An Enhanced Privacy-preserving Federated Few-shot Learning Framework for Respiratory Disease Diagnosis
Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology(能源化工过程智能制造重点实验室,教育部,东华大学);Research Institute of Intelligent Control and Systems, School of Astronautics, Harbin Institute of Technology(智能控制与系统研究所,航天学院,哈尔滨工业大学);Department of Emergency Medicine, Provincial Key Laboratory of Precise Diagnosis and Treatment of Abdominal Infection, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine(急诊科,腹部感染精准诊断与治疗省级重点实验室,邵氏医院,浙江大学医学院);School of Medicine, Shaoxing University(医学院,绍兴大学)
Ming Wang, Zhaoyang Duan, Dong Xue, Fangzhou Liu, Zhongheng Zhang
The labor-intensive nature of medical data annotation presents a significant challenge for respiratory disease diagnosis, resulting in a scarcity of high-quality labeled datasets in resource-constrained settings. Moreover, patient privacy concerns complicate the direct sharing of local medical data across institutions, and existing centralized data-driven approaches, which rely on amounts of available data, often compromise data privacy. This study proposes a federated few-shot learning framework with privacy-preserving mechanisms to address the issues of limited labeled data and privacy protection in diagnosing respiratory diseases. In particular, a meta-stochastic gradient descent algorithm is proposed to mitigate the overfitting problem that arises from insufficient data when employing traditional gradient descent methods for neural network training. Furthermore, to ensure data privacy against gradient leakage, differential privacy noise from a standard Gaussian distribution is integrated into the gradients during the training of private models with local data, thereby preventing the reconstruction of medical images. Given the impracticality of centralizing respiratory disease data dispersed across various medical institutions, a weighted average algorithm is employed to aggregate local diagnostic models from different clients, enhancing the adaptability of a model across diverse scenarios. Experimental results show that the proposed method yields compelling results with the implementation of differential privacy, while effectively diagnosing respiratory diseases using data from different structures, categories, and distributions.
Federated Meta-Learning for Few-Shot Fault Diagnosis with Representation Encoding
Nanjing University of Science and Technology(南京理工大学);The Hong Kong Polytechnic University(香港理工大学);China Academy of Information and Communications Technology(中国信息通信研究院)
AI4COVID-19: AI Enabled Preliminary Diagnosis for COVID-19 from Cough Samples via an App
University of Oklahoma(俄克拉荷马大学);AI4Lyf LLC(AI4Lyf有限责任公司);Kharkiv National Medical University(哈尔科夫国立医科大学);Michigan State University(密歇根州立大学);Allergy, Asthma & Immunology Center PC(过敏、哮喘与免疫学中心PC)
FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Microsoft Research Asia(微软亚洲研究院)
Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosis
Department of Psychiatry, Wonkwang University Hospital(精神医学科,Wonkwang大学医院);RSC LAB, MODULABS(RSC实验室,MODULABS);The State University of New York, Korea, Republic of Korea(纽约州立大学,韩国);Department of Pediatrics, Seoul National University Bundang Hospital(儿科,首尔国立大学医院 Bundang 分院);Department of Pediatrics, Seoul National University College of Medicine(儿科,首尔国立大学医学院)
Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice
Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers
Luca Healthcare(卢卡医疗);Ruijin Hospital, Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属瑞金医院);Shanghai Key Laboratory of Emergency Prevention, Diagnosis and Treatment of Respiratory Infectious Disease(上海市呼吸道传染病应急防控诊治重点实验室)
Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
School of Information, Computer, and Communication Technology(信息、计算机与通信技术学院);Sirindhorn International Institute of Technology, Thammasat University(泰国朱拉隆功大学国际技术学院)
Accurate Diagnosis of Respiratory Viruses Using an Explainable Machine Learning with Mid-Infrared Biomolecular Fingerprinting of Nasopharyngeal Secretions
School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院);School of Instrumentation and Optoelectronic Engineering, Beihang University(北京航空航天大学仪器科学与光电工程学院);Department of Science and Development, Beijing Youan Hospital, Capital Medical University(首都医科大学附属北京佑安医院科学发展部)
Federated Learning for Diabetic Retinopathy Diagnosis: Enhancing Accuracy and Generalizability in Under-Resourced Regions
High Technology High School(高新技术高中);Massachusetts Eye and Ear Harvard Medical School(马萨诸塞眼耳医院哈佛医学院);Harvard Medical School(哈佛医学院);Harvard Ophthalmology AI Lab(哈佛眼科人工智能实验室)
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
University of Pittsburgh(匹兹堡大学);University of Notre Dame(圣母大学);George Mason University(乔治梅森大学);University of New Mexico(新墨西哥大学);University of Pittsburgh Medical Center(匹兹堡大学医学中心)
Real-Time Magnetic Tracking and Diagnosis of COVID-19 via Machine Learning
University of South Florida(南佛罗里达大学);Hue Central Hospital(顺化中央医院);Riga Stradinš University(里加斯特拉迪宁什大学);Vietnam National University(越南国家大学);University Medical Center(大学医学中心);Traditional Medicine Hospital, Ministry of Public Security(公安部传统医学医院)
Deep Learning-Based Detection of the Acute Respiratory Distress Syndrome: What Are the Models Learning?
University of California, Davis(加利福尼亚大学戴维斯分校)
急性呼吸窘迫综合征(ARDS)是一种严重的低氧性呼吸衰竭,住院死亡率为35- 46%。高死亡率被认为部分与快速诊断的挑战有关,这反过来可能会延迟循证治疗的实施。利用无偏呼吸机波形数据(VWD)的深度神经网络(DNN)算法可能有助于改善ARDS的筛查。我们首先证明了基于卷积神经网络的ARDS检测模型在AUC(0.95+/-0.019 vs. 0.88+/-0.064)、准确性(0.84+/-0.026 vs. 0.80+/-0.078)和特异性(0.81+/-0.06 vs. 0.71+/-0.089)方面优于随机森林模型。频率消融研究意味着我们的模型可以从通常用于专家特征工程的低频域和可能难以手动特征化的高频信息中学习特征。进一步的实验表明,微妙的,生理信号的高频分量可以解释DL模型优于传统ML的性能时,使用生理波形数据。我们的观察结果可以提高基于DL的生理模型的可解释性,并可以提高对生理数据中的高频信息如何影响DL模型性能的理解。
Semi-Supervised Federated Learning via Dual Contrastive Learning and Soft Labeling for Intelligent Fault Diagnosis
School of Electronic and Optical Engineering, Nanjing University of Science and Technology(南京理工大学电子与光学工程学院);School of Information Science and Engineering, Southeast University(东南大学信息科学与工程学院);Institute of Artificial Intelligence Research, Jiangsu Second Normal University(江苏第二师范学院人工智能研究所);Digital Research Institute, ENN Group(ENN集团数字研究院);School of Computing, Engineering and Mathematical Sciences, La Trobe University(拉筹伯大学计算、工程与数学科学学院);College of Science and Engineering, James Cook University(詹姆斯库克大学科学与工程学院)
Accurate and Private Diagnosis of Rare Genetic Syndromes from Facial Images with Federated Deep Learning
Medical Data Privacy and Privacy Preserving Machine Learning (MDPPML)(医学数据隐私与隐私保护机器学习);University of Tübingen(图宾根大学);Institute for Bioinformatics and Medical Informatics (IBMI)(生物信息学与医学信息学研究所);Institute for Genomic Statistics and Bioinformatics(基因组统计与生物信息学研究所);University of Bonn(波恩大学)
Optimising MFCC parameters for the automatic detection of respiratory diseases
Institute of Data Science, Maastricht University(数据科学研究所,马斯特里赫特大学);Department of Respiratory Medicine, NUTRIM Research Institute of Nutrition and Translational Research in Metabolism, Faculty of Health Medicine and Life Sciences, Maastricht University(呼吸科系,营养与代谢转化研究 institute,健康医学与生命科学学院,马斯特里赫特大学);Department of Respiratory Medicine, Maastricht University Medical Centre(呼吸科系,马斯特里赫特大学医学中心);Department of Research and Development, Ciro(研发部,Ciro)
Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);College of Biomedical Engineering, Sichuan University(四川大学生物医学工程学院);AI Lab, Tencent(腾讯AI实验室);The Fourth Hospital of Hebei Medical University(河北医科大学第四医院);Massachusetts General Hospital(麻省总医院);Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Harvard Medical School(哈佛医学院);Children’s Hospital of Chongqing Medical University(重庆医科大学附属儿童医院);The Affiliated Yantai Yuhuangding Hospital of Qingdao University(青岛大学附属烟台毓璜顶医院)
Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner
East China Normal University(华东师范大学);Ryerson University(瑞尔森大学);Shanghai Jianglai Data Technology Co., Ltd(上海江来数据科技有限公司)
研究意义:本文的扩展版本已被IEEE Internet of Things期刊(DOI:10.1109/JIOT.2020.2991456)接受,请引用期刊版本。在疫情防控期间,我们的研究有助于基于呼吸特征的COVID-19(新型冠状病毒)感染患者的预后、诊断和筛查。根据最新的临床研究,COVID-19的呼吸模式与流感和普通感冒的呼吸模式不同。COVID-19中发生的一个重要症状是呼吸急促。感染COVID-19的人呼吸更快。本研究可用于各种呼吸模式的识别,并可初步投入实用。该方法在单受试者和双受试者情况下的演示视频可以在线下载。研究详情:以远程和不显眼的方式准确检测人的意外异常呼吸模式具有重要意义。在这项工作中,我们创新地利用深度相机和深度学习来实现这一目标。这项任务的挑战是双重的:真实世界的数据量不足以训练获得深度模型;不同类型的呼吸模式的类内变化很大,类外变化很小。本文针对呼吸信号的特点,提出了一种新颖高效的呼吸仿真模型(Respiratory Simulation Model,简称RSM),以弥补训练数据量大和真实数据量少的不足。所提出的深度模型和建模思想具有很大的潜力,可以扩展到大规模的应用,如公共场所,睡眠场景,办公环境。
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
KAIST AI(韩国科学技术院人工智能学院);Department of AI, Kyungpook National University(庆北国立大学人工智能系);SmartSound(SmartSound公司);Dongguk University(东国大学);MODULABS(MODULABS机构)
SeaCausal-FL: Federated Fuzzy Causal Learning for Maritime IoT Fault Diagnosis and Counterfactual Reasoning
Jimei University(集美大学);Hebei University of Technology(河北工业大学);R. M. K. Engineering College(R.M.K.工程学院);University of Science and Technology of China(中国科学技术大学);Waseda University(早稻田大学);University of Luxembourg(卢森堡大学)
Towards Case-based Interpretability for Medical Federated Learning
The Netherlands Cancer Institute(荷兰癌症研究所);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Maastricht University Medical Center(马斯特里赫特大学医学中心);Utrecht University(乌得勒支大学);INESC TEC