Affiliation:
1. School of Computer Science and Engineering, Central South University, China
2. Faculty of Data Science, Shiga University, Japan
3. Changsha Tobacco Factory of China Tobacco Hunan Industrial Co., Ltd., China
4. Department of Dermatology, Third Xiangya Hospital, Central South University, China
Abstract
With the development of intelligent medicine, lesion detection supported by Internet of Things (IoT), big data, and deep learning has become a hotspot. However, lesion detection technology based on deep learning requires huge amounts of high-quality medical image data, and the data from social IoT has the problems of uneven quality and lack of lesion labeling. Current studies usually ignore the unstable quality of IoT data and the interpretability of diagnostic results, resulting in deeper model layers, larger models, poor real-time performance, and lack of persuasion. To address the problems, this article first proposes a core data extraction method for multi-class lesion detection based on unlabeled medical image from social IoT. Then, we propose an ensemble algorithm based on lightweight models to improve the detection accuracy. Finally, we visualize pathological features to enhance the interpretability of core data and detection results. The experimental results show that our method can effectively extract the core data of multiple lesions from low-quality medical images and improve the accuracy of the lightweight lesion detection model as well as the interpretation of detection results.
Funder
Natural Science Foundation of China
Open Research Projects of Zhejiang Lab
Hunan Provincial Science and Technology Plan Project
Key projects of Hunan Education Department
National Science Foundation of Hunan Province
National Social Science Fund of China
Postgraduate Scientific Research Innovation Project of Hunan Province
Fundamental Research Funds for the Central Universities of Central South University
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications
Reference54 articles.
1. Hamed H. Aghdam, Abel Gonzalez-Garcia, Joost van de Weijer, and Antonio M. López. 2019. Active learning for deep detection neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 3672–3680.
2. Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network
3. Automated skin lesion segmentation using attention-based deep convolutional neural network;Arora Ridhi;Biomed. Sign. Process. Contr.,2021
4. Bagging predictors
5. Pasting small votes for classification in large databases and on-line;Breiman Leo;Mach. Learn.,1999
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Empowering Medical Data Analysis: An Advanced Deep Fusion Model for Sorting Medicine Document;IEEE Access;2024
2. Discussion on Network Security under SDN Architecture;2023 26th ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter);2023-07-05