Syoji Kobashi

Background: Hematoma expansion (HE) is a significant risk factor for poor prognosis in patients with intracerebral hemorrhage (ICH). Accurately predicting HE is crucial for determining optimal treatment strategies. Methods: This study enrolled 452 patients with ICH from 10 hospitals. To predict HE, 28 clinical variables available on patient arrival (including medical history, ICH location, and ICH volume) and 1142 radiomics features extracted from noncontrast computed tomography images of the ICH regions were used. Clinical variables and radiomics features were selected using gradient boosting and the least absolute shrinkage and selection operator. Three HE prediction models were built on clinical variables alone, radiomics features alone, and a third combining both. The models were compared using 5‐fold cross‐validation, and the mean area under the receiver operating characteristic curve was calculated for each. Additionally, the important features of HE prediction in the combined model were explored. Results: The combined model demonstrated the highest performance for predicting HE with a 5‐fold mean area under the receiver operating characteristic curve of 0.77±0.05, compared with 0.70±0.06 for the clinical variables alone and 0.73±0.04 for the radiomics features alone. Permutation feature importance analysis suggested that anticoagulant treatment was the most predictive of HE. Conclusions: A predictive model for HE was developed using the medical history, clinical features available on the patient’s arrival, imaging, and radiomics features extracted from computed tomography images. This prediction model will assist non–stroke care specialists in making treatment decisions for ICH in emergency settings.

Purpose Distinguishing idiopathic normal pressure hydrocephalus (iNPH) from progressive supranuclear palsy (PSP) presents a clinical challenge due to overlapping clinical symptoms such as gait disturbances and cognitive decline. This study presents a novel multi-scale deep learning framework that integrates global and local magnetic resonance imaging (MRI) features using a mixture of experts (MoE) mechanism, enhancing diagnostic accuracy and minimizing interobserver variability. Methods The proposed framework combines a 3D convolutional neural network (CNN) for capturing global volumetric features with a 2.5D recurrent CNN focusing on disease-specific regions of interest (ROIs), including the lateral ventricles, high convexity sulci, midbrain, and Sylvian fissures. The MoE mechanism dynamically weights global and local features, optimizing the classification process. Model performance was assessed using stratified fivefold cross-validation on T1-weighted MRI from 118 patients (53 iNPH, 65 PSP) to ensure balanced class distributions across training folds. Results The MoE model using ResNet-34 achieved an accuracy of 0.983 (95% CI 0.875–1.000), a recall of 0.985 (95% CI 0.750–1.000), a precision of 0.986 (95% CI 0.769–1.000), and an area under the curve (AUC) of 1.000 (95% CI 1.000–1.000), outperforming traditional morphological markers and single-branch deep learning models. The MoE mechanism allowed adaptive weighting of global and local features, contributing to both improved robustness and interpretability. Grad-CAM visualizations highlighted disease-specific regions, demonstrating that the model focused on relevant features in both successful and failure modes of the 3D CNN expert for iNPH and PSP. Conclusion The dynamic integration of global and local MRI features through the MoE framework offers a powerful, robust, and interpretable tool for differentiating iNPH from PSP. This approach reduces reliance on subjective visual assessments and has the potential for broader clinical application through dataset expansion and multicenter validation.

Background: The optimal scale of urbanization for stroke health care provision and the potential impact of compact city design on stroke outcomes remain unclear. We investigated the impact of zip code area‐level compact city design using the walkability index (WI) and its mediators on stroke outcomes. Methods: This nationwide retrospective study used data from patients with stroke from the J‐ASPECT study (2017–2022). WI was calculated as the average of 3 Z ‐scored city design elements (population density, road connectivity, and variation in walkable facilities) from 113 1156 zip code areas in Japan. The association between WI and in‐hospital mortality, functional independence at discharge, and medical costs was assessed using multivariable mixed‐effects logistic regression model. Results: Overall, 555 296 patients (median age, 75 [interquartile range, 66–83] years; female, 42.5%) from 818 hospitals were included. Higher WI was significantly associated with decreased in‐hospital mortality (odds ratio [OR], 0.94 [95% CI, 0.92–0.96]) and increased functional independence (OR, 1.03 [95% CI, 1.02–1.04]). The highest WI group was associated with decreased mortality, primarily mediated by management in intensive or stroke care units (proportion mediated, 0.46 [95% CI, 0.35–0.63]), and the highest WI group was associated with increased functional independence, mediated by short road distance to the hospital (proportion mediated, 0.30 [95% CI, 0.21–0.44]). Conclusions: Zip code area‐level compact city design was associated with decreased in‐hospital mortality and increased functional independence. Compact city design at community level, even without large‐scale urbanization, may contribute to improving stroke care provision and outcomes in increasingly urbanized societies.

Impacted third molar extraction, particularly of mandibular teeth, is a common procedure performed to alleviate pain, infection, and misalignment. Accurate diagnosis and classification of impaction types are crucial for effective treatment planning. This study introduces a novel algorithm for automatically measuring the impaction angles of mandibular third molars (T32 and T17) from orthopantomogram (OPG) images. The proposed method is based on deep learning techniques, including segmentation and key point detection models. It categorizes impactions into Winter’s classification: distoangular, mesioangular, horizontal, vertical, and other on both sides, using the measured angles. The proposed method used 450 OPGs, achieving high mandibular molar segmentation accuracy with dice similarity coefficients (DSC) values of 0.9058–0.9162 and intersection over union (IOU) scores of 0.82–0.84. The object keypoint similarity (OKS) for detecting the four corner points of each molar was 0.82. Angle measurement analysis showed 80% accuracy within ±5° deviation for distoangular impaction of T32 and within ±8° for T17. The F1-scores for mesioangular classifications were 0.88 for T32 and 0.91 for T17, with varying performance in other categories. Nonetheless, the predicted angles aid in identifying impaction types, showcasing the method’s potential to enhance dental diagnostics and treatment planning.

Background: Ultrasonography is used to diagnose osteochondritis dissecans (OCD) of the humerus; however, its reliability depends on the technical proficiency of the examiner. Recently, computer-aided diagnosis (CAD) using deep learning has been applied in the field of medical science, and high diagnostic accuracy has been reported. We aimed to develop a deep learning-based CAD system for OCD detection on ultrasound images and to evaluate the accuracy of OCD detection using the CAD system. Methods: The CAD process comprises 2 steps: humeral capitellum detection using an object-detection algorithm and OCD classification using an image classification network. Four-directional ultrasound images of the elbow of the throwing arm of 196 baseball players (mean age, 11.2 years), including 104 players with normal findings and 92 with OCD, were used for training and validation. An external dataset of 20 baseball players (10 with normal findings and 10 with OCD) was used to evaluate the accuracy of the CAD system. A confusion matrix and the area under the receiver operating characteristic curve (AUC) were used to evaluate the system. Results: Clinical evaluation using the external dataset resulted in high AUCs in all 4 directions: 0.969 for the anterior long axis, 0.966 for the anterior short axis, 0.996 for the posterior long axis, and 0.993 for the posterior short axis. The accuracy of OCD detection thus exceeded 0.9 in all 4 directions. Conclusions: We propose a deep learning-based CAD system to detect OCD lesions on ultrasound images. The CAD system achieved high accuracy in all 4 directions of the elbow. This CAD system with a deep learning model may be useful for OCD screening during medical checkups to reduce the probability of missing an OCD lesion. Level of Evidence: Diagnostic Level II. See Instructions for Authors for a complete description of levels of evidence.

Purpose: Osteochondritis dissecans (OCD) of the humeral capitellum is a common cause of elbow disorders, particularly among young throwing athletes. Conservative treatment is the preferred treatment for managing OCD, and early intervention significantly influences the possibility of complete disease resolution. The purpose of this study is to develop a deep learning-based classification model in ultrasound images for computer-aided diagnosis. Methods: This paper proposes a deep learning-based OCD classification method in ultrasound images. The proposed method first detects the humeral capitellum detection using YOLO and then estimates the OCD probability of the detected region probability using VGG16. We hypothesis that the performance will be improved by eliminating unnecessary regions. To validate the performance of the proposed method, it was applied to 158 subjects (OCD: 67, Normal: 91) using five-fold-cross-validation. Results: The study demonstrated that the humeral capitellum detection achieved a mean average precision (mAP) of over 0.95, while OCD probability estimation achieved an average accuracy of 0.890, precision of 0.888, recall of 0.927, F1 score of 0.894, and an area under the curve (AUC) of 0.962. On the other hand, when the classification model was constructed for the entire image, accuracy, precision, recall, F1 score, and AUC were 0.806, 0.806, 0.932, 0.843, and 0.928, respectively. The findings suggest the high-performance potential of the proposed model for OCD classification in ultrasonic images. Conclusion: This paper introduces a deep learning-based OCD classification method. The experimental results emphasize the effectiveness of focusing on the humeral capitellum for OCD classification in ultrasound images. Future work should involve evaluating the effectiveness of employing the proposed method by physicians during medical check-ups for OCD.