Automatic Detection and Segmentation of Liver Metastatic Lesions
on Serial CT Examinations

 

Overview

Metastatic liver lesions can be derived from different primary cancer types and there is a large variability in their appearance. Computed tomography (CT) is the most common modality used for detection, diagnosis and follow-up of liver lesions. The images are acquired after intravenous injection of a contrast agent. Follow-up (FU) CT examinations are conducted in intervals of a couple of months. The main criterion for evaluation of a therapy is change in tumor size. Tracking lesions over time and measuring diameter length is a time consuming task as the radiologist compares two 3D CT scans which may include multiple metastases.

We present a fully automated method for detection and segmentation of liver metastases on serial CT examinations (portal phase) given a 2D baseline segmentation mask. This method is based on the information given in the baseline CT scan which contains the lesion's segmentation mask marked manually by a radiologist. The 2D baseline segmentation mask is used to identify the lesion location in the follow-up CT scan using non-rigid image registration and template matching. The baseline CT scan is also used to locate regions of tissues surrounding the lesion and to map them onto the follow-up CT scan, in order to reduce the search area on the follow-up CT scan. Adaptive region-growing and mean-shift clustering are used to obtain the lesion segmentation. Finally, the segmentation mask is propagated to 3D for validation purposes.

Publications

Ben Cohen, A., Diamant, I., Klang, E., Amitai, M., & Greenspan, H. (2014, March). Automatic detection and segmentation of liver metastatic lesions on serial CT examinations. In SPIE Medical Imaging (pp. 903519-903519). International Society for Optics and Photonics. (PDF)

  Ben Cohen, A., Klang, E., Diamant, I.,Rozendorn, N., Amitai, M., & Greenspan, H. (2015). Automated method for detection and segmentation of liver metastatic lesions in follow-up CT examinations. Journal of Medical Imaging, 2(3), 034502-034502.

horizontal rule

For problems or questions regarding this web page contact hayit@eng.tau.ac.il.
Last updated: 12/11/15.