» Articles » PMID: 38587766

A Classification-Based Adaptive Segmentation Pipeline: Feasibility Study Using Polycystic Liver Disease and Metastases from Colorectal Cancer CT Images

Overview
Publisher Springer Nature
Specialty Radiology
Date 2024 Apr 8
PMID 38587766
Authors
Affiliations
Soon will be listed here.
Abstract

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.

References
1.
Dagata I, Jonas M, Perez-Atayde A, Guay-Woodford L . Combined cystic disease of the liver and kidney. Semin Liver Dis. 1994; 14(3):215-28. DOI: 10.1055/s-2007-1007313. View

2.
Weston A, Korfiatis P, Philbrick K, Conte G, Kostandy P, Sakinis T . Complete abdomen and pelvis segmentation using U-net variant architecture. Med Phys. 2020; 47(11):5609-5618. DOI: 10.1002/mp.14422. View

3.
Qian Q, Li A, King B, Kamath P, Lager D, Huston 3rd J . Clinical profile of autosomal dominant polycystic liver disease. Hepatology. 2002; 37(1):164-71. DOI: 10.1053/jhep.2003.50006. View

4.
Graham S, Vu Q, Jahanifar M, Raza S, Minhas F, Snead D . One model is all you need: Multi-task learning enables simultaneous histology image segmentation and classification. Med Image Anal. 2022; 83:102685. DOI: 10.1016/j.media.2022.102685. View

5.
Isensee F, Jaeger P, Kohl S, Petersen J, Maier-Hein K . nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2020; 18(2):203-211. DOI: 10.1038/s41592-020-01008-z. View