FP-CNN: Fuzzy pooling-based convolutional neural network for lung ultrasound image classification with explainable AI.

Autor: Hasan MM; Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, 1902, Dhaka, Bangladesh. Electronic address: mahmodul.mbstu@gmail.com., Hossain MM; Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, 1902, Dhaka, Bangladesh; Department of Computer Science and Engineering, Bangladesh University, Mohammadpur, Dhaka, 1207, Bangladesh. Electronic address: minoarhossain16005@gmail.com., Rahman MM; Department of Computer Science and Engineering, Mawlana Bhashani Science and Technology University, Tangail, 1902, Dhaka, Bangladesh. Electronic address: motiurcse@mbstu.ac.bd., Azad A; Department of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 13318, Saudi Arabia. Electronic address: kazad@imamu.edu.sa., Alyami SA; Department of Mathematics and Statistics, Faculty of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 13318, Saudi Arabia. Electronic address: saalyami@imamu.edu.sa., Moni MA; Artificial Intelligence & Data Science, School of Health and Rehabilitation Sciences, The University of Queensland, Brisbane, QLD 4072, Australia; Artificial Intelligence and Cyber Futures Institute, Charles Stuart University, Bathurst, NSW 2795, Australia. Electronic address: m.moni@uq.edu.au.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2023 Oct; Vol. 165, pp. 107407. Date of Electronic Publication: 2023 Sep 01.
DOI: 10.1016/j.compbiomed.2023.107407
Abstrakt: The COVID-19 pandemic wreaks havoc on healthcare systems all across the world. In pandemic scenarios like COVID-19, the applicability of diagnostic modalities is crucial in medical diagnosis, where non-invasive ultrasound imaging has the potential to be a useful biomarker. This research develops a computer-assisted intelligent methodology for ultrasound lung image classification by utilizing a fuzzy pooling-based convolutional neural network FP-CNN with underlying evidence of particular decisions. The fuzzy-pooling method finds better representative features for ultrasound image classification. The FPCNN model categorizes ultrasound images into one of three classes: covid, disease-free (normal), and pneumonia. Explanations of diagnostic decisions are crucial to ensure the fairness of an intelligent system. This research has used Shapley Additive Explanation (SHAP) to explain the prediction of the FP-CNN models. The prediction of the black-box model is illustrated using the SHAP explanation of the intermediate layers of the black-box model. To determine the most effective model, we have tested different state-of-the-art convolutional neural network architectures with various training strategies, including fine-tuned models, single-layer fuzzy pooling models, and fuzzy pooling at all pooling layers. Among different architectures, the Xception model with all pooling layers having fuzzy pooling achieves the best classification results of 97.2% accuracy. We hope our proposed method will be helpful for the clinical diagnosis of covid-19 from lung ultrasound (LUS) images.
Competing Interests: Declaration of competing interest The authors declare that they have no conflicts of interest regarding publishing the paper.
(Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: