Segmentation-based Assessment of Tumor-Vessel Involvement for Surgical Resectability Prediction of Pancreatic Ductal Adenocarcinoma

TL;DR

This paper introduces a deep learning workflow for automatic segmentation and assessment of tumor-vessel involvement in pancreatic cancer, aiding surgical resectability decisions with high accuracy and uncertainty quantification.

Contribution

It presents a novel deep learning-based segmentation method that automates tumor-vessel involvement assessment, incorporating uncertainty estimation to support clinical decision-making.

Findings

High segmentation accuracy with nnU-Net, 3D U-Net, and Probabilistic 3D U-Net.

Automated detection of tumor-vessel contact with sensitivity 0.88 and specificity 0.86.

Uncertainty quantification enhances interpretability of tumor-vessel involvement predictions.

Abstract

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer with limited treatment options. This research proposes a workflow and deep learning-based segmentation models to automatically assess tumor-vessel involvement, a key factor in determining tumor resectability. Correct assessment of resectability is vital to determine treatment options. The proposed workflow involves processing CT scans to segment the tumor and vascular structures, analyzing spatial relationships and the extent of vascular involvement, which follows a similar way of working as expert radiologists in PDAC assessment. Three segmentation architectures (nnU-Net, 3D U-Net, and Probabilistic 3D U-Net) achieve a high accuracy in segmenting veins, arteries, and the tumor. The segmentations enable automated detection of tumor involvement with high accuracy (0.88 sensitivity and 0.86 specificity) and automated computation of the degree of tumor-vessel contact. Additionally, due to significant inter-observer variability in these important structures, we present the uncertainty captured by each of the models to further increase insights into the predicted involvement. This result provides clinicians with a clear indication of tumor-vessel involvement and may be used to facilitate more informed decision-making for surgical interventions. The proposed method offers a valuable tool for improving patient outcomes, personalized treatment strategies and survival rates in pancreatic cancer.