Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images
ObjectivesColorectal 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. Fo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.886517/full |
| _version_ | 1811216719300001792 |
|---|---|
| author | Brian M. Anderson Brian M. Anderson Bastien Rigaud Yuan-Mao Lin A. Kyle Jones HynSeon Christine Kang Bruno C. Odisio Kristy K. Brock |
| author_facet | Brian M. Anderson Brian M. Anderson Bastien Rigaud Yuan-Mao Lin A. Kyle Jones HynSeon Christine Kang Bruno C. Odisio Kristy K. Brock |
| author_sort | Brian M. Anderson |
| collection | DOAJ |
| description | ObjectivesColorectal 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.MethodsFour 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.ResultsThe 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.ConclusionThe Hybrid-WNet model provided fast (<30 s) and accurate segmentations of CRLM and ablation zones on contrast-enhanced CT scans, with positive physician reviews. |
| first_indexed | 2024-04-12T06:43:25Z |
| format | Article |
| id | doaj.art-1eac90c390ab4389a8443032d95ae862 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-12T06:43:25Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-1eac90c390ab4389a8443032d95ae8622022-12-22T03:43:38ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-08-011210.3389/fonc.2022.886517886517Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT imagesBrian M. Anderson0Brian M. Anderson1Bastien Rigaud2Yuan-Mao Lin3A. Kyle Jones4HynSeon Christine Kang5Bruno C. Odisio6Kristy K. Brock7Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesUTHealth Graduate School of Biomedical Sciences, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Interventional Radiology, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Abdominal Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Interventional Radiology, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesDepartment of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, United StatesObjectivesColorectal 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.MethodsFour 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.ResultsThe 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.ConclusionThe Hybrid-WNet model provided fast (<30 s) and accurate segmentations of CRLM and ablation zones on contrast-enhanced CT scans, with positive physician reviews.https://www.frontiersin.org/articles/10.3389/fonc.2022.886517/fulldeep-learningliver cancerpercutaneous ablationcomputed tomographybiomechanical modeling |
| spellingShingle | Brian M. Anderson Brian M. Anderson Bastien Rigaud Yuan-Mao Lin A. Kyle Jones HynSeon Christine Kang Bruno C. Odisio Kristy K. Brock Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images Frontiers in Oncology deep-learning liver cancer percutaneous ablation computed tomography biomechanical modeling |
| title | Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images |
| title_full | Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images |
| title_fullStr | Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images |
| title_full_unstemmed | Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images |
| title_short | Automated segmentation of colorectal liver metastasis and liver ablation on contrast-enhanced CT images |
| title_sort | automated segmentation of colorectal liver metastasis and liver ablation on contrast enhanced ct images |
| topic | deep-learning liver cancer percutaneous ablation computed tomography biomechanical modeling |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.886517/full |
| work_keys_str_mv | AT brianmanderson automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT brianmanderson automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT bastienrigaud automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT yuanmaolin automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT akylejones automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT hynseonchristinekang automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT brunocodisio automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages AT kristykbrock automatedsegmentationofcolorectallivermetastasisandliverablationoncontrastenhancedctimages |