Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI
BackgroundAlthough accurate treatment response assessment for brain metastases (BMs) is crucial, it is highly labor intensive. This retrospective study aimed to develop a computer-aided detection (CAD) system for automated BM detection and treatment response evaluation using deep learning.MethodsWe...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-10-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2021.739639/full |
| _version_ | 1818894113236320256 |
|---|---|
| author | Jungheum Cho Young Jae Kim Leonard Sunwoo Leonard Sunwoo Gi Pyo Lee Toan Quang Nguyen Se Jin Cho Sung Hyun Baik Yun Jung Bae Byung Se Choi Cheolkyu Jung Chul-Ho Sohn Jung-Ho Han Chae-Yong Kim Kwang Gi Kim Jae Hyoung Kim |
| author_facet | Jungheum Cho Young Jae Kim Leonard Sunwoo Leonard Sunwoo Gi Pyo Lee Toan Quang Nguyen Se Jin Cho Sung Hyun Baik Yun Jung Bae Byung Se Choi Cheolkyu Jung Chul-Ho Sohn Jung-Ho Han Chae-Yong Kim Kwang Gi Kim Jae Hyoung Kim |
| author_sort | Jungheum Cho |
| collection | DOAJ |
| description | BackgroundAlthough accurate treatment response assessment for brain metastases (BMs) is crucial, it is highly labor intensive. This retrospective study aimed to develop a computer-aided detection (CAD) system for automated BM detection and treatment response evaluation using deep learning.MethodsWe included 214 consecutive MRI examinations of 147 patients with BM obtained between January 2015 and August 2016. These were divided into the training (174 MR images from 127 patients) and test datasets according to temporal separation (temporal test set #1; 40 MR images from 20 patients). For external validation, 24 patients with BM and 11 patients without BM from other institutions were included (geographic test set). In addition, we included 12 MRIs from BM patients obtained between August 2017 and March 2020 (temporal test set #2). Detection sensitivity, dice similarity coefficient (DSC) for segmentation, and agreements in one-dimensional and volumetric Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria between CAD and radiologists were assessed.ResultsIn the temporal test set #1, the sensitivity was 75.1% (95% confidence interval [CI]: 69.6%, 79.9%), mean DSC was 0.69 ± 0.22, and false-positive (FP) rate per scan was 0.8 for BM ≥ 5 mm. Agreements in the RANO-BM criteria were moderate (κ, 0.52) and substantial (κ, 0.68) for one-dimensional and volumetric, respectively. In the geographic test set, sensitivity was 87.7% (95% CI: 77.2%, 94.5%), mean DSC was 0.68 ± 0.20, and FP rate per scan was 1.9 for BM ≥ 5 mm. In the temporal test set #2, sensitivity was 94.7% (95% CI: 74.0%, 99.9%), mean DSC was 0.82 ± 0.20, and FP per scan was 0.5 (6/12) for BM ≥ 5 mm.ConclusionsOur CAD showed potential for automated treatment response assessment of BM ≥ 5 mm. |
| first_indexed | 2024-12-19T18:23:20Z |
| format | Article |
| id | doaj.art-b85137459aba47fca032ca470b8aeddb |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-19T18:23:20Z |
| publishDate | 2021-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-b85137459aba47fca032ca470b8aeddb2022-12-21T20:10:54ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-10-011110.3389/fonc.2021.739639739639Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRIJungheum Cho0Young Jae Kim1Leonard Sunwoo2Leonard Sunwoo3Gi Pyo Lee4Toan Quang Nguyen5Se Jin Cho6Sung Hyun Baik7Yun Jung Bae8Byung Se Choi9Cheolkyu Jung10Chul-Ho Sohn11Jung-Ho Han12Chae-Yong Kim13Kwang Gi Kim14Jae Hyoung Kim15Department of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Biomedical Engineering, Gachon University Gil Medical Center, Incheon, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaCenter for Artificial Intelligence in Healthcare, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Biomedical Engineering, Gachon University Gil Medical Center, Incheon, South KoreaDepartment of Radiology, Vietnam National Cancer Hospital, Hanoi, VietnamDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Radiology, Seoul National University Hospital, Seoul, South KoreaDepartment of Neurosurgery, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Neurosurgery, Seoul National University Bundang Hospital, Seongnam, South KoreaDepartment of Biomedical Engineering, Gachon University Gil Medical Center, Incheon, South KoreaDepartment of Radiology, Seoul National University Bundang Hospital, Seongnam, South KoreaBackgroundAlthough accurate treatment response assessment for brain metastases (BMs) is crucial, it is highly labor intensive. This retrospective study aimed to develop a computer-aided detection (CAD) system for automated BM detection and treatment response evaluation using deep learning.MethodsWe included 214 consecutive MRI examinations of 147 patients with BM obtained between January 2015 and August 2016. These were divided into the training (174 MR images from 127 patients) and test datasets according to temporal separation (temporal test set #1; 40 MR images from 20 patients). For external validation, 24 patients with BM and 11 patients without BM from other institutions were included (geographic test set). In addition, we included 12 MRIs from BM patients obtained between August 2017 and March 2020 (temporal test set #2). Detection sensitivity, dice similarity coefficient (DSC) for segmentation, and agreements in one-dimensional and volumetric Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria between CAD and radiologists were assessed.ResultsIn the temporal test set #1, the sensitivity was 75.1% (95% confidence interval [CI]: 69.6%, 79.9%), mean DSC was 0.69 ± 0.22, and false-positive (FP) rate per scan was 0.8 for BM ≥ 5 mm. Agreements in the RANO-BM criteria were moderate (κ, 0.52) and substantial (κ, 0.68) for one-dimensional and volumetric, respectively. In the geographic test set, sensitivity was 87.7% (95% CI: 77.2%, 94.5%), mean DSC was 0.68 ± 0.20, and FP rate per scan was 1.9 for BM ≥ 5 mm. In the temporal test set #2, sensitivity was 94.7% (95% CI: 74.0%, 99.9%), mean DSC was 0.82 ± 0.20, and FP per scan was 0.5 (6/12) for BM ≥ 5 mm.ConclusionsOur CAD showed potential for automated treatment response assessment of BM ≥ 5 mm.https://www.frontiersin.org/articles/10.3389/fonc.2021.739639/fullbrain metastasiscomputer-aided detectionmachine learningdeep learningResponse Assessment in Neuro-Oncology Brain Metastases (RANO-BM) |
| spellingShingle | Jungheum Cho Young Jae Kim Leonard Sunwoo Leonard Sunwoo Gi Pyo Lee Toan Quang Nguyen Se Jin Cho Sung Hyun Baik Yun Jung Bae Byung Se Choi Cheolkyu Jung Chul-Ho Sohn Jung-Ho Han Chae-Yong Kim Kwang Gi Kim Jae Hyoung Kim Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI Frontiers in Oncology brain metastasis computer-aided detection machine learning deep learning Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) |
| title | Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI |
| title_full | Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI |
| title_fullStr | Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI |
| title_full_unstemmed | Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI |
| title_short | Deep Learning-Based Computer-Aided Detection System for Automated Treatment Response Assessment of Brain Metastases on 3D MRI |
| title_sort | deep learning based computer aided detection system for automated treatment response assessment of brain metastases on 3d mri |
| topic | brain metastasis computer-aided detection machine learning deep learning Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2021.739639/full |
| work_keys_str_mv | AT jungheumcho deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT youngjaekim deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT leonardsunwoo deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT leonardsunwoo deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT gipyolee deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT toanquangnguyen deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT sejincho deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT sunghyunbaik deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT yunjungbae deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT byungsechoi deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT cheolkyujung deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT chulhosohn deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT junghohan deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT chaeyongkim deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT kwanggikim deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri AT jaehyoungkim deeplearningbasedcomputeraideddetectionsystemforautomatedtreatmentresponseassessmentofbrainmetastaseson3dmri |