Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study
Abstract Objectives To assess whether a deep learning-based system (DLS) with black-blood imaging for brain metastasis (BM) improves the diagnostic workflow in a multi-center setting. Materials and methods In this retrospective study, a DLS was developed in 101 patients and validated on 264 consecut...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | Cancer Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40644-024-00669-9 |
| _version_ | 1797209088310902784 |
|---|---|
| author | Yae Won Park Ji Eun Park Sung Soo Ahn Kyunghwa Han NakYoung Kim Joo Young Oh Da Hyun Lee So Yeon Won Ilah Shin Ho Sung Kim Seung-Koo Lee |
| author_facet | Yae Won Park Ji Eun Park Sung Soo Ahn Kyunghwa Han NakYoung Kim Joo Young Oh Da Hyun Lee So Yeon Won Ilah Shin Ho Sung Kim Seung-Koo Lee |
| author_sort | Yae Won Park |
| collection | DOAJ |
| description | Abstract Objectives To assess whether a deep learning-based system (DLS) with black-blood imaging for brain metastasis (BM) improves the diagnostic workflow in a multi-center setting. Materials and methods In this retrospective study, a DLS was developed in 101 patients and validated on 264 consecutive patients (with lung cancer) having newly developed BM from two tertiary university hospitals, which performed black-blood imaging between January 2020 and April 2021. Four neuroradiologists independently evaluated BM either with segmented masks and BM counts provided (with DLS) or not provided (without DLS) on a clinical trial imaging management system (CTIMS). To assess reading reproducibility, BM count agreement between the readers and the reference standard were calculated using limits of agreement (LoA). Readers’ workload was assessed with reading time, which was automatically measured on CTIMS, and were compared between with and without DLS using linear mixed models considering the imaging center. Results In the validation cohort, the detection sensitivity and positive predictive value of the DLS were 90.2% (95% confidence interval [CI]: 88.1–92.2) and 88.2% (95% CI: 85.7–90.4), respectively. The difference between the readers and the reference counts was larger without DLS (LoA: −0.281, 95% CI: −2.888, 2.325) than with DLS (LoA: −0.163, 95% CI: −2.692, 2.367). The reading time was reduced from mean 66.9 s (interquartile range: 43.2–90.6) to 57.3 s (interquartile range: 33.6–81.0) (P <.001) in the with DLS group, regardless of the imaging center. Conclusion Deep learning-based BM detection and counting with black-blood imaging improved reproducibility and reduced reading time, on multi-center validation. |
| first_indexed | 2024-03-07T14:43:59Z |
| format | Article |
| id | doaj.art-be5e7fa958e441e88ced44911cdc2103 |
| institution | Directory Open Access Journal |
| issn | 1470-7330 |
| language | English |
| last_indexed | 2024-04-24T09:49:08Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Imaging |
| spelling | doaj.art-be5e7fa958e441e88ced44911cdc21032024-04-14T11:27:54ZengBMCCancer Imaging1470-73302024-03-0124111010.1186/s40644-024-00669-9Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center studyYae Won Park0Ji Eun Park1Sung Soo Ahn2Kyunghwa Han3NakYoung Kim4Joo Young Oh5Da Hyun Lee6So Yeon Won7Ilah Shin8Ho Sung Kim9Seung-Koo Lee10Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of MedicineDepartment of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical CenterDepartment of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of MedicineDepartment of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of MedicineDynapex, LLCDepartment of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical CenterDepartment of Radiology, Ajou University Medical CenterDepartment of Radiology, Samsung Seoul HospitalDepartment of Radiology, The Catholic University of Korea, Seoul St. Mary‘s hospitalDepartment of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical CenterDepartment of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of MedicineAbstract Objectives To assess whether a deep learning-based system (DLS) with black-blood imaging for brain metastasis (BM) improves the diagnostic workflow in a multi-center setting. Materials and methods In this retrospective study, a DLS was developed in 101 patients and validated on 264 consecutive patients (with lung cancer) having newly developed BM from two tertiary university hospitals, which performed black-blood imaging between January 2020 and April 2021. Four neuroradiologists independently evaluated BM either with segmented masks and BM counts provided (with DLS) or not provided (without DLS) on a clinical trial imaging management system (CTIMS). To assess reading reproducibility, BM count agreement between the readers and the reference standard were calculated using limits of agreement (LoA). Readers’ workload was assessed with reading time, which was automatically measured on CTIMS, and were compared between with and without DLS using linear mixed models considering the imaging center. Results In the validation cohort, the detection sensitivity and positive predictive value of the DLS were 90.2% (95% confidence interval [CI]: 88.1–92.2) and 88.2% (95% CI: 85.7–90.4), respectively. The difference between the readers and the reference counts was larger without DLS (LoA: −0.281, 95% CI: −2.888, 2.325) than with DLS (LoA: −0.163, 95% CI: −2.692, 2.367). The reading time was reduced from mean 66.9 s (interquartile range: 43.2–90.6) to 57.3 s (interquartile range: 33.6–81.0) (P <.001) in the with DLS group, regardless of the imaging center. Conclusion Deep learning-based BM detection and counting with black-blood imaging improved reproducibility and reduced reading time, on multi-center validation.https://doi.org/10.1186/s40644-024-00669-9Brain metastasesBrain tumorsDeep learningMagnetic resonance imaging |
| spellingShingle | Yae Won Park Ji Eun Park Sung Soo Ahn Kyunghwa Han NakYoung Kim Joo Young Oh Da Hyun Lee So Yeon Won Ilah Shin Ho Sung Kim Seung-Koo Lee Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study Cancer Imaging Brain metastases Brain tumors Deep learning Magnetic resonance imaging |
| title | Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study |
| title_full | Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study |
| title_fullStr | Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study |
| title_full_unstemmed | Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study |
| title_short | Deep learning-based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with MRI: a multi-center study |
| title_sort | deep learning based metastasis detection in patients with lung cancer to enhance reproducibility and reduce workload in brain metastasis screening with mri a multi center study |
| topic | Brain metastases Brain tumors Deep learning Magnetic resonance imaging |
| url | https://doi.org/10.1186/s40644-024-00669-9 |
| work_keys_str_mv | AT yaewonpark deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT jieunpark deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT sungsooahn deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT kyunghwahan deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT nakyoungkim deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT jooyoungoh deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT dahyunlee deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT soyeonwon deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT ilahshin deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT hosungkim deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy AT seungkoolee deeplearningbasedmetastasisdetectioninpatientswithlungcancertoenhancereproducibilityandreduceworkloadinbrainmetastasisscreeningwithmriamulticenterstudy |