TY - JOUR
T1 - Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images
AU - Anderson, Brian M.
AU - Rigaud, Bastien
AU - Lin, Yuan Mao
AU - Jones, A. Kyle
AU - Kang, Hyn Seon Christine
AU - Odisio, Bruno C.
AU - Brock, Kristy K.
N1 - Funding Information:
Funding from the Society of Interventional Radiology Foundation Allied Scientist Grant, NIH (NCI R01CA221971, NCI R01CA235564), and the Helen Black Image Guided Fund.
Publisher Copyright:
Copyright © 2022 Anderson, Rigaud, Lin, Jones, Kang, Odisio and Brock.
PY - 2022/8/11
Y1 - 2022/8/11
N2 - 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 that 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 3D-UNet, Residual 3D-UNet, 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 those submitted to the LiTS challenge (n = 70). Qualitative evaluations of our institutional data were performed by two board-certified radiologists (interventional and diagnostic) and a radiology-trained physician fellow, using a Likert scale of 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), the median surface distance was 1.75 mm (0.57–7.63 mm), and the 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 ≥15 mm 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 s) and accurate segmentations of CRLM and ablation zones on contrast-enhanced CT scans, with positive physician reviews.
AB - 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 that 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 3D-UNet, Residual 3D-UNet, 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 those submitted to the LiTS challenge (n = 70). Qualitative evaluations of our institutional data were performed by two board-certified radiologists (interventional and diagnostic) and a radiology-trained physician fellow, using a Likert scale of 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), the median surface distance was 1.75 mm (0.57–7.63 mm), and the 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 ≥15 mm 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 s) and accurate segmentations of CRLM and ablation zones on contrast-enhanced CT scans, with positive physician reviews.
KW - biomechanical modeling
KW - computed tomography
KW - deep-learning
KW - liver cancer
KW - percutaneous ablation
UR - http://www.scopus.com/inward/record.url?scp=85137005241&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137005241&partnerID=8YFLogxK
U2 - 10.3389/fonc.2022.886517
DO - 10.3389/fonc.2022.886517
M3 - Article
C2 - 36033508
AN - SCOPUS:85137005241
SN - 2234-943X
VL - 12
JO - Frontiers in Oncology
JF - Frontiers in Oncology
M1 - 886517
ER -