Medical image segmentation using customized U-Net with adaptive activation functions
- PDF / 2,381,254 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 212 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Medical image segmentation using customized U-Net with adaptive activation functions Ali Farahani1 • Hadis Mohseni1 Received: 17 February 2020 / Accepted: 24 September 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Since medical imaging is a fundamental step in clinical diagnosis and treatment, medical image processing is an attractive field for researchers. Among the different applications of medical image processing, this paper focuses on the segmentation task using a customized deep convolutional neural network (CNN). The proposed network is developed based on the idea of improving a deep network performance and speeding up its learning process while using less parameters. Using the famous U-Net architecture which has proven its effectiveness in the segmentation field, the customization is done here by applying adaptive activation functions. In the proposed network, the U-Net complexity is reduced about 200 times by alleviating some parameters to accelerate the learning process. However, the important modification is the use of adaptive activation functions where each convolution layer learns its own data-adaptive activation function as a linear combination of 16 well-known basic functions. This modification successfully compensates the accuracy drop caused by parameter alleviation and also makes the model capable to be tuned with small amount of training data. Conducting several experiments on five famous retinal image datasets, namely DRIVE, STARE, CHASE, HRF, and ARIA, the proposed customized U-Net achieved 96%, 97%, 96%, 97%, and 95% accuracy in segmenting blood vessels, respectively. The proposed network also showed 98% accuracy on ISIC skin lesion dataset for segmenting the lesion area. The obtained results obviously confirm the high performance of the proposed customized network compared to the previous successful researches in handling the medical segmentation task. They also light the hope that many famous deep networks can benefit from these types of customization to become efficient compact models with the ability to handle lack of sufficient data. Keywords Adaptive activation function U-Net Customized network Medical segmentation Retinal images
1 Introduction Medical image segmentation is the task of labeling each pixel in an image into class labels (such as liver, heart, brain, and vessel), which can be useful for the diagnosis of diseases. However, manual extraction and segmentation of medical images are hard and time-consuming when the images are large, or there are many images, which makes the automatic segmentation methods considerable [1]. In this paper, we focus on the segmentation of blood vessels & Hadis Mohseni [email protected] Ali Farahani [email protected] 1
in fundus images and skin lesions in dermatoscopy images, using a customized deep convolutional neural network with adaptive activation functions. Despite the variation in image datasets and application, the proposed method open
Data Loading...
