Scholarlink

Objective <p>This study aimed to develop and evaluate a Transformer-CNN framework for automated segmentation of multiple sclerosis (MS) lesions on FLAIR MRI. The model was benchmarked against U-Net and DeepLabV3 and assessed for both segmentation accuracy and across-center performance under internal 5-fold cross-validation to ensure robustness across diverse clinical datasets.</p> Materials and methods <p>A dataset of 1,800 3D FLAIR MRI scans from five clinical centers was split using 5-fold cross-validation. Preprocessing included isotropic resampling, intensity normalization, and bias field correction. The Transformer-CNN combined CNN-based local feature extraction with Transformer-based global context modeling. Data augmentation strategies, including geometric transformations and noise injection, enhanced generalization. Performance was evaluated using Dice score, IoU, HD95, and pixel accuracy, along with internal cross-validation-based metrics such as Generalized Dice Similarity Coefficient (GDSC), Domain-wise IoU (DwIoU), Cross-Fold Dice Deviation (CFDD), and Volume Agreement (Intraclass Correlation Coefficient, ICC). Statistical significance was tested using Kruskal-Wallis and Dunn’s post-hoc analyses to compare models.</p> Results <p>The Transformer-CNN achieved the best overall performance, with a Dice score of 92.3%, IoU of 91.4%, HD95 of 2.25&#xa0;mm, and pixel accuracy of 95.6%. It also excelled in internal cross-validation-based across-center metrics, achieving the highest GDSC (91.3%) and DwIoU (89.2%), the lowest CFDD (1.05%), and the highest ICC (96.5%). DeepLabV3 and U-Net scored 85.1% and 83.0% in Dice, with HD95 values of 4.15&#xa0;mm and 4.30&#xa0;mm, respectively. The worst performance was observed in U-Net, which exhibited high variability across datasets and struggled with small lesion detection.</p> Conclusions <p>The Transformer-CNN outperformed U-Net and DeepLabV3 in segmentation accuracy and across-center performance under internal 5-fold cross-validation. Its robustness, minimal variability, and ability to generalize across diverse datasets establish it as a practical and reliable tool for clinical MS lesion segmentation and monitoring.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A multi-center study of transformer-based CNNs for multiple sclerosis lesion segmentation on 3D FLAIR MRI

  • 期刊论文

  • 发表日期：

    2025年10月14日

查看全文
  • Mohamed J. Saadh,
  • Wajida Ataallah Khidr,
  • Rafid Jihad Albadr,
  • Hardik Doshi,
  • M. M. Rekha,
  • Mayank Kundlas,
  • D. Alex Anand,
  • Aziz Kubaev,
  • Waam Mohammed Taher,
  • Mariem Alwan,
  • Mahmod Jasem Jawad,
  • Ali M. Ali Al-Nuaimi,
  • Bagher Farhood

摘要

Objective

This study aimed to develop and evaluate a Transformer-CNN framework for automated segmentation of multiple sclerosis (MS) lesions on FLAIR MRI. The model was benchmarked against U-Net and DeepLabV3 and assessed for both segmentation accuracy and across-center performance under internal 5-fold cross-validation to ensure robustness across diverse clinical datasets.

Materials and methods

A dataset of 1,800 3D FLAIR MRI scans from five clinical centers was split using 5-fold cross-validation. Preprocessing included isotropic resampling, intensity normalization, and bias field correction. The Transformer-CNN combined CNN-based local feature extraction with Transformer-based global context modeling. Data augmentation strategies, including geometric transformations and noise injection, enhanced generalization. Performance was evaluated using Dice score, IoU, HD95, and pixel accuracy, along with internal cross-validation-based metrics such as Generalized Dice Similarity Coefficient (GDSC), Domain-wise IoU (DwIoU), Cross-Fold Dice Deviation (CFDD), and Volume Agreement (Intraclass Correlation Coefficient, ICC). Statistical significance was tested using Kruskal-Wallis and Dunn’s post-hoc analyses to compare models.

Results

The Transformer-CNN achieved the best overall performance, with a Dice score of 92.3%, IoU of 91.4%, HD95 of 2.25 mm, and pixel accuracy of 95.6%. It also excelled in internal cross-validation-based across-center metrics, achieving the highest GDSC (91.3%) and DwIoU (89.2%), the lowest CFDD (1.05%), and the highest ICC (96.5%). DeepLabV3 and U-Net scored 85.1% and 83.0% in Dice, with HD95 values of 4.15 mm and 4.30 mm, respectively. The worst performance was observed in U-Net, which exhibited high variability across datasets and struggled with small lesion detection.

Conclusions

The Transformer-CNN outperformed U-Net and DeepLabV3 in segmentation accuracy and across-center performance under internal 5-fold cross-validation. Its robustness, minimal variability, and ability to generalize across diverse datasets establish it as a practical and reliable tool for clinical MS lesion segmentation and monitoring.