Lung Nodule Segmentation Using Federated Active Learning

被引:0
作者
Tenescu, Andrei [1 ]
Bercean, Bogdan [1 ]
Avramescu, Cristian [1 ]
Marcu, Marius [1 ]
机构
[1] Politehn Univ Timisoara, Timisoara, Timis, Romania
来源
PROCEEDINGS OF THE 16TH ACM INTERNATIONAL CONFERENCE ON PERVASIVE TECHNOLOGIES RELATED TO ASSISTIVE ENVIRONMENTS, PETRA 2023 | 2023年
关键词
federated learning; data privacy; computer vision; artificial intelligence; chest CT; lung nodule segmentation; PULMONARY NODULES;
D O I
10.1145/3594806.3594850
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Lung nodule segmentation on computed tomography (CT) is at the same time one of the most common and laborious tasks in oncological radiology. Fortunately, artificial intelligence agents have been showing promising results in streamlining the process. We study some of the challenges of training an AI model for lung nodule segmentation, including the degradation of performance due to distribution shift, privacy concerns and limited bandwidth for cloud data transmission. The article explores different federated learning strategies, over a pool of 1506 CT studies collected from four hospitals. The results show that federated learning models reach near standard classical training DICE score performance (i.e., 87.24% vs. 88.96%), and even surpass it in a privacy-centered context (i.e., 87.24% vs. 84.78%). Additionally, active learning was proven to increase the new model's DICE score by 1.76% over the random sampling strategy. The article adds to the growing body of research exploring the use of federated learning in healthcare and demonstrates its potential for improving lung nodule segmentation on CT.
引用
收藏
页码:17 / 21
页数:5
相关论文
共 50 条
[41]   Multi-Crop Convolutional Neural Networks for Fast Lung Nodule Segmentation [J].
Chen, Quan ;
Xie, Wei ;
Zhou, Pan ;
Zheng, Chuansheng ;
Wu, Dapeng .
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2022, 6 (05) :1190-1200
[42]   KFS-Net: Key Features Sampling Network for Lung Nodule Segmentation [J].
Yue, Yuhan ;
Kong, Fanning ;
Cheng, Ming ;
Cao, Huaisheng ;
Qi, Junyu ;
Shi, Zaifeng .
SENSING AND IMAGING, 2023, 25 (01)
[43]   Lung nodule segmentation in chest computed tomography using a novel background estimation method [J].
Cavalcanti, Pablo G. ;
Shirani, Shahram ;
Scharcanski, Jacob ;
Fong, Crystal ;
Meng, Jane ;
Castelli, Jane ;
Koff, David .
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY, 2016, 6 (01) :16-24
[44]   Automatic Lung Nodule Segmentation and Intra-Nodular Heterogeneity Image Generation [J].
Song, Jiangdian ;
Huang, Shih-Cheng ;
Kelly, Brendan ;
Liao, Guanqun ;
Shi, Jingyun ;
Wu, Ning ;
Li, Weimin ;
Liu, Zaiyi ;
Cui, Lei ;
Lungre, Matthew ;
Moseley, Michael E. ;
Gao, Peng ;
Tian, Jie ;
Yeom, Kristen W. .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (06) :2570-2581
[45]   Federated vs. centralized learning for medical image classification and segmentation [J].
Rakotoarisedy, Irina ;
Fragkiadakis, Adam ;
Haigron, Pascal ;
Simon, Antoine .
MEDICAL IMAGING 2025: COMPUTER-AIDED DIAGNOSIS, 2025, 13407
[46]   CAD system for lung nodule detection using deep learning with CNN [J].
Manickavasagam, R. ;
Selvan, S. ;
Selvan, Mary .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2022, 60 (01) :221-228
[47]   Lung Nodule Classification on Computed Tomography Images Using Deep Learning [J].
Naik, Amrita ;
Edla, Damodar Reddy .
WIRELESS PERSONAL COMMUNICATIONS, 2021, 116 (01) :655-690
[48]   AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation [J].
Banu, Syeda Furruka ;
Sarker, Md. Mostafa Kamal ;
Abdel-Nasser, Mohamed ;
Puig, Domenec ;
Raswan, Hatem A. .
APPLIED SCIENCES-BASEL, 2021, 11 (21)
[49]   Lung Nodule: Imaging Features and Evaluation in the Age of Machine Learning [J].
Sayyouh, M. ;
Hadjiiyski, L. M. ;
Chan, H-P. ;
Agarwal, P. .
CURRENT PULMONOLOGY REPORTS, 2019, 8 (03) :86-95
[50]   Federated Learning for Lung Sound Analysis [J].
Farjana, Afia ;
Makkar, Aaisha .
RECENT TRENDS IN IMAGE PROCESSING AND PATTERN RECOGNITION, RTIP2R 2022, 2023, 1704 :120-134