Multimodal integration of neuroimaging and genetic data for the diagnosis of mood disorders based on computer vision models

Mood disorders, particularly major depressive disorder (MDD) and bipolar disorder (BD), are often underdiagnosed, leading to substantial morbidity. Harnessing the potential of emerging methodologies, we propose a novel multimodal fusion approach that integrates patient-oriented brain structural magnetic resonance imaging (sMRI) scans with DNA whole-exome sequencing (WES) data. Multimodal data fusion aims to improve the detection of mood disorders by employing established deep-learning architectures for computer vision and machine-learning strategies. We analyzed brain imaging genetic data of 321 East Asian individuals, including 147 patients with MDD, 78 patients with BD, and 96 healthy controls. We developed and evaluated six fusion models by leveraging common computer vision models in image classification: Vision Transformer (ViT), Inception-V3, and ResNet50, in conjunction with advanced machine-learning techniques (XGBoost and LightGBM) known for high-dimensional data analysis. Model validation was performed using a 10-fold cross-validation. Our ViT ⊕ XGBoost fusion model with MRI scans, genomic Single Nucleotide polymorphism (SNP) data, and unweighted polygenic risk score (PRS) outperformed baseline models, achieving an incremental area under the curve (AUC) of 0.2162 (32.03% increase) and 0.0675 (+8.19%) and incremental accuracy of 0.1455 (+25.14%) and 0.0849 (+13.28%) compared to SNP-only and image-only baseline models, respectively. Our findings highlight the opportunity to refine mood disorder diagnostics by demonstrating the transformative potential of integrating diverse, yet complementary, data modalities and methodologies.

Development and multicenter validation of deep convolutional neural network-based detection of colorectal cancer on abdominal CT

OBJECTIVES

This study aims to develop computer-aided detection (CAD) for colorectal cancer (CRC) using abdominal CT based on a deep convolutional neural network.

METHODS

This retrospective study included consecutive patients with colorectal adenocarcinoma who underwent abdominal CT before CRC resection surgery (training set = 379, test set = 103). We customized the 3D U-Net of nnU-Net (CUNET) for CRC detection, which was trained with fivefold cross-validation using annotated CT images. CUNET was validated using datasets covering various clinical situations and institutions: an internal test set (n = 103), internal patients with CRC first determined by CT (n = 54) and asymptomatic CRC (n = 51), and an external validation set from two institutions (n = 60). During each validation, data from the healthy population were added (internal = 60; external = 130). CUNET was compared with other deep CNNs: residual U-Net and EfficientDet. The CAD performances were evaluated using per-CRC sensitivity (true positive/all CRCs), free-response receiver operating characteristic (FROC), and jackknife alternative FROC (JAFROC) curves.

RESULTS

CUNET showed a higher maximum per-CRC sensitivity than residual U-Net and EfficientDet (internal test set 91.3% vs. 61.2%, and 64.1%). The per-CRC sensitivity of CUNET at false-positive rates of 3.0 was as follows: internal CRC determined by CT, 89.3%; internal asymptomatic CRC, 87.3%; and external validation, 89.6%. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 89.7% (252/281) of CRCs from all validation sets.

CONCLUSIONS

CUNET can detect CRC on abdominal CT in patients with various clinical situations and from external institutions.

KEY POINTS

• Customized 3D U-Net of nnU-Net (CUNET) can be applied to the opportunistic detection of colorectal cancer (CRC) in abdominal CT, helping radiologists detect unexpected CRC. • CUNET showed the best performance at false-positive rates ≥ 3.0, and 30.1% of false-positives were in the colorectum. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 87.3% (48/55) of asymptomatic CRCs. • CUNET detected CRCs in multiple validation sets composed of varying clinical situations and from different institutions, and CUNET detected 89.7% (252/281) of CRCs from all validation sets.

Development and validation of CT‑based radiomics model of PET-negative residual CT masses: a potential biomarker for predicting relapse‑free survival in non-Hodgkin lymphoma patients showing complete metabolic response

PURPOSE

PET-negative residual CT masses (PnRCMs) are usually dismissed as nonviable post-treatment lesions in non-Hodgkin lymphoma (NHL) patients showing complete metabolic response (CMR). We aimed to develop and validate computed tomography (CT)-based radiomics model of PET-negative residual CT mass (PnRCM) for predicting relapse-free survival (RFS) in NHL patients showing CMR.

METHODS

A total of 224 patients who showed CMR after completing first-line chemotherapy for PET-avid NHL were recruited for model development. Patients with PnRCM were selected in accordance with the Lugano classification. Three-dimensional segmentation was done by two readers. Radiomic scores (RS) were constructed using features extracted using the Least-absolute shrinkage and selection operator analysis among radiomics features of PnRCMs showing more than substantial interobserver agreement (> 0.6). Cox regression analysis was performed with clinical and radiologic features. The performance of the model was evaluated using area under the curve (AUC). For validation, 153 patients from an outside hospital were recruited and analyzed in the same way.

RESULTS

In the model development cohort, 68 (30.4%) patients had PnRCM. Kaplan-Meier analysis showed that patients with PnRCM had significantly (p = 0.005) shorter RFS than those without PnRCM. In Kaplan-Meier analysis, the high RS group showed significantly (p = 0.038) shorter RFS than the low-scoring group. Multivariate Cox regression analysis showed that high IPI score [hazard ratio (HR) 2.46; p = 0.02], treatment without rituximab (HR 3.821; p = 0.019) were factors associated with shorter RFS. In estimating RFS, combined model in both development and validation cohort showed AUC values of 0.81.

CONCLUSION

The combined model that incorporated both clinical parameters and CT-based RS showed good performance in predicting relapse in NHL patients with PnRCM.

Deep Learning-Based Synthetic TOF-MRA Generation Using Time-Resolved MRA in Fast Stroke Imaging

BACKGROUND AND PURPOSE

Time-resolved MRA enables collateral evaluation in acute ischemic stroke with large-vessel occlusion; however, a low SNR and spatial resolution impede the diagnosis of vascular occlusion. We developed a CycleGAN-based deep learning model to generate high-resolution synthetic TOF-MRA images using time-resolved MRA and evaluated its image quality and clinical efficacy.

MATERIALS AND METHODS

This retrospective, single-center study included 397 patients who underwent both TOF- and time-resolved MRA between April 2021 and January 2022. Patients were divided into 2 groups for model development and image-quality validation. Image quality was evaluated qualitatively and quantitatively with 3 sequences. A multireader diagnostic optimality evaluation was performed by 16 radiologists. For clinical validation, we evaluated 123 patients who underwent fast stroke MR imaging to assess acute ischemic stroke. The diagnostic confidence level and decision time for large-vessel occlusion were also evaluated.

RESULTS

Median values of overall image quality, noise, sharpness, venous contamination, and SNR for M1, M2, the basilar artery, and posterior cerebral artery are better with synthetic TOF than with time-resolved MRA. However, with respect to real TOF, synthetic TOF presents worse median values of overall image quality, sharpness, vascular conspicuity, and SNR for M3, the basilar artery, and the posterior cerebral artery. During the multireader evaluation, radiologists could not discriminate synthetic TOF images from TOF images. During clinical validation, both readers demonstrated increases in diagnostic confidence levels and decreases in decision time.

CONCLUSIONS

A CycleGAN-based deep learning model was developed to generate synthetic TOF from time-resolved MRA. Synthetic TOF can potentially assist in the detection of large-vessel occlusion in stroke centers using time-resolved MRA.

General Overview of Artificial Intelligence for Interstitial Cystitis in Urology

Our understanding of interstitial cystitis/bladder pain syndrome (IC/BPS) has evolved over time. The diagnosis of IC/BPS is primarily based on symptoms such as urgency, frequency, and bladder or pelvic pain. While the exact causes of IC/BPS remain unclear, it is thought to involve several factors, including abnormalities in the bladder's urothelium, mast cell degranulation within the bladder, inflammation of the bladder, and altered innervation of the bladder. Treatment options include patient education, dietary and lifestyle modifications, medications, intravesical therapy, and surgical interventions. This review article provides insights into IC/BPS, including aspects of treatment, prognosis prediction, and emerging therapeutic options. Additionally, it explores the application of deep learning for diagnosing major diseases associated with IC/BPS.

Machine Learning-Based Magnetic Resonance Radiomics Analysis for Predicting Low- and High-Grade Clear Cell Renal Cell Carcinoma

PURPOSE

To explore whether high- and low-grade clear cell renal cell carcinomas (ccRCC) can be distinguished using radiomics features extracted from magnetic resonance imaging.

METHODS

In this retrospective study, 154 patients with pathologically proven clear ccRCC underwent contrast-enhanced 3 T magnetic resonance imaging and were assigned to the development (n = 122) and test (n = 32) cohorts in a temporal-split setup. A total of 834 radiomics features were extracted from whole-tumor volumes using 3 sequences: T2-weighted imaging (T2WI), diffusion-weighted imaging, and contrast-enhanced T1-weighted imaging. A random forest regressor was used to extract important radiomics features that were subsequently used for model development using the random forest algorithm. Tumor size, apparent diffusion coefficient value, and percentage of tumor-to-renal parenchymal signal intensity drop in the tumors were recorded by 2 radiologists for quantitative analysis. The area under the receiver operating characteristic curve (AUC) was generated to predict ccRCC grade.

RESULTS

In the development cohort, the T2WI-based radiomics model demonstrated the highest performance (AUC, 0.82). The T2WI-based radiomics and radiologic feature hybrid model showed AUCs of 0.79 and 0.83, respectively. In the test cohort, the T2WI-based radiomics model achieved an AUC of 0.82. The range of AUCs of the hybrid model of T2WI-based radiomics and radiologic features was 0.73 to 0.80.

CONCLUSION

Magnetic resonance imaging-based classifier models using radiomics features and machine learning showed satisfactory diagnostic performance in distinguishing between high- and low-grade ccRCC, thereby serving as a helpful noninvasive tool for predicting ccRCC grade.

Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI

This study aimed to develop a screening model for rotator cuff tear detection in all three planes of routine shoulder MRI using a deep neural network. A total of 794 shoulder MRI scans (374 men and 420 women; aged 59 ± 11 years) were utilized. Three musculoskeletal radiologists labeled the rotator cuff tear. The YOLO v8 rotator cuff tear detection model was then trained; training was performed with all imaging planes simultaneously and with axial, coronal, and sagittal images separately. The performances of the models were evaluated and compared using receiver operating curves and the area under the curve (AUC). The AUC was the highest when using all imaging planes (0.94; p < 0.05). Among a single imaging plane, the axial plane showed the best performance (AUC: 0.71), followed by the sagittal (AUC: 0.70) and coronal (AUC: 0.68) imaging planes. The sensitivity and accuracy were also the highest in the model with all-plane training (0.98 and 0.96, respectively). Thus, deep-learning-based automatic rotator cuff tear detection can be useful for detecting torn areas in various regions of the rotator cuff in all three imaging planes.

Aortic Annulus Detection Based on Deep Learning for Transcatheter Aortic Valve Replacement Using Cardiac Computed Tomography

BACKGROUND

To propose a deep learning architecture for automatically detecting the complex structure of the aortic annulus plane using cardiac computed tomography (CT) for transcatheter aortic valve replacement (TAVR).

METHODS

This study retrospectively reviewed consecutive patients who underwent TAVR between January 2017 and July 2020 at a tertiary medical center. Annulus Detection Permuted AdaIN network (ADPANet) based on a three-dimensional (3D) U-net architecture was developed to detect and localize the aortic annulus plane using cardiac CT. Patients (N = 72) who underwent TAVR between January 2017 and July 2020 at a tertiary medical center were enrolled. Ground truth using a limited dataset was delineated manually by three cardiac radiologists. Training, tuning, and testing sets (70:10:20) were used to build the deep learning model. The performance of ADPANet for detecting the aortic annulus plane was analyzed using the root mean square error (RMSE) and dice similarity coefficient (DSC).

RESULTS

In this study, the total dataset consisted of 72 selected scans from patients who underwent TAVR. The RMSE and DSC values for the aortic annulus plane using ADPANet were 55.078 ± 35.794 and 0.496 ± 0.217, respectively.

CONCLUSION

Our deep learning framework was feasible to detect the 3D complex structure of the aortic annulus plane using cardiac CT for TAVR. The performance of our algorithms was higher than other convolutional neural networks.

Prediction of Axillary Lymph Node Metastasis in Early-stage Triple-Negative Breast Cancer Using Multiparametric and Radiomic Features of Breast MRI

RATIONALE AND OBJECTIVES

To investigate whether machine learning (ML) approaches using breast magnetic resonance imaging (MRI)-derived multiparametric and radiomic features could predict axillary lymph node metastasis (ALNM) in stage I-II triple-negative breast cancer (TNBC).

MATERIALS AND METHODS

Between 2013 and 2019, 86 consecutive patients with TNBC who underwent preoperative MRI and surgery were enrolled and divided into ALNM (N = 27) and non-ALNM (n = 59) groups according to histopathologic results. For multiparametric features, kinetic features using computer-aided diagnosis (CAD), morphologic features, and apparent diffusion coefficient (ADC) values at diffusion-weighted images were evaluated. For extracting radiomic features, three-dimensional segmentation of tumors using T2-weighted images (T2WI) and T1-weighted subtraction images were respectively performed by two radiologists. Each predictive model using three ML algorithms was built using multiparametric features or radiomic features, or both. The diagnostic performances of models were compared using the DeLong method.

RESULTS

Among multiparametric features, non-circumscribed margin, peritumoral edema, larger tumor size, and larger angio-volume at CAD were associated with ALNM in univariate analysis. In multivariate analysis, larger angio-volume was the sole statistically significant predictor for ALNM (odds ratio = 1.33, P = 0.008). Regarding ADC values, there were no significant differences according to ALNM status. The area under the receiver operating characteristic curve for predicting ALNM was 0.74 using multiparametric features, 0.77 using radiomic features from T1-weighted subtraction images, 0.80 using radiomic features from T2WI, and 0.82 using all features.

CONCLUSION

A predictive model incorporating breast MRI-derived multiparametric and radiomic features may be valuable in predicting ALNM preoperatively in patients with TNBC.

Value of Breast MRI and Nomogram After Negative Axillary Ultrasound for Predicting Axillary Lymph Node Metastasis in Patients With Clinically T1-2 N0 Breast Cancer

BACKGROUND

There are increasing concerns about that sentinel lymph node biopsy (SLNB) could be omitted in patients with clinically T1-2 N0 breast cancers who has negative axillary ultrasound (AUS). This study aims to assess the false negative result (FNR) of AUS, the rate of high nodal burden (HNB) in clinically T1-2 N0 breast cancer patients, and the diagnostic performance of breast magnetic resonance imaging (MRI) and nomogram.

METHODS

We identified 948 consecutive patients with clinically T1-2 N0 cancers who had negative AUS, subsequent MRI, and breast conserving therapy between 2013 and 2020 from two tertiary medical centers. Patients from two centers were assigned to development and validation sets, respectively. Among 948 patients, 402 (mean age ± standard deviation, 57.61 ± 11.58) were within development cohort and 546 (54.43 ± 10.02) within validation cohort. Using logistic regression analyses, clinical-imaging factors associated with lymph node (LN) metastasis were analyzed in the development set from which nomogram was created. The performance of MRI and nomogram was assessed. HNB was defined as ≥ 3 positive LNs.

RESULTS

The FNR of AUS was 20.1% (81 of 402) and 19.2% (105 of 546) and the rates of HNB were 1.2% (5/402) and 2.2% (12/546), respectively. Clinical and imaging features associated with LN metastasis were progesterone receptor positivity, outer tumor location on mammography, breast imaging reporting and data system category 5 assessment of cancer on ultrasound, and positive axilla on MRI. In validation cohorts, the positive predictive value (PPV) and negative predictive value (NPV) of MRI and clinical-imaging nomogram was 58.5% and 86.5%, and 56.0% and 82.0%, respectively.

CONCLUSION

The FNR of AUS was approximately 20% but the rate of HNB was low. The diagnostic performance of MRI was not satisfactory with low PPV but MRI had merit in reaffirming negative AUS with high NPV. Patients who had low probability scores from our clinical-imaging nomogram might be possible candidates for the omission of SLNB.

Downward adjustment of rehabilitation goals may facilitate post-stroke arm motor recovery

Objective: Patients starting with physical rehabilitation often hold unrealistically high expectations for their recovery. Because of a lower-than-expected rate of recovery, such unrealistic goals have been linked to adverse effects on mental health. Additionally, overtraining due to overly ambitious goals can lead to suboptimal recovery. We investigated the effectiveness of adjusting rehabilitation goals to a more realistic level as a strategy to select appropriate exercise intensity and achieve better recovery outcomes. Design: Patients with arm paralysis from recent stroke were recruited and went through 6-8 weeks of telerehabilitation and in-clinic rehabilitation programme conducted at 11 US sites (N = 124). Main Outcome Measures: Adjustment of recovery goal was assessed in two timepoints during the rehabilitation programme and arm motor function was assessed before and after the clinical trial. Results: Greater use of goal adjustment strategies predicted better recovery of arm motor function, independent from therapy compliance. This pattern was observed only when the choice of exercises is patient-regulated rather than directed by a physical therapist. Conclusion: Benefits from goal adjustment were more pronounced among patients who entered the programme with poorer motor functions, suggesting that goal adjustment is the most beneficial when goals of complete recovery are most unrealistic.

Intravesical Bladder Treatment and Deep Learning Applications to Improve Irritative Voiding Symptoms Caused by Interstitial Cystitis: A Literature Review

Our comprehension of interstitial cystitis/painful bladder syndrome (IC/PBS) has evolved over time. The term painful bladder syndrome, preferred by the International Continence Society, is characterized as "a syndrome marked by suprapubic pain during bladder filling, alongside increased daytime and nighttime frequency, in the absence of any proven urinary infection or other pathology." The diagnosis of IC/PBS primarily relies on symptoms of urgency/frequency and bladder/pelvic pain. The exact pathogenesis of IC/PBS remains a mystery, but it is postulated to be multifactorial. Theories range from bladder urothelial abnormalities, mast cell degranulation in the bladder, bladder inflammation, to altered bladder innervation. Therapeutic strategies encompass patient education, dietary and lifestyle modifications, medication, intravesical therapy, and surgical intervention. This article delves into the diagnosis, treatment, and prognosis prediction of IC/PBS, presenting the latest research findings, artificial intelligence technology applications in diagnosing major diseases in IC/PBS, and emerging treatment alternatives.

Identifying fragile calcifications of the aortic valve in transcatheter aortic valve replacement: iodine concentration of aortic valvular calcification by spectral CT

OBJECTIVE

To demonstrate the relationship between spectral computed tomography (CT) measured iodine concentration and strength of aortic valvular calcification (AVC) in patients with aortic valve stenosis (AVS).

METHODS

A retrospective study was performed on patients who underwent transcatheter aortic valve replacement (TAVR) for symptomatic AVS and underwent both pre and postprocedural electrocardiogram gated CT scans using a spectral CT system. Preprocedural CT was used to evaluate the volume and iodine concentration (IC) in the AVC. Postprocedural CT data were used to calculate the volume reduction percentage (VRP) of AVC. Multiple linear regression analysis was used to identify the independent variables related to the VRP in AVCs.

RESULTS

A total of 94 AVCs were selected from 22 patients. The mean volume and IC of the AVCs before TAVR were 0.37 mL ± 0.15 mL and 7 mg/mL ± 10.5 mg/mL, respectively. After TAVR, a median VRP of all 94 AVCs was 18.5%. Multiple linear regression analysis showed that the IC was independently associated with the VRP (coefficient = 1.64, p < 0.001). When an optimal IC cutoff point was set at 4 mg/mL in the assessment of a fragile AVC which showed the VRP was > 18.5%, the sensitivity was 63%; specificity, 91%; positive predictive value, 88%; and negative predictive value, 71%.

CONCLUSIONS

When using spectral CT to prepare the TAVR, measuring the IC of the AVC may be useful to assess the probability of AVC deformity after TAVR.

KEY POINTS

• A dual-layer detector-based spectral CT enables quantifying iodine of contrast media in the aortic valve calcification (AVC) on contrast-enhanced CT images. • The AVC including iodine of contrast media on contrast-enhanced CT image may have loose compositions, associated with the deformity of AVC after TAVR. • Measuring the iodine concentration in AVC may have the potential to assess the probability of AVC deformity, which may be associated with the outcome and complications after TAVR.2.

Formation and evolution of carbonaceous asteroid Ryugu: Direct evidence from returned samples

Samples of the carbonaceous asteroid Ryugu were brought to Earth by the Hayabusa2 spacecraft. We analyzed 17 Ryugu samples measuring 1 to 8 millimeters. Carbon dioxide-bearing water inclusions are present within a pyrrhotite crystal, indicating that Ryugu's parent asteroid formed in the outer Solar System. The samples contain low abundances of materials that formed at high temperatures, such as chondrules and calcium- and aluminum-rich inclusions. The samples are rich in phyllosilicates and carbonates, which formed through aqueous alteration reactions at low temperature, high pH, and water/rock ratios of <1 (by mass). Less altered fragments contain olivine, pyroxene, amorphous silicates, calcite, and phosphide. Numerical simulations, based on the mineralogical and physical properties of the samples, indicate that Ryugu's parent body formed ~2 million years after the beginning of Solar System formation.

Hepatocellular carcinoma pathologic grade prediction using radiomics and machine learning models of gadoxetic acid-enhanced MRI: a two-center study

PURPOSE

To develop a radiomics-based hepatocellular carcinoma (HCC) grade classifier model based on data from gadoxetic acid-enhanced MRI.

METHODS

This retrospective study included 137 patients who underwent hepatectomy for a single HCC and gadoxetic acid-enhanced MRI within 60 days before surgery. HCC grade was categorized as low or high (modified Edmondson-Steiner grade I-II vs. III-IV). We used the hepatobiliary phase (HBP), portal venous phase, T2-weighted image(T2WI), and T1-weighted image(T1WI). From the volume of interest in HCC, 833 radiomic features were extracted. Radiomic and clinical features were selected using a random forest regressor, and the classification model was trained and validated using a random forest classifier and tenfold stratified cross-validation. Eight models were developed using the radiomic features alone or by combining the radiomic and clinical features. Models were validated with internal enrolled data (internal validation) and a dataset (28 patients) at a separate institution (external validation). The area under the curve (AUC) of the validation results was compared using the DeLong test.

RESULTS

In internal and external validation, the HBP radiomics-only model showed the highest AUC (internal 0.80 ± 0.09, external 0.70 ± 0.09). In external validation, all models showed lower AUC than those for internal validation, while the T2WI and T1WI models failed to predict the HCC grade (AUC 0.30-0.58) in contrast to the internal validation results (AUC 0.67-0.78).

CONCLUSION

The radiomics-based machine learning model from gadoxetic acid-enhanced liver MRI could distinguish between low- and high-grade HCCs. The radiomics-only HBP model showed the best AUC among the eight models, good performance in internal validation, and fair performance in external validation.

Radiomics Analysis of Magnetic Resonance Proton Density Fat Fraction for the Diagnosis of Hepatic Steatosis in Patients With Suspected Non-Alcoholic Fatty Liver Disease

BACKGROUND

This study aimed to assess the diagnostic feasibility of radiomics analysis based on magnetic resonance (MR)-proton density fat fraction (PDFF) for grading hepatic steatosis in patients with suspected non-alcoholic fatty liver disease (NAFLD).

METHODS

This retrospective study included 106 patients with suspected NAFLD who underwent a hepatic parenchymal biopsy. MR-PDFF and MR spectroscopy were performed on all patients using a 3.0-T scanner. Following whole-volume segmentation of the MR-PDFF images, 833 radiomic features were analyzed using a commercial program. Radiologic features were analyzed, including median and mean values of the multiple regions of interest and variable clinical features. A random forest regressor was used to extract the important radiomic, radiologic, and clinical features. The model was trained using 20 repeated 10-fold cross-validations to classify the NAFLD steatosis grade. The area under the receiver operating characteristic curve (AUROC) was evaluated using a classifier to diagnose steatosis grades.

RESULTS

The levels of pathological hepatic steatosis were classified as low-grade steatosis (grade, 0-1; n = 82) and high-grade steatosis (grade, 2-3; n = 24). Fifteen important features were extracted from the radiomic analysis, with the three most important being wavelet-LLL neighboring gray tone difference matrix coarseness, original first-order mean, and 90th percentile. The MR spectroscopy mean value was extracted as a more important feature than the MR-PDFF mean or median in radiologic measures. Alanine aminotransferase has been identified as the most important clinical feature. The AUROC of the classifier using radiomics was comparable to that of radiologic measures (0.94 ± 0.09 and 0.96 ± 0.08, respectively).

CONCLUSION

MR-PDFF-derived radiomics may provide a comparable alternative for grading hepatic steatosis in patients with suspected NAFLD.

Synthetic Time of Flight Magnetic Resonance Angiography Generation Model Based on Cycle-Consistent Generative Adversarial Network Using PETRA-MRA in the Patients With Treated Intracranial Aneurysm

BACKGROUND

Pointwise encoding time reduction with radial acquisition (PETRA) magnetic resonance angiography (MRA) is useful for evaluating intracranial aneurysm recurrence, but the problem of severe background noise and low peripheral signal-to-noise ratio (SNR) remain. Deep learning could reduce noise using high- and low-quality images.

PURPOSE

To develop a cycle-consistent generative adversarial network (cycleGAN)-based deep learning model to generate synthetic TOF (synTOF) using PETRA.

STUDY TYPE

Retrospective.

POPULATION

A total of 377 patients (mean age: 60 ± 11; 293 females) with treated intracranial aneurysms who underwent both PETRA and TOF from October 2017 to January 2021. Data were randomly divided into training (49.9%, 188/377) and validation (50.1%, 189/377) groups.

FIELD STRENGTH/SEQUENCE

Ultra-short echo time and TOF-MRA on a 3-T MR system.

ASSESSMENT

For the cycleGAN model, the peak SNR (PSNR) and structural similarity (SSIM) were evaluated. Image quality was compared qualitatively (5-point Likert scale) and quantitatively (SNR). A multireader diagnostic optimality evaluation was performed with 17 radiologists (experience of 1-18 years).

STATISTICAL TESTS

Generalized estimating equation analysis, Friedman's test, McNemar test, and Spearman's rank correlation. P < 0.05 indicated statistical significance.

RESULTS

The PSNR and SSIM between synTOF and TOF were 17.51 [16.76; 18.31] dB and 0.71 ± 0.02. The median values of overall image quality, noise, sharpness, and vascular conspicuity were significantly higher for synTOF than for PETRA (4.00 [4.00; 5.00] vs. 4.00 [3.00; 4.00]; 5.00 [4.00; 5.00] vs. 3.00 [2.00; 4.00]; 4.00 [4.00; 4.00] vs. 4.00 [3.00; 4.00]; 3.00 [3.00; 4.00] vs. 3.00 [2.00; 3.00]). The SNRs of the middle cerebral arteries were the highest for synTOF (synTOF vs. TOF vs. PETRA; 63.67 [43.25; 105.00] vs. 52.42 [32.88; 74.67] vs. 21.05 [12.34; 37.88]). In the multireader evaluation, there was no significant difference in diagnostic optimality or preference between synTOF and TOF (19.00 [18.00; 19.00] vs. 20.00 [18.00; 20.00], P = 0.510; 8.00 [6.00; 11.00] vs. 11.00 [9.00, 14.00], P = 1.000).

DATA CONCLUSION

The cycleGAN-based deep learning model provided synTOF free from background artifact. The synTOF could be a versatile alternative to TOF in patients who have undergone PETRA for evaluating treated aneurysms.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Prediction of atrial fibrillation in patients with embolic stroke with undetermined source using electrocardiogram deep learning algorithm and clinical risk factors

Background

Combining the artificial intelligence algorithm with the known clinical risk factors may provide enhanced accuracy for prediction of the hidden atrial fibrillation (AF) in patients with embolic stroke with undetermined source (ESUS).

Purpose

We aimed to develop enhanced prediction models for AF with deep learning algorithm (DLA) and clinical predictors in patients with ESUS. The DLA was created to identify the patients with paroxysmal AF based on their electrocardiograms (ECG) during sinus rhythm.

Methods

We analyzed the 221 patients who underwent insertable cardiac monitor (ICM) for AF detection following ESUS. The DLA was previously developed with sinus rhythm ECGs of 10,605 paroxysmal AF patients and 50,522 non-AF patients. The convolutional neural network was used for the DLA. The primary endpoint was defined as any AF episode lasting over 5 min by ICM. The atrial ectopic burden (AEB) was calculated as the percentage of the number of conducted QRS by atrial ectopy on Holter monitoring.

Results

AF (≥5 min) was detected by ICM in 32 patients (14.5%) during follow-up period of 15.1±8.6 months. AF patients had higher AEB (0.199% vs 0.023%, p&lt;0.001), larger left atrial diameters (LAD, 41.2 mm vs 35.7 mm, p&lt;0.001), and larger left atrial volume index (LAVI, 46.4 ml/m2 vs 32.3 ml/m2, p&lt;0.001) than those without AF. The means of calculated probabilities of AF by DLA were higher in patients with AF than those without AF (63.8% vs 40.2%, p&lt;0.001). In the receiver operating characteristic curve analysis, the areas under the curve (AUC) were the highest in DLA (0.824) followed by AEB (0.784), LAVI (0.780), and LAD (0.768). The multivariable model with AEB, LAVI, and DLA demonstrated excellent prediction accuracy for paroxysmal AF (AUC: 0.902, Figure 1)

Conclusions

In patients with ESUS, the DLA outperformed other clinical risk factors for prediction of AF. Combining DLA with AEB, LAD and LAVI could is a potential useful tool to predict AF in ESUS patients.

Funding Acknowledgement

Type of funding sources: None.

Computer-aided hepatocellular carcinoma detection on the hepatobiliary phase of gadoxetic acid-enhanced magnetic resonance imaging using a convolutional neural network: Feasibility evaluation with multi-sequence data

BACKGROUND AND OBJECTIVES

Diagnosis of hepatocellular carcinoma (HCC) on liver MRI needs analysis of multi-sequence images. However, developing computer-aided detection (CAD) for every single sequence requires considerable time and labor for image segmentation. Therefore, we developed CAD for HCC on the hepatobiliary phase (HBP) of gadoxetic acid-enhanced magnetic resonance imaging (MRI) using a convolutional neural network (CNN) and evaluated its feasibility on multi-sequence, multi-unit, and multi-center data.

METHODS

Patients who underwent gadoxetic acid-enhanced MRI and surgery for HCC in Korea University Anam Hospital (KUAH) and Korea University Guro Hospital (KUGH) were reviewed. Finally, 170 nodules from 155 consecutive patients from KUAH and 28 nodules from 28 patients randomly selected from KUGH were included. Regions of interests were drawn on the whole HCC volume on HBP, T1-weighted (T1WI), T2-weighted (T2WI), and portal venous phase (PVP) images. The CAD was developed from the HBP images of KUAH using customized-nnUNet and post-processed for false-positive reduction. Internal and external validation of the CAD was performed with HBP, T1WI, T2WI, and PVP of KUAH and KUGH.

RESULTS

The figure of merit and recall of the jackknife alternative free-response receiver operating characteristic of the CAD for HBP, T1WI, T2WI, and PVP at false-positive rate 0.5 were (0.87 and 87.0), (0.73 and 73.3), (0.13 and 13.3), and (0.67 and 66.7) in KUAH and (0.86 and 86.0), (0.61 and 53.6), (0.07 and 0.07), and (0.57 and 53.6) in KUGH, respectively.

CONCLUSIONS

The CAD for HCC on gadoxetic acid-enhanced MRI developed by CNN from HBP detected HCCs feasibly on HBP, T1WI, and PVP of gadoxetic acid-enhanced MRI obtained from multiple units and centers. This result imply that the CAD developed using single MRI sequence may be applied to other similar sequences and this will reduce labor and time for CAD development in multi-sequence MRI.

Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging

BACKGROUND

To propose fully automatic segmentation of left atrium using active learning with limited dataset in late gadolinium enhancement in cardiac magnetic resonance imaging (LGE-CMRI).

METHODS

An active learning framework was developed to segment the left atrium in cardiac LGE-CMRI. Patients (n = 98) with atrial fibrillation from the Korea University Anam Hospital were enrolled. First, 20 cases were delineated for ground truths by two experts and used for training a draft model. Second, the 20 cases from the first step and 50 new cases, corrected in a human-in-the-loop manner after predicting using the draft model, were used to train the next model; all 98 cases (70 cases from the second step and 28 new cases) were trained. An additional 20 LGE-CMRI were evaluated in each step.

RESULTS

The Dice coefficients for the three steps were 0.85 ± 0.06, 0.89 ± 0.02, and 0.90 ± 0.02, respectively. The biases (95% confidence interval) in the Bland-Altman plots of each step were 6.36% (-14.90-27.61), 6.21% (-9.62-22.03), and 2.68% (-8.57-13.93). Deep active learning-based annotation times were 218 ± 31 seconds, 36.70 ± 18 seconds, and 36.56 ± 15 seconds, respectively.

CONCLUSION

Deep active learning reduced annotation time and enabled efficient training on limited LGE-CMRI.

Prediction of Mortality after Burn Surgery in Critically Ill Burn Patients Using Machine Learning Models

Severe burns may lead to a series of pathophysiological processes that result in death. Machine learning models that demonstrate prognostic performance can be used to build analytical models to predict postoperative mortality. This study aimed to identify machine learning models with the best diagnostic performance for predicting mortality in critically ill burn patients after burn surgery, and then compare them. Clinically important features for predicting mortality in patients after burn surgery were selected using a random forest (RF) regressor. The area under the receiver operating characteristic curve (AUC) and classifier accuracy were evaluated to compare the predictive accuracy of different machine learning algorithms, including RF, adaptive boosting, decision tree, linear support vector machine, and logistic regression. A total of 731 patients met the inclusion and exclusion criteria. The 90-day mortality of the critically ill burn patients after burn surgery was 27.1% (198/731). RF showed the highest AUC (0.922, 95% confidence interval = 0.902–0.942) among the models, with sensitivity and specificity of 66.2% and 93.8%, respectively. The most significant predictors for mortality after burn surgery as per machine learning models were total body surface area burned, red cell distribution width, and age. The RF algorithm showed the best performance for predicting mortality.

Spacecraft sample collection and subsurface excavation of asteroid (101955) Bennu

Carbonaceous asteroids, such as (101955) Bennu, preserve material from the early Solar System, including volatile compounds and organic molecules. We report spacecraft imaging and spectral data collected during and after retrieval of a sample from Bennu’s surface. The sampling event mobilized rocks and dust into a debris plume, excavating a 9-m-long elliptical crater. This exposed material that is darker, spectrally redder, and more abundant in fine particulates than the original surface. The bulk density of the displaced subsurface material was 500–700 kg per cubic meter, about half that of the whole asteroid. Particulates that landed on instrument optics spectrally resemble aqueously altered carbonaceous meteorites. The spacecraft stored 250 ± 101 g of material, which will be delivered to Earth in 2023.

Pebbles and sand on asteroid (162173) Ryugu: In situ observation and particles returned to Earth

The Hayabusa2 spacecraft investigated the C-type (carbonaceous) asteroid (162173) Ryugu. The mission performed two landing operations to collect samples of surface and subsurface material, the latter exposed by an artificial impact. We present images of the second touchdown site, finding that ejecta from the impact crater was present at the sample location. Surface pebbles at both landing sites show morphological variations ranging from rugged to smooth, similar to Ryugu's boulders, and shapes from quasi-spherical to flattened. The samples were returned to Earth on 6 December 2020. We describe the morphology of >5 grams of returned pebbles and sand. Their diverse color, shape, and structure are consistent with the observed materials of Ryugu; we conclude that they are a representative sample of the asteroid.

Lumbar Spine Computed Tomography to Magnetic Resonance Imaging Synthesis Using Generative Adversarial Network: Visual Turing Test

(1) Introduction: Computed tomography (CT) and magnetic resonance imaging (MRI) play an important role in the diagnosis and evaluation of spinal diseases, especially degenerative spinal diseases. MRI is mainly used to diagnose most spinal diseases because it shows a higher resolution than CT to distinguish lesions of the spinal canals and intervertebral discs. When it is inevitable for CT to be selected instead of MR in evaluating spinal disease, evaluation of spinal disease may be limited. In these cases, it is very helpful to diagnose spinal disease with MR images synthesized with CT images. (2) Objective: To create synthetic lumbar magnetic resonance (MR) images from computed tomography (CT) scans using generative adversarial network (GAN) models and assess how closely the synthetic images resembled the true images using visual Turing tests (VTTs). (3) Material and Methods: Overall, 285 patients aged ≥ 40 years who underwent lumbar CT and MRI were enrolled. Based on axial CT and T2-weighted axial MR images from 285 patients, an image synthesis model using a GAN was trained using three algorithms (unsupervised, semi-supervised, and supervised methods). Furthermore, VTT to determine how similar the synthetic lumbar MR images generated from lumbar CT axial images were to the true lumbar MR axial images were conducted with 59 patients who were not included in the model training. For the VTT, we designed an evaluation form comprising 600 randomly distributed axial images (150 true and 450 synthetic images from unsupervised, semi-supervised, and supervised methods). Four readers judged the authenticity of each image and chose their first- and second-choice candidates for the true image. In addition, for the three models, structural similarities (SSIM) were evaluated and the peak signal to noise ratio (PSNR) was compared among the three methods. (4) Results: The mean accuracy for the selection of true images for all four readers for their first choice was 52.0% (312/600). The accuracies of determining the true image for each reader’s first and first + second choices, respectively, were as follows: reader 1, 51.3% and 78.0%; reader 2, 38.7% and 62.0%, reader 3, 69.3% and 84.0%, and reader 4, 48.7% and 70.7%. In the case of synthetic images chosen as first and second choices, supervised algorithm-derived images were the most often selected (supervised, 118/600 first and 164/600 second; semi-supervised, 90/600 and 144/600; and unsupervised, 80/600 and 114/600). For image quality, the supervised algorithm received the best score (PSNR: 15.987 ± 1.039, SSIM: 0.518 ± 0.042). (5) Conclusion: This was the pilot study to apply GAN to synthesize lumbar spine MR images from CT images and compare training algorithms of the GAN. Based on VTT, the axial MR images synthesized from lumbar CT using GAN were fairly realistic and the supervised training algorithm was found to provide the closest image to true images.

Deep semi-supervised learning for automatic segmentation of inferior alveolar nerve using a convolutional neural network

Background

The inferior alveolar nerve (IAN) innervates and regulates the sensation of the mandibular teeth and lower lip. The position of the IAN should be monitored prior to surgery. Therefore, a study using artificial intelligence (AI) was planned to image and track the position of the IAN automatically for a quicker and safer surgery.

Methods

A total of 138 cone-beam computed tomography datasets (Internal: 98, External: 40) collected from multiple centers (three hospitals) were used in the study. A customized 3D nnU-Net was used for image segmentation. Active learning, which consists of three steps, was carried out in iterations for 83 datasets with cumulative additions after each step. Subsequently, the accuracy of the model for IAN segmentation was evaluated using the 50 datasets. The accuracy by deriving the dice similarity coefficient (DSC) value and the segmentation time for each learning step were compared. In addition, visual scoring was considered to comparatively evaluate the manual and automatic segmentation.

Results

After learning, the DSC gradually increased to 0.48 ± 0.11 to 0.50 ± 0.11, and 0.58 ± 0.08. The DSC for the external dataset was 0.49 ± 0.12. The times required for segmentation were 124.8, 143.4, and 86.4 s, showing a large decrease at the final stage. In visual scoring, the accuracy of manual segmentation was found to be higher than that of automatic segmentation.

Conclusions

The deep active learning framework can serve as a fast, accurate, and robust clinical tool for demarcating IAN location.

Active Learning for Efficient Segmentation of Liver with Convolutional Neural Network-Corrected Labeling in Magnetic Resonance Imaging-Derived Proton Density Fat Fraction

This study aimed to propose an efficient method for self-automated segmentation of the liver using magnetic resonance imaging-derived proton density fat fraction (MRI-PDFF) through deep active learning. We developed an active learning framework for liver segmentation using labeled and unlabeled data in MRI-PDFF. A total of 77 liver samples on MRI-PDFF were obtained from patients with nonalcoholic fatty liver disease. For the training, tuning, and testing of the liver segmentation, the ground truth of 71 (internal) and 6 (external) MRI-PDFF scans for training and testing were verified by an expert reviewer. For 100 randomly selected slices, manual and deep learning (DL) segmentations for visual assessments were classified, ranging from very accurate to mostly accurate. The dice similarity coefficients for each step were 0.69 ± 0.21, 0.85 ± 0.12, and 0.94 ± 0.01, respectively (p-value = 0.1389 between the first step and the second step or p-value = 0.0144 between the first step and the third step for paired t-test), indicating that active learning provides superior performance compared with non-active learning. The biases in the Bland-Altman plots for each step were - 24.22% (from - 82.76 to - 2.70), - 21.29% (from - 59.52 to 3.06), and - 0.67% (from - 10.43 to 4.06). Additionally, there was a fivefold reduction in the required annotation time after the application of active learning (2 min with, and 13 min without, active learning in the first step). The number of very accurate slices for DL (46 slices) was greater than that for manual segmentations (6 slices). Deep active learning enables efficient learning for liver segmentation on a limited MRI-PDFF.

Effect of chemotherapy on effect-site concentration of propofol for loss of consciousness in colorectal cancer patients

Background

The depth of anesthesia is an essential factor in surgical prognosis. The neurotoxic effect of chemotherapeutic drugs affects the sensitivity to anesthetics. This study was conducted to determine whether the effect-site concentration (Ce) of propofol for loss of consciousness (LOC) differs in patients undergoing preoperative chemotherapy.

Methods

A total of 60 patients scheduled for surgery for colorectal cancer under general anesthesia were included in this study. Patients who had received chemotherapy comprised the experimental (C) group, and those without a previous history of chemotherapy comprised the control (N) group. Propofol was administered as an effect-site target-controlled infusion, and the Modified Observer’s Assessment of Alertness/Sedation (MOAA/S) scores were evaluated. When the plasma concentration and Ce were similar, and if the MOAA/S score did not change, the target Ce was increased by 0.2 μg/ml; otherwise, the Ce was maintained for 2 min and then increased.

Results

The Ce values of propofol for loss of verbal contact (LVC) in groups C and N were 2.40 ± 0.39 and 2.29 ± 0.39 μg/ml (P = 0.286), respectively, and those for LOC in groups C and N were 2.69 ± 0.43 and 2.50 ± 0.36 μg/ml (P = 0.069), respectively. No significant difference was observed in Ce values between the two groups.

Conclusions

Chemotherapy had no effect on the Ce of propofol for LVC and LOC in patients with colorectal cancer. We do not recommend reducing the dose of propofol for the induction of LOC in patients with colorectal cancer undergoing chemotherapy.

Deep convolution neural networks to differentiate between COVID-19 and other pulmonary abnormalities on chest radiographs: Evaluation using internal and external datasets

We aimed to evaluate the performance of convolutional neural networks (CNNs) in the classification of coronavirus disease 2019 (COVID-19) disease using normal, pneumonia, and COVID-19 chest radiographs (CXRs). First, we collected 9194 CXRs from open datasets and 58 from the Korea University Anam Hospital (KUAH). The number of normal, pneumonia, and COVID-19 CXRs were 4580, 3884, and 730, respectively. The CXRs obtained from the open dataset were randomly assigned to the training, tuning, and test sets in a 70:10:20 ratio. For external validation, the KUAH (20 normal, 20 pneumonia, and 18 COVID-19) dataset, verified by radiologists using computed tomography, was used. Subsequently, transfer learning was conducted using DenseNet169, InceptionResNetV2, and Xception to identify COVID-19 using open datasets (internal) and the KUAH dataset (external) with histogram matching. Gradient-weighted class activation mapping was used for the visualization of abnormal patterns in CXRs. The average AUC and accuracy of the multiscale and mixed-COVID-19Net using three CNNs over five folds were (0.99 ± 0.01 and 92.94% ± 0.45%), (0.99 ± 0.01 and 93.12% ± 0.23%), and (0.99 ± 0.01 and 93.57% ± 0.29%), respectively, using the open datasets (internal). Furthermore, these values were (0.75 and 74.14%), (0.72 and 68.97%), and (0.77 and 68.97%), respectively, for the best model among the fivefold cross-validation with the KUAH dataset (external) using domain adaptation. The various state-of-the-art models trained on open datasets show satisfactory performance for clinical interpretation. Furthermore, the domain adaptation for external datasets was found to be important for detecting COVID-19 as well as other diseases.

Machine learning with multiparametric breast MRI for prediction of Ki-67 and histologic grade in early-stage luminal breast cancer

OBJECTIVES

To investigate whether machine learning-based prediction models using 3-T multiparametric MRI (mpMRI) can predict Ki-67 and histologic grade in stage I-II luminal cancer.

METHODS

Between 2013 and 2019, consecutive women with luminal cancers who underwent preoperative MRI with diffusion-weighted imaging (DWI) and surgery were included. For prediction models, morphology, kinetic features using computer-aided diagnosis (CAD), and apparent diffusion coefficient (ADC) at DWI were evaluated by two radiologists. Logistic regression analysis was used to identify mpMRI features for predicting Ki-67 and grade. Diagnostic performance was assessed using eight machine learning algorithms incorporating mpMRI features and compared using the DeLong method.

RESULTS

Of 300 women, 203 (67.7%) had low Ki-67 and 97 (32.3%) had high Ki-67; 242 (80.7%) had low grade and 58 (19.3%) had high grade. In multivariate analysis, independent predictors for higher Ki-67 were washout component > 13.5% (odds ratio [OR] = 4.16; p < 0.001) and intratumoral high SI on T2-weighted image (OR = 1.89; p = 0.022). Those for higher grade were washout component > 15.5% (OR = 7.22; p < 0.001), rim enhancement (OR = 2.59; p = 0.022), and ADC value < 0.945 × 10^-3 mm²/s (OR = 2.47; p = 0.015). Among eight models using these predictors, six models showed the equivalent performance for Ki-67 (area under the receiver operating characteristic curve [AUC]: 0.70) and Naive Bayes classifier showed the highest performance for grade (AUC: 0.79).

CONCLUSIONS

A prediction model incorporating mpMRI features shows good diagnostic performance for predicting Ki-67 and histologic grade in patients with luminal breast cancers.

KEY POINTS

• Among multiparametric MRI features, kinetic feature of washout component >13.5% and intratumoral high signal intensity on T2-weighted image were associated with higher Ki-67. • Washout component >15.5%, rim enhancement, and mean apparent diffusion coefficient value < 0.945 × 10^-3 mm²/s were associated with higher histologic grade. • Machine learning-based prediction models incorporating multiparametric MRI features showed good diagnostic performance for Ki-67 and histologic grade in luminal breast cancers.

Optimal number of strong labels for curriculum learning with convolutional neural network to classify pulmonary abnormalities in chest radiographs

BACKGROUND AND OBJECTIVE

It is important to alleviate annotation efforts and costs by efficiently training on medical images. We performed a stress test on several strong labels for curriculum learning with a convolutional neural network to differentiate normal and five types of pulmonary abnormalities in chest radiograph images.

METHODS

The numbers of CXR images of healthy subjects and patients, acquired at Asan Medical Center (AMC), were 6069 and 3465, respectively. The numbers of CXR images of patients with nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax were 944, 550, 280, 1360, and 331, respectively. The AMC dataset was split into training, tuning, and test, with a ratio of 7:1:2. All lesions were strongly labeled by thoracic expert radiologists, with confirmation of the corresponding CT. For curriculum learning, normal and abnormal patches (N = 26658) were randomly extracted around the normal lung and strongly labeled abnormal lesions, respectively. In addition, 1%, 5%, 20%, 50%, and 100% of strong labels were used to determine an optimal number for them. Each patch dataset was trained with the ResNet-50 architecture, and all CXRs with weak labels were used for fine-tuning them in a transfer-learning manner. A dataset acquired from the Seoul National University Bundang Hospital (SNUBH) was used for external validation.

RESULTS

The detection accuracies of the 1%, 5%, 20%, 50%, and 100% datasets were 90.51, 92.15, 93.90, 94.54, and 95.39, respectively, in the AMC dataset and 90.01, 90.14, 90.97, 91.92, and 93.00 in the SNUBH dataset.

CONCLUSIONS

Our results showed that curriculum learning with over 20% sampling rate for strong labels are sufficient to train a model with relatively high performance, which can be easily and efficiently developed in an actual clinical setting.

The role of goal adjustment during rehabilitation from stroke

We investigated motivational regulation involving adjustment of recovery goals in post-stroke rehabilitation via standard in-clinic physiotherapy and in-home telerehabilitation (TR). We used a secondary dataset collected at 11 US sites as part of a clinical trial using video games and game control pads designed to induce certain arm movements required for recovery (n = 124; M_age  = 61.44, SD = 13.30). Participants were randomly assigned to either the TR or in-clinic condition and underwent 36 therapy sessions, reporting on their activity-inherent enjoyment for 6-8 weeks. Compared with the in-clinic patients and TR patients with high game performance, TR patients with lower game performance reported lower activity-inherent enjoyment, which is an important motivational resource for successful recovery. The results suggest that these differences occur because TR patients become discouraged by low game score feedback, which may have signaled a poor prospect for recovery. However, the results also suggest that low game performers who successfully adjusted their recovery goals were resilient to the impact of low game score feedback on their motivational resources and satisfaction with therapy. The findings suggest that goal adjustment may be particularly beneficial when patients are discouraged by feedback indicating suboptimal recovery prospects.

Deep Active Learning for Automatic Segmentation of Maxillary Sinus Lesions Using a Convolutional Neural Network

The aim of this study was to segment the maxillary sinus into the maxillary bone, air, and lesion, and to evaluate its accuracy by comparing and analyzing the results performed by the experts. We randomly selected 83 cases of deep active learning. Our active learning framework consists of three steps. This framework adds new volumes per step to improve the performance of the model with limited training datasets, while inferring automatically using the model trained in the previous step. We determined the effect of active learning on cone-beam computed tomography (CBCT) volumes of dental with our customized 3D nnU-Net in all three steps. The dice similarity coefficients (DSCs) at each stage of air were 0.920 ± 0.17, 0.925 ± 0.16, and 0.930 ± 0.16, respectively. The DSCs at each stage of the lesion were 0.770 ± 0.18, 0.750 ± 0.19, and 0.760 ± 0.18, respectively. The time consumed by the convolutional neural network (CNN) assisted and manually modified segmentation decreased by approximately 493.2 s for 30 scans in the second step, and by approximately 362.7 s for 76 scans in the last step. In conclusion, this study demonstrates that a deep active learning framework can alleviate annotation efforts and costs by efficiently training on limited CBCT datasets.

Engineered ionizable lipid nanoparticles for targeted delivery of RNA therapeutics into different types of cells in the liver

Ionizable lipid nanoparticles (LNPs) have been widely used for in vivo delivery of RNA therapeutics into the liver. However, a main challenge remains to develop LNP formulations for selective delivery of RNA into certain types of liver cells, such as hepatocytes and liver sinusoidal endothelial cells (LSECs). Here, we report the engineered LNPs for the targeted delivery of RNA into hepatocytes and LSECs. The effects of particle size and polyethylene glycol-lipid content in the LNPs were evaluated for the hepatocyte-specific delivery of mRNA by ApoE-mediated cellular uptake through low-density lipoprotein receptors. Targeted delivery of RNA to LSECs was further investigated using active ligands. Incorporation of mannose allowed the selective delivery of RNA to LSECs, while minimizing the unwanted cellular uptake by hepatocytes. These results demonstrate that engineered LNPs have great potential for the cell type-specific delivery of RNA into the liver and other tissues.

Developing a predictive model for distinguishing invasive nail unit melanoma from nail unit melanoma in situ

BACKGROUND

Clinical information that distinguishes invasive nail unit melanoma from nail unit melanoma in situ before surgery would aid physicians in the decision-making process and estimating prognosis. However, limited information is available on the detailed demographic and dermoscopic features of invasive nail unit melanoma and nail unit melanoma in situ for differential diagnosis.

OBJECTIVE

This study aimed to investigate the demographic data and dermoscopic features of invasive nail unit melanoma and nail unit melanoma in situ and establish a predictive model for differentiating these two forms of nail unit melanoma.

METHODS

A retrospective observational study of ninety-seven patients diagnosed with nail unit melanoma (59 in situ and 38 invasive cases) in four healthcare centres in South Korea (three tertiary referral hospitals and one second referral hospital) from March 2014 to December 2019.

RESULTS

A multivariable analysis revealed that ulcer (odds ratio = 21.6, confidence interval = 2.1-219.8, P = 0.009), total melanonychia (odds ratio = 17.6, confidence interval = 3.0-104.0, P = 0.002), nail plate destruction (odds ratio = 10.9, confidence interval = 2.0-59.4, P = 0.006) and polychromia (odds ratio = 5.3, confidence interval = 1.36-20.57, P = 0.016) were distinctive dermoscopic features of invasive nail unit melanoma. A predictive model with scores ranging from 0 to 6 points demonstrated a reliable diagnostic value (C-statistic = 0.902) in differentiating invasive nail unit melanoma from nail unit melanoma in situ.

CONCLUSIONS

Invasive nail unit melanoma and nail unit melanoma in situ have different dermoscopic features. A predictive model based on morphologic dermoscopic features could aid in differentiating invasive nail unit melanoma from nail unit melanoma in situ.

Evaluation of Left Atrial Appendage Isolation Using Cardiac MRI after Catheter Ablation of Atrial Fibrillation: Paradox of Appendage Reservoir

Objective

To assess the effect of left atrial appendage (LAA) isolation on LAA emptying and left atrial (LA) function using cardiac MRI in patients who underwent successful catheter ablation of atrial fibrillation (AF).

Materials and Methods

This retrospective study included 84 patients (mean age, 59 ± 10 years; 67 males) who underwent cardiac MRI after successful catheter ablation of AF. According to the electrical activity of LAA after catheter ablation, patients showed either LAA isolation or LAA normal activity. The LAA emptying phase (LAA-EP, in the systolic phase [SP] or diastolic phase), LAA emptying flux (LAA-EF, mL/s), and LA ejection fraction (LAEF, %) were evaluated by cardiac MRI.

Results

Of the 84 patients, 61 (73%) and 23 (27%) patients showed LAA normal activity and LAA isolation, respectively. Incidence of LAA emptying in SP was significantly higher in LAA isolation (91% vs. 0%, p < 0.001) than in LAA normal activation. LAA-EF was significantly lower in LAA isolation (40.1 ± 16.2 mL/s vs. 80.2 ± 25.1 mL/s, p < 0.001) than in LAA normal activity. Furthermore, LAEF was significantly lower in LAA isolation (23.7% ± 11.2% vs. 31.1% ± 16.6%, p = 0.04) than in LAA normal activity. Multivariate analysis demonstrated that the LAA-EP was independent from LAEF (p = 0.01).

Conclusion

LAA emptying in SP may be a critical characteristic of LAA isolation, and it may adversely affect the LAEF after catheter ablation of AF.