A Survey on Explainable Artificial Intelligence (XAI) Techniques for Visualizing Deep Learning Models in Medical Imaging

Overview

Journal J Imaging

Publisher MDPI

Specialty Radiology

Date 2024 Oct 25

PMID 39452402

Authors

Deepshikha Bhati

Fnu Neha

Md Amiruzzaman

Affiliations

Soon will be listed here.

Abstract

The combination of medical imaging and deep learning has significantly improved diagnostic and prognostic capabilities in the healthcare domain. Nevertheless, the inherent complexity of deep learning models poses challenges in understanding their decision-making processes. Interpretability and visualization techniques have emerged as crucial tools to unravel the black-box nature of these models, providing insights into their inner workings and enhancing trust in their predictions. This survey paper comprehensively examines various interpretation and visualization techniques applied to deep learning models in medical imaging. The paper reviews methodologies, discusses their applications, and evaluates their effectiveness in enhancing the interpretability, reliability, and clinical relevance of deep learning models in medical image analysis.

References

Ko H, Chung H, Kang W, Kim K, Shin Y, Kang S . COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation. J Med Internet Res. 2020; 22(6):e19569. PMC: 7332254. DOI: 10.2196/19569. View

Hosny A, Parmar C, Coroller T, Grossmann P, Zeleznik R, Kumar A . Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study. PLoS Med. 2018; 15(11):e1002711. PMC: 6269088. DOI: 10.1371/journal.pmed.1002711. View

Jia X, Ren L, Cai J . Clinical implementation of AI technologies will require interpretable AI models. Med Phys. 2019; 47(1):1-4. DOI: 10.1002/mp.13891. View

Bramlage L, Cortese A . Generalized attention-weighted reinforcement learning. Neural Netw. 2021; 145:10-21. DOI: 10.1016/j.neunet.2021.09.023. View

Philbrick K, Yoshida K, Inoue D, Akkus Z, Kline T, Weston A . What Does Deep Learning See? Insights From a Classifier Trained to Predict Contrast Enhancement Phase From CT Images. AJR Am J Roentgenol. 2018; 211(6):1184-1193. DOI: 10.2214/AJR.18.20331. View

Dunnmon J, Yi D, Langlotz C, Re C, Rubin D, Lungren M . Assessment of Convolutional Neural Networks for Automated Classification of Chest Radiographs. Radiology. 2018; 290(2):537-544. PMC: 6358056. DOI: 10.1148/radiol.2018181422. View

Yu Z, Tan E, Ni D, Qin J, Chen S, Li S . A Deep Convolutional Neural Network-Based Framework for Automatic Fetal Facial Standard Plane Recognition. IEEE J Biomed Health Inform. 2017; 22(3):874-885. DOI: 10.1109/JBHI.2017.2705031. View

Park S, Kim G, Oh Y, Seo J, Lee S, Kim J . Self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation. Nat Commun. 2022; 13(1):3848. PMC: 9252561. DOI: 10.1038/s41467-022-31514-x. View

Wang S, Xing Y, Zhang L, Gao H, Zhang H . Deep Convolutional Neural Network for Ulcer Recognition in Wireless Capsule Endoscopy: Experimental Feasibility and Optimization. Comput Math Methods Med. 2019; 2019:7546215. PMC: 6766681. DOI: 10.1155/2019/7546215. View

10.

Chen X, You S, Tezcan K, Konukoglu E . Unsupervised lesion detection via image restoration with a normative prior. Med Image Anal. 2020; 64:101713. DOI: 10.1016/j.media.2020.101713. View

11.

Shome D, Kar T, Mohanty S, Tiwari P, Muhammad K, Altameem A . COVID-Transformer: Interpretable COVID-19 Detection Using Vision Transformer for Healthcare. Int J Environ Res Public Health. 2021; 18(21). PMC: 8583247. DOI: 10.3390/ijerph182111086. View

12.

Gecer B, Aksoy S, Mercan E, Shapiro L, Weaver D, Elmore J . Detection and classification of cancer in whole slide breast histopathology images using deep convolutional networks. Pattern Recognit. 2019; 84:345-356. PMC: 6342566. DOI: 10.1016/j.patcog.2018.07.022. View

13.

Gheflati B, Rivaz H . Vision Transformers for Classification of Breast Ultrasound Images. Annu Int Conf IEEE Eng Med Biol Soc. 2022; 2022:480-483. DOI: 10.1109/EMBC48229.2022.9871809. View

14.

Nundy S, Montgomery T, Wachter R . Promoting Trust Between Patients and Physicians in the Era of Artificial Intelligence. JAMA. 2019; 322(6):497-498. DOI: 10.1001/jama.2018.20563. View

15.

Chen J, Frey E, He Y, Segars W, Li Y, Du Y . TransMorph: Transformer for unsupervised medical image registration. Med Image Anal. 2022; 82:102615. PMC: 9999483. DOI: 10.1016/j.media.2022.102615. View

16.

Hu P, Wu F, Peng J, Bao Y, Chen F, Kong D . Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets. Int J Comput Assist Radiol Surg. 2016; 12(3):399-411. DOI: 10.1007/s11548-016-1501-5. View

17.

Perdomo O, Rios H, Rodriguez F, Otalora S, Meriaudeau F, Muller H . Classification of diabetes-related retinal diseases using a deep learning approach in optical coherence tomography. Comput Methods Programs Biomed. 2019; 178:181-189. DOI: 10.1016/j.cmpb.2019.06.016. View

18.

Bohle M, Eitel F, Weygandt M, Ritter K . Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification. Front Aging Neurosci. 2019; 11:194. PMC: 6685087. DOI: 10.3389/fnagi.2019.00194. View

19.

Tang Y, Tang Y, Peng Y, Yan K, Bagheri M, Redd B . Automated abnormality classification of chest radiographs using deep convolutional neural networks. NPJ Digit Med. 2020; 3:70. PMC: 7224391. DOI: 10.1038/s41746-020-0273-z. View

20.

Heinemann F, Birk G, Stierstorfer B . Deep learning enables pathologist-like scoring of NASH models. Sci Rep. 2019; 9(1):18454. PMC: 6895116. DOI: 10.1038/s41598-019-54904-6. View