A Classification-Based Adaptive Segmentation Pipeline: Feasibility Study Using Polycystic Liver Disease and Metastases from Colorectal Cancer CT Images
This addresses the need for more accurate and adaptable segmentation pipelines in clinical settings, though it is incremental as it builds on existing classification and segmentation methods.
The study tackled the problem of automated segmentation tools struggling with accuracy and adaptability across different pathologies by proposing a workflow that routes images to specifically trained segmentation models based on a deep learning classifier. It achieved a statistically significant improvement in total liver segmentation compared to a generic single model, as validated on 700 CT images from patients with polycystic liver disease and liver metastases.
Automated segmentation tools often encounter accuracy and adaptability issues when applied to images of different pathology. The purpose of this study is to explore the feasibility of building a workflow to efficiently route images to specifically trained segmentation models. By implementing a deep learning classifier to automatically classify the images and route them to appropriate segmentation models, we hope that our workflow can segment the images with different pathology accurately. The data we used in this study are 350 CT images from patients affected by polycystic liver disease and 350 CT images from patients presenting with liver metastases from colorectal cancer. All images had the liver manually segmented by trained imaging analysts. Our proposed adaptive segmentation workflow achieved a statistically significant improvement for the task of total liver segmentation compared to the generic single segmentation model (non-parametric Wilcoxon signed rank test, n=100, p-value << 0.001). This approach is applicable in a wide range of scenarios and should prove useful in clinical implementations of segmentation pipelines.