These image related data will be collected and randomly divided into training set (80% of all) and test set (20% of all). The training set will be used to establish a cascade network of 3D-US skeletal image segmentation and BA prediction model to achieve end-to-end prediction of image to BA. The test set will be used to evaluate the accuracy of AI BA model of 3D-US. We have developed a new ultrasonic scanning device, which can be proposed to automatic 3D-US scanning of hands. AI algorithms, such as convolutional neural network, will be used to identify and segment the skeletal structures in the hand 3D-US images. We will achieve automatic segmentation of hand skeletal 3D-US images, establish BA prediction model of 3D-US, and test the accuracy of the prediction model.

ETHICS AND DISSEMINATION

The Ethics Committee of Shanghai Sixth People's Hospital approved this study. The approval number is 2022-019. A written informed consent will be obtained from their parent or guardian of each participant. Final results will be published in peer-reviewed journals and presented at national and international conferences.

TRIAL REGISTRATION NUMBER

ChiCTR2200057236.

4D flow cardiac MRI to assess pulmonary blood flow in patients with pulmonary arterial hypertension associated with congenital heart disease

PURPOSE

The purpose of this study was to evaluate the accuracy of four-dimensional flow cardiac magnetic resonance imaging (4D flow MRI) compared to right heart catheterization in measuring pulmonary flow (Qp), systemic flow (Qs) and pulmonary-to-systemic flow ratio (Qp/Qs) in patients with pulmonary arterial hypertension associated with congenital heart disease (PAH-CHD).

MATERIALS AND METHODS

The study was registered on Clinical-trial.gov (NCT03928002). Sixty-four patients with PAH-CHD who underwent 4D flow MRI were included. There were 16 men and 48 women with a mean age of 45.3 ± 13.7 (standard deviation [SD]) years (age range: 21-77 years). Fifty patients (50/64; 78%) presented with pre-tricuspid shunt. Qp (L/min), Qs (L/min) and Qp/Qs were measured invasively using direct Fick method during right heart catheterization and compared with measurements assessed by 4D flow MRI within a 24-48-hour window.

RESULTS

The average mean pulmonary artery pressure was 51 ± 17 (SD) mm Hg with median pulmonary vascular resistance of 8.8 Wood units (Q1, Q3: 5.3, 11.7). A strong linear correlation was found between Qp measurements obtained with 4D flow MRI and those obtained with the Fick method (r = 0.96; P < 0.001). Bland Altman analysis indicated a mean difference of 0.15 ± 0.48 (SD) L/min between Qp estimated by 4D flow MRI and by right heart catheterization. A strong correlation was found between Qs and Qp/Qs measured by 4D flow MRI and those obtained with the direct Fick method (r = 0.85 and r = 0.92; P < 0.001 for both).

CONCLUSION

Qp as measured by 4D flow MRI shows a strong correlation with measurements derived from the direct Fick method. Further investigation is needed to develop less complex and standardized methods for measuring essential PAH parameters, such as pulmonary arterial pressures and pulmonary vascular resistance.

Comparing the performance of 2 human papillomavirus assays for a new use indication: a real-world evidence-based evaluation in the United States

BACKGROUND

The US Food and Drug Administration supports innovations to facilitate new indications for high-risk human papillomavirus testing. This report describes the retrospective testing of stored specimens and analysis of existing data to efficiently and cost-effectively support a new indication for the Onclarity human papillomavirus assay (Becton, Dickinson and Company, BD Life Sciences - Integrated Diagnostic Solutions, Sparks, MD). The performance of this index test was compared with that of a predicate test, the cobas human papillomavirus assay (Roche Diagnostics, Indianapolis, IN). Both human papillomavirus assays are based on real-time polymerase chain reaction platforms that detect the presence of 14 high-risk human papillomavirus genotypes. The predicate assay reports human papillomavirus types 16 and 18 as individual results and the other 12 human papillomavirus genotypes as 1 pooled result. The index assay reports 9 independent results (human papillomavirus types 16, 18, 31, 33/58, 35/39/68, 45, 51, 52, and 56/59/66). Both the index and predicate assays are approved by the Food and Drug Administration for cervical cancer screening, but at the time that this study was initiated, the index human papillomavirus assay was not approved for use with cervical specimens collected in PreservCyt (Hologic, Inc, San Diego, CA) liquid-based cytology media.

OBJECTIVE

The performance of the index human papillomavirus assay was compared with that of the predicate human papillomavirus assay for the detection of cervical intraepithelial neoplasia grades 2 or greater and 3 or greater (≥CIN2 or ≥CIN3) using PreservCyt liquid-based cytology specimens collected from women aged 21 to 65 years. In addition, the ability of the index test's extended genotyping to stratify ≥CIN2 and ≥CIN3 risks, using these specimens, was evaluated.

STUDY DESIGN

The New Mexico HPV Pap Registry was used to select an age- and cytology-stratified random sample of 19,879 women undergoing opportunistic cervical screening and follow-up in routine clinical practice across New Mexico. A subset (n = 4820) of PreservCyt specimens was selected from 19,879 women for paired testing by the index and predicate human papillomavirus assays within age and cytology strata and included women with or without cervical biopsy follow-up. Point estimate differences and ratios were calculated for cervical disease detection and positivity rates, respectively, with 95% confidence intervals to determine statistical significance. The cumulative risk of ≥CIN2 or ≥CIN3, with up to 5-year follow-up, was estimated for the index assay using Kaplan-Meier methods.

RESULTS

The 5-year cumulative ≥CIN3 detection rates were 5.6% for the index assay and 4.6% for the predicate assay (difference, 1.0%; 95% confidence interval, 0.5%-1.5%). The ≥CIN3 positivity rates within <1 year were 95.3% for the index assay and 94.5% for the predicate assay (ratio, 1.01; 95% confidence interval, 0.98-1.06). The ≥CIN3 cumulative positivity rates for the index and predicate assays were also similar at 5 years. Among cases of ≥CIN3, the positive agreement rates between the index and predicate assays for human papillomavirus types 16 and 18 were 100.0% (95% confidence interval, 95.0%-100.0%) and 90.9% (95% confidence interval, 62.3%-98.4%), respectively. Human papillomavirus type 16 carried the highest ≥CIN2 or ≥CIN3 risk, followed by human papillomavirus types 18/31/33/58/52/45 and human papillomavirus types 35/56/59/51/56/59/66.

CONCLUSION

The index and predicate human papillomavirus assays demonstrated equivalent performance, and extended human papillomavirus genotyping, using the index assay, provided effective ≥CIN2 and ≥CIN3 risk stratification, supporting a new indication for use of the index assay with PreservCyt.

Deep learning enables the differentiation between early and late stages of hip avascular necrosis

OBJECTIVES

To develop a deep learning methodology that distinguishes early from late stages of avascular necrosis of the hip (AVN) to determine treatment decisions.

METHODS

Three convolutional neural networks (CNNs) VGG-16, Inception ResnetV2, InceptionV3 were trained with transfer learning (ImageNet) and finetuned with a retrospectively collected cohort of (n = 104) MRI examinations of AVN patients, to differentiate between early (ARCO 1-2) and late (ARCO 3-4) stages. A consensus CNN ensemble decision was recorded as the agreement of at least two CNNs. CNN and ensemble performance was benchmarked on an independent cohort of 49 patients from another country and was compared to the performance of two MSK radiologists. CNN performance was expressed with areas under the curve (AUC), the respective 95% confidence intervals (CIs) and precision, and recall and f1-scores. AUCs were compared with DeLong's test.

RESULTS

On internal testing, Inception-ResnetV2 achieved the highest individual performance with an AUC of 99.7% (95%CI 99-100%), followed by InceptionV3 and VGG-16 with AUCs of 99.3% (95%CI 98.4-100%) and 97.3% (95%CI 95.5-99.2%) respectively. The CNN ensemble the same AUCs Inception ResnetV2. On external validation, model performance dropped with VGG-16 achieving the highest individual AUC of 78.9% (95%CI 51.6-79.6%) The best external performance was achieved by the model ensemble with an AUC of 85.5% (95%CI 72.2-93.9%). No significant difference was found between the CNN ensemble and expert MSK radiologists (p = 0.22 and 0.092 respectively).

CONCLUSION

An externally validated CNN ensemble accurately distinguishes between the early and late stages of AVN and has comparable performance to expert MSK radiologists.

CLINICAL RELEVANCE STATEMENT

This paper introduces the use of deep learning for the differentiation between early and late avascular necrosis of the hip, assisting in a complex clinical decision that can determine the choice between conservative and surgical treatment.

KEY POINTS

• A convolutional neural network ensemble achieved excellent performance in distinguishing between early and late avascular necrosis. • The performance of the deep learning method was similar to the performance of expert readers.

Advancing Diagnostics and Patient Care: The Role of Biomarkers in Radiology

The integration of biomarkers into medical practice has revolutionized the field of radiology, allowing for enhanced diagnostic accuracy, personalized treatment strategies, and improved patient care outcomes. This review offers radiologists a comprehensive understanding of the diverse applications of biomarkers in medicine. By elucidating the fundamental concepts, challenges, and recent advancements in biomarker utilization, it will serve as a bridge between the disciplines of radiology and epidemiology. Through an exploration of various biomarker types, such as imaging biomarkers, molecular biomarkers, and genetic markers, I outline their roles in disease detection, prognosis prediction, and therapeutic monitoring. I also discuss the significance of robust study designs, blinding, power and sample size calculations, performance metrics, and statistical methodologies in biomarker research. By fostering collaboration between radiologists, statisticians, and epidemiologists, I hope to accelerate the translation of biomarker discoveries into clinical practice, ultimately leading to improved patient care.

Hybrid ultrasound and single wavelength optoacoustic imaging reveals muscle degeneration in peripheral artery disease

Peripheral arterial disease (PAD) leads to chronic vascular occlusion and results in end organ damage in critically perfused limbs. There are currently no clinical methods available to determine the muscular damage induced by chronic mal-perfusion. This monocentric prospective cross-sectional study investigated n = 193 adults, healthy to severe PAD, in order to quantify the degree of calf muscle degeneration caused by PAD using a non-invasive hybrid ultrasound and single wavelength optoacoustic imaging (US/SWL-OAI) approach. While US provides morphologic information, SWL-OAI visualizes the absorption of pulsed laser light and the resulting sound waves from molecules undergoing thermoelastic expansion. US/SWL-OAI was compared to multispectral data, clinical disease severity, angiographic findings, phantom experiments, and histological examinations from calf muscle biopsies. We were able to show that synergistic use of US/SWL-OAI is most likely to map clinical degeneration of the muscle and progressive PAD.

Crimson clues: advancing endometriosis detection and management with novel blood biomarkers

Endometriosis is an inflammatory condition affecting approximately 10% of the female-born population. Despite its prevalence, the lack of noninvasive biomarkers has contributed to an established global diagnostic delay. The intricate pathophysiology of this enigmatic disease may leave signatures in the blood, which, when detected, can be used as noninvasive biomarkers. This review provides an update on how investigators are utilizing the established disease pathways and innovative methodologies, including genome-wide association studies, next-generation sequencing, and machine learning, to unravel the clues left in the blood to develop blood biomarkers. Many blood biomarkers show promise in the discovery phase, but because of a lack of standardized and robust methodologies, they rarely progress to the development stages. However, we are now seeing biomarkers being validated with high diagnostic accuracy and improvements in standardization protocols, providing promise for the future of endometriosis blood biomarkers.

A guide to conducting systematic reviews of clinical laboratory tests

Clinical laboratory professionals have an instrumental role in supporting clinical decision making with the optimal use of laboratory testing for screening, risk stratification, diagnostic, prognostic, treatment selection and monitoring of different states of health and disease. Delivering evidence-based laboratory medicine relies on review of available data and literature. The information derived, supports many national policies to improve patient care through clinical practice guidelines or best practice recommendations. The quality, validity and bias of this literature is variable. Hence, there is a need to collate similar studies and data and analyse them critically. Systematic review, thus, becomes the most important source of evidence. A systematic review, unlike a scoping or narrative review, involves a thorough understanding of the procedure involved and a stepwise methodology. There are nuances that need some consideration for laboratory medicine systematic reviews. The purpose of this article is to describe the process of performing a systematic review in the field of laboratory medicine, describing the available methodologies, tools and software packages that can be used to facilitate this process.

Translating radiological research into practice-from discovery to clinical impact

At the European Society of Radiology (ESR), we strive to provide evidence for radiological practices that improve patient outcomes and have a societal impact. Successful translation of radiological research into clinical practice requires multiple factors including tailored methodology, a multidisciplinary approach aiming beyond technical validation, and a focus on unmet clinical needs. Low levels of evidence are a threat to radiology, resulting in low visibility and credibility. Here, we provide the background and rationale for the thematic series Translating radiological research into practice-from discovery to clinical impact, inviting authors to describe their processes of achieving clinically impactful radiological research. We describe the challenges unique to radiological research. Additionally, a survey was sent to non-radiological clinical societies. The majority of respondents (6/11) were in the field of gastrointestinal/abdominal medicine. The implementation of CT/MRI techniques for disease characterisation, detection and staging of cancer, and treatment planning and radiological interventions were mentioned as the most important radiological developments in the past years. The perception was that patients are substantially unaware of the impact of these developments. Unmet clinical needs were mostly early diagnosis and staging of cancer, microstructural/functional assessment of tissues and organs, and implant assessment. All but one respondent considered radiology important for research in their discipline, but five indicated that radiology is currently not involved in their research. Radiology research holds the potential for being transformative to medical practice. It is our responsibility to take the lead in studies including radiology and strive towards the highest levels of evidence.Critical relevance statement For radiological research to make a clinical and societal impact, radiologists should take the lead in radiological studies, go beyond the assessment of technical feasibility and diagnostic accuracy, and-in a multidisciplinary approach-address clinical unmet needs.Key points• Multiple factors are essential for radiological research to make a clinical and societal impact.• Radiological research needs to go beyond diagnostic accuracy and address unmet clinical needs.• Radiologists should take the lead in radiological studies with a multidisciplinary approach.

Synovial Fluid C-reactive Protein Clinical Decision Limit and Diagnostic Accuracy for Periprosthetic Joint Infection

Introduction C-reactive protein (CRP) has long served as a prototypical biomarker for periprosthetic joint infection (PJI). Recently, synovial fluid (SF)-CRP has garnered interest as a diagnostic tool, with several studies demonstrating its diagnostic superiority over serum CRP for the diagnosis of PJI. Although previous studies have identified diagnostic thresholds for SF-CRP, they have been limited in scope and employed various CRP assays without formal validation for PJI diagnosis. This study aimed to conduct a formal single clinical laboratory validation to determine the optimal clinical decision limit of SF-CRP for the diagnosis of PJI. Methods A retrospective analysis of prospectively collected data was performed using receiver operating characteristic (ROC) and area under the curve (AUC) analyses. Synovial fluid samples from hip and knee arthroplasties, received from over 2,600 institutions, underwent clinical testing for PJI at a single clinical laboratory (CD Laboratories, Zimmer Biomet, Towson, MD) between 2017 and 2022. Samples were assayed for SF-CRP, alpha-defensin, white blood cell count, neutrophil percentage, and microbiological culture. After applying selection criteria, the samples were classified with the 2018 ICM PJI scoring system as "infected," "not infected," or "inconclusive." Data were divided into training and validation sets. The Youden Index was employed to optimize the clinical decision limit. Results A total of 96,061 samples formed the training (n = 67,242) and validation (n = 28,819) datasets. Analysis of the biomarker median values, culture positivity, anatomic distribution, and days from aspiration to testing revealed nearly identical specimen characteristics in both the training set and validation set. SF-CRP demonstrated an AUC of 0.929 (95% confidence interval (CI): 0.926-0.932) in the training set, with an optimal SF-CRP clinical decision limit for PJI diagnosis of 4.45 mg/L. Applying this cutoff to the validation dataset yielded a sensitivity of 86.1% (95% CI: 85.0-87.1%) and specificity of 87.1% (95% CI: 86.7-87.5%). No statistically significant difference in diagnostic performance was observed between the validation and training sets. Conclusion This study represents the largest single clinical laboratory evaluation of an SF-CRP assay for PJI diagnosis. The optimal CRP cutoff (4.45 mg/L) for PJI, which yielded a sensitivity of 86.1% and a specificity of 87.1%, is specific to the assay methodology and laboratory performing the assay. We propose that an SF-CRP test with a laboratory-validated optimal clinical decision limit for PJI may be preferable, in a clinical diagnostic setting, to serum CRP tests that do not have laboratory-validated clinical decision limits for PJI.

Accuracy of ChatGPT generated diagnosis from patient's medical history and imaging findings in neuroradiology cases

PURPOSE

The noteworthy performance of Chat Generative Pre-trained Transformer (ChatGPT), an artificial intelligence text generation model based on the GPT-4 architecture, has been demonstrated in various fields; however, its potential applications in neuroradiology remain unexplored. This study aimed to evaluate the diagnostic performance of GPT-4 based ChatGPT in neuroradiology.

METHODS

We collected 100 consecutive "Case of the Week" cases from the American Journal of Neuroradiology between October 2021 and September 2023. ChatGPT generated a diagnosis from patient's medical history and imaging findings for each case. Then the diagnostic accuracy rate was determined using the published ground truth. Each case was categorized by anatomical location (brain, spine, and head & neck), and brain cases were further divided into central nervous system (CNS) tumor and non-CNS tumor groups. Fisher's exact test was conducted to compare the accuracy rates among the three anatomical locations, as well as between the CNS tumor and non-CNS tumor groups.

RESULTS

ChatGPT achieved a diagnostic accuracy rate of 50% (50/100 cases). There were no significant differences between the accuracy rates of the three anatomical locations (p = 0.89). The accuracy rate was significantly lower for the CNS tumor group compared to the non-CNS tumor group in the brain cases (16% [3/19] vs. 62% [36/58], p < 0.001).

CONCLUSION

This study demonstrated the diagnostic performance of ChatGPT in neuroradiology. ChatGPT's diagnostic accuracy varied depending on disease etiologies, and its diagnostic accuracy was significantly lower in CNS tumors compared to non-CNS tumors.

The endorsement of general and artificial intelligence reporting guidelines in radiological journals: a meta-research study

BACKGROUND

Complete reporting is essential for clinical research. However, the endorsement of reporting guidelines in radiological journals is still unclear. Further, as a field extensively utilizing artificial intelligence (AI), the adoption of both general and AI reporting guidelines would be necessary for enhancing quality and transparency of radiological research. This study aims to investigate the endorsement of general reporting guidelines and those for AI applications in medical imaging in radiological journals, and explore associated journal characteristic variables.

METHODS

This meta-research study screened journals from the Radiology, Nuclear Medicine & Medical Imaging category, Science Citation Index Expanded of the 2022 Journal Citation Reports, and excluded journals not publishing original research, in non-English languages, and instructions for authors unavailable. The endorsement of fifteen general reporting guidelines and ten AI reporting guidelines was rated using a five-level tool: "active strong", "active weak", "passive moderate", "passive weak", and "none". The association between endorsement and journal characteristic variables was evaluated by logistic regression analysis.

RESULTS

We included 117 journals. The top-five endorsed reporting guidelines were CONSORT (Consolidated Standards of Reporting Trials, 58.1%, 68/117), PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses, 54.7%, 64/117), STROBE (STrengthening the Reporting of Observational Studies in Epidemiology, 51.3%, 60/117), STARD (Standards for Reporting of Diagnostic Accuracy, 50.4%, 59/117), and ARRIVE (Animal Research Reporting of In Vivo Experiments, 35.9%, 42/117). The most implemented AI reporting guideline was CLAIM (Checklist for Artificial Intelligence in Medical Imaging, 1.7%, 2/117), while other nine AI reporting guidelines were not mentioned. The Journal Impact Factor quartile and publisher were associated with endorsement of reporting guidelines in radiological journals.

CONCLUSIONS

The general reporting guideline endorsement was suboptimal in radiological journals. The implementation of reporting guidelines for AI applications in medical imaging was extremely low. Their adoption should be strengthened to facilitate quality and transparency of radiological study reporting.

Ultrasound tissue scatterer distribution imaging: An adjunctive diagnostic tool for shear wave elastography in characterizing focal liver lesions

OBJECTIVES

Focal liver lesion (FLL) is a prevalent finding in cross-sectional imaging, and distinguishing between benign and malignant FLLs is crucial for liver health management. While shear wave elastography (SWE) serves as a conventional quantitative ultrasound tool for evaluating FLLs, ultrasound tissue scatterer distribution imaging (TSI) emerges as a novel technique, employing the Nakagami statistical distribution parameter to estimate backscattered statistics for tissue characterization. In this prospective study, we explored the potential of TSI in characterizing FLLs and evaluated its diagnostic efficacy with that of SWE.

METHODS

A total of 235 participants (265 FLLs; the study group) were enrolled to undergo abdominal examinations, which included data acquisition from B-mode, SWE, and raw radiofrequency data for TSI construction. The area under the receiver operating characteristic curve (AUROC) was used to evaluate performance. A dataset of 20 patients (20 FLLs; the validation group) was additionally acquired to further evaluate the efficacy of the TSI cutoff value in FLL characterization.

RESULTS

In the study group, our findings revealed that while SWE achieved a success rate of 49.43 % in FLL measurements, TSI boasted a success rate of 100 %. In cases where SWE was effectively implemented, the AUROCs for characterizing FLLs using SWE and TSI stood at 0.84 and 0.83, respectively. For instances where SWE imaging failed, TSI achieved an AUROC of 0.78. Considering all cases, TSI presented an overall AUROC of 0.81. There was no statistically significant difference in AUROC values between TSI and SWE (p > 0.05). In the validation group, using a TSI cutoff value of 0.67, the AUROC for characterizing FLLs was 0.80.

CONCLUSIONS

In conclusion, ultrasound TSI holds promise as a supplementary diagnostic tool to SWE for characterizing FLLs.

Radiomics Nomogram with Added Nodal Features Improves Treatment Response Prediction in Locally Advanced Esophageal Squamous Cell Carcinoma: A Multicenter Study

OBJECTIVE

We aimed to develop and validate a radiomics nomogram and determine the value of radiomic features from lymph nodes (LNs) for predicting pathological complete response (pCR) to neoadjuvant chemoradiotherapy (NCRT) in patients with locally advanced esophageal squamous cell carcinoma (ESCC).

METHODS

In this multicenter retrospective study, eligible participants who had undergone NCRT followed by radical esophagectomy were consecutively recruited. Three radiomics models (modelT, modelLN, and modelTLN) based on tumor and LN features, alone and combined, were developed in the training cohort. The radiomics nomogram was developed by incorporating the prediction value of the radiomics model and clinicoradiological risk factors using multivariate logistic regression, and was evaluated using the receiver operating characteristic curve, validated in two external validation cohorts.

RESULTS

Between October 2011 and December 2018, 116 patients were included in the training cohort. Between June 2015 and October 2020, 51 and 27 patients from two independent hospitals were included in validation cohorts 1 and 2, respectively. The radiomics modelTLN performed better than the radiomics modelT for predicting pCR. The radiomics nomogram incorporating the predictive value of the radiomics modelTLN and heterogeneous after NCRT outperformed the clinicoradiological model, with an area under the curve (95% confidence interval) of 0.833 (0.765-0.894) versus 0.764 (0.686-0.833) [p = 0.088, DeLong test], 0.824 (0.718-0.909) versus 0.692 (0.554-0.809) [p = 0.012], and 0.902 (0.794-0.984) versus 0.696 (0.526-0.857) [p = 0.024] in all three cohorts.

CONCLUSIONS

Radiomic features from LNs could provide additional value for predicting pCR in ESCC patients, and the radiomics nomogram provided an accurate prediction of pCR, which might aid treatment decision.

Diagnostic properties of natriuretic peptides and opportunities for personalized thresholds for detecting heart failure in primary care

OBJECTIVES

Heart failure (HF) is a prevalent syndrome with considerable disease burden, healthcare utilization and costs. Timely diagnosis is essential to improve outcomes. This study aimed to compare the diagnostic performance of B-type natriuretic peptide (BNP) and N-terminal proBNP (NT-proBNP) in detecting HF in primary care. Our second aim was to explore if personalized thresholds (using age, sex, or other readily available parameters) would further improve diagnostic accuracy over universal thresholds.

METHODS

A retrospective study was performed among patients without prior HF who underwent natriuretic peptide (NP) testing in the Amsterdam General Practice Network between January 2011 and December 2021. HF incidence was based on registration out to 90 days after NP testing. Diagnostic accuracy was evaluated with AUROC, sensitivity and specificity based on guideline-recommended thresholds (125 ng/L for NT-proBNP and 35 ng/L for BNP). We used inverse probability of treatment weighting to adjust for confounding.

RESULTS

A total of 15,234 patients underwent NP testing, 6,870 with BNP (4.5 % had HF), and 8,364 with NT-proBNP (5.7 % had HF). NT-proBNP was more accurate than BNP, with an AUROC of 89.9 % (95 % CI: 88.4-91.2) vs. 85.9 % (95 % CI 83.5-88.2), with higher sensitivity (95.3 vs. 89.7 %) and specificity (59.1 vs. 58.0 %). Differentiating NP cut-off by clinical variables modestly improved diagnostic accuracy for BNP and NT-proBNP compared with a universal threshold.

CONCLUSIONS

NT-proBNP outperforms BNP for detecting HF in primary care. Personalized instead of universal diagnostic thresholds led to modest improvement.

Post-mortem CT radiomics for the prediction of time since death

OBJECTIVES

Post-mortem interval (PMI) estimation has long been relying on sequential post-mortem changes on the body as a function of extrinsic, intrinsic, and environmental factors. Such factors are difficult to account for in complicated death scenes; thus, PMI estimation can be compromised. Herein, we aimed to evaluate the use of post-mortem CT (PMCT) radiomics for the differentiation between early and late PMI.

METHODS

Consecutive whole-body PMCT examinations performed between 2016 and 2021 were retrospectively included (n = 120), excluding corpses without an accurately reported PMI (n = 23). Radiomics data were extracted from liver and pancreas tissue and randomly split into training and validation sets (70:30%). Following data preprocessing, significant features were selected (Boruta selection) and three XGBoost classifiers were built (liver, pancreas, combined) to differentiate between early (< 12 h) and late (> 12 h) PMI. Classifier performance was assessed with receiver operating characteristics (ROC) curves and areas under the curves (AUC), which were compared by bootstrapping.

RESULTS

A total of 97 PMCTs were included, representing individuals (23 females and 74 males) with a mean age of 47.1 ± 23.38 years. The combined model achieved the highest AUC reaching 75% (95%CI 58.4-91.6%) (p = 0.03 compared to liver and p = 0.18 compared to pancreas). The liver-based and pancreas-based XGBoost models achieved AUCs of 53.6% (95%CI 34.8-72.3%) and 64.3% (95%CI 46.7-81.9%) respectively (p > 0.05 for the comparison between liver- and pancreas-based models).

CONCLUSION

The use of radiomics analysis on PMCT examinations differentiated early from late PMI, unveiling a novel image-based method with important repercussions in forensic casework.

CLINICAL RELEVANCE STATEMENT

This paper introduces the employment of radiomics in forensic diagnosis by presenting an effective automated alternative method of estimating post-mortem interval from targeted tissues, thus paving the way for improvement in speed and quality of forensic investigations.

KEY POINTS

• A combined liver-pancreas radiomics model differentiated early from late post-mortem intervals (using a 12-h threshold) with an area under the curve of 75% (95%CI 58.4-91.6%). • XGBoost models based on liver-only or pancreas-only radiomics demonstrated inferior performance to the combined model in predicting the post-mortem interval.

Diagnostic Accuracy of Abdominal CT for Locally Advanced Colon Tumors: Can We Really Entrust Certain Decisions to the Reliability of CT?

Many different options of neoadjuvant treatments for advanced colon cancer are emerging. An accurate preoperative staging is crucial to select the most appropriate treatment option. A retrospective study was carried out on a national series of operated patients with T4 tumors. Considering the anatomo-pathological analysis of the surgical specimen as the gold standard, a diagnostic accuracy study was carried out on the variables T and N staging and the presence of peritoneal metastases (M1c). The parameters calculated were sensitivity, specificity, positive and negative predictive values, and positive and negative likelihood ratios, as well as the overall accuracy. A total of 50 centers participated in the study in which 1950 patients were analyzed. The sensitivity of CT for correct staging of T4 colon tumors was 57%. Regarding N staging, the overall accuracy was 63%, with a sensitivity of 64% and a specificity of 62%; however, the positive and negative likelihood ratios were 1.7 and 0.58, respectively. For the diagnosis of peritoneal metastases, the accuracy was 94.8%, with a sensitivity of 40% and specificity of 98%; in the case of peritoneal metastases, the positive and negative likelihood ratios were 24.4 and 0.61, respectively. The diagnostic accuracy of CT in the setting of advanced colon cancer still has some shortcomings for accurate diagnosis of stage T4, correct classification of lymph nodes, and preoperative detection of peritoneal metastases.

The LEAP checklist for laboratory evaluation and analytical performance characteristics reporting of clinical measurement procedures

Reporting a measurement procedure and its analytical performance following method evaluation in a peer-reviewed journal is an important means for clinical laboratory practitioners to share their findings. It also represents an important source of evidence base to help others make informed decisions about their practice. At present, there are significant variations in the information reported in laboratory medicine journal publications describing the analytical performance of measurement procedures. These variations also challenge authors, readers, reviewers, and editors in deciding the quality of a submitted manuscript. The International Federation of Clinical Chemistry and Laboratory Medicine Working Group on Method Evaluation Protocols (IFCC WG-MEP) developed a checklist and recommends its adoption to enable a consistent approach to reporting method evaluation and analytical performance characteristics of measurement procedures in laboratory medicine journals. It is envisioned that the LEAP checklist will improve the standardisation of journal publications describing method evaluation and analytical performance characteristics, improving the quality of the evidence base that is relied upon by practitioners.