Abstract
Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and experience. Computer-aided design methods are vital for the treatment because they facilitate early diagnosis of intracranial hemorrhage. At this point, deep learning can provide effective outcomes through an automated diagnosis way. However, as different from the known solutions, diagnosis of five different hemorrhage subtypes is a critical problem to be solved.This study focused on deep learning methods and employed cranial computed tomography scans in order to detect intracranial hemorrhage. The diagnosis approach in the study aimed to detect five subtypes of hemorrhage. In detail, EfficientNet-B3 and ResNet-Inception-V2 architectures were used for diagnosis purposes. Eventually, the study also proposed a two-architecture hybrid method for the diagnosis purpose. The obtained findings by the hybrid method were evaluated in terms of a comparative perspective.Results showed that the newly designed hybrid method was quite effective in terms of increasing classification rates of detecting intracranial hemorrhage according to the subtypes. Briefly, an accuracy of 98.5%, which is higher than those of the EfficientNet-B3 and the Inception-ResNet-V2, were obtained thanks to the developed hybrid method.
Highlights
Intracranial hemorrhage is a type of bleeding, which is caused by the rupture of a blood vessel in the brain
Essential imaging methods used in the diagnosis of intracranial hemorrhage are positron emission tomography (PET), cerebral angiography, computed tomographyangiography (CT-A), magnetic resonance imaging (MRI), and magnetic resonance angiography (MRA) (Muir et al, 2006)
Moving from that, the study focused on a dataset of 752.803 head CT scans [an open dataset on Kaggle Kaggle (RSNA Intracranial Hemorrhage Detection, n.d.)] collected by the Radiology Society of North America (RSNA)
Summary
Intracranial hemorrhage is a type of bleeding, which is caused by the rupture of a blood vessel in the brain. Arjun Majumdar et al (2018) classified 4300 scans of 134 cases into six groups, which are respectively no hemorrhage, epidural, subdural, subarachnoid, intraparenchymal, and intraventricular They designed a CNN model of nine blocks with one convolution layer in each block and used maximum pooling (for data reduction) and a 2x2 nearest neighbor augmentation method (after the first four blocks). Phong et al (2017) focused on a dataset of 2000 CT scans (20 scans of each case in 115 hospitals in Vietnam) and developed a system in order to distinguish CT scans as normal or abnormal (presence of intracranial hemorrhage) They used the CNN methods of LeNet, GoogLeNet, and Inception-ResNet-V2 and reached to the accuracy values of 99%, 98%, and 99% respectively. The developed hybrid method was compared with alternative archictures and the results showed that this newly designed method / architecture was more successful than the latest deep neural network architectures
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call