What question did this study set out to answer?

This research aims to create a Clinical Decision Support System that enhances the early diagnosis of axial spondyloarthritis through multi-sequence MRI analysis and clinical data integration.

April 1, 2026Open Access

A Comprehensive Clinical Decision Support System for the Early Diagnosis of Axial Spondyloarthritis: Multi-Sequence MRI, Clinical Risk Integration, and Explainable Segmentation

Key Points

This research aims to create a Clinical Decision Support System that enhances the early diagnosis of axial spondyloarthritis through multi-sequence MRI analysis and clinical data integration.
Analyzed multi-sequence sacroiliac joint MRI data from 367 participants
Employed deep learning models like VGG16 and DenseNet121 for sequence-based classification
Used logistic regression to integrate image-based and clinical risk scores
Segmented active inflammation using the MDC-UNet model for visual interpretability
Applied Dynamic Top-K Averaging method for patient-level scoring.
VGG16 achieved the highest accuracy of 87.8% on T1-WI images
DenseNet121 demonstrated a 79.3% accuracy on STIR images
The lightweight SacroNet model provided competitive performance with fewer parameters
MDC-UNet segmented active inflammation effectively, with Dice scores of 0.752 for STIR and 0.682 for T2-WI.

Abstract

Background/Objectives: This study aims to develop a comprehensive Clinical Decision Support System (CDSS) that integrates multi-sequence sacroiliac joint (SIJ) MRIs with rheumatological, clinical, and laboratory findings into the decision-making process for the early diagnosis of axial spondyloarthritis (axSpA), incorporating segmentation-supported explainability. Methods: Multi-sequence SIJ MRI data (T1-WI, T2-WI, STIR, and PD-WI) were analysed from 367 participants (n = 193 axSpA; n = 174 non-axSpA controls). Sequence-based classification was performed using VGG16, ResNet50, DenseNet121, and InceptionV3 models; additionally, a lightweight and parameter-efficient SacroNet architecture was developed. Slice-level probability scores were converted to patient-level scores using the Dynamic Top-K Averaging method. Image-based scores were combined with a logistic regression-based clinical risk score using weighted linear integration (0.60 image/0.40 clinical) and a conservative threshold (τ = 0.70). Grad-CAM was applied for visual interpretability. Furthermore, to support the diagnostic outcomes with precise spatial data, active inflammation in STIR and T2-WI sequences was segmented. For this purpose, the MDC-UNet model was employed and compared with baseline U-Net derivatives. Results: Sequence-specific analysis showed VGG16 performing best on T1-WI (AUC = 0.920; Accuracy = 0.878) and DenseNet121 on STIR (AUC = 0.793; Accuracy = 0.771). The SacroNet architecture provided competitive classification performance at the patient level despite its low number of parameters (~110 K). Furthermore, MDC-UNet successfully segmented active inflammation, yielding Dice scores of 0.752 (HD95: 19.25) for STIR and 0.682 (HD95: 26.21) for T2-WI. Conclusions: The findings demonstrate that patient-level decision integration based on multi-sequence MRI, when used in conjunction with clinical risk scoring and segmentation-assisted interpretability, can provide a feasible and interpretable DSS framework for the early diagnosis of axSpA.

A Comprehensive Clinical Decision Support System for the Early Diagnosis of Axial Spondyloarthritis: Multi-Sequence MRI, Clinical Risk Integration, and Explainable Segmentation

Key Points

Abstract

Cite This Study