Deep Learning Using Havrda-Charvat Entropy for Classification of Pulmonary Optical Endomicroscopy |
| |
| Institution: | 1. LITIS, Eq. Quantif, University of Rouen, France;2. GREYC, Eq. Image, Ensicaen, France;3. University Hospital of Rouen, France;1. EIE Department, TIET, Patiala, India;2. ICE Division, NSUT, India;1. Division of Gastroenterology, Hepatology, and Nutrition, The Ohio State University, Columbus, Ohio;3. Department of Internal Medicine, The Ohio State University, Columbus, Ohio;4. Division of Surgical Oncology, The Ohio State University, Columbus, Ohio;6. Department of General Surgery, The Ohio State University, Columbus, Ohio;5. Center for Biostatistics, Department of Biomedical Informatics, College of Medicine, The Ohio State University, Columbus, Ohio;1. Department of Biotechnology and Medical Engineering, National Institute of Technology, Rourkela, 769008, India;2. Department of International Agricultural Technology & Institute of Green BioScience and Technology, Seoul National University, Gwangwon-do-25354, Republic of Korea;1. Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata 700015, India;2. Department of Computer Science and Engineering, Jadavpur University, Kolkata 700032, India;1. INEGI, Faculdade de Engenharia, Universidade do Porto, Rua Dr. Roberto Frias, 400, 4200-465 Porto, Portugal;2. Centro de Investigação Clínica em Anestesiologia, Serviço de Anestesiologia, Centro Hospitalar do Porto, Largo Professor Abel Salazar, 4099-001 Porto, Portugal;3. Departamento de Anestesia, Unidade Local de Saúde de Matosinhos - Hospital Pedro Hispano, Rua de Dr. Eduardo Torres, 4464-513 Sra. da Hora, Portugal;4. Departamento de Ciências e Tecnologia, Universidade Aberta, Delegação do Porto, Rua do Amial 752, 4200-055 Porto, Portugal |
| |
| Abstract: | 1) ObjectivePulmonary optical endomicroscopy (POE) is an imaging technology in real time. It allows to examine pulmonary alveoli at a microscopic level. Acquired in clinical settings, a POE image sequence can have as much as 25% of the sequence being uninformative frames (i.e. pure-noise and motion artifacts). For future data analysis, these uninformative frames must be first removed from the sequence. Therefore, the objective of our work is to develop an automatic detection method of uninformative images in endomicroscopy images.2) Material and methodsWe propose to take the detection problem as a classification one. Considering advantages of deep learning methods, a classifier based on CNN (Convolutional Neural Network) is designed with a new loss function based on Havrda-Charvat entropy which is a parametrical generalization of the Shannon entropy. We propose to use this formula to get a better hold on all sorts of data since it provides a model more stable than the Shannon entropy.3) ResultsOur method is tested on one POE dataset including 3895 distinct images and is showing better results than using Shannon entropy and behaves better with regard to the problem of overfitting. We obtain 70% of accuracy with Shannon entropy versus 77 to 79% with Havrda-Charvat.4) ConclusionWe can conclude that Havrda-Charvat entropy is better suited for restricted and or noisy datasets due to its generalized nature. It is also more suitable for classification in endomicroscopy datasets. |
| |
| Keywords: | Deep learning CNN Shannon entropy Havrda-Charvat entropy Pulmonary optical endomicroscopy |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
