Mycosis fungoides is characterized by widespread skin patches that may progress to plaques and tumors, necessitating precise tumor burden assessment for staging and treatment guidance. However, existing methods, including the widely accepted modified Severity Weighted Assessment Tool (mSWAT), present significant challenges in routine practice owing to their time-consuming nature and interobserver variability. This study developed an artificial intelligence model, mSWAT-Net, to estimate mSWAT scores using clinical images of patients with mycosis fungoides. Notably, the overlap area segmentation submodule of mSWAT-Net addressed double-counting errors in multiangle photos through training on 3904 annotated images generated from 61 three-dimensional human images. Across 2463 standardized full-body photographs from 134 imaging series, mSWAT-Net demonstrated performance comparable with that of experienced cutaneous lymphoma specialists, achieving intraclass correlation coefficients of 0.917 (internal validation) and 0.846 (temporal validation) for mSWAT score. Moreover, mSWAT-Net outperformed 3 junior dermatologists in image-based scoring (intraclass correlation coefficient = 0.917 vs 0.777) and demonstrated robust performance when compared with ground truth derived from 3-dimensional patient imaging (intraclass correlation coefficient = 0.812). Finally, mSWAT-Net was deployed as a free web application to support mycosis fungoides management in clinical settings. These findings highlight the potential of mSWAT-Net as an accurate, automated clinical tool for facilitating patient follow-up, treatment monitoring, and remote consultations.

Magnetic Resonance Imaging (MRI) is widely used in diagnosing anterior cruciate ligament (ACL) injuries due to its ability to provide detailed image data. However, existing deep learning approaches often overlook additional factors beyond the image itself. In this study, we aim to bridge this gap by exploring the relationship between ACL rupture and the bone morphology of the femur and tibia. Leveraging extensive clinical experience, we acknowledge the significance of this morphological data, which is not readily observed manually. To effectively incorporate this vital information, we introduce ACLNet, a novel model that combines the convolutional representation of MRI images with the transformer representation of bone morphological point clouds. This integration significantly enhances ACL injury predictions by leveraging both imaging and geometric data. Our methodology demonstrated an enhancement in diagnostic precision on the in-house dataset compared to image-only methods, elevating the accuracy from 87.59% to 92.57%. This strategy of utilizing implicitly relevant information to enhance performance holds promise for a variety of medical-related tasks.