Multi-representational deep transfer learning for classifying hemorrhagic metastases and non-neoplastic intracranial hematomas in multi-modal brain MRI scans.
Authors
Affiliations (6)
Affiliations (6)
- School of Information Science and Engineering, Shandong University, Qingdao 266237, China; Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, China; Aeronautical, Automotive, Chemical and Materials Engineering, Loughborough University, Leicester LE11 3TU, UK.
- Department of Radiology, Qilu Hospital of Shandong University, Jinan 250012, China; Department of Radiology, Weihai Central Hospital Affiliated to Qingdao University, Weihai 264400, China.
- School of Information Science and Engineering, Shandong University, Qingdao 266237, China; Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, China.
- Department of Radiology, Qilu Hospital of Shandong University, Jinan 250012, China; Department of Radiology, Weihai Central Hospital Affiliated to Qingdao University, Weihai 264400, China. Electronic address: [email protected].
- School of Information Science and Engineering, Shandong University, Qingdao 266237, China; Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, China. Electronic address: [email protected].
- School of Information Science and Engineering, Shandong University, Qingdao 266237, China; Institute of Brain and Brain-Inspired Science, Shandong University, Jinan 250012, China. Electronic address: [email protected].
Abstract
With an increasing incidence of malignant tumors, occurrence of brain metastases (BMs) has increased. BM represents the most common adult malignant brain tumors. BM is associated with hemorrhages, cystic necrosis, and calcification, which leads to significant diagnostic challenges when differentiating between hemorrhagic brain metastasis (HBM) and non-neoplastic intracranial hematomas (nn-ICH). This study addressed the limitations of small sample sizes, limited imaging features, and underutilized machine learning techniques reported in previous radiomic studies and introduced a novel multi-representation deep transfer learning (MRDTL) framework. Compared to existing radiomics feature analysis methods, MRDTL utilizes multi-modal MRI scans with two substantial merits: (1) A multi-representation fusion (MRF) module which extracted typical feature combinations by explicitly learning the complementarities between multi-modal sequences and multiple representations; (2) a neighborhood embedding (NE) module that measured metrics and clustering on cross-centric data to enhance transferable representations and improve model generalization. On the self-constructed HBMRI dataset, MRDTL outperformed five other baseline methods in AUC, F1-score, and accuracy. It improved accuracy to 94.5% and 93.5% in Co-site and Separate site testing, respectively, and overall provided more reliable diagnostic insights.