Scholarlink

Objectives <p>To train and validate segmentation models for automated segmentation of gallbladder cancer (GBC) lesions from contrast-enhanced CT images.</p> Materials and methods <p>This retrospective study comprised consecutive patients with pathologically proven treatment naïve GBC who underwent a contrast-enhanced CT scan at four different tertiary care referral hospitals. The training and validation cohort comprised CT scans of 317 patients (center 1). The internal test cohort comprised a temporally independent cohort (<i>n</i> = 29) from center 1 (internal test 1). The external test cohort comprised CT scans from three centers [ (<i>n</i> = 85)]. We trained the state-of-the-art 2D and 3D image segmentation models, SAM Adapter, MedSAM, 3D TransUNet, SAM-Med3D, and 3D-nnU-Net, for automated segmentation of the GBC. The models’ performance for GBC segmentation on the test datasets was assessed via dice score and intersection over union (IoU) using manual segmentation as the reference standard.</p> Results <p>The 2D models performed better than 3D models. Overall, MedSAM achieved the highest dice and IoU scores on both the internal [mean dice (SD) 0.776 (0.106) and mean IoU 0.653 (0.133)] and external [mean dice (SD) 0.763 (0.098) and mean IoU 0.637 (0.116)] test sets. Among the 3D models, TransUNet showed the best segmentation performance with mean dice (SD) and IoU (SD) of 0.479 (0.268) and 0.356 (0.235) in the internal test and 0.409 (0.339) and 0.317 (0.283) in the external test sets. The segmentation performance was not associated with GBC morphology. There was weak correlation between the dice/IoU and the size of the GBC lesions for any segmentation model.</p> Conclusion <p>We trained 2D and 3D GBC segmentation models on a large dataset and validated these models on external datasets. MedSAM, a 2D prompt-based foundational model, achieved the best segmentation performance.</p> Graphical abstract <p></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

Deep learning-based segmentation of gallbladder cancer on abdominal computed tomography scans: a multicenter study

  • 期刊论文

  • 发表日期：

    2025年4月1日

查看全文
  • Pankaj Gupta,
  • Niharika Dutta,
  • Ajay Tomar,
  • Shravya Singh,
  • Sonam Choudhary,
  • Nandita Mehta,
  • Vansha Mehta,
  • Rishabh Sheth,
  • Divyashree Srivastava,
  • Salai Thanihai,
  • Palki Singla,
  • Gaurav Prakash,
  • Thakur Yadav,
  • Lileswar Kaman,
  • Santosh Irrinki,
  • Harjeet Singh,
  • Niket Shah,
  • Amit Choudhari,
  • Shraddha Patkar,
  • Mahesh Goel,
  • Rajnikant Yadav,
  • Archana Gupta,
  • Ishan Kumar,
  • Kajal Seth,
  • Usha Dutta,
  • Chetan Arora

摘要

Objectives

To train and validate segmentation models for automated segmentation of gallbladder cancer (GBC) lesions from contrast-enhanced CT images.

Materials and methods

This retrospective study comprised consecutive patients with pathologically proven treatment naïve GBC who underwent a contrast-enhanced CT scan at four different tertiary care referral hospitals. The training and validation cohort comprised CT scans of 317 patients (center 1). The internal test cohort comprised a temporally independent cohort (n = 29) from center 1 (internal test 1). The external test cohort comprised CT scans from three centers [ (n = 85)]. We trained the state-of-the-art 2D and 3D image segmentation models, SAM Adapter, MedSAM, 3D TransUNet, SAM-Med3D, and 3D-nnU-Net, for automated segmentation of the GBC. The models’ performance for GBC segmentation on the test datasets was assessed via dice score and intersection over union (IoU) using manual segmentation as the reference standard.

Results

The 2D models performed better than 3D models. Overall, MedSAM achieved the highest dice and IoU scores on both the internal [mean dice (SD) 0.776 (0.106) and mean IoU 0.653 (0.133)] and external [mean dice (SD) 0.763 (0.098) and mean IoU 0.637 (0.116)] test sets. Among the 3D models, TransUNet showed the best segmentation performance with mean dice (SD) and IoU (SD) of 0.479 (0.268) and 0.356 (0.235) in the internal test and 0.409 (0.339) and 0.317 (0.283) in the external test sets. The segmentation performance was not associated with GBC morphology. There was weak correlation between the dice/IoU and the size of the GBC lesions for any segmentation model.

Conclusion

We trained 2D and 3D GBC segmentation models on a large dataset and validated these models on external datasets. MedSAM, a 2D prompt-based foundational model, achieved the best segmentation performance.

Graphical abstract