Extremely imbalanced Subarachnoid Hemorrhage detection based on DenseNet-LSTM network with Class-Balanced Loss and Transfer Learning

摘要

Subarachnoid Hemorrhage (SAH) is an acute, severe, high incidence disease which confused clinicians for a long time. With the rise of deep learning technologies, SAH detection made a significant breakthrough in recent ten years. Whereas, the performances of CNN recognition are significantly degraded on imbalanced data, makes deep learning models have always suffered criticism. In this study, we present a DenseNet-LSTM network with Class-Balanced Loss and the transfer learning strategy to solve the SAH detection problem on an extremely imbalanced dataset. Compared to the previous works, the proposed framework not only effectively integrate grayscale features and the spatial information from the consecutive CT scans, but also employ Class-Balanced loss and transfer learning to alleviate the adverse effects and broaden feature diversity respectively on an extreme SAH cases scarcity dataset, mimicking the actual situation of emergency departments. On one hand, we employed DcnscNet-121 to extract grayscale features from individual CT scan. On the other hand, we ordered the extracted individual grayscale features based on their CT scan sequences and imported them into LSTM for learning the spatial relationship information. Besides, we utilized CB-loss to handle the imbalanced data issue. Comprehensive experiments are conducted on a dataset, consisted of 2,519 cases without hemorrhage cases and only 33 cases with SAH. Experimental results demonstrated the F-mcasurc score of SAH detection achieved a remarkable improvement, the backbone DenseNet121 gained around 33% promotion after transfer learning, and on this basis, importing the Class-Balanced Loss and the LSTM structure, the F-measure score further increased 6.1% and 2.7% sequentially.