Multi-Scale Coarse-to-Fine Segmentation for Screening Pancreatic Ductal Adenocarcinoma
This work addresses a critical medical screening task for radiologists by improving detection accuracy for pancreatic cancer, though it is incremental as it builds on existing segmentation and classification methods.
The paper tackles the problem of detecting pancreatic ductal adenocarcinoma (PDAC) in abdominal CT scans by proposing a multi-scale segmentation-for-classification approach, achieving a sensitivity of 94.1% at a specificity of 98.5% on a new dataset of 439 scans.
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.