Back to all papers

ConLymphNet: A Generalizable Region-Constrained Deep Learning Architecture for Precise Abdominal Lymph Node Segmentation Across Cancer Types.

July 15, 2026pubmed logopapers

Authors

Gupta P,Saini S,Aggarwal A,Gulati A,Patkar S,Dutta N,Jeswani S,Kakkar L,Bose K,Prakash G,Yadav TD,Kaman L,Irrinki S,Singh H,Khosla D,Shah N,Choudhari A,Goel M,Kapoor R,Gupta R,Dutta U,Arora C

Affiliations (3)

  • Postgraduate Institute of Medical Education and Research, Chandigarh, India.
  • Indian Institute of Technology, New Delhi, India.
  • Tata Memorial Hospital, Mumbai, India.

Abstract

Accurate identification and segmentation of abdominal lymph nodes on computed tomography (CT) is crucial for cancer staging and treatment planning but remains a challenging and time-consuming radiologic task. We developed and validated ConLymphNet, a deep learning-based approach for automated abdominal lymph node segmentation using vertebral landmarks as anatomic reference points to standardize the region of interest. We implemented a novel preprocessing pipeline incorporating vertebral landmark-based region selection followed by a 3D nnUNet segmentation model. The model was trained on 481 contrast-enhanced CT scans from patients with gallbladder cancer (GBC) and validated on external data sets including GBC (n = 54), public lymph node (n = 81), and multicancer data sets (n = 606). Performance was compared with three radiologists of varying experience levels. Interobserver agreement among radiologists and the incremental value of artificial intelligence (AI)-assisted reading were also assessed. To support reproducibility and future research, we also contribute 45 expert-verified lymph node segmentations for cases from public multicancer data sets. ConLymphNet achieved mean Dice coefficients of 0.696 ± 0.179, 0.631 ± 0.187, and 0.639 ± 0.176 and low false-positive rates of 0.78 ± 0.35, 0.81 ± 0.33, 0.93 ± 0.47/volume on internal cross-validation, external GBC, and public lymph node data sets, respectively. Performance varied by lymph node location (<i>P</i> = .0080) and size (<i>P</i> = .0444), with larger nodes yielding better results. The model's detection rate (89.6%) was comparable with experienced residents (89.2%) but with reduced processing time (28.7 ± 12.4s <i>v</i> 165.3 ± 47.8 s). AI assistance improved radiologists' performance significantly, particularly for less experienced readers (detection rate +20.2%, segmentation accuracy +13.0%, <i>P</i> < .001), while reducing false positives by 33.3%. ConLymphNet demonstrates reasonable performance across diverse cancer types and imaging protocols, offering segmentation accuracy comparable with radiologists with substantially faster processing times.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ 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.