Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinoma

TL;DR

This paper introduces a multi-scale coarse-to-fine segmentation approach for detecting pancreatic ductal adenocarcinoma in CT scans, providing accurate tumor localization and high diagnostic performance, which could aid clinical diagnosis.

Contribution

The study presents a novel multi-scale segmentation-for-classification framework and a large PDAC dataset, improving detection accuracy and robustness over existing methods.

Findings

Achieved 94.1% sensitivity at 98.5% specificity.

Developed the largest PDAC CT scan dataset to date.

Demonstrated clinical potential of the method.

Abstract

We propose an intuitive approach of detecting pancreatic ductal adenocarcinoma (PDAC), the most common type of pancreatic cancer, by checking abdominal CT scans. Our idea is named multi-scale segmentation-for-classification, which classifies volumes by checking if at least a sufficient number of voxels is segmented as tumors, by which we can provide radiologists with tumor locations. In order to deal with tumors with different scales, we train and test our volumetric segmentation networks with multi-scale inputs in a coarse-to-fine flowchart. A post-processing module is used to filter out outliers and reduce false alarms. We collect a new dataset containing 439 CT scans, in which 136 cases were diagnosed with PDAC and 303 cases are normal, which is the largest set for PDAC tumors to the best of our knowledge. To offer the best trade-off between sensitivity and specificity, our proposed framework reports a sensitivity of 94.1% at a specificity of 98.5%, which demonstrates the potential to make a clinical impact.