A deep-learning model for intracranial aneurysm detection on CT angiography images in China: a stepwise, multicentre, early-stage clinical validation study

BACKGROUND

Artificial intelligence (AI) models in real-world implementation are scarce. Our study aimed to develop a CT angiography (CTA)-based AI model for intracranial aneurysm detection, assess how it helps clinicians improve diagnostic performance, and validate its application in real-world clinical implementation.

METHODS

We developed a deep-learning model using 16 546 head and neck CTA examination images from 14 517 patients at eight Chinese hospitals. Using an adapted, stepwise implementation and evaluation, 120 certified clinicians from 15 geographically different hospitals were recruited. Initially, the AI model was externally validated with images of 900 digital subtraction angiography-verified CTA cases (examinations) and compared with the performance of 24 clinicians who each viewed 300 of these cases (stage 1). Next, as a further external validation a multi-reader multi-case study enrolled 48 clinicians to individually review 298 digital subtraction angiography-verified CTA cases (stage 2). The clinicians reviewed each CTA examination twice (ie, with and without the AI model), separated by a 4-week washout period. Then, a randomised open-label comparison study enrolled 48 clinicians to assess the acceptance and performance of this AI model (stage 3). Finally, the model was prospectively deployed and validated in 1562 real-world clinical CTA cases.

FINDINGS

The AI model in the internal dataset achieved a patient-level diagnostic sensitivity of 0·957 (95% CI 0·939-0·971) and a higher patient-level diagnostic sensitivity than clinicians (0·943 [0·921-0·961] vs 0·658 [0·644-0·672]; p<0·0001) in the external dataset. In the multi-reader multi-case study, the AI-assisted strategy improved clinicians' diagnostic performance both on a per-patient basis (the area under the receiver operating characteristic curves [AUCs]; 0·795 [0·761-0·830] without AI vs 0·878 [0·850-0·906] with AI; p<0·0001) and a per-aneurysm basis (the area under the weighted alternative free-response receiver operating characteristic curves; 0·765 [0·732-0·799] vs 0·865 [0·839-0·891]; p<0·0001). Reading time decreased with the aid of the AI model (87·5 s vs 82·7 s, p<0·0001). In the randomised open-label comparison study, clinicians in the AI-assisted group had a high acceptance of the AI model (92·6% adoption rate), and a higher AUC when compared with the control group (0·858 [95% CI 0·850-0·866] vs 0·789 [0·780-0·799]; p<0·0001). In the prospective study, the AI model had a 0·51% (8/1570) error rate due to poor-quality CTA images and recognition failure. The model had a high negative predictive value of 0·998 (0·994-1·000) and significantly improved the diagnostic performance of clinicians; AUC improved from 0·787 (95% CI 0·766-0·808) to 0·909 (0·894-0·923; p<0·0001) and patient-level sensitivity improved from 0·590 (0·511-0·666) to 0·825 (0·759-0·880; p<0·0001).

INTERPRETATION

This AI model demonstrated strong clinical potential for intracranial aneurysm detection with improved clinician diagnostic performance, high acceptance, and practical implementation in real-world clinical cases.

FUNDING

National Natural Science Foundation of China.

TRANSLATION

For the Chinese translation of the abstract see Supplementary Materials section.

Combined brain topological metrics with machine learning to distinguish essential tremor and tremor-dominant Parkinson's disease

BACKGROUND

Essential tremor (ET) and Parkinson's disease (PD) are the two most prevalent movement disorders, sharing several overlapping tremor clinical features. Although growing evidence pointed out that changes in similar brain network nodes are associated with these two diseases, the brain network topological properties are still not very clear.

OBJECTIVE

The combination of graph theory analysis with machine learning (ML) algorithms provides a promising way to reveal the topological pathogenesis in ET and tremor-dominant PD (tPD).

METHODS

Topological metrics were extracted from Resting-state functional images of 86 ET patients, 86 tPD patients, and 86 age- and sex-matched healthy controls (HCs). Three steps were conducted to feature dimensionality reduction and four frequently used classifiers were adopted to discriminate ET, tPD, and HCs.

RESULTS

A support vector machine classifier achieved the best classification performance of four classifiers for discriminating ET, tPD, and HCs with 89.0% mean accuracy (mACC) and was used for binary classification. Particularly, the binary classification performances among ET vs. tPD, ET vs. HCs, and tPD vs. HCs were with 94.2% mACC, 86.0% mACC, and 86.3% mACC, respectively. The most power discriminative features were mainly located in the default, frontal-parietal, cingulo-opercular, sensorimotor, and cerebellum networks. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with clinical characteristics.

CONCLUSIONS

These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET, tPD, and HCs but also help to reveal the potential brain topological network pathogenesis in ET and tPD.

Nomogram for preoperative differentiation of benign and malignant breast tumors using contrast-enhanced cone-beam breast CT (CE CB-BCT) quantitative imaging and assessment features

PURPOSE

Breast cancer's impact necessitates refined diagnostic approaches. This study develops a nomogram using radiology quantitative features from contrast-enhanced cone-beam breast CT for accurate preoperative classification of benign and malignant breast tumors.

MATERIAL AND METHODS

A retrospective study enrolled 234 females with breast tumors, split into training and test sets. Contrast-enhanced cone-beam breast CT-images were acquired using Koning Breast CT-1000. Quantitative assessment features were extracted via 3D-slicer software, identifying independent predictors. The nomogram was constructed to preoperative differentiation benign and malignant breast tumors. Calibration curve was used to assess whether the model showed favorable correspondence with pathological confirmation. Decision curve analysis confirmed the model's superiority.

RESULTS

The study enrolled 234 female patients with a mean age of 50.2 years (SD ± 9.2). The training set had 164 patients (89 benign, 75 malignant), and the test set had 70 patients (29 benign, 41 malignant). The nomogram achieved excellent predictive performance in distinguishing benign and malignant breast lesions with an AUC of 0.940 (95% CI 0.900-0.940) in the training set and 0.970 (95% CI 0.940-0.970) in the test set.

CONCLUSION

This study illustrates the effectiveness of quantitative radiology features derived from contrast-enhanced cone-beam breast CT in distinguishing between benign and malignant breast tumors. Incorporating these features into a nomogram-based diagnostic model allows for breast tumor diagnoses that are objective and possess good accuracy. The application of these insights could substantially increase reliability and efficacy in the management of breast tumors, offering enhanced diagnostic capability.

Computed tomography-based 3D convolutional neural network deep learning model for predicting micropapillary or solid growth pattern of invasive lung adenocarcinoma

PURPOSE

To investigate the value of a computed tomography (CT)-based deep learning (DL) model to predict the presence of micropapillary or solid (M/S) growth pattern in invasive lung adenocarcinoma (ILADC).

MATERIALS AND METHODS

From June 2019 to October 2022, 617 patients with ILADC who underwent preoperative chest CT scans in our institution were randomly placed into training and internal validation sets in a 4:1 ratio, and 353 patients with ILADC from another institution were included as an external validation set. Then, a self-paced learning (SPL) 3D Net was used to establish two DL models: model 1 was used to predict the M/S growth pattern in ILADC, and model 2 was used to predict that pattern in ≤ 2-cm-diameter ILADC.

RESULTS

For model 1, the training cohort's area under the curve (AUC), accuracy, recall, precision, and F1-score were 0.924, 0.845, 0.851, 0.842, and 0.843; the internal validation cohort's were 0.807, 0.744, 0.756, 0.750, and 0.743; and the external validation cohort's were 0.857, 0.805, 0.804, 0.806, and 0.804, respectively. For model 2, the training cohort's AUC, accuracy, recall, precision, and F1-score were 0.946, 0.858, 0.881,0.844, and 0.851; the internal validation cohort's were 0.869, 0.809, 0.786, 0.794, and 0.790; and the external validation cohort's were 0.831, 0.792, 0.789, 0.790, and 0.790, respectively. The SPL 3D Net model performed better than the ResNet34, ResNet50, ResNeXt50, and DenseNet121 models.

CONCLUSION

The CT-based DL model performed well as a noninvasive screening tool capable of reliably detecting and distinguishing the subtypes of ILADC, even in small-sized tumors.

Reconfiguration of Structural and Functional Connectivity Coupling in Patient Subgroups With Adolescent Depression

Importance

Adolescent major depressive disorder (MDD) is associated with serious adverse implications for brain development and higher rates of self-injury and suicide, raising concerns about its neurobiological mechanisms in clinical neuroscience. However, most previous studies regarding the brain alterations in adolescent MDD focused on single-modal images or analyzed images of different modalities separately, ignoring the potential role of aberrant interactions between brain structure and function in the psychopathology.

Objective

To examine alterations of structural and functional connectivity (SC-FC) coupling in adolescent MDD by integrating both diffusion magnetic resonance imaging (MRI) and resting-state functional MRI data.

Design, Setting, and Participants

This cross-sectional study recruited participants aged 10 to 18 years from January 2, 2020, to December 28, 2021. Patients with first-episode MDD were recruited from the outpatient psychiatry clinics at The First Affiliated Hospital of Chongqing Medical University. Healthy controls were recruited by local media advertisement from the general population in Chongqing, China. The sample was divided into 5 subgroup pairs according to different environmental stressors and clinical characteristics. Data were analyzed from January 10, 2022, to February 20, 2023.

Main Outcomes and Measures

The SC-FC coupling was calculated for each brain region of each participant using whole-brain SC and FC. Primary analyses included the group differences in SC-FC coupling and clinical symptom associations between SC-FC coupling and participants with adolescent MDD and healthy controls. Secondary analyses included differences among 5 types of MDD subgroups: with or without suicide attempt, with or without nonsuicidal self-injury behavior, with or without major life events, with or without childhood trauma, and with or without school bullying.

Results

Final analyses examined SC-FC coupling of 168 participants with adolescent MDD (mean [mean absolute deviation (MAD)] age, 16.0 [1.7] years; 124 females [73.8%]) and 101 healthy controls (mean [MAD] age, 15.1 [2.4] years; 61 females [60.4%]). Adolescent MDD showed increased SC-FC coupling in the visual network, default mode network, and insula (Cohen d ranged from 0.365 to 0.581; false discovery rate [FDR]-corrected P < .05). Some subgroup-specific alterations were identified via subgroup analyses, particularly involving parahippocampal coupling decrease in participants with suicide attempt (partial η2 = 0.069; 90% CI, 0.025-0.121; FDR-corrected P = .007) and frontal-limbic coupling increase in participants with major life events (partial η2 ranged from 0.046 to 0.068; FDR-corrected P < .05).

Conclusions and Relevance

Results of this cross-sectional study suggest increased SC-FC coupling in adolescent MDD, especially involving hub regions of the default mode network, visual network, and insula. The findings enrich knowledge of the aberrant brain SC-FC coupling in the psychopathology of adolescent MDD, underscoring the vulnerability of frontal-limbic SC-FC coupling to external stressors and the parahippocampal coupling in shaping future-minded behavior.

Differences in Patellofemoral Alignment Between Static and Dynamic Extension Positions in Patients With Patellofemoral Pain

Background

Considering that patellofemoral pain (PFP) is related to dynamic factors, dynamic extension on 4-dimensional computed tomography (4-DCT) may better reflect the influence of muscles and surrounding soft tissue than static extension.

Purpose

To compare the characteristics of patellofemoral alignment between the static and dynamic knee extension position in patients with PFP and controls via 4-DCT.

Study Design

Cross-sectional study; Level of evidence, 3.

Methods

Included were 39 knees (25 patients) with PFP and 37 control knees (24 participants). For each knee, an image of the dynamic extension position (a single frame of the knee in full extension [flexion angle of -5° to 0°] selected from 21 frames of continuous images acquired by 4-DCT during active flexion and extension) and an image of the static extension position (acquired using the same equipment with the knee fully extended and the muscles relaxed) were selected. Patellofemoral alignment was evaluated between the dynamic and static extension positions and between the PFP and control groups with the following parameters: patella-patellar tendon angle (P-PTA), Blackburne-Peel ratio, bisect-offset (BO) index, lateral patellar tilt (LPT), and tibial tuberosity-trochlear groove (TT-TG) distance.

Results

In both PFP patients and controls, the P-PTA, Blackburne-Peel ratio, and BO index in the static extension position were significantly lower (P < .001 for all), while the LPT and TT-TG distance in the static extension position were significantly higher (P ≤ .034 and P < .001, respectively) compared with values in the dynamic extension position. In the comparison between groups, only P-PTA in the static extension position was significantly different (134.97° ± 4.51° [PFP] vs 137.82° ± 5.63° [control]; P = .027). No difference was found in the rate of change from the static to the dynamic extension position of any parameter between the study groups.

Conclusion

The study results revealed significant differences in patellofemoral alignment characteristics between the static and dynamic extension positions of PFP patients and controls. Multiplanar measurements may have a role in subsequent patellofemoral alignment evaluation.

Innovative Neuroimaging Biomarker Distinction of Major Depressive Disorder and Bipolar Disorder through Structural Connectome Analysis and Machine Learning Models

Major depressive disorder (MDD) and bipolar disorder (BD) share clinical features, which complicates their differentiation in clinical settings. This study proposes an innovative approach that integrates structural connectome analysis with machine learning models to discern individuals with MDD from individuals with BD. High-resolution MRI images were obtained from individuals diagnosed with MDD or BD and from HCs. Structural connectomes were constructed to represent the complex interplay of brain regions using advanced graph theory techniques. Machine learning models were employed to discern unique connectivity patterns associated with MDD and BD. At the global level, both BD and MDD patients exhibited increased small-worldness compared to the HC group. At the nodal level, patients with BD and MDD showed common differences in nodal parameters primarily in the right amygdala and the right parahippocampal gyrus when compared with HCs. Distinctive differences were found mainly in prefrontal regions for BD, whereas MDD was characterized by abnormalities in the left thalamus and default mode network. Additionally, the BD group demonstrated altered nodal parameters predominantly in the fronto-limbic network when compared with the MDD group. Moreover, the application of machine learning models utilizing structural brain parameters demonstrated an impressive 90.3% accuracy in distinguishing individuals with BD from individuals with MDD. These findings demonstrate that combined structural connectome and machine learning enhance diagnostic accuracy and may contribute valuable insights to the understanding of the distinctive neurobiological signatures of these psychiatric disorders.

Revolutionizing vascular imaging: trends and future directions of 4D flow MRI based on a 20-year bibliometric analysis

Background

Four-dimensional flow magnetic resonance imaging (4D flow MRI) is a promising new technology with potential clinical value in hemodynamic quantification. Although an increasing number of articles on 4D flow MRI have been published over the past decades, few studies have statistically analyzed these published articles. In this study, we aimed to perform a systematic and comprehensive bibliometric analysis of 4D flow MRI to explore the current hotspots and potential future directions.

Methods

The Web of Science Core Collection searched for literature on 4D flow MRI between 2003 and 2022. CiteSpace was utilized to analyze the literature data, including co-citation, cooperative network, cluster, and burst keyword analysis.

Results

A total of 1,069 articles were extracted for this study. The main research hotspots included the following: quantification and visualization of blood flow in different clinical settings, with keywords such as "cerebral aneurysm", "heart", "great vessel", "tetralogy of Fallot", "portal hypertension", and "stiffness"; optimization of image acquisition schemes, such as "resolution" and "reconstruction"; measurement and analysis of flow components and patterns, as indicated by keywords "pattern", "KE", "WSS", and "fluid dynamics". In addition, international consensus for metrics derived from 4D flow MRI and multimodality imaging may also be the future research direction.

Conclusions

The global domain of 4D flow MRI has grown over the last 2 decades. In the future, 4D flow MRI will evolve towards becoming a relatively short scan duration with adequate spatiotemporal resolution, expansion into the diagnosis and treatment of vascular disease in other related organs, and a shift in focus from vascular structure to function. In addition, artificial intelligence (AI) will assist in the clinical promotion and application of 4D flow MRI.

Development and validation of a CT-based deep learning radiomics nomogram to predict muscle invasion in bladder cancer

Objective

This study aimed to develop a nomogram combining CT-based handcrafted radiomics and deep learning (DL) features to preoperatively predict muscle invasion in bladder cancer (BCa) with multi-center validation.

Methods

In this retrospective study, 323 patients underwent radical cystectomy with pathologically confirmed BCa were enrolled and randomly divided into the training cohort (n = 226) and internal validation cohort (n = 97). And fifty-two patients from another independent medical center were enrolled as an independent external validation cohort. Handcrafted radiomics and DL features were constructed from preoperative nephrographic phase CT images. Least absolute shrinkage and selection operator (LASSO) regression was used to identify the most discriminative features in train cohort. Multivariate logistic regression was used to develop the predictive model and a deep learning radiomics nomogram (DLRN) was constructed. The predictive performance of models was evaluated by area under the curves (AUC) in the three cohorts. The calibration and clinical usefulness of DLRN were estimated by calibration curve and decision curve analysis.

Results

The nomogram that incorporated radiomics signature and DL signature demonstrated satisfactory predictive performance for differentiating non-muscle invasive bladder cancer (NMIBC) from muscle invasive bladder cancer (MIBC), with an AUC of 0.884 (95 % CI: 0.813-0.953) in internal validation cohort and 0.862 (95 % CI: 0.756-0.968) in external validation cohort, respectively. Decision curve analysis confirmed the clinical usefulness of the nomogram.

Conclusions

A CT-based deep learning radiomics nomogram exhibited a promising performance for preoperative prediction of muscle invasion in bladder cancer, and may be helpful in the clinical decision-making process.

Comparison of different classification systems for pulmonary nodules: a multicenter retrospective study in China

BACKGROUND

To compare the diagnostic performance of Lung-RADS (lung imaging-reporting and data system) 2022 and PNI-GARS (pulmonary node imaging-grading and reporting system).

METHODS

Pulmonary nodules (PNs) were selected at four centers, namely, CQ Center (January 1, 2018-December 31, 2021), HB Center (January 1, 2021-June 30, 2022), SC Center (September 1, 2021-December 31, 2021), and SX Center (January 1, 2021-December 31, 2021). PNs were divided into solid nodules (SNs), partial solid nodules (PSNs) and ground-glass nodules (GGNs), and they were then classified by the Lung-RADS and PNI-GARS. The sensitivity, specificity and agreement rate were compared between the two systems by the χ2 test.

RESULTS

For SN and PSN, the sensitivity of PNI-GARS and Lung-RADS was close (SN 99.8% vs. 99.4%, P < 0.001; PSN 99.9% vs. 98.4%, P = 0.015), but the specificity (SN 51.2% > 35.1%, PSN 13.3% > 5.7%, all P < 0.001) and agreement rate (SN 81.1% > 74.5%, P < 0.001, PSN 94.6% > 92.7%, all P < 0.05) of PNI-GARS were superior to those of Lung-RADS. For GGN, the sensitivity (96.5%) and agreement rate (88.6%) of PNI-GARS were better than those of Lung-RADS (0, 18.5%, P < 0.001). For the whole sample, the sensitivity (98.5%) and agreement rate (87.0%) of PNI-GARS were better than Lung-RADS (57.5%, 56.5%, all P < 0.001), whereas the specificity was slightly lower (49.8% < 53.4%, P = 0.003).

CONCLUSION

PNI-GARS was superior to Lung-RADS in diagnostic performance, especially for GGN.

Non-contrast enhanced MRI for efficiency evaluation of high-intensity focused ultrasound in adenomyosis ablation

OBJECTIVE

To investigate the value of T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) in evaluating the therapeutic effect of high-intensity focused ultrasound (HIFU) in adenomyosis ablation.

MATERIAL AND METHODS

One hundred eighty-nine patients with adenomyosis were treated with HIFU. The ablation areas on T2WI and DWI sequences were classified into different types: type I, relatively ill-defined rim or unrecognizable; subtype IIa, well-defined rim with hyperintensity; subtype IIb, well-defined rim with hypointensity. The volume of ablation areas on T2WI (VT2WI) and DWI (VDWI) was measured and compared with the non-perfused volume (NPV), and linear regression was conducted to analyze their correlation with NPV.

RESULTS

The VT2WI of type I and type II (subtype IIa and subtype IIb) were statistically different from the corresponding NPV (p = 0.004 and 0.024, respectively), while no significant difference was found between the VDWI of type I and type II with NPV (p = 0.478 and 0.561, respectively). In the linear regression analysis, both VT2WI and VDWI were positively correlated with NPV, with R2 reaching 0.96 and 0.97, respectively.

CONCLUSIONS

Both T2WI and DWI have the potential for efficient evaluation of HIFU treatment in adenomyosis, and DWI can be a replacement for CE-T1WI to some extent.

Factors influencing magnetic resonance imaging changes associated with pelvic bone injury after high-intensity focused ultrasound ablation of uterine fibroids: a retrospective case-control study

Background

The application of high-intensity focused ultrasound (HIFU) in the treatment of uterine fibroids is becoming increasingly widespread, and postoperative collateral thermal damage to adjacent tissue has become a prominent subject of discussion. However, there is limited research related to bone injury. Therefore, the aim of this study was to investigate the potential factors influencing unintentional pelvic bone injury after HIFU ablation of uterine fibroids with magnetic resonance imaging (MRI).

Methods

A total of 635 patients with fibroids treated with HIFU in the First Affiliated Hospital of Chongqing Medical University were enrolled. All patients underwent contrast-enhanced MRI (CE-MRI) pre- and post-HIFU. Based on the post-treatment MRI, the patients were divided into two groups: pelvic bone injury group and non-injury group, while the specific site of pelvic bone injury of each patient was recorded. The univariate and multivariate analyses were used to assess the correlations between the factors of fibroid features and treatment parameters and pelvic bone injury, and to further analyze the factors influencing the site of injury.

Results

Signal changes in the pelvis were observed on CE-MRI in 51% (324/635) of patients after HIFU. Among them, 269 (42.4%) patients developed sacral injuries and 135 (21.3%) had pubic bone injuries. Multivariate analyses showed that patients with higher age [P=0.003; odds ratio (OR), 1.692; 95% confidence interval (CI): 1.191-2.404], large anterior side-to-skin distance of fibroid (P<0.001; OR, 2.297; 95% CI: 1.567-3.365), posterior wall fibroid (P=0.006; OR, 1.897; 95% CI: 1.204-2.989), hyperintensity on T2-weighted imaging (T2WI, P=0.003; OR, 2.125; 95% CI: 1.283-3.518), and large therapeutic dose (TD, P<0.001; OR, 3.007; 95% CI: 2.093-4.319) were at higher risk of postoperative pelvic bone injury. Further analysis of the factors influencing the site of the pelvic bone injury showed that some of the fibroid features and treatment parameters were associated with it. Moreover, some postoperative pain-related adverse events were associated with the pelvic bone injury.

Conclusions

Post-HIFU treatment, patients may experience pelvic injuries to the sacrum, pubis, or a combination of both, and some of them experienced adverse events. Some fibroid features and treatment parameters are associated with the injury. Taking its influencing factors into full consideration preoperatively, slowing down treatment, and prolonging intraoperative cooling phase can help optimize treatment decisions for HIFU.

Prediction of non-perfusion volume ratio for uterine fibroids treated with ultrasound-guided high-intensity focused ultrasound based on MRI radiomics combined with clinical parameters

BACKGROUND

Prediction of non-perfusion volume ratio (NPVR) is critical in selecting patients with uterine fibroids who will potentially benefit from ultrasound-guided high-intensity focused ultrasound (HIFU) treatment, as it reduces the risk of treatment failure. The purpose of this study is to construct an optimal model for predicting NPVR based on T2-weighted magnetic resonance imaging (T2MRI) radiomics features combined with clinical parameters by machine learning.

MATERIALS AND METHODS

This retrospective study was conducted among 223 patients diagnosed with uterine fibroids from two centers. The patients from one center were allocated to a training cohort (n = 122) and an internal test cohort (n = 46), and the data from the other center (n = 55) was used as an external test cohort. The least absolute shrinkage and selection operator (LASSO) algorithm was employed for feature selection in the training cohort. The support vector machine (SVM) was adopted to construct a radiomics model, a clinical model, and a radiomics-clinical model for NPVR prediction, respectively. The area under the curve (AUC) and the decision curve analysis (DCA) were performed to evaluate the predictive validity and the clinical usefulness of the model, respectively.

RESULTS

A total of 851 radiomic features were extracted from T2MRI, of which seven radiomics features were screened for NPVR prediction-related radiomics features. The radiomics-clinical model combining radiomics features and clinical parameters showed the best predictive performance in both the internal (AUC = 0.824, 95% CI 0.693-0.954) and external (AUC = 0.773, 95% CI 0.647-0.902) test cohorts, and the DCA also suggested the radiomics-clinical model had the highest net benefit.

CONCLUSIONS

The radiomics-clinical model could be applied to the NPVR prediction of patients with uterine fibroids treated by HIFU to provide an objective and effective method for selecting potential patients who would benefit from the treatment mostly.

Clinicopathological and computed tomography features associated with recurrence-free survival of patients with small-sized peripheral invasive lung adenocarcinoma after sublobectomy

Background

Sublobar resection is gradually becoming a standard treatment for small-sized (≤2 cm) peripheral non-small cell lung cancer (NSCLC), with lung adenocarcinoma (LADC) being the most frequent histologic subtype. However, the prognostic predictors for preoperatively determining whether sublobectomy is feasible for patients with early LADC have not yet been well identified. Therefore, this study aimed to investigate the clinicopathological and computed tomography (CT) features associated with the recurrence-free survival (RFS) of patients with small-sized invasive LADC (SILADC) after sublobar resection.

Methods

This retrospective cohort study analyzed 107 patients with SILADC who underwent preoperative chest CT scan and sublobar resection from December 2012 to March 2019. The Kaplan-Meier survival was used to analyze the relationship between clinicopathological characteristics, preoperative chest CT findings, and RFS. The Cox proportional hazards regression was used to identify independent prognostic factors of poor RFS.

Results

For clinicopathological characteristics, RFS was shorter in patients aged ≥70 years, smokers, and those with micropapillary/solid-predominant adenocarcinomas (all P values <0.05). For preoperative CT features, RFS was shorter in patients with tumor size ≥1.4 cm, solid component size ≥1.1 cm, proportion of solid component ≥72%, solid density, spiculation, vascular convergence sign, peripheral fibrosis, and type II pleural tag (all P values <0.05). Multivariate analysis showed proportion of solid component ≥72% [hazard ratio (HR): 5.920; P=0.006; 95% confidence interval (CI): 1.686-20.794], spiculation (HR: 5.026; P=0.001; 95% CI: 2.008-12.581), and type II pleural tag (HR: 4.638; P=0.002; 95% CI: 1.773-12.136) were independent risk factors for poor prognosis in patients with SILADC after sub-lobectomy.

Conclusions

Clinicopathological and CT characteristics are helpful for predicting the RFS of patients with SILADC after sublobar resection and can be used as an auxiliary tool for thoracic surgeons to choose the best surgical mode.

A Combined Model Integrating Radiomics and Deep Learning Based on Contrast-Enhanced CT for Preoperative Staging of Laryngeal Carcinoma

RATIONALE AND OBJECTIVES

Accurate staging of laryngeal carcinoma can inform appropriate treatment decision-making. We developed a radiomics model, a deep learning (DL) model, and a combined model (incorporating radiomics features and DL features) based on the venous-phase CT images and explored the performance of these models in stratifying patients with laryngeal carcinoma into stage I-II and stage III-IV, and also compared these models with radiologists.

MATERIALS AND METHODS

Three hundreds and nineteen patients with pathologically confirmed laryngeal carcinoma were randomly divided into a training set (n = 223) and a test set (n = 96). In the training set, the radiomics features with inter- and intraclass correlation coefficients (ICCs)> 0.75 were screened by Spearman correlation analysis and recursive feature elimination (RFE); then support vector machine (SVM) classifier was applied to develop the radiomics model. The DL model was built using ResNet 18 by the cropped 2D regions of interest (ROIs) in the maximum tumor ROI slices and the last fully connected layer of this network served as the DL feature extractor. Finally, a combined model was developed by pooling the radiomics features and extracted DL features to predict the staging.

RESULTS

The area under the curves (AUCs) for radiomics model, DL model, and combined model in the test set were 0.704 (95% confidence interval [CI]: 0.588-0.820), 0.724 (95% CI: 0.613-0.835), and 0.849 (95% CI: 0.755-0.943), respectively. The combined model outperformed the radiomics model and the DL model in discriminating stage I-II from stage III-IV (p = 0.031 and p = 0.020, respectively). Only the combined model performed significantly better than radiologists (p < 0.050 for both).

CONCLUSION

The combined model can help tailor the therapeutic strategy for laryngeal carcinoma patients by enabling more accurate preoperative staging.

Growth characteristics of early-stage (IA) lung adenocarcinoma and its value in predicting lymph node metastasis

BACKGROUND

We aim to compare the differences in growth characteristics between part-solid and solid lung adenocarcinoma, and to investigate the value of volume doubling time (VDT) or mass doubling time (MDT) in predicting lymph node (LN) metastasis and preoperative evaluation in patients of early-stage (IA) non-small cell lung cancer (NSCLC).

METHOD

We reviewed 8,653 cases of surgically resected stage IA lung adenocarcinoma between 2018 and 2022, with two follow-up visits at least 3 months apart, comparing diameter, volume, and mass growth of pSN and SN. VDT and MDT calculations for nodules with a volume change of at least 25%. Univariable or multivariable analysis was used to identify the risk factors. The area under the curve (AUC) for the receiver operating characteristic (ROC) curves was used to evaluate the diagnostic value.

RESULTS

A total of 144 patients were included 114 with solid nodules (SN) and 25 with part-solid nodules (pSN). During the follow-up period, the mean VDTt and MDTt of SN were shorter than those of pSN, 337 vs. 541 days (p = 0.005), 298 vs. 458 days (p = 0.018), respectively. Without considering the ground-glass component, the mean VDTc and MDTc of SN were shorter than the solid component of pSN, 337 vs. 498 days (p = 0.004) and 298 vs. 453 days (p = 0.003), respectively. 27 nodules were clinically and pathologically diagnosed as N1/N2. Logistic regression identified initial diameter (p < 0.001), consolidation increase (p = 0.019), volume increase (p = 0.020), mass increase (p = 0.021), VDTt (p = 0.002), and MDTt (p = 0.004) were independent factors for LN metastasis. The ROC curves showed that the AUC for VDTt was 0.860 (95% CI, 0.778-0.943; p < 0.001) and for MDTt was 0.848 (95% CI, 0.759-0.936; p < 0.001).

CONCLUSIONS

Our study showed significant differences in the growth characteristics of pSN and SN, and the application of VDT and MDT could be a valid predictor LN metastasis in patients with early-stage NSCLC.

Potential application of peripheral blood biomarkers in intracranial aneurysms

Intracranial aneurysm (IA) counts are increasing yearly, with a high mortality and disability after rupture. Current diagnosis and treatment rely on costly equipment, lacking effective indicators for progression prediction and specific drugs for treatment. Recently, peripheral blood biomarkers, as common clinical test samples, reflecting the immune and inflammatory state of the body in real-time, have shown promise in providing additional information for risk stratification and treatment in IA patients, which may improve their outcomes after aneurysm rupture through anti-inflammatory therapy. Therefore, this paper reviewed the progress of potential biomarkers of IAs, including inflammatory blood indicators, cytokines, and blood lipids, aiming to aid individual management and therapy of aneurysms in clinical practices.

Validity of a multiphase CT-based radiomics model in predicting the Leibovich risk groups for localized clear cell renal cell carcinoma: an exploratory study

OBJECTIVE

To develop and validate a multiphase CT-based radiomics model for preoperative risk stratification of patients with localized clear cell renal cell carcinoma (ccRCC).

METHODS

A total of 425 patients with localized ccRCC were enrolled and divided into training, validation, and external testing cohorts. Radiomics features were extracted from three-phase CT images (unenhanced, arterial, and venous), and radiomics signatures were constructed by the least absolute shrinkage and selection operator (LASSO) regression algorithm. The radiomics score (Rad-score) for each patient was calculated. The radiomics model was established and visualized as a nomogram by incorporating significant clinical factors and Rad-score. The predictive performance of the radiomics model was evaluated by the receiver operating characteristic curve, calibration curve, and decision curve analysis (DCA).

RESULTS

The AUC of the triphasic radiomics signature reached 0.862 (95% CI: 0.809-0.914), 0.853 (95% CI: 0.785-0.921), and 0.837 (95% CI: 0.714-0.959) in three cohorts, respectively, which were higher than arterial, venous, and unenhanced radiomics signatures. Multivariate logistic regression analysis showed that Rad-score (OR: 4.066, 95% CI: 3.495-8.790) and renal vein invasion (OR: 12.914, 95% CI: 1.118-149.112) were independent predictors and used to develop the radiomics model. The radiomics model showed good calibration and discrimination and yielded an AUC of 0.872 (95% CI: 0.821-0.923), 0.865 (95% CI: 0.800-0.930), and 0.848 (95% CI: 0.728-0.967) in three cohorts, respectively. DCA showed the clinical usefulness of the radiomics model in predicting the Leibovich risk groups.

CONCLUSIONS

The radiomics model can be used as a non-invasive and useful tool to predict the Leibovich risk groups for localized ccRCC patients.

CRITICAL RELEVANCE STATEMENT

The triphasic CT-based radiomics model achieved favorable performance in preoperatively predicting the Leibovich risk groups in patients with localized ccRCC. Therefore, it can be used as a non-invasive and effective tool for preoperative risk stratification of patients with localized ccRCC.

KEY POINTS

• The triphasic CT-based radiomics signature achieves better performance than the single-phase radiomics signature. • Radiomics holds prospects in preoperatively predicting the Leibovich risk groups for ccRCC. • This study provides a non-invasive method to stratify patients with localized ccRCC.

Childhood trauma is linked to abnormal static-dynamic brain topology in adolescents with major depressive disorder

Childhood trauma is a leading risk factor for adolescents developing major depressive disorder (MDD); however, the underlying neuroimaging mechanisms remain unclear. This study aimed to investigate the association among childhood trauma, MDD and brain dysfunctions by combining static and dynamic brain network models. We recruited 46 first-episode drug-naïve adolescent MDD patients with childhood trauma (MDD-CT), 53 MDD patients without childhood trauma (MDD-nCT), and 90 healthy controls (HCs) for resting-state functional magnetic resonance imaging (fMRI) scans; all participants were aged 13-18 years. Compared to the HCs and MDD-nCT groups, the MDD-CT group exhibited significantly higher global and local efficiency in static brain networks and significantly higher temporal correlation coefficients in dynamic brain network models at the whole-brain level, and altered the local efficiency of default mode network (DMN) and temporal correlation coefficients of DMN, salience (SAN), and attention (ATN) networks at the local perspective. Correlation analysis indicated that altered brain network features and clinical symptoms, childhood trauma, and particularly emotional neglect were highly correlated in adolescents with MDD. This study may provide new evidence for the dysconnectivity hypothesis regarding the associations between childhood trauma and MDD in adolescents from the perspectives of both static and dynamic brain topology.

Effect of body mass index (BMI) on image contrast in the hepatobiliary phase of Gd-EOB-DTPA-enhanced-MRI and the feasibility of the application of half-dose Gd-EOB-DTPA to hepatobiliary phase imaging in patients with a BMI less than 24: a comparative study

Background

Gadolinium-ethoxybenzyl-diethylenetriamine-pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) can detect more lesions through the image contrast of hepatobiliary phase. Body mass index (BMI) reflects the composition ratio of human tissue, which is an influencing factor of magnetic resonance image contrast. Meanwhile, Gd-EOB-DTPA is recommended to use the minimum dose when the diagnosis demands could be met. The aim of this paper was to investigate the effect of BMI on hepatobiliary phase image contrast and explore the feasibility of using low-dose Gd-EOB-DTPA to obtain good hepatobiliary phase image contrast in patients with normal and lean BMI.

Methods

Eighty-two patients who had previously undergone Gd-EOB-DTPA-enhanced MRI (0.025 mmol/kg) were collected and divided into group A (BMI <24 kg/m2) and group B (BMI ≥24 kg/m2) according to Chinese BMI standards. Liver-to-portal vein contrast ratio (LPC20) and liver-to-spleen contrast ratio (LSC20) in hepatobiliary phase (20 min after injection) were calculated. Thirty patients with a BMI <24 kg/m2 who were about to receive Gd-EOB-DTPA-enhanced MRI were randomly divided into group C (0.0125 mmol/kg) and group D (0.025 mmol/kg). Image acquisition was performed at 10, 15, and 20 min after injection. LPC10, LPC15, LPC20 and LSC10, LSC15, LSC20 in corresponding phases were calculated.

Results

In retrospective grouping study, compared with group B, group A's LPC20 was significantly higher [2.63 (2.42-3.00) vs. 2.22 (1.97-2.67); P<0.01]. In prospective grouping study, there were no differences in LPC15, LSC15, LPC20 and LSC20 between group C and group D. Intragroup comparison in each group showed that LPC15 (group C: 2.67±0.33; group D: 2.61±0.21) and LPC20 (group C: 2.74±0.37; group D: 2.72±0.27) were higher than LPC10 (group C: 2.19±0.18; group D: 1.94±0.17) (all P<0.01), while there were no changes between LPC15 and LPC20.

Conclusions

Under conventional dose, hepatobiliary phase image contrast in patients with a BMI <24 was higher, which was mainly manifested in the high LPC. For patients with a BMI <24 kg/m2, using a half conventional dose (0.0125 mmol/kg), good hepatobiliary phase image contrast can still be obtained at 15-20 min after administration.

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study

OBJECTIVES

To develop deep learning-assisted diagnosis models based on CT images to facilitate radiologists in differentiating benign and malignant parotid tumors.

METHODS

Data from 573 patients with histopathologically confirmed parotid tumors from center 1 (training set: n = 269; internal-testing set: n = 116) and center 2 (external-testing set: n = 188) were retrospectively collected. Six deep learning models (MobileNet V3, ShuffleNet V2, Inception V3, DenseNet 121, ResNet 50, and VGG 19) based on arterial-phase CT images, and a baseline support vector machine (SVM) model integrating clinical-radiological features with handcrafted radiomics signatures were constructed. The performance of senior and junior radiologists with and without optimal model assistance was compared. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the clinical benefit of using the optimal model.

RESULTS

MobileNet V3 had the best predictive performance, with sensitivity increases of 0.111 and 0.207 (p < 0.05) in the internal- and external-testing sets, respectively, relative to the SVM model. Clinical benefit and overall efficiency of junior radiologist were significantly improved with model assistance; for the internal- and external-testing sets, respectively, the AUCs improved by 0.128 and 0.102 (p < 0.05), the sensitivity improved by 0.194 and 0.120 (p < 0.05), the NRIs were 0.257 and 0.205 (p < 0.001), and the IDIs were 0.316 and 0.252 (p < 0.001).

CONCLUSIONS

The developed deep learning models can assist radiologists in achieving higher diagnostic performance and hopefully provide more valuable information for clinical decision-making in patients with parotid tumors.

KEY POINTS

• The developed deep learning models outperformed the traditional SVM model in predicting benign and malignant parotid tumors. • Junior radiologist can obtain greater clinical benefits with assistance from the optimal deep learning model. • The clinical decision-making process can be accelerated in patients with parotid tumors using the established deep learning model.

An interpretable MRI-based radiomics model predicting the prognosis of high-intensity focused ultrasound ablation of uterine fibroids

BACKGROUND

Accurate preoperative assessment of the efficacy of high-intensity focused ultrasound (HIFU) ablation for uterine fibroids is essential for good treatment results. The aim of this study was to develop robust radiomics models for predicting the prognosis of HIFU-treated uterine fibroids and to explain the internal predictive process of the model using Shapley additive explanations (SHAP).

METHODS

This retrospective study included 300 patients with uterine fibroids who received HIFU and were classified as having a favorable or unfavorable prognosis based on the postoperative nonperfusion volume ratio. Patients were divided into a training set (N = 240) and a test set (N = 60). The 1295 radiomics features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI) scans. After data preprocessing and feature filtering, radiomics models were constructed by extreme gradient boosting and light gradient boosting machine (LightGBM), and the optimal performance was obtained by Bayesian optimization. Finally, the SHAP approach was used to explain the internal prediction process.

RESULTS

The models constructed using LightGBM had the best performance, and the AUCs of the T2WI and CE-T1WI models were 87.2 (95% CI = 87.1-87.5) and 84.8 (95% CI = 84.6-85.7), respectively. The use of SHAP technology can help physicians understand the impact of radiomic features on the predicted outcomes of the model from a global and individual perspective.

CONCLUSION

Multiparametric radiomic models have shown their robustness in predicting HIFU prognosis. Radiomic features can be a potential source of biomarkers to support preoperative assessment of HIFU treatment and improve the understanding of uterine fibroid heterogeneity.

CLINICAL RELEVANCE STATEMENT

An interpretable radiomics model can help clinicians to effectively predict the prognosis of HIFU treatment for uterine fibroids. The heterogeneity of fibroids can be characterized by various radiomics features and the application of SHAP can be used to visually explain the prediction process of radiomics models.

Proposal of Modified Lung-RADS in Assessing Pulmonary Nodules of Patients with Previous Malignancies: A Primary Study

BACKGROUND

In addition to the diameters of pulmonary nodules, the number and morphology of blood vessels in pure ground-glass nodules (pGGNs) were closely related to the occurrence of lung cancer. Moreover, the benign and malignant signs of nodules were also valuable for the identification of nodules. Based on these two points, we tried to revise Lung-RADS 2022 and proposed our Modified Lung-RADS. The aim of the study was to verify the diagnostic performance of Modified Lung-RADS for pulmonary solid nodules (SNs) and pure ground-glass nodules (pGGNs) in patients with previous malignancies.

METHODS

The chest CT and clinical data of patients with prior cancer who underwent pulmonary nodulectomies from 1 January 2018 to 30 November 2021 were enrolled according to inclusion and exclusion criteria. A total of 240 patients with 293 pulmonary nodules were included in this study. In contrast with the original version, the risk classification of pGGNs based on the GGN-vascular relationships (GVRs), and the SNs without burrs and with benign signs, could be downgraded to category 2. The sensitivity, specificity, and agreement rate of the original Lung-RADS 2022 and Modified Lung-RADS for pGGNs and SNs were calculated and compared.

RESULTS

Compared with the original version, the sensitivity and agreement rate of the Modified version for pGGNs increased from 0 and 23.33% to 97.10% and 92.22%, respectively, while the specificity decreased from 100% to 76.19%. As regards SNs, the specificity and agreement rate of the Modified version increased from 44.44% to 75.00% (p < 0.05) and 88.67% to 94.09% (p = 0.052), respectively, while the sensitivity was unchanged (98.20%).

CONCLUSIONS

In general, the diagnostic efficiency of Modified Lung-RADS was superior to that of the original version, and Modified Lung-RADS could be a preliminary attempt to improve Lung-RADS 2022.

Using histogram analysis of the intrinsic brain activity mapping to identify essential tremor

Background

Essential tremor (ET) is one of the most common movement disorders. Histogram analysis based on brain intrinsic activity imaging is a promising way to identify ET patients from healthy controls (HCs) and further explore the spontaneous brain activity change mechanisms and build the potential diagnostic biomarker in ET patients.

Methods

The histogram features based on the Resting-state functional magnetic resonance imaging (Rs-fMRI) data were extracted from 133 ET patients and 135 well-matched HCs as the input features. Then, a two-sample t-test, the mutual information, and the least absolute shrinkage and selection operator methods were applied to reduce the feature dimensionality. Support vector machine (SVM), logistic regression (LR), random forest (RF), and k-nearest neighbor (KNN) were used to differentiate ET and HCs, and classification performance of the established models was evaluated by the mean area under the curve (AUC). Moreover, correlation analysis was carried out between the selected histogram features and clinical tremor characteristics.

Results

Each classifier achieved a good classification performance in training and testing sets. The mean accuracy and area under the curve (AUC) of SVM, LR, RF, and KNN in the testing set were 92.62%, 0.948; 92.01%, 0.942; 93.88%, 0.941; and 92.27%, 0.939, respectively. The most power-discriminative features were mainly located in the cerebello-thalamo-motor and non-motor cortical pathways. Correlation analysis showed that there were two histogram features negatively and one positively correlated with tremor severity.

Conclusion

Our findings demonstrated that the histogram analysis of the amplitude of low-frequency fluctuation (ALFF) images with multiple machine learning algorithms could identify ET patients from HCs and help to understand the spontaneous brain activity pathogenesis mechanisms in ET patients.

The influence of different previous cancer histories on the diagnostic efficacy of Lung Imaging Reporting and Data System

Background

For lung cancer screening in patients with previous malignant tumors, Lung Imaging Reporting and Data System (Lung-RADS) and other lung cancer screening tools are controversial in terms of requirements for the previous cancer history. This study investigated the effect of the length and type of malignancy history on the diagnostic efficacy of Lung Imaging Reporting and Data System (Lung-RADS) 2022 in pulmonary nodules (PNs).

Methods

Chest computed tomography and clinical data of PNs in patients with a history of cancer who underwent surgical resection in The First Affiliated Hospital of Chongqing Medical University from January 1, 2018, to November 30, 2021, were retrospectively collected and evaluated based on Lung-RADS. All PNs were divided into 2 groups: the prior lung cancer (PLC) and the prior extrapulmonary cancer (PEPC) groups. Each group was divided into the ≥5 years and <5 years groups based on the duration of cancer history. The diagnostic agreement of Lung-RADS was evaluated based on the pathological diagnosis of nodules after operation. The diagnostic agreement rate (AR) of Lung-RADS and the composition ratios of different types between different groups were calculated and compared.

Results

A total of 451 patients with 565 PNs were included in this study. These patients were divided into the PLC group (<5 years: 135 cases, 175 PNs; ≥5 years: 9 cases, 12 PNs) and the PEPC group (<5 years: 219 cases, 278 PNs; ≥5 years: 88 cases, 100 PNs). The diagnostic AR of partial solid nodules (93.0%; 95% CI: 88.7-97.2%) and solid nodules (88.1%; 95% CI: 84.1-92.1%) was close (P=0.13), while both were higher than that of the pure ground-glass nodules (24.0%; 95% CI: 17.5-30.4%; all P values <0.001). Within 5 years, the composition ratio of PNs and the diagnostic AR (PLC: 58.9%, 95% CI: 51.5-66.2%; PEPC: 76.6%, 95% CI: 71.6-81.6%) between the PLC and PEPC groups were all different (all P values <0.001), and the others [composition ratio of PNs & the diagnostic AR: PLC (≥5 years) vs. PEPC (≥5 years); PLC (<5 years) vs. PLC (≥5 years); PEPC (<5 years) vs. PEPC (≥5 years)] were similar (all P values >0.05; range: 0.10-0.93).

Conclusions

The length of prior cancer history may affect the diagnostic agreement of Lung-RADS, especially for patients with prior lung cancer within 5 years.

Altered neurometabolite levels in the brains of patients with depression: A systematic analysis of magnetic resonance spectroscopy studies

BACKGROUND

Numerous magnetic resonance spectroscopy (MRS) studies have reported metabolic abnormalities in the brains of patients with depression, although inconsistent results have been reported. The aim of this study was to explore changes in neurometabolite levels in patients with depression across large-scale MRS studies.

METHOD

A total of 307 differential metabolite entries associated with depression were retrieved from 180 MRS studies retrieved from the Metabolite Network of Depression Database. The vote-counting method was used to identify consistently altered metabolites in the whole brain and specific brain regions of patients with depression.

RESULTS

Only few differential neurometabolites showed a stable change trend. The levels of total choline (tCho) and the tCho/N-acetyl aspartate (NAA) ratio were consistently higher in the brains of patients with depression, and that the levels of NAA, glutamate and glutamine (Glx), and gamma-aminobutyric acid (GABA) were lower. For specific brain regions, we found lower Glx levels in the prefrontal cortex and lower GABA concentrations in the occipital cortex. We also found lower concentrations of NAA in the anterior cingulate cortex and prefrontal cortex. The levels of tCho were higher in the prefrontal cortex and putamen.

CONCLUSION

Our results revealed that most altered neurometabolites in previous studies lack of adequate reproducibility. Through vote-counting method with large-scale studies, downregulation of glutamatergic neurometabolites, impaired neuronal integrity, and disturbed membrane metabolism were found in the pathobiology of depression, which contribute to existing knowledge of neurometabolic changes in depression. Further studies based on a larger dataset are needed to confirm our findings.

DARU‐Net: A dual attention residual U‐Net for uterine fibroids segmentation on MRI

PURPOSE

Uterine fibroid is the most common benign tumor in female reproductive organs. In order to guide the treatment, it is crucial to detect the location, shape, and size of the tumor. This study proposed a deep learning approach based on attention mechanisms to segment uterine fibroids automatically on preoperative Magnetic Resonance (MR) images.

METHODS

The proposed method is based on U-Net architecture and integrates two attention mechanisms: channel attention of squeeze-and-excitation (SE) blocks with residual connections, spatial attention of pyramid pooling module (PPM). We did the ablation study to verify the performance of these two attention mechanisms module and compared DARU-Net with other deep learning methods. All experiments were performed on a clinical dataset consisting of 150 cases collected from our hospital. Among them, 120 cases were used as the training set, and 30 cases are used as the test set. After preprocessing and data augmentation, we trained the network and tested it on the test dataset. We evaluated segmentation performance through the Dice similarity coefficient (DSC), precision, recall, and Jaccard index (JI).

RESULTS

The average DSC, precision, recall, and JI of DARU-Net reached 0.8066 ± 0.0956, 0.8233 ± 0.1255, 0.7913 ± 0.1304, and 0.6743 ± 0.1317. Compared with U-Net and other deep learning methods, DARU-Net was more accurate and stable.

CONCLUSION

This work proposed an optimized U-Net with channel and spatial attention mechanisms to segment uterine fibroids on preoperative MR images. Results showed that DARU-Net was able to accurately segment uterine fibroids from MR images.

The Effect of Magnetic Resonance Imaging Based Radiomics Models in Discriminating stage I-II and III-IVa Nasopharyngeal Carcinoma

BACKGROUND

Nasopharyngeal carcinoma (NPC) is a common tumor in China. Accurate stages of NPC are crucial for treatment. We therefore aim to develop radiomics models for discriminating early-stage (I-II) and advanced-stage (III-IVa) NPC based on MR images.

METHODS

329 NPC patients were enrolled and randomly divided into a training cohort (n = 229) and a validation cohort (n = 100). Features were extracted based on axial contrast-enhanced T1-weighted images (CE-T1WI), T1WI, and T2-weighted images (T2WI). Least absolute shrinkage and selection operator (LASSO) was used to build radiomics signatures. Seven radiomics models were constructed with logistic regression. The AUC value was used to assess classification performance. The DeLong test was used to compare the AUCs of different radiomics models and visual assessment.

RESULTS

Models A, B, C, D, E, F, and G were constructed with 13, 9, 7, 9, 10, 7, and 6 features, respectively. All radiomics models showed better classification performance than that of visual assessment. Model A (CE-T1WI + T1WI + T2WI) showed the best classification performance (AUC: 0.847) in the training cohort. CE-T1WI showed the greatest significance for staging NPC.

CONCLUSION

Radiomics models can effectively distinguish early-stage from advanced-stage NPC patients, and Model A (CE-T1WI + T1WI + T2WI) showed the best classification performance.

Combined brain network topological metrics with machine learning algorithms to identify essential tremor

BACKGROUND AND OBJECTIVE

Essential tremor (ET) is a common movement syndrome, and the pathogenesis mechanisms, especially the brain network topological changes in ET are still unclear. The combination of graph theory (GT) analysis with machine learning (ML) algorithms provides a promising way to identify ET from healthy controls (HCs) at the individual level, and further help to reveal the topological pathogenesis in ET.

METHODS

Resting-state functional magnetic resonance imaging (fMRI) data were obtained from 101 ET and 105 HCs. The topological properties were analyzed by using GT analysis, and the topological metrics under every single threshold and the area under the curve (AUC) of all thresholds were used as features. Then a Mann-Whitney U-test and least absolute shrinkage and selection operator (LASSO) were conducted to feature dimensionality reduction. Four ML algorithms were adopted to identify ET from HCs. The mean accuracy, mean balanced accuracy, mean sensitivity, mean specificity, and mean AUC were used to evaluate the classification performance. In addition, correlation analysis was carried out between selected topological features and clinical tremor characteristics.

RESULTS

All classifiers achieved good classification performance. The mean accuracy of Support vector machine (SVM), logistic regression (LR), random forest (RF), and naïve bayes (NB) was 84.65, 85.03, 84.85, and 76.31%, respectively. LR classifier achieved the best classification performance with 85.03% mean accuracy, 83.97% sensitivity, and an AUC of 0.924. Correlation analysis results showed that 2 topological features negatively and 1 positively correlated with tremor severity.

CONCLUSION

These results demonstrated that combining topological metrics with ML algorithms could not only achieve high classification accuracy for discrimination ET from HCs but also help us to reveal the potential topological pathogenesis of ET.

Combining multiparametric MRI features-based transfer learning and clinical parameters: application of machine learning for the differentiation of uterine sarcomas from atypical leiomyomas

OBJECTIVES

To explore the feasibility and effectiveness of machine learning (ML) based on multiparametric magnetic resonance imaging (mp-MRI) features extracted from transfer learning combined with clinical parameters to differentiate uterine sarcomas from atypical leiomyomas (ALMs).

METHODS

The data of 86 uterine sarcomas between July 2011 and December 2019 and 86 ALMs between June 2013 and June 2017 were retrospectively reviewed. We extracted deep-learning features and radiomics features from T2-weighted imaging (T2WI) and diffusion weighted imaging (DWI). The two feature extraction methods, transfer learning and radiomics, were compared. Random forest was adopted as the classifier. T2WI features, DWI features, combined T2WI and DWI (mp-MRI) features, and combined clinical parameters and mp-MRI features were applied to establish T2, DWI, T2-DWI, and complex multiparameter (mp) models, respectively. Predictive performance was assessed with the area under the receiver operating characteristic curve (AUC).

RESULTS

In the test set, the T2, DWI, T2-DWI and complex mp models based on transfer learning (AUCs range from 0.76 to 0.81, 0.80 to 0.88, 0.85 to 0.92, and 0.94 to 0.96, respectively) outperformed the models based on radiomics (AUCs of 0.73, 0.76, 0.79, and 0.92, respectively). Moreover, the complex mp model showed the best prediction performance, with the Resnet50-complex mp model achieving the highest AUC (0.96) and accuracy (0.87).

CONCLUSIONS

Transfer learning is feasible and superior to radiomics in the differential diagnosis of uterine sarcomas and ALMs in our dataset. ML models based on deep learning features of nonenhanced mp-MRI and clinical parameters can achieve good diagnostic efficacy.

KEY POINTS

• The ML model combining nonenhanced mp-MRI features and clinical parameters can distinguish uterine sarcomas from ALMs. • Transfer learning can be applied to differentiate uterine sarcomas from ALMs and outperform radiomics. • The most accurate prediction model was Resnet50-based transfer learning, built with the deep-learning features of mp-MRI and clinical parameters.

Myocardial infarction size as an independent predictor of intramyocardial haemorrhage in acute reperfused myocardial ischaemic rats

Background

In previous studies, haemorrhage occurred only with large infarct sizes, and studies found a moderate correlation between the extent of necrosis and haemorrhage, but the extent of infarction size in these studies was limited. This study aimed to find the correlations between intramyocardial haemorrhage (IMH), myocardial infarction (MI), and myocardial oedema (ME) from small to large sizes of MI in a 7.0-T MR scanner.

Methods

Different sizes of myocardial infarction were induced by occluding different sections of the proximal left anterior descending coronary artery (1–3 mm under the left auricle). T2*-mapping, T2-mapping and late gadolinium enhancement (LGE) sequences were performed on a 7.0 T MR system at Days 2 and 7. T2*- and T2-maps were calculated using custom-made software. All areas were expressed as a percentage of the entire myocardial tissue of the left ventricle. The rats were divided into two groups based on the T2* results and pathological findings; MI with IMH was referred to as the + IMH group, while MI without IMH was referred to as the –IMH group.

Results

The final experimental sample consisted of 25 rats in the + IMH group and 10 rats in the –IMH group. For the + IMH group on Day 2, there was a significant positive correlation between IMH size and MI size (r = 0.677, P < 0.01) and a positive correlation between IMH size and ME size (r = 0.552, P < 0.01). On Day 7, there was a significant positive correlation between IMH size and MI size (r = 0.711, P < 0.01), while no correlation was found between IMH size and ME size (r = 0.429, P = 0.097). The MI sizes of the + IMH group were larger than those of the –IMH group (P < 0.01).

Conclusions

Infarction size prior to reperfusion is a critical factor in determining IMH size in rats.

Prevalence and Characteristics of Adrenal Tumors in an Unselected Screening Population : A Cross-Sectional Study

BACKGROUND

With the widespread use of advanced imaging technology, adrenal tumors are increasingly being identified.

OBJECTIVE

To investigate the prevalence and characteristics of adrenal tumors in an unselected screening population in China.

DESIGN

Cross-sectional study. (ClinicalTrials.gov: NCT04682938).

SETTING

A health examination center in China.

PATIENTS

Adults having an annual checkup were invited to be screened for adrenal tumors by adrenal computed tomography.

MEASUREMENTS

The participants with adrenal tumors had further evaluation for malignancy risk and adrenal function.

RESULTS

A total of 25 356 participants were screened, 351 of whom were found to have adrenal tumors, for a prevalence of 1.4%. The prevalence increased with age, from 0.2% in participants aged 18 to 25 years to 3.2% in those older than 65 years. Among 351 participants with adrenal tumors, 337 were diagnosed with an adrenocortical adenoma, 14 with another benign nodule, and none with a malignant mass. In 212 participants with an adenoma who completed endocrine testing, 69.3% were diagnosed with a nonfunctioning adenoma, 18.9% with cortisol autonomy, 11.8% with primary aldosteronism, and none with pheochromocytoma. Proportions of nonfunctioning adenomas were similarly high in various age groups (72.2%, 67.8%, and 72.2% in those aged <46, 46 to 65, and ≥66 years, respectively).

LIMITATION

Only 212 of 337 participants with an adrenocortical adenoma had endocrine testing.

CONCLUSION

The prevalence of adrenal tumors in the general adult screening population is 1.4%, and most of these tumors are nonfunctioning regardless of patient age. Cortisol and aldosterone secretion are the main causes of functional adenomas.

PRIMARY FUNDING SOURCE

National Key Research and Development Program of China and National Natural Science Foundation of China.

Dual-energy CT with virtual monoenergetic images and iodine maps improves tumor conspicuity in patients with pancreatic ductal adenocarcinoma

Objectives

To evaluate the value of monoenergetic images (MEI [+]) and iodine maps in dual-source dual-energy computed tomography (DECT) for assessing pancreatic ductal adenocarcinoma (PDAC), including the visually isoattenuating PDAC.

Materials and methods

This retrospective study included 75 PDAC patients, who underwent contrast-enhanced DECT examinations. Conventional polyenergetic image (PEI) and 40–80 keV MEI (+) (10-keV increments) were reconstructed. The tumor contrast, contrast-to-noise ratio (CNR) of the tumor and peripancreatic vessels, the signal-to-noise ratio (SNR) of the pancreas and tumor, and the tumor diameters were quantified. On iodine maps, the normalized iodine concentration (NIC) in the tumor and parenchyma was compared. For subjective analysis, two radiologists independently evaluated images on a 5-point scale.

Results

All the quantitative parameters were maximized at 40-keV MEI (+) and decreased gradually with increasing energy. The tumor contrast, SNR of pancreas and CNRs in 40–60 keV MEI (+) were significantly higher than those in PEI (p < 0.05). For visually isoattenuating PDAC, 40–50 keV MEI (+) provided significantly higher tumor CNR compared to PEI (p < 0.05). The reproducibility in tumor measurements was highest in 40-keV MEI (+) between the two radiologists. The tumor and parenchyma NIC were 1.28 ± 0.65 and 3.38 ± 0.72 mg/mL, respectively (p < 0.001). 40–50 keV MEI (+) provided the highest subjective scores, compared to PEI (p < 0.001).

Conclusions

Low-keV MEI (+) of DECT substantially improves the subjective and objective image quality and consistency of tumor measurements in patients with PDAC. Combining the low-keV MEI (+) and iodine maps may yield diagnostically adequate tumor conspicuity in visually isoattenuating PDAC.

The SP-ET index is a new index for assessing the vertical position of patella

Background

Some parameters in previous studies did not better reflect the vertical position of the patella relative to the femoral trochlear. This study aimed to assess the value of the most superior point of patella-entrance of femoral trochlea distance ratio (SP-ET index) as a newer index in defining the vertical position of patella relative to the trochlea, correlate it with the Insall–Salvati ratio, and investigate the effect of the new index on patellar cartilage lesions.

Methods

A total of 99 knees of 77 patients with patellar cartilage lesions were retrospectively analyzed using magnetic resonance imaging (MRI) data. The Insall–Salvati ratio and SP-ET index were measured on MR images. Ninety-nine knees just with meniscus rupture were enrolled as the control group. The two parameters of the patellar cartilage lesions were compared with those of the control group.

Results

The Insall–Salvati ratio and SP-ET index in the patellar cartilage lesions group were significantly higher than those in the control group (p < 0.001). The SP-ET index showed a moderate positive correlation with the Insall–Salvati ratio (r = 0.307, p < 0.001). Receiver operating characteristic (ROC) analysis showed that the diagnostic efficiency of the SP-ET index was better than that of the Insall–Salvati ratio in patients with patellar cartilage lesions.

Conclusion

The SP-ET index may be a useful complement parameter to define the vertical position of the patella relative to the femoral trochlear. Increased SP-ET index may be an important risk factor for patellar cartilage lesions.

MRI radiomics-based machine learning model integrated with clinic-radiological features for preoperative differentiation of sinonasal inverted papilloma and malignant sinonasal tumors

Objective

To explore the best MRI radiomics-based machine learning model for differentiation of sinonasal inverted papilloma (SNIP) and malignant sinonasal tumor (MST), and investigate whether the combination of radiomics features and clinic–radiological features can produce a superior diagnostic performance.

Methods

The database of 247 patients with SNIP (n=106) or MST (n=141) were analyzed. Dataset from scanner A were randomly divided into training set (n=135) and test set 1 (n=58) in a ratio of 7:3, and dataset from scanner B and C were used as an additional independent test set 2 (n=54). Fourteen clinic-radiological features were analyzed by using univariate analysis, and those with significant differences were applied to construct clinical model. Based on the radiomics features extracted from single sequence (T2WI or CE-T1WI) and combined sequence, four commonly used classifiers (logistic regression (LR), support vector machine (SVM), decision tree (DT) and k-nearest neighbor (KNN)) were employed to constitute twelve different machine learning models, and the best-performing one was confirmed as the optimal radiomics model. Furthermore, a combined model incorporated best radiomics feature subsets and clinic-radiological features was developed. The diagnostic performances of these models were assessed by the area under the receiver operating characteristic (ROC) curve (AUC) and the calibration curves.

Results

Five clinic-radiological features (age, convoluted cerebriform pattern sign, heterogeneity, adjacent bone involvement and infiltration of surrounding tissue) were considered to be significantly different between the tumor groups (P < 0.05). Among the twelve machine learning models, the T2WI-SVM model exhibited optimal predictive efficacy for classification tasks on the two test sets, with the AUC of 0.878 and 0.914, respectively. For three types of diagnostic models, the combined model achieved highest AUC of 0.912 (95%CI: 0.807-0.970) and 0.927 (95%CI: 0.823-0.980) for differentiation of SNIP and MST in test 1 and test 2 sets, which performed prominently better than clinical model (P=0.011, 0.005), but not significantly different from the optimal radiomics model (P=0.100, 0.452).

Conclusion

The machine learning model based on T2WI sequence and SVM classifier achieved best performance in differentiation of SNIP and MST, and the combination of radiomics features and clinic-radiological features significantly improved the diagnostic capability of the model.

Factors influencing magnetic resonance imaging finding of endopelvic fascial edema after ultrasound-guided high-intensity focused ultrasound ablation of uterine fibroids

OBJECTIVE

Investigate the relationships between endopelvic fascial edema and its influencing factors after ultrasound-guided high-intensity focused ultrasound (USgHIFU) ablation of uterine fibroids.

METHODS

This retrospective study included 688 women with uterine fibroids treated by USgHIFU; based on post-treatment MRI, the patients were divided into two groups: endopelvic fascial edema group and nonedema group. The specific location of fascial edema of each patient was also recorded. Fascial edema and fibroid features and treatment parameters were set as the dependent and independent variables, respectively, and the correlations were studied using univariate and multivariate analyses. The relationship between the pain-related adverse events and location of fascial edema was analyzed by χ² and fisher's exact tests.

RESULTS

Edema and nonedema groups had 556 and 112 patients, respectively. Among the edema patients, posterior fascial edema incidence was the highest. Multifactorial analysis showed that the energy efficiency factor (EEF), fibroid location, and enhancement type were positively associated with endopelvic fascial edema (p < 0.05), while the distance from dorsal surface of the fibroid to sacrum was negatively correlated (p < 0.001). Patients with anterior, posterior and perirectal, and right lateral fascial edemas were associated with lower abdominal pain, sacrococcygeal pain, and leg numbness/pain, respectively.

CONCLUSION

Post-USgHIFU ablation, patients were prone to developing endopelvic fascial edema, and some of them experienced pain-related adverse events. The fibroid location, its types of contrast enhancement, the distance from the dorsal surface of the fibroid to the sacrum, and EEF were the influencing factors resulting in the endopelvic fascial edema after USgHIFU ablation.

The value of HPV genotypes combined with clinical indicators in the classification of cervical squamous cell carcinoma and adenocarcinoma

Background

To investigate the differences in HPV genotypes and clinical indicators between cervical squamous cell carcinoma and adenocarcinoma and to identify independent predictors for differentiating cervical squamous cell carcinoma and adenocarcinoma.

Methods

A total of 319 patients with cervical cancer, including 238 patients with squamous cell carcinoma and 81 patients with adenocarcinoma, were retrospectively analysed. The clinical characteristics and laboratory indicators, including HPV genotypes, SCCAg, CA125, CA19-9, CYFRA 21–1 and parity, were analysed by univariate and multivariate analyses, and a classification model for cervical squamous cell carcinoma and adenocarcinoma was established. The model was validated in 96 patients with cervical cancer.

Results

There were significant differences in SCCAg, CA125, CA19-9, CYFRA 21–1, HPV genotypes and clinical symptoms between cervical squamous cell carcinoma and adenocarcinoma (P < 0.05). Logistic regression analysis showed that SCCAg and HPV genotypes (high risk) were independent predictors for differentiating cervical squamous cell carcinoma from adenocarcinoma. The AUC value of the established classification model was 0.854 (95% CI: 0.804–0.904). The accuracy, sensitivity and specificity of the model were 0.846, 0.691 and 0.899, respectively. The classification accuracy was 0.823 when the model was verified.

Conclusion

The histological type of cervical cancer patients with persistent infection of high-risk HPV subtypes and low serum SCCAg levels was more prone to being adenocarcinoma. When the above independent predictors occur, the occurrence and development of cervical adenocarcinoma should be anticipated, and early active intervention treatment should be used to improve the prognosis and survival of patients.

Multiphasic CT-Based Radiomics Analysis for the Differentiation of Benign and Malignant Parotid Tumors

Objective

This study aims to investigate the value of machine learning models based on clinical-radiological features and multiphasic CT radiomics features in the differentiation of benign parotid tumors (BPTs) and malignant parotid tumors (MPTs).

Methods

This retrospective study included 312 patients (205 cases of BPTs and 107 cases of MPTs) who underwent multiphasic enhanced CT examinations, which were randomly divided into training (N = 218) and test (N = 94) sets. The radiomics features were extracted from the plain, arterial, and venous phases. The synthetic minority oversampling technique was used to balance minority class samples in the training set. Feature selection methods were done using the least absolute shrinkage and selection operator (LASSO), mutual information (MI), and recursive feature extraction (RFE). Two machine learning classifiers, support vector machine (SVM), and logistic regression (LR), were then combined in pairs with three feature selection methods to build different radiomics models. Meanwhile, the prediction performances of different radiomics models based on single phase (plain, arterial, and venous phase) and multiphase (three-phase combination) were compared to determine which model construction method and phase were more discriminative. In addition, clinical models based on clinical-radiological features and combined models integrating radiomics features and clinical-radiological features were established. The prediction performances of the different models were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and the drawing of calibration curves.

Results

Among the 24 established radiomics models composed of four different phases, three feature selection methods, and two machine learning classifiers, the LASSO-SVM model based on a three-phase combination had the optimal prediction performance with AUC (0.936 [95% CI = 0.866, 0.976]), sensitivity (0.78), specificity (0.90), and accuracy (0.86) in the test set, and its prediction performance was significantly better than with the clinical model based on LR (AUC = 0.781, p = 0.012). In the test set, the combined model based on LR had a lower AUC than the optimal radiomics model (AUC = 0.933 vs. 0.936), but no statistically significant difference (p = 0.888).

Conclusion

Multiphasic CT-based radiomics analysis showed a machine learning model based on clinical-radiological features and radiomics features has the potential to provide a valuable tool for discriminating benign from malignant parotid tumors.

Magnetic Resonance Imaging under Image Enhancement Algorithm to Analyze the Clinical Value of Placement of Drainage Tube on Incision Healing after Hepatobiliary Surgery

This study was aimed at exploring the application value of magnetic resonance imaging (MRI) based on image enhancement algorithm in analyzing the placement of drainage tubes in the healing of incisions after hepatobiliary surgery. A total of 70 patients with liver cancer undergoing laparoscopic hepatobiliary surgery were selected, including 34 males and 36 females. According to the detection method of postoperative recovery, they were divided into a group A (conventional MRI detection) and a group B (MRI detection based on Retinex algorithm). Patients were divided into two groups according to whether subcutaneous drainage tubes were placed: group C (no subcutaneous drainage tubes were placed) and group D (subcutaneous drainage tubes were placed), with 35 patients in each group. The results showed that there was no significant difference between group A and group B in tumor residual or recurrence. The detection rate of tumor capsule in group B was significantly higher than that in group A (P < 0.05). The sensitivity, specificity, and accuracy of group A for the detection of recurrent lesions were 63.40%, 86.90%, and 78.60%, respectively; those in group B were 82.70%, 98.50%, and 93.20%, respectively. Therefore, the difference between the two groups was statistically significant (P < 0.05). The incidence of poor wound healing and infection in group C were significantly lower than those in group D (P < 0.05). Therefore, the effect of MRI detection based on image enhancement algorithm was more conducive to the evaluation of postoperative recovery due to the traditional MRI detection. In addition, the drainage tube was helpful to the postoperative wound healing and showed high clinical value.

Combined Intrinsic Local Functional Connectivity With Multivariate Pattern Analysis to Identify Depressed Essential Tremor

Background

Although depression is one of the most common neuropsychiatric symptoms in essential tremor (ET), the diagnosis biomarker and intrinsic brain activity remain unclear. We aimed to combine multivariate pattern analysis (MVPA) with local brain functional connectivity to identify depressed ET.

Methods

Based on individual voxel-level local brain functional connectivity (regional homogeneity, ReHo) mapping from 41 depressed ET, 43 non-depressed ET, and 45 healthy controls (HCs), the binary support vector machine (BSVM) and multiclass Gaussian Process Classification (MGPC) algorithms were used to identify depressed ET patients from non-depressed ET and HCs, the accuracy and permutations test were used to assess the classification performance.

Results

The MGPC algorithm was able to classify the three groups (depressed ET, non-depressed ET, and HCs) with a total accuracy of 84.5%. The BSVM algorithm achieved a better classification performance with total accuracy of 90.7, 88.64, and 90.48% for depressed ET vs. HCs, non-depressed ET vs. HCs, and depressed ET vs. non-depressed ET, and the sensitivity for them at 80.49, 76.64, and 80.49%, respectively. The significant discriminative features of depressed ET vs. HCs were primarily located in the cerebellar-motor-prefrontal gyrus-anterior cingulate cortex pathway, and for depressed ET vs. non-depressed ET located in the cerebellar-prefrontal gyrus-anterior cingulate cortex circuits. The partial correlation showed that the ReHo values in the bilateral middle prefrontal gyrus (positive) and the bilateral cerebellum XI (negative) were significantly correlated with clinical depression severity.

Conclusion

Our findings suggested that combined individual ReHo maps with MVPA not only could be used to identify depressed ET but also help to reveal the intrinsic brain activity changes and further act as the potential diagnosis biomarker in depressed ET patients.

A multi-scale and multi-domain heart sound feature-based machine learning model for ACC/AHA heart failure stage classification

OBJECTIVE

Heart sounds can reflect detrimental changes in cardiac mechanical activity that are common pathological characteristics of chronic heart failure (CHF). The ACC/AHA heart failure (HF) stage classification is essential for clinical decision-making and the management of CHF. Herein, a machine learning model that makes use of multi-scale and multi-domain heart sound features was proposed to provide an objective aid for ACC/AHA HF stage classification.

APPROACH

A dataset containing phonocardiogram (PCG) signals from 275 subjects was obtained from two medical institutions and used in this study. Complementary ensemble empirical mode decomposition and tunable-Q wavelet transform were used to construct self-adaptive sub-sequences and multi-level sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear feature extraction were then applied to the original PCG signal, heart sound sub-sequences and sub-band signals to construct multi-scale and multi-domain heart sound features. The features selected via the least absolute shrinkage and selection operator were fed into a machine learning classifier for ACC/AHA HF stage classification. Finally, mainstream machine learning classifiers, including least-squares support vector machine (LS-SVM), deep belief network (DBN) and random forest (RF), were compared to determine the optimal model.

MAIN RESULTS

The results showed that the LS-SVM, which utilized a combination of multi-scale and multi-domain features, achieved better classification performance than the DBN and RF using multi-scale or multi-domain features alone or together, with average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the testing set, respectively.

SIGNIFICANCE

PCG signal analysis provides efficient measurement information regarding CHF severity and is a promising noninvasive method for ACC/AHA HF stage classification.

Evaluation of high intensity focused ultrasound treatment for different types of adenomyosis based on magnetic resonance imaging classification

OBJECTIVE

To evaluate the mid-term symptom improvement of patients with different types of adenomyosis based on magnetic resonance imaging (MRI) classification after ultrasound-guided high intensity focused ultrasound (USgHIFU) treatment.

MATERIALS AND METHODS

A total of 321 patients with adenomyosis who underwent HIFU and completed 18-month follow-up were retrospectively reviewed. Based on the relationship between the adenomyotic lesion and the uterine structural components on T2-weighted imaging (T2WI), adenomyotic lesions were classified as internal, external, full thickness and intramural adenomyosis. Based on the extent of the myometrial involvement, these lesions were further subclassified as asymmetric and symmetric adenomyosis.

RESULTS

All patients completed HIFU ablation in one session. The range of median menstrual pain score in patients with asymmetric internal, symmetric internal, asymmetric external, asymmetric full thickness, symmetric full thickness, and intramural adenomyosis was between 6 and 8 points before HIFU, the median menstrual pain score decreased to 2-4 points 18-month post-HIFU (p < .005). The menstrual pain relief rate was 68.3%, 62.1%, 54.7%, 64.1%, 60%, and 100%, respectively. The median menstrual blood volume score range was between 2 and 4 points in the different groups of patients before HIFU, it decreased to 1-3 points 18-month after HIFU with a relief rate of 68.3%, 51.6%, 51.0%, 55.5%, 57.2%, and 100%, respectively. No serious complication occurred in any of these patients.

CONCLUSIONS

Based on our results, USgHIFU is safe and effective in the treatment of patients with different subtypes of adenomyosis with mid-term sustained improvement in symptoms of menstrual pain and menstrual blood volume.

Patellar shape is associated with femoral trochlear morphology in individuals with mature skeletal development

Background

As several studies have detected correlations between patellar and femoral trochlear development, this raises the question of whether patellar shape is associated with trochlear developmental outcomes.

Methods

Patellar shape and femoral trochlear morphology were retrospectively analyzed in 183 subjects, of whom 61 each were classified as having Wiberg type I, II, and III patellae (groups A, B, and C, respectively). The sulcus angle (SA), lateral trochlea inclination angle (LTA), medial trochlear inclination angle (MTA), lateral facet length (LFL), medial facet length (MFL), lateral trochlear height (LTH), medial trochlear height (MTH), trochlea sulcus height (TH), and lateral-medial trochlear facet distance (TD) were analyzed as a means of evaluating trochlear morphology. Trochlear depth, trochlear condyle asymmetry, and trochlear facet asymmetry were additionally calculated, and differences in trochlear morphology and correlations between trochlear morphology and patellar shape were evaluated.

Results

The femoral trochlear parameters of patients in group A differed significantly from those of patients in groups B and C. No significant differences between groups B and C were evident. Patellar shape was positively correlated with LTA, MTA, MFL, trochlear condyle asymmetry, and trochlear facet asymmetry, and was negatively correlated with SA.

Conclusions

These data indicated that patellar shape and trochlear morphology are related to one another,which suggest normalized patella morphology surgery and trochlear surgery are better choices for patients with patella instability.

Trial registration

Retrospectively registered.

Aberrant frontolimbic circuit in female depressed adolescents with and without suicidal attempts: A resting-state functional magnetic resonance imaging study

BACKGROUND

The neurobiological basis of suicidal behaviors among female adolescents with major depressive disorder (MDD) remains largely unclear.

MATERIALS AND METHODS

Fifty-eight drug-naïve, first-episode female adolescent MDD [including 31 patients with suicidal attempt (SA group) and 27 patients without SA (non-SA group)], and 36 matched healthy controls (HCs) participated in the present study. Resting-state functional magnetic resonance imaging (MRI) was performed on each subject. The metrics of the amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF), and regional homogeneity (ReHo) were compared among the three groups. Then seed-based functional connectivity (FC) was conducted based on the ALFF/fALFF and ReHo results, which were then correlated to clinical variables.

RESULTS

Compared with the non-SA group, the SA group exhibited increased fALFF in the bilateral insula and right precentral gyrus, and enhanced ReHo in the left superior temporal gyrus, left middle cingulate cortex, right insula, and right precentral gyrus. Relative to the HCs, the SA group demonstrated additionally reduced fALFF and ReHo in the left middle frontal gyrus. Moreover, the SA group showed increased FC between the right precentral gyrus and the left middle frontal gyrus and left insula, and between the right insula and anterior/middle cingulate cortex compared to the non-SA and HC groups. In addition, the fALFF in the left middle frontal gyrus was positively correlated with the 17-item Hamilton Depression Rating Scale scores, and the values in the fALFF/ReHo in the right insula were positively correlated with the duration of MDD within the patient group.

CONCLUSION

These findings highlight the multiple abnormalities of the frontolimbic circuit, which may enhance our understanding of the neurobiological basis underlying female MDD with SA during adolescence.

A CT-Based Radiomics Nomogram Integrated With Clinic-Radiological Features for Preoperatively Predicting WHO/ISUP Grade of Clear Cell Renal Cell Carcinoma

Objective

This study aims to develop and validate a CT-based radiomics nomogram integrated with clinic-radiological factors for preoperatively differentiating high-grade from low-grade clear cell renal cell carcinomas (CCRCCs).

Methods

370 patients with complete clinical, pathological, and CT image data were enrolled in this retrospective study, and were randomly divided into training and testing sets with a 7:3 ratio. Radiomics features were extracted from nephrographic phase (NP) contrast-enhanced images, and then a radiomics model was constructed by the selected radiomics features using a multivariable logistic regression combined with the most suitable feature selection algorithm determined by the comparison among least absolute shrinkage and selection operator (LASSO), recursive feature elimination (RFE) and ReliefF. A clinical model was established using clinical and radiological features. A radiomics nomogram was constructed by integrating the radiomics signature and independent clinic-radiological features. Performance of these three models was assessed using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).

Results

Using multivariate logistic regression analysis, three clinic-radiological features including intratumoral necrosis (OR=3.00, 95% CI=1.30-6.90, p=0.049), intratumoral angiogenesis (OR=3.28, 95% CI=1.22-8.78, p=0.018), and perinephric metastasis (OR=2.90, 95% CI=1.03-8.17, p=0.044) were found to be independent predictors of WHO/ISUP grade in CCRCC. Incorporating the above clinic-radiological predictors and radiomics signature constructed by LASSO, a CT-based radiomics nomogram was developed, and presented better predictive performance than clinic-radiological model and radiomics signature model, with an AUC of 0.891 (95% CI=0.832-0.962) and 0.843 (95% CI=0.718-0.975) in the training and testing sets, respectively. DCA indicated that the nomogram has potential clinical usefulness.

Conclusion

The CT-based radiomics nomogram is a promising tool to predict WHO/ISUP grade of CCRCC preoperatively and noninvasively.

Machine learning-based CT radiomics approach for predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma: an exploratory and comparative study

Purpose

To investigate the predictive performance of machine learning-based CT radiomics for differentiating between low- and high-nuclear grade of clear cell renal cell carcinomas (CCRCCs).

Methods

This retrospective study enrolled 406 patients with pathologically confirmed low- and high-nuclear grade of CCRCCs according to the WHO/ISUP grading system, which were divided into the training and testing cohorts. Radiomics features were extracted from nephrographic-phase CT images using PyRadiomics. A support vector machine (SVM) combined with three feature selection algorithms such as least absolute shrinkage and selection operator (LASSO), recursive feature elimination (RFE), and ReliefF was performed to determine the most suitable classification model, respectively. Clinicoradiological, radiomics, and combined models were constructed using the radiological and clinical characteristics with significant differences between the groups, selected radiomics features, and a combination of both, respectively. Model performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses.

Results

SVM-ReliefF algorithm outperformed SVM-LASSO and SVM-RFE in distinguishing low- from high-grade CCRCCs. The combined model showed better prediction performance than the clinicoradiological and radiomics models (p < 0.05, DeLong test), which achieved the highest efficacy, with an area under the ROC curve (AUC) value of 0.887 (95% confidence interval [CI] 0.798–0.952), 0.859 (95% CI 0.748–0.935), and 0.828 (95% CI 0.731–0.929) in the training, validation, and testing cohorts, respectively. The calibration and decision curves also indicated the favorable performance of the combined model.

Conclusion

A combined model incorporating the radiomics features and clinicoradiological characteristics can better predict the WHO/ISUP nuclear grade of CCRCC preoperatively, thus providing effective and noninvasive assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01107-1.

Low-dose dobutamine cardiovascular magnetic resonance segmental strain study of early phase of intramyocardial hemorrhage rats

Background

This study investigates the segmental myocardial strain of the early phase of intramyocardial hemorrhage (IMH) caused by reperfused myocardial infarction (MI) in rats by low-dose dobutamine (LDD) cardiovascular magnetic resonance (CMR) feature-tracking.

Methods

Nine sham rats and nine rats with 60-min myocardial ischemia followed by 48-h reperfusion were investigated using CMR, including T2*-mapping sequence and fast imaging with steady-state precession (FISP)–cine sequence. Another FISP–cine sequence was acquired after 2 min of dobutamine injection; the MI, IMH, and Non-MI (NMI) areas were identified. The values of peak radial strains (PRS) and peak circumferential strains (PCS) of the MI, IMH and NMI segments were acquired. The efficiency of PRS and PCS (EPRS and EPCS, respectively) were calculated on the basis of the time of every single heartbeat.

Results

The PRS, PCS, EPRS, and EPCS of the sham group increased after LDD injection. However, the PRS, PCS, EPRS, and EPCS of the IMH segment did not increase. Moreover, the PRS and PCS of the MI and NMI segments did not increase, but the EPRS and EPCS of these segments increased. The PRS, PCS, EPRS, and EPCS of the IMH segment were lower than those of the MI and NMI segments before and after LDD injection, but without a significant difference between MI segment and NMI segment before and after LDD injection.

Conclusions

LDD could help assess dysfunctions in segments with IMH, especially using the efficiency of strain. IMH was a crucial factor that decreased segmental movement and reserved function.