DeepFixCX: Explainable privacy-preserving image compression for medical image analysis

被引:7
作者
Gaudio, Alex [2 ,3 ]
Smailagic, Asim [1 ]
Faloutsos, Christos [1 ]
Mohan, Shreshta [1 ]
Johnson, Elvin [1 ]
Liu, Yuhao [1 ]
Costa, Pedro [2 ,3 ]
Campilho, Aurelio [2 ,3 ]
机构
[1] Carnegie Mellon Univ, Elect & Comp Engn, Pittsburgh, PA 15213 USA
[2] Univ Porto, Fac Engn, Porto, Portugal
[3] INESC TEC, Elect & Comp Engn, Porto, Portugal
基金
美国安德鲁·梅隆基金会;
关键词
compression; deep networks; explainability; medical image analysis; privacy; wavelets; CLASSIFICATION; FOUNDATIONS;
D O I
10.1002/widm.1495
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Explanations of a model's biases or predictions are essential to medical image analysis. Yet, explainable machine learning approaches for medical image analysis are challenged by needs to preserve privacy of patient data, and by current trends in deep learning to use unsustainably large models and large datasets. We propose DeepFixCX for explainable and privacy-preserving medical image compression that is nimble and performant. We contribute a review of the field and a conceptual framework for simultaneous privacy and explainability via tools of compression. DeepFixCX compresses images without learning by removing or obscuring spatial and edge information. DeepFixCX is ante-hoc explainable and gives privatized post hoc explanations of spatial and edge bias without accessing the original image. DeepFixCX privatizes images to prevent image reconstruction and mitigate patient re-identification. DeepFixCX is nimble. Compression can occur on a laptop CPU or GPU to compress and privatize 1700 images per second of size 320 x 320. DeepFixCX enables use of low memory MLP classifiers for vision data; permitting small performance loss gives end-to-end MLP performance over 70x faster and batch size over 100x larger. DeepFixCX consistently improves predictive classification performance of a Deep Neural Network (DNN) by 0.02 AUC ROC on Glaucoma and Cervix Type detection datasets, and can improve multi-label chest x-ray classification performance in seven of 10 tested settings. In all three datasets, compression to less than 5% of original number of pixels gives matching or improved performance. Our main novelty is to define an explainability versus privacy problem and address it with lossy compression.This article is categorized under:Fundamental Concepts of Data and Knowledge > Explainable AICommercial, Legal, and Ethical Issues > Security and PrivacyFundamental Concepts of Data and Knowledge > Big Data Mining
引用
收藏
页数:47
相关论文
共 106 条
[1]   Deep Learning with Differential Privacy [J].
Abadi, Martin ;
Chu, Andy ;
Goodfellow, Ian ;
McMahan, H. Brendan ;
Mironov, Ilya ;
Talwar, Kunal ;
Zhang, Li .
CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, :308-318
[2]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[3]  
Adebayo J., 2018, NEURIPS
[4]  
ADNAN M, 2022, SCI REP-UK, V12, P1, DOI [DOI 10.1038/S41598-022-05539-7, DOI 10.1038/S41598]
[5]  
Ahmed N, 2020, DE DEMOCRATIZATION D
[6]   A deep learning model for the detection of both advanced and early glaucoma using fundus photography [J].
Ahn, Jin Mo ;
Kim, Sangsoo ;
Ahn, Kwang-Sung ;
Cho, Sung-Hoon ;
Lee, Kwan Bok ;
Kim, Ungsoo Samuel .
PLOS ONE, 2018, 13 (11)
[7]  
Angles T., 2018, PREPRINT
[8]   Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI [J].
Barredo Arrieta, Alejandro ;
Diaz-Rodriguez, Natalia ;
Del Ser, Javier ;
Bennetot, Adrien ;
Tabik, Siham ;
Barbado, Alberto ;
Garcia, Salvador ;
Gil-Lopez, Sergio ;
Molina, Daniel ;
Benjamins, Richard ;
Chatila, Raja ;
Herrera, Francisco .
INFORMATION FUSION, 2020, 58 :82-115
[9]  
Behrmann J, 2019, PR MACH LEARN RES, V97
[10]  
Biran O., 2017, IJCAI 17 WORKSH EXPL