Back to all papers

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

November 27, 2025pubmed logopapers

Authors

Böhm D,Andel PCM,Akkermans PA,Boekestijn B,van der Geest W,de Haas RJ,Kist JW,Molenaar IQ,Nederend J,Nio CY,Pranger BK,van Santvoort HC,Struik F,Verpalen IM,Wessels FJ,Veldhuis WB,Verkooijen HM,Willemssen FEJA,Zoetekouw RI,Dijkstra J,Intven MPW,Weinmann M,Daamen LA

Affiliations (14)

  • Datacation B.V., Eindhoven, The Netherlands.
  • Delft University of Technology, TU Delft, The Netherlands.
  • Regional Academic Cancer Center Utrecht, UMC Utrecht Cancer Center & St. Antonius Hospital Nieuwegein, Department of Surgery, Utrecht, The Netherlands.
  • Medical Spectrum Twente, Department of Radiology, Enschede, The Netherlands.
  • Leiden University Medical Center, Department of Radiology, Leiden, The Netherlands.
  • University Medical Center Groningen, Department of Radiology, Groningen, The Netherlands.
  • Amsterdam UMC, location University of Amsterdam, Department of Radiology, Amsterdam, The Netherlands.
  • Catharina Hospital Eindhoven, Department of Radiology, Eindhoven, The Netherlands.
  • UMC Utrecht Cancer Center, Department of Radiology, Utrecht, The Netherlands.
  • University Medical Center Utrecht, Division of Imaging and Oncology, Rotterdam, The Netherlands.
  • Erasmus MC, University Medical Centre Rotterdam, Department of Radiology and Nuclear Medicine, Delft, The Netherlands.
  • UMC Utrecht Cancer Center, Department of Radiation Oncology, Utrecht, The Netherlands.
  • Regional Academic Cancer Center Utrecht, UMC Utrecht Cancer Center & St. Antonius Hospital Nieuwegein, Department of Surgery, Utrecht, The Netherlands. [email protected].
  • University Medical Center Utrecht, Division of Imaging and Oncology, Rotterdam, The Netherlands. [email protected].

Abstract

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. 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. 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%). 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.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.