Semantic segmentation of brain tumor with nested residual attention networks
- PDF / 2,012,333 Bytes
- 18 Pages / 439.642 x 666.49 pts Page_size
- 21 Downloads / 219 Views
Semantic segmentation of brain tumor with nested residual attention networks Jingchao Sun1 · Jianqiang Li1
· Lu Liu1
Received: 4 December 2019 / Revised: 15 June 2020 / Accepted: 9 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Brain tumors are one of the most serious brain diseases, which often result in a short life. However, in developing areas, medical resources are in shortage, which affect the diagnosis of brain tumors. With the development of computer science, many diseases can be diagnosed by telemedicine systems, which help physicians save much time and improve diagnostic accuracy. Therefore, we propose a semantic segmentation method for brain tumors based on nested residual attention networks. It can be deployed in social mx‘edia environment to work as a remote diagnosis system. The proposed method uses an improved residual attention block (RAB) as the basic unit. Based on the improved RAB, a nested RAB is designed to build the proposed method, which has better generalization. The proposed method includes an encoder part, a decoder part and skip connections. The encoder part learns multiple feature representations from inputs and the decoder part utilizes the learnt features to make segmentation predictions. In addition, high-level attention feature maps are exploited to induce low-level feature maps in skip connections to discard useless information. The proposed method is mainly validated on the dataset of Brain Tumor Segmentation challenge (BraTS) 2015. The proposed method achieves an average dice score of 0.87 (0.80, 0.72) for the whole tumor (core tumor, enhancing tumor) regions on BraTS 2015 dataset. Keywords Brain tumors · Social media environment · Telemedicine systems · Residual attention block · Nested residual attention block
1 Introduction Brain tumors have become one of the most serious diseases hazard to human life and health. They are caused by abnormal cells within the brain, which include malignant tumors and benign tumors [11, 25]. Benign tumors, like meningiomas, are reasonably easy to treat. Malignant gliomas have the highest morbidity rate and mortality risk among brain tumors. Based on the duration of tumors, they are classified into Low-Grade Gliomas (LGG) and High-Grade Gliomas (HGG), which are more infiltrative than LGG. Currently, the most Jianqiang Li
[email protected] 1
School of Software Engineering, Beijing University of Technology, Beijing, China
Multimedia Tools and Applications
effective treatment for gliomas is surgery. In addition, chemotherapy and radiotherapy are often used to slow this cancer. However, few cases of gliomas are entirely cured, in which survival time is at most several years. Prompt diagnosis is of high significance for the treatment of gliomas. Magnetic resonance imaging (MRI) is one of the most effective medical image techniques to detect brain tumors. Comparing with computerized tomography scan, MRI is a safe and non-invasive diagnostic tool and provides more detailed information on bra
Data Loading...
