Abstract
For the segmentation task of stroke lesions, using the attention U-Net model based on the self-attention mechanism can suppress irrelevant regions in an input image while highlighting salient features useful for specific tasks. However, when the lesion is small and the lesion contour is blurred, attention U-Net may generate wrong attention coefficient maps, leading to incorrect segmentation results. To cope with this issue, we propose a dual-path attention compensation U-Net (DPAC-UNet) network, which consists of a primary network and auxiliary path network. Both networks are attention U-Net models and identical in structure. The primary path network is the core network that performs accurate lesion segmentation and outputting of the final segmentation result. The auxiliary path network generates auxiliary attention compensation coefficients and sends them to the primary path network to compensate for and correct possible attention coefficient errors. To realize the compensation mechanism of DPAC-UNet, we propose a weighted binary cross-entropy Tversky (WBCE-Tversky) loss to train the primary path network to achieve accurate segmentation and propose another compound loss function called tolerance loss to train the auxiliary path network to generate auxiliary compensation attention coefficient maps with expanded coverage area to perform compensate operations. We conducted segmentation experiments using the 239 MRI scans of the anatomical tracings of lesions after stroke (ATLAS) dataset to evaluate the performance and effectiveness of our method. The experimental results show that the DSC score of the proposed DPAC-UNet network is 6% higher than the single-path attention U-Net. It is also higher than the existing segmentation methods of the related literature. Therefore, our method demonstrates powerful abilities in the application of stroke lesion segmentation.
Highlights
Recent global statistics on the incidence of stroke cases demonstrate that there are up to 10.3 million new cases annually [1]
Since FPR 1 −Specificity, it implies that the larger the proportion of nonlesions identified as nonlesions, the smaller the FPR, and the less tolerant the auxiliary compensation attention coefficient map. erefore, we introduce a specificity reducing item to reduce the specificity of segmentation results, increase the FPR of the auxiliary network’s training results, and increase the size of the coverage area of the attention coefficient map
We explained the relationship between the values of different hyperparameters δ and λ and the coverage area of the auxiliary compensation attention coefficient map in Section 2.2. e coverage area of the auxiliary attention coefficient map is proportional to the FPR value, and the FPR value is proportional to λ and inversely proportional to δ
Summary
Recent global statistics on the incidence of stroke cases demonstrate that there are up to 10.3 million new cases annually [1]. Stroke has become one of the top three lethal diseases, besides chronic diseases. Accurate diagnosis of the severity of the stroke and timely thrombolytic therapy can effectively improve blood supply in the ischemic area and significantly reduce the risk of disability or even death. Erefore, it is clinically significant to quickly and accurately locate and segment the stroke lesions [2]. Since manual segmentation relies on the doctor’s professional experience and medical skills, individual subjectivity can reduce segmentation accuracy. Manual segmentation of the stroke lesion is time-consuming. It may take a skilled tracer several hours to complete accurate labeling and rechecking of a single large complex lesion on magnetic resonance imaging (MRI) [3]
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
