Automatic quantification and grading of hip bone marrow oedema in ankylosing spondylitis based on deep learning.

OBJECTIVE: This study has developed a new automatic algorithm for the quantificationy and grading of ankylosing spondylitis (AS)-hip arthritis with magnetic resonance imaging (MRI). METHODS: (1) This study designs a new segmentation network based on deep learning, and a classification network based on deep learning. (2) We train the segmentation model and classification model with the training data and validate the performance of the model. (3) The segmentation results of inflammation in MRI images were obtained and the hip joint was quantified using the segmentation results. RESULTS: A retrospective analysis was performed on 141 cases; 101 patients were included in the derived cohort and 40 in the validation cohort. In the derivation group, median percentage of bone marrow oedema (BME) for each grade was as follows: 36% for grade 1 (<15%), 42% for grade 2 (15-30%),and 22% for grade 3 (≥30%). The accuracy of 44 cases on 835 AS images was 85.7%. Our model made 31 correct decisions out of 40 AS test cases. This study showed that THE accuracy rate 85.7%. CONCLUSIONS: An automatic computer-based analysis of MRI has the potential of being a useful method for the diagnosis and grading of AS hip BME.

Visual interpretable MRI fine grading of meniscus injury for intelligent assisted diagnosis and treatment.

Meniscal injury represents a common type of knee injury, accounting for over 50% of all knee injuries. The clinical diagnosis and treatment of meniscal injury heavily rely on magnetic resonance imaging (MRI). However, accurately diagnosing the meniscus from a comprehensive knee MRI is challenging due to its limited and weak signal, significantly impeding the precise grading of meniscal injuries. In this study, a visual interpretable fine grading (VIFG) diagnosis model has been developed to facilitate intelligent and quantified grading of meniscal injuries. Leveraging a multilevel transfer learning framework, it extracts comprehensive features and incorporates an attributional attention module to precisely locate the injured positions. Moreover, the attention-enhancing feedback module effectively concentrates on and distinguishes regions with similar grades of injury. The proposed method underwent validation on FastMRI_Knee and Xijing_Knee dataset, achieving mean grading accuracies of 0.8631 and 0.8502, surpassing the state-of-the-art grading methods notably in error-prone Grade 1 and Grade 2 cases. Additionally, the visually interpretable heatmaps generated by VIFG provide accurate depictions of actual or potential meniscus injury areas beyond human visual capability. Building upon this, a novel fine grading criterion was introduced for subtypes of meniscal injury, further classifying Grade 2 into 2a, 2b, and 2c, aligning with the anatomical knowledge of meniscal blood supply. It can provide enhanced injury-specific details, facilitating the development of more precise surgical strategies. The efficacy of this subtype classification was evidenced in 20 arthroscopic cases, underscoring the potential enhancement brought by intelligent-assisted diagnosis and treatment for meniscal injuries.