Guardado en:
Detalles Bibliográficos
Autores principales: Gomez, Jorge Tapias, Kanata, Despoina, Rangnekar, Aneesh, Lee, Christina, Williams, Hannah, Thompson, Hannah, Smith, J. Joshua, Sanchez-Vega, Francisco, Sabuncu, Mert R., Garcia-Aguilar, Julio, Veeraraghavan, Harini
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.12855
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914561491206144
author Gomez, Jorge Tapias
Kanata, Despoina
Rangnekar, Aneesh
Lee, Christina
Williams, Hannah
Thompson, Hannah
Smith, J. Joshua
Sanchez-Vega, Francisco
Sabuncu, Mert R.
Garcia-Aguilar, Julio
Veeraraghavan, Harini
author_facet Gomez, Jorge Tapias
Kanata, Despoina
Rangnekar, Aneesh
Lee, Christina
Williams, Hannah
Thompson, Hannah
Smith, J. Joshua
Sanchez-Vega, Francisco
Sabuncu, Mert R.
Garcia-Aguilar, Julio
Veeraraghavan, Harini
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12855
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy
Gomez, Jorge Tapias
Kanata, Despoina
Rangnekar, Aneesh
Lee, Christina
Williams, Hannah
Thompson, Hannah
Smith, J. Joshua
Sanchez-Vega, Francisco
Sabuncu, Mert R.
Garcia-Aguilar, Julio
Veeraraghavan, Harini
Computer Vision and Pattern Recognition
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.
title Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12855