Background

Radiological follow-up of tumors is the cornerstone of modern oncology. About 25% of the 60 million worldwide yearly CT studies are related to oncology, with a higher proportion for brain MRI studies. Currently, radiologists perform the initial diagnosis and subsequent tumor follow-up manually. This evaluation is tedious, time-consuming, and error-prone, as it varies among radiologists and can be can off by up to 50%. These drawbacks hamper the clinical decision-making process and may lead to sub-optimal or inadequate treatment.

Purpose

A new paradigm for automatic radiological follow-up volumetric evaluation based on the tumors baseline delineation to increase accuracy and robustness, reduce radiologist time, and reduce observer variability. Demonstrate the paradigm for brain, lungs, and liver solid tumors.

Methods

We have developed a new robust, accurate, and automatic or nearly automatic delineation and follow-up methods for solid tumors segmentation methods for brain, lungs, and liver solid tumors and for Plexiform Neurofibromas progression evaluation. The method consists of: 1) registration of the baseline tumors to the follow-up scan; 2) follow-up tumors boundary changes detection and correction based on baseline delineation; 3) follow-up tumors segmentation correction, and 4) internal tumors components segmentation (when appropriate).

Results

Our results on more than 200 scans show that our paradigm reduces the volumetric overlap error of follow-up tumors segmentation from 25-35% for standalone segmentation to 10-15%. A software prototype of our system for brain tumors and Plexiform Neurofibromas progression evaluation is being used for clinical research since 2013 at the Tel-Aviv Sourasky Medical Center.  

Participants: L. Weizman, R. Vivanti, D. Helfer, L. Joskowicz CASMIP Lab, Y. Shoshan, J. Sosna, Hadassah. D. Ben Bashat, L. Pratt, L. Ben Sira, B. Shofty, S. Constantini, TA Sourasky Medical Center.

Publication:

Segmentation and follow-up of multi-component low-grade gliomas in longitudinal MRI studies. L. Weizman et al. Medical Physics 41:052303, 2014.

Tumor burden evaluation in NF1 patients with plexiform neurofibromas in the daily clinical practice. L. Pratt et al. Acta Neurochirurgica 157(5):855-861, 2015.

One-page description (pdf) >

3-Picture1 3-Picture2

Computer-based tumors analysis and follow-up in radiological oncology