Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy

• URL: http://arxiv.org/abs/2605.12855v1
• Date: Wed, 13 May 2026 01:02:58 GMT
• Title: Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy
• Abstract summary: There are no objectively accurate methods to early detect local tumor regrowth in patients undergoing rectal cancer surveillance.<n>We developed Temporal Rectal Endoscopy Cross-attention (TREX), a longitudinal deep learning approach that combines images acquired at restaging and follow-up to distinguish CR from LR.<n>TREX achieved the highest accuracy in detecting LR with a high sensitivity of 97% $pm$ 6% and a balanced accuracy of 90% $pm$ 3%.
• Score: 4.441994284170737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical trial studies indicate benefit of watch-and-wait (WW) surveillance for patients with rectal cancer showing a complete or near clinical response (CR) directly after treatment (restaging). However, there are no objectively accurate methods to early detect local tumor regrowth (LR) in patients undergoing WW from follow-up exams. Hence, we developed Temporal Rectal Endoscopy Cross-attention (TREX), a longitudinal deep learning approach that combines pairs of images acquired at restaging and follow-up to distinguish CR from LR. TREX uses pretrained Swin Transformers in a siamese setting to extract features from longitudinal images and dual cross-attention to combine the features without spatial co-registration between image pairs. TREX and Swin-based baselines were trained under two settings: (a) detecting LR or CR at the last available follow-up and (b) early detection of LR at 3--6, 6--12, and 12--24 months before clinical confirmation. TREX achieved the highest accuracy in detecting LR with a high sensitivity of 97% $\pm$ 6% and a balanced accuracy of 90% $\pm$ 3%, and outperformed all baselines in early detection at both 3--6 (74% $\pm$ 1%) and 6--12 months (62% $\pm$ 4%) prior to clinical detection. Clinical validation via a surgeon survey showed that TREX matched attending-level overall accuracy (TREX: 86.21% vs.\ Clinicians: 87.84% $\pm$ 1.28%). Finally, we explored TREX's ability to predict treatment response by combining pre-treatment (pre-TNT) and restaging endoscopies, achieving a balanced accuracy of 73% $\pm$ 12%. These results show that longitudinal deep learning analysis of endoscopy may improve surveillance and enable earlier identification of rectal cancer regrowth.

Related papers

• Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials [15.128815032056806]
  Protocol optimization in computed tomography (CT) aims to improve diagnostic image quality while reducing radiation dose.<n>We propose a virtual imaging trial framework with reinforcement learning for efficient CT protocol optimization.
  arXiv  Detail & Related papers  (2026-09-10T15:00:41Z)
• Vision Transformers for Preoperative CT-Based Prediction of Histopathologic Chemotherapy Response Score in High-Grade Serous Ovarian Carcinoma [5.924316400347799]
  We propose a 2.5D multimodal deep learning framework that processes lesion-dense omental slices using a pre-trained Vision Transformer encoder.<n>Our model, integrating imaging and clinical data, achieved a ROC-AUC of 0.95 alongside 95% accuracy and 80% precision on the internal test cohort.<n>These preliminary results demonstrate the feasibility of transformer-based deep learning for preoperative prediction of CRS in HGSOC.
  arXiv  Detail & Related papers  (2026-04-10T10:33:07Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Dual Cross-Attention Siamese Transformer for Rectal Tumor Regrowth Assessment in Watch-and-Wait Endoscopy [1.8302060641103655]
  We developed a Siamese Swin Transformer with Dual Cross-Attention (SSDCA) to combine longitudinal endoscopic images at restaging and follow-up.<n>SSDCA produced the best balanced accuracy (81.76% $pm$ 0.04), sensitivity (90.07% $pm$0.08), and specificity (72.86% $pm$ 0.05)<n> robustness analysis showed stable performance irrespective of artifacts including blood, stool, telangiectasia, and poor image quality.
  arXiv  Detail & Related papers  (2025-12-03T15:34:29Z)
• Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation [64.42236775544579]
  Cone beam computed tomography (CBCT)-guided puncture has become an established approach for diagnosing and treating thoracic tumours.<n>DeepPriorCBCT is a three-stage deep learning framework that achieves diagnostic-grade reconstruction using only one-sixth of the conventional radiation dose.
  arXiv  Detail & Related papers  (2025-11-30T12:45:02Z)
• A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer [54.58205672910646]
  RenalCLIP is a visual-language foundation model for characterization, diagnosis and prognosis of renal mass.<n>It achieved better performance and superior generalizability across 10 core tasks spanning the full clinical workflow of kidney cancer.
  arXiv  Detail & Related papers  (2025-08-22T17:48:19Z)
• Lung Disease Detection with Vision Transformers: A Comparative Study of Machine Learning Methods [0.0]
  This study explores the application of Vision Transformers (ViT), a state-of-the-art architecture in machine learning, to chest X-ray analysis. I present a comparative analysis of two ViT-based approaches: one utilizing full chest X-ray images and another focusing on segmented lung regions.
  arXiv  Detail & Related papers  (2024-11-18T08:40:25Z)
• Improving Breast Cancer Grade Prediction with Multiparametric MRI Created Using Optimized Synthetic Correlated Diffusion Imaging [71.91773485443125]
  Grading plays a vital role in breast cancer treatment planning. The current tumor grading method involves extracting tissue from patients, leading to stress, discomfort, and high medical costs. This paper examines using optimized CDI$s$ to improve breast cancer grade prediction.
  arXiv  Detail & Related papers  (2024-05-13T15:48:26Z)
• Swin transformers are robust to distribution and concept drift in endoscopy-based longitudinal rectal cancer assessment [3.0468533447146244]
  Endoscopic images are used at various stages of rectal cancer treatment to assess response and toxicity from treatments.<n> subjective assessment is highly variable and can underestimate the degree of response in some patients.<n>Advances in deep learning has shown the ability to produce consistent and objective response assessment for endoscopic images.
  arXiv  Detail & Related papers  (2024-05-06T18:01:13Z)
• CoRe: An Automated Pipeline for The Prediction of Liver Resection Complexity from Preoperative CT Scans [53.561797148529664]
  Tumors located in critical positions are known to complexify liver resections. CoRe is an automated medical image processing pipeline for the prediction of postoperative LR complexity.
  arXiv  Detail & Related papers  (2022-10-15T15:29:24Z)
• A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI [70.04389979779195]
  We propose a novel convolutional method for the detection and identification of vertebrae in whole spine MRIs. This involves using a learnt vector field to group detected vertebrae corners together into individual vertebral bodies. We demonstrate the clinical applicability of this method, using it for automated scoliosis detection in both lumbar and whole spine MR scans.
  arXiv  Detail & Related papers  (2020-07-06T09:37:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.