ELNet:Automatic classification and segmentation for esophageal lesions using convolutional neural network

Autor: Shuo Li, Xiaopu He, Jie Hua, Minli Wen, Pinzheng Zhang, Gaoshuang Liu, Yang Chen, Rongjun Ge, Zhan Wu, Limin Luo
Přispěvatelé: Southeast University [Jiangsu], School of Computer Engineering and Science [Shanghai], University of Shanghai [Shanghai], Nanjing Medical University, Centre de Recherche en Information Biomédicale sino-français (CRIBS), Université de Rennes (UR)-Southeast University [Jiangsu]-Institut National de la Santé et de la Recherche Médicale (INSERM), Jiangsu Normal University (JSNU), University of Western Ontario (UWO), This research was supported in part by the State's Key Project of Research and Development Plan under Grant 2017YFA0104302, Grant 2017YFC0109202 and 2017YFC0107900, in part by the National Natural Science Foundation under Grant 61801003, 61871117 and 81471752, in part by the China Scholarship Council under NO. 201906090145., Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Southeast University [Jiangsu]-Institut National de la Santé et de la Recherche Médicale (INSERM)
Rok vydání: 2021
Předmět:
Computer science
Health Informatics
Esophageal lesions
Convolutional neural network
030218 nuclear medicine & medical imaging
Dual-stream esophageal lesion classification
Lesion
03 medical and health sciences
0302 clinical medicine
medicine
Humans
Radiology
Nuclear Medicine and imaging
Segmentation
convolutional neural network (CNN)
Index Terms-Esophageal lesions
Radiological and Ultrasound Technology
Pixel
Esophageal disease
business.industry
Deep learning
deep learning
[SDV.MHEP.HEG]Life Sciences [q-bio]/Human health and pathology/Hépatology and Gastroenterology
Pattern recognition
medicine.disease
Computer Graphics and Computer-Aided Design
Clinical method
[SDV.IB]Life Sciences [q-bio]/Bioengineering
Neural Networks
Computer
Computer Vision and Pattern Recognition
Artificial intelligence
medicine.symptom
business
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
030217 neurology & neurosurgery
Zdroj: Medical Image Analysis
Medical Image Analysis, 2021, 67, pp.101838. ⟨10.1016/j.media.2020.101838⟩
Medical Image Analysis, Elsevier, 2021, 67, pp.101838. ⟨10.1016/j.media.2020.101838⟩
ISSN: 1361-8415
1361-8423
Popis: International audience; Automatic and accurate esophageal lesion classification and segmentation is of great significance to clinically estimate the lesion statuses of the esophageal diseases and make suitable diagnostic schemes. Due to individual variations and visual similarities of lesions in shapes, colors, and textures, current clinical methods remain subject to potential high-risk and time-consumption issues. In this paper, we propose an Esophageal Lesion Network (ELNet) for automatic esophageal lesion classification and segmentation using deep convolutional neural networks (DCNNs). The underlying method automatically integrates dual-view contextual lesion information to extract global features and local features for esophageal lesion classification and lesion-specific segmentation network is proposed for automatic esophageal lesion annotation at pixel level. For the established clinical large-scale database of 1051 white-light endoscopic images, ten-fold cross-validation is used in method validation. Experiment results show that the proposed framework achieves classification with sensitivity of 0.9034, specificity of 0.9718, and accuracy of 0.9628, and the segmentation with sensitivity of 0.8018, specificity of 0.9655, and accuracy of 0.9462. All of these indicate that our method enables an efficient, accurate, and reliable esophageal lesion diagnosis in clinics.
Databáze: OpenAIRE
Externí odkaz: