A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images-Reference-Cited by-同舟云学术

A Survey on Deep Learning and Explainability for Automatic Report Generation from Medical Images

Published:2022-01-31 Issue:10s Volume:54 Page:1-40
ISSN:0360-0300
Container-title:ACM Computing Surveys
language:en
Short-container-title:ACM Comput. Surv.

Author:

Messina Pablo¹^ORCID,Pino Pablo¹,Parra Denis¹,Soto Alvaro¹,Besa Cecilia²,Uribe Sergio²,Andía Marcelo²,Tejos Cristian³,Prieto Claudia⁴,Capurro Daniel⁵

Affiliation:

1. Computer Science Department, Pontificia Universidad Católica de Chile, Vicuña Mackenna, Santiago, Chile

2. Department of Radiology, School of Medicine, Pontificia Universidad Católica de Chile, Santiago, Chile

3. Department of Electrical Engineering, Pontificia Universidad Católica de Chile, Vicuña Mackenna, Santiago, Chile

4. School of Biomedical Engineering and Imaging Sciences, King’s College London,St Thomas’ Hospital, London, UK

5. School of Computing and Information Systems, The University of Melbourne, Australia

Abstract

Every year physicians face an increasing demand of image-based diagnosis from patients, a problem that can be addressed with recent artificial intelligence methods. In this context, we survey works in the area of automatic report generation from medical images, with emphasis on methods using deep neural networks, with respect to (1) Datasets, (2) Architecture Design, (3) Explainability, and (4) Evaluation Metrics. Our survey identifies interesting developments but also remaining challenges. Among them, the current evaluation of generated reports is especially weak, since it mostly relies on traditional Natural Language Processing (NLP) metrics, which do not accurately capture medical correctness.

Funder

National Agency for Research and Development (ANID) / Scholarship Program / Doctorado Becas Chile/2019

Magíster Becas Chile/2020

Millennium Science Initiative Program

Basal Fund for Center of Excellence

Fondecyt

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science,Theoretical Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3522747

Reference167 articles.

1. Automated Analysis of Retinal Images for Detection of Referable Diabetic Retinopathy

2. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

3. Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. In Advances in Neural Information Processing Systems 31. Curran Associates, Inc., 9505–9515.

4. Muhammad Aurangzeb Ahmad, Carly Eckert, and Ankur Teredesai. 2018. Interpretable machine learning in healthcare. In Proc. of the 2018 ACM Intl. Conf. on Bioinformatics, Computational Biology, and Health Informatics (BCB’18). ACM, New York, NY, 559–560.

5. Automated Generation of Radiologic Descriptions on Brain Volume Changes From T1-Weighted MR Images: Initial Assessment of Feasibility

Cited by 20 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. Chest radiology report generation based on cross-modal multi-scale feature fusion;Journal of Radiation Research and Applied Sciences;2024-03

2. Advances in medical image analysis with vision Transformers: A comprehensive review;Medical Image Analysis;2024-01

3. Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities;AIMS Public Health;2024

4. Deep learning for report generation on chest X-ray images;Computerized Medical Imaging and Graphics;2024-01

5. A systematic review of deep learning based image segmentation to detect polyp;Artificial Intelligence Review;2024-01