A Multicenter Study on Deep Learning Model-Assisted Detection of Brain Metastases in MR Images.
Authors
Affiliations (6)
Affiliations (6)
- Department of Radiology, Affiliated Hospital of Hebei University/School of Clinical Medicine, Baoding, People's Republic China (M.H.).
- Department of Radiology, Affiliated Hospital of Hebei University, Baoding, People's Republic China (L.Z.).
- Affiliated Hospital of Hebei University, Baoding, People's Republic China (Y.Z., Y.X., Y.H., F.Z., L.Y., T.W., C.R., Z.Y., X.L., X.Y.).
- Affiliated Hospital of Hebei University, Baoding, People's Republic China (Y.Z., Y.X., Y.H., F.Z., L.Y., T.W., C.R., Z.Y., X.L., X.Y.); Taizhou Hospital of Zhejiang Province, Taizhou, People's Republic of China (X.L.).
- Department of Radiology, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, People's Republic of China (R.Z.).
- Department of Radiology, Affiliated Hospital of Hebei University, No. 212 Eastern Yuhua Road, Baoding, Hebei 071000, People's Republic China (J.W.). Electronic address: [email protected].
Abstract
This study aimed to develop and validate a deep learning-based brain metastasis detection model (BMDM) in magnetic resonance images for diagnosing brain metastases (BMs). We retrospectively collected data from 950 patients serving as the training and test sets for developing BMDM and from an additional 423 patients as the validation set. Three reading modes were compared: radiologists only (10 total, four with ≤3 years of experience and six with >3 years of experience), BMDM only, and radiologists assisted by the BMDM. The alternative free-response receiver operating characteristic (AFROC) method was used for evaluation. The reading time was reduced by 30.87%, AFROC-area under the curve improved from 0.837 to 0.954, and sensitivity increased from 0.685 to 0.916 with BMDM assistance. The improvement in sensitivity was more pronounced among less experienced radiologists (24.59% vs 22.03%). The detection sensitivity improved by 33.45% for lesions ≤3 mm and by 43.00% for insular lesions. The results demonstrated that BMDM significantly enhanced time efficiency and diagnostic performance for BM detection, providing clinical benefits.