Development and Multicenter, Multiprotocol Validation of Neural Network for Aberrant Right Subclavian Artery Detection.

PURPOSE: This study aimed to develop and validate a convolutional neural network (CNN) that automatically detects an aberrant right subclavian artery (ARSA) on preoperative computed tomography (CT) for thyroid cancer evaluation. MATERIALS AND METHODS: A total of 556 CT with ARSA and 312 CT with normal aortic arch from one institution were used as the training set for model development. A deep learning model for the classification of patch images for ARSA was developed using two-dimension CNN from EfficientNet. The diagnostic performance of our model was evaluated using external test sets (112 and 126 CT) from two institutions. The performance of the model was compared with that of radiologists for detecting ARSA using an independent dataset of 1683 consecutive neck CT. RESULTS: The performance of the model was achieved using two external datasets with an area under the curve of 0.97 and 0.99, and accuracy of 97% and 99%, respectively. In the temporal validation set, which included a total of 20 patients with ARSA and 1663 patients without ARSA, radiologists overlooked 13 ARSA cases. In contrast, the CNN model successfully detected all the 20 patients with ARSA. CONCLUSION: We developed a CNN-based deep learning model that detects ARSA using CT. Our model showed high performance in the multicenter validation.

Deep learning-based surgical phase recognition in laparoscopic cholecystectomy.

Backgrounds/Aims: Artificial intelligence (AI) technology has been used to assess surgery quality, educate, and evaluate surgical performance using video recordings in the minimally invasive surgery era. Much attention has been paid to automating surgical workflow analysis from surgical videos for an effective evaluation to achieve the assessment and evaluation. This study aimed to design a deep learning model to automatically identify surgical phases using laparoscopic cholecystectomy videos and automatically assess the accuracy of recognizing surgical phases. Methods: One hundred and twenty cholecystectomy videos from a public dataset (Cholec80) and 40 laparoscopic cholecystectomy videos recorded between July 2022 and December 2022 at a single institution were collected. These datasets were split into training and testing datasets for the AI model at a 2:1 ratio. Test scenarios were constructed according to structural characteristics of the trained model. No pre- or post-processing of input data or inference output was performed to accurately analyze the effect of the label on model training. Results: A total of 98,234 frames were extracted from 40 cases as test data. The overall accuracy of the model was 91.2%. The most accurate phase was Calot's triangle dissection (F1 score: 0.9421), whereas the least accurate phase was clipping and cutting (F1 score: 0.7761). Conclusions: Our AI model identified phases of laparoscopic cholecystectomy with a high accuracy.

Prediction of cerebral hemorrhagic transformation after thrombectomy using a deep learning of dual-energy CT.

OBJECTIVES: To develop and validate a deep learning model for predicting hemorrhagic transformation after endovascular thrombectomy using dual-energy computed tomography (CT). MATERIALS AND METHODS: This was a retrospective study from a prospective registry of acute ischemic stroke. Patients admitted between May 2019 and February 2023 who underwent endovascular thrombectomy for acute anterior circulation occlusions were enrolled. Hemorrhagic transformation was defined using follow-up magnetic resonance imaging or CT. The deep learning model was developed using post-thrombectomy dual-energy CT to predict hemorrhagic transformation within 72 h. Temporal validation was performed with patients who were admitted after July 2022. The deep learning model's performance was compared with a logistic regression model developed from clinical variables using the area under the receiver operating characteristic curve (AUC). RESULTS: Total of 202 patients (mean age 71.4 years ± 14.5 [standard deviation], 92 men) were included, with 109 (54.0%) patients having hemorrhagic transformation. The deep learning model performed consistently well, showing an average AUC of 0.867 (95% confidence interval [CI], 0.815-0.902) upon five-fold cross validation and AUC of 0.911 (95% CI, 0.774-1.000) with the test dataset. The clinical variable model showed an AUC of 0.775 (95% CI, 0.709-0.842) on the training dataset (p < 0.01) and AUC of 0.634 (95% CI, 0.385-0.883) on the test dataset (p = 0.06). CONCLUSION: A deep learning model was developed and validated for prediction of hemorrhagic transformation after endovascular thrombectomy in patients with acute stroke using dual-energy computed tomography. CLINICAL RELEVANCE STATEMENT: This study demonstrates that a convolutional neural network (CNN) can be utilized on dual-energy computed tomography (DECT) for the accurate prediction of hemorrhagic transformation after thrombectomy. The CNN achieves high performance without the need for region of interest drawing. KEY POINTS: • Iodine leakage on dual-energy CT after thrombectomy may be from blood-brain barrier disruption. • A convolutional neural network on post-thrombectomy dual-energy CT enables individualized prediction of hemorrhagic transformation. • Iodine leakage is an important predictor of hemorrhagic transformation following thrombectomy for ischemic stroke.

Deep Learning for the Detection of Breast Cancers on Chest Computed Tomography.

BACKGROUND: Incidental breast cancers can be detected on chest computed tomography (CT) scans. With the use of deep learning, the sensitivity of incidental breast cancer detection on chest CT would improve. This study aimed to evaluate the performance of a deep learning algorithm to detect breast cancers on chest CT and to validate the results in the internal and external datasets. PATIENTS AND METHODS: This retrospective study collected 1170 preoperative chest CT scans after the diagnosis of breast cancer for algorithm development (n = 1070), internal test (n = 100), and external test (n = 100). A deep learning algorithm based on RetinaNet was developed and tested to detect breast cancer on chest CT. RESULTS: In the internal test set, the algorithm detected 96.5% of breast cancers with 13.5 false positives per case (FPs/case). In the external test set, the algorithm detected 96.1% of breast cancers with 15.6 FPs/case. When the candidate probability of 0.3 was used as the cutoff value, the sensitivities were 92.0% with 7.36 FPs/case for the internal test set and 93.0% with 8.85 FPs/case for the external test set. When the candidate probability of 0.4 was used as the cutoff value, the sensitivities were 88.5% with 5.24 FPs/case in the internal test set and 90.7% with 6.3 FPs/case in the external test set. CONCLUSION: The deep learning algorithm could sensitively detect breast cancer on chest CT in both the internal and external test sets.

Diagnostic performance of shoulder magnetic resonance arthrography for labral tears having surgery as reference: comparison of high-resolution isotropic 3D sequence (THRIVE) with standard protocol.

PURPOSE: To compare the diagnostic performance of T1 high-resolution isotropic volume excitation (THRIVE) sequence with that of a standard protocol for direct shoulder magnetic resonance arthrography (MRA) for the diagnosis of superior labral anterior-to-posterior (SLAP) and Bankart lesions, using arthroscopy findings as a reference standard. MATERIALS AND METHODS: We retrospectively studied 84 patients who underwent direct shoulder 3T MRA using THRIVE and two-dimensional three-plane proton-density fat-suppressed (2D-PD-FS) sequences. One reviewer evaluated the contrast-to-noise ratio (CNR) as a quantitative image quality. Other two reviewers independently evaluated the subjective image noise, image sharpness, and radiologic diagnosis as qualitative image quality. Arthroscopic surgical findings were considered the reference standard. Wilcoxon rank sum, Chi-square/Fisher's exact, and DeLong's tests, as well as intraclass correlation coefficients (ICCs) were used to evaluate differences between THRIVE and 2D-PD-FS images. RESULTS: THRIVE images had significantly higher CNR (p < 0.001), and subjective ratings of image noise (p = 0.009) and sharpness (p = 0.039) than 2D-PD-FS images (p < 0.001). THRIVE images had similar (p ≥ 0.18) diagnostic performance (sensitivity, 93.0-97.2%; specificity, 95.8-100%; accuracy, 95.2-97.6%) for the diagnosis of SLAP and Bankart lesions with excellent agreement (ICC = 0.898-0.942) when compared to 2D-PD-FS images (sensitivity, 86.1-91.7%; specificity, 93.8-95.8%; accuracy, 90.5-92.9%; agreement, ICC = 0.782-0.858). The scan time was reduced by 69% for THRIVE sequence compared to 2D-PD-FS sequence (2 min 40 s vs. 8 min 40 s). CONCLUSION: The THRIVE sequence may be helpful in the diagnosis of SLAP and Bankart lesions, and may be routinely used during direct shoulder 3T MRA.