AUTHOR=Anderson Brian M. , Rigaud Bastien , Lin Yuan-Mao , Jones A. Kyle , Kang HynSeon Christine , Odisio Bruno C. , Brock Kristy K. 

TITLE=Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.886517

DOI=10.3389/fonc.2022.886517

ISSN=2234-943X

ABSTRACT=Objectives: Colorectal cancer (CRC), the third most common cancer in the USA, is a leading cause of cancer-related death worldwide. Up to 60% of patients develop liver metastasis(CRLM). Treatments like radiation and ablation therapies require disease segmentation for planning and therapy delivery. For ablation, ablation-zone segmentation is required to evaluate disease coverage. 
We hypothesize fully convolutional (FC) neural networks, trained using novel methods, will provide rapid and accurate identification and segmentation of CRLM and ablation-zones.
Methods: Four FC model styles were investigated: Standard-, Residual-, Dense-3D-UNet, and Hybrid-WNet. Models were trained on 92 patients from the Liver Tumor Segmentation(LiTS) challenge. For the evaluation, we acquired 15 patients from the 3D-IRCADb database, 18 patients from our institution(CRLM=24, ablation-zone=19), and submitted to the LiTS challenge(n=70). Qualitative evaluations of our institutional data were performed by two board certified radiologists(interventional, diagnostic), and a radiology-trained physician fellow, using a Likert scale 1-5. 
Results: The most accurate model was the Hybrid-WNet. On a patient-by-patient basis in the 3D-IRCADb dataset, the median(min-max) Dice similarity coefficient(DSC) was 0.73(0.41-0.88), median surface distance was 1.75mm(0.57–7.63mm), and number of false-positives was 1(0-4). In the LiTS challenge(n=70), the global DSC was 0.810.  The model sensitivity was 98%(47/48) for sites ≥15mm in diameter. Qualitatively, 100%(24/24; minority vote) of the CRLM and 84%(16/19; majority vote) of the ablation-zones had Likert scores ≥4. 
Conclusion: The Hybrid-WNet model provided fast(<30 seconds) and accurate segmentations of CRLM and ablation-zones on contrast-enhanced CT scans, with positive physician reviews.