Scholarlink

Purpose <p>Accurate interpretation of CT scans after pancreatic resection is crucial for detecting abnormalities, including postoperative complications and cancer recurrence. This study investigates the feasibility and clinical utility of a novel MKNet-family deep learning architecture for auto-segmentation of the residual pancreas on postoperative CT imaging, in comparison to previous approaches.</p> Method <p>Novel MKNet, MSKNet and MAKNet architectures were developed. Two datasets were used: the National Institutes of Health (NIH) dataset, comprising 82 annotated normal preoperative CT scans, and the IMPACT Consortium dataset (NCT06055010; <a href="https://github.com/IMPACTconsortium/IMPACT">https://github.com/IMPACTconsortium/IMPACT</a>), comprising 81 annotated postoperative CT scans obtained &lt; 4 weeks after pancreatectomy. Performance was assessed by Hausdorff Distance (HD), 95th-percentile-HD (HD95) and Normalized Surface Distance (NSD), and secondarily by Dice Similarity Coefficient (DSC), and compared with self-implemented existing models for preoperative pancreas auto-segmentation. Qualitative evaluation was conducted by ten abdominal radiologists.</p> Results <p>In the postoperative setting, the MAKNet architecture showed the best performance, with an HD and HD95 of 17.3 ± 11.2&#xa0;mm and 11.5 ± 10.2&#xa0;mm, respectively. DSC (64.9 ± 14.8%) and NSD (27.2 ± 8.2%) were comparable to the Attention-U-Net (DSC 66.0 ± 13.8%; NSD 27.8 ± 8.4%). Clinical evaluation indicated that the MKNet-family accurately defined the postoperative pancreas (i.e., requiring minimal or no modifications) in 64 of 81 segmentations (79%).</p> Conclusion <p>This study demonstrates the effectiveness of novel MKNet-family architectures to accurately segment the residual pancreas on postoperative CT imaging over previous approaches. This advances the state-of-the-art in pancreas auto-segmentation and may be beneficial for medical application and education, acceleration of data annotation, and future research.</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

MKNet-family architectures for auto-segmentation of the residual pancreas after pancreatic resection: a deep learning comparative study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月27日

查看全文
  • Dennis Böhm,
  • Paul C. M. Andel,
  • Paul A. Akkermans,
  • Bas Boekestijn,
  • Willem van der Geest,
  • Robbert J. de Haas,
  • Jakob W. Kist,
  • I. Quintus Molenaar,
  • Joost Nederend,
  • C. Yung Nio,
  • Bobby K. Pranger,
  • Hjalmar C. van Santvoort,
  • Femke Struik,
  • Inez M. Verpalen,
  • Frank J. Wessels,
  • Wouter B. Veldhuis,
  • Helena M. Verkooijen,
  • François E. J. A. Willemssen,
  • Ralf I. Zoetekouw,
  • Jouke Dijkstra,
  • Martijn P. W. Intven,
  • Michael Weinmann,
  • Lois A. Daamen

摘要

Purpose

Accurate interpretation of CT scans after pancreatic resection is crucial for detecting abnormalities, including postoperative complications and cancer recurrence. This study investigates the feasibility and clinical utility of a novel MKNet-family deep learning architecture for auto-segmentation of the residual pancreas on postoperative CT imaging, in comparison to previous approaches.

Method

Novel MKNet, MSKNet and MAKNet architectures were developed. Two datasets were used: the National Institutes of Health (NIH) dataset, comprising 82 annotated normal preoperative CT scans, and the IMPACT Consortium dataset (NCT06055010; https://github.com/IMPACTconsortium/IMPACT), comprising 81 annotated postoperative CT scans obtained < 4 weeks after pancreatectomy. Performance was assessed by Hausdorff Distance (HD), 95th-percentile-HD (HD95) and Normalized Surface Distance (NSD), and secondarily by Dice Similarity Coefficient (DSC), and compared with self-implemented existing models for preoperative pancreas auto-segmentation. Qualitative evaluation was conducted by ten abdominal radiologists.

Results

In the postoperative setting, the MAKNet architecture showed the best performance, with an HD and HD95 of 17.3 ± 11.2 mm and 11.5 ± 10.2 mm, respectively. DSC (64.9 ± 14.8%) and NSD (27.2 ± 8.2%) were comparable to the Attention-U-Net (DSC 66.0 ± 13.8%; NSD 27.8 ± 8.4%). Clinical evaluation indicated that the MKNet-family accurately defined the postoperative pancreas (i.e., requiring minimal or no modifications) in 64 of 81 segmentations (79%).

Conclusion

This study demonstrates the effectiveness of novel MKNet-family architectures to accurately segment the residual pancreas on postoperative CT imaging over previous approaches. This advances the state-of-the-art in pancreas auto-segmentation and may be beneficial for medical application and education, acceleration of data annotation, and future research.