Explainable-AI in Automated Medical Report Generation Using Chest X-ray Images
Source abstract
Abstract
The use of machine learning in healthcare has the potential to revolutionize virtually every aspect of the industry. However, the lack of transparency in AI applications may lead to the problem of trustworthiness and reliability of the information provided by these applications. Medical practitioners rely on such systems for clinical decision making, but without adequate explanations, diagnosis made by these systems cannot be completely trusted. Explainability in Artificial Intelligence (XAI) aims to improve our understanding of why a given output has been produced by an AI system. Automated medical report generation is one area that would benefit greatly from XAI. This survey provides an extensive literature review on XAI techniques used in medical image analysis and automated medical report generation. We present a systematic classification of XAI techniques used in this field, highlighting the most important features of each one that could be used by future research to select the most appropriate XAI technique to create understandable and reliable explanations for decisions made by AI systems. In addition to providing an overview of the state of the art in this area, we identify some of the most important issues that need to be addressed and on which research should be focused.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Explainable Artificial Intelligence (XAI) · Artificial Intelligence in Healthcare and Education · Radiomics and Machine Learning in Medical Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science, Middlesex College, Western University, London, ON N6A 5B7, Canada
Funding
Natural Sciences and Engineering Research Council of Canada
References (85)
Show source-provided references
1. Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai10.1016/j.inffus.2019.12.012 ↗
2. Jung, H., and Oh, Y. (2021, January 10–17). Towards better explanations of class activation mapping. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00137 ↗
3. Peeking inside the black-box: A survey on explainable artificial intelligence (xai)10.1109/ACCESS.2018.2870052 ↗
4. Deep learning for chest radiology: A review10.1007/s40134-019-0333-9 ↗
5. Ausawalaithong, W., Thirach, A., Marukatat, S., and Wilaiprasitporn, T. (2018, January 21–24). Automatic lung cancer prediction from chest X-ray images using the deep learning approach. Proceedings of the 11th Biomedical Engineering International Conference (BMEICON), Chiang Mai, Thailand.10.1109/BMEiCON.2018.8609997 ↗
6. Deep multiscale convolutional feature learning for weakly supervised localization of chest pathologies in X-ray images10.1007/978-3-030-00919-9_31 ↗
7. Learning hierarchical attention for weakly-supervised chest X-ray abnormality localization and diagnosis
8. Clinically accurate chest X-ray report generation
9. Automated radiology report generation using conditioned transformers10.1016/j.imu.2021.100557 ↗
10. Explainable deep learning for pulmonary disease and coronavirus COVID-19 detection from X-rays10.1016/j.cmpb.2020.105608 ↗
11. Cao, J., and Li, X. (2021). A 3D 2D convolutional neural network model for hyperspectral image classification. arXiv.10.1155/2021/1759111 ↗
12. Convolutional neural network in network (cnnin): Hyperspectral image classification and dimensionality reduction10.1049/iet-ipr.2017.1375 ↗
13. Ahmed, S.B., Naz, S., Razzak, M.I., and Yousaf, R. (2017, January 3–5). Deep learning based isolated arabic scene character recognition. Proceedings of the 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), Nancy, France.10.1109/ASAR.2017.8067758 ↗
14. Simonyan, K., Vedaldi, A., and Zisserman, A. (2014, January 14–16). Deep inside convolutional networks: Visualising image classification models and saliency maps. Proceedings of the 2nd International Conference on Learning Representations, ICLR, Banff, AB, Canada.
15. Xue, Y., Xu, T., Long, L.R., Xue, Z., Antani, S., Thoma, G.R., and Huang, X. (2018, January 16–20). Multimodal recurrent model with attention for automated radiology report generation. Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2018, Granada, Spain.10.1007/978-3-030-00928-1_52 ↗
16. Automatic arabic image captioning using rnn-lstm-based language model and cnn
17. Evolutionary recurrent neural network for image captioning10.1016/j.neucom.2020.03.087 ↗
18. Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R.L., and Shpanskaya, K.S. (February, January 27). Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
19. Chen, Z., Song, Y., Chang, T.-H., and Wan, X. (2020, January 19–20). Generating radiology reports via memory-driven transformer. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online.10.18653/v1/2020.emnlp-main.112 ↗
20. Working memory underpins cognitive development, learning, and education10.1007/s10648-013-9246-y ↗
21. Galassi, A., Lippi, L., and Torroni, P. (2019). Attention, please! A Critical Review of Neural Attention Models in Natural Language Processing. arXiv, Available online: http://arxiv.org/abs/1902.02181.
22. Xue, Y. (2019). Attention based image compression post-processing convlutional neural network. CVPR Workshops, Computer Vision Foundation/IEEE.
23. Show, attend and tell: Neural image caption generation with visual attention
24. Spatial transformer networks
25. Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., and Chua, T.-S. (2017, January 21–26). Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.667 ↗
26. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA.
27. Shang, Y., Xu, N., Jin, Z., and Yao, X. (2021, January 20–22). Capsule network based on self-attention mechanism. Proceedings of the 2021 13th International Conference on Wireless Communications and Signal Processing (WCSP), Changsha, China.10.1109/WCSP52459.2021.9613717 ↗
28. Berg, A., O’Connor, M., and Cruz, M.T. (September, January 30). Keyword transformer: A self-attention model for keyword spotting. Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czech Republic.10.21437/Interspeech.2021-1286 ↗
29. Definitions, methods, and applications in interpretable machine learning10.1073/pnas.1900654116 ↗
30. Rajpurkar, P., Irvin, J., Ball, R.L., K, Y.B.Z., Mehta, H., Duan, T., Ding, D., Bagul, A., and Langlotz, C.P. (2018). Deep learning for chest radiograph diagnosis: A retrospective comparison of the chexnext algorithm to practicing radiologists. PLoS Med., 15.10.1371/journal.pmed.1002686 ↗
31. Multi-attention and incorporating background information model for chest X-ray image report generation10.1109/ACCESS.2019.2947134 ↗
32. Hoffer, E., and Ailon, N. (2015). Deep Metric Learning Using Triplet Network, SIMBAD.10.1007/978-3-319-24261-3_7 ↗
33. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
34. Can i outperform a junior resident? comparison of deep neural network to first-year radiology residents for identification of pneumothorax10.1007/s10140-020-01767-4 ↗
35. Sdfn: Segmentation-based deep fusion network for thoracic disease classification in chest X-ray images10.1016/j.compmedimag.2019.05.005 ↗
36. Khakzar, A., Albarqouni, S., and Navab, N. (2019, January 13–17). Learning interpretable features via adversarially robust optimization. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32226-7_88 ↗
37. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.74 ↗
38. Lesion location attention guided network for multi-label thoracic disease classification in chest X-rays10.1109/JBHI.2019.2952597 ↗
39. Covxnet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization10.1016/j.compbiomed.2020.103869 ↗
40. Covidgr dataset and covid-sdnet methodology for predicting COVID-19 based on chest X-ray images10.1109/JBHI.2020.3037127 ↗
41. Lin, T.-C., and Lee, H.-C. (2020, January 14–16). COVID-19 chest radiography images analysis based on integration of image preprocess, guided grad-cam, machine learning and risk management. Proceedings of the 4th International Conference on Medical and Health Informatics, Kamakura City, Japan.10.1145/3418094.3418096 ↗
42. Chattopadhyay, A., Sarkar, A., Howlader, P., and Balasubramanian, V.N. (2018, January 12–15). Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, WACV 2018, Lake Tahoe, NV, USA.10.1109/WACV.2018.00097 ↗
43. Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the Computer Vision—ECCV 2014, Zurich, Switzerland.10.1007/978-3-319-10593-2 ↗
44. Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M.A. (2015). Striving for simplicity: The all convolutional net. arXiv.
45. Precup, D., and Teh, Y.W. (2017, January 6–11). Axiomatic attribution for deep networks. Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia.
46. Benchmarking saliency methods for chest X-ray interpretation10.1038/s42256-022-00536-x ↗
47. Karim, M.R., Döhmen, T., Cochez, M., Beyan, O., Rebholz-Schuhmann, D., and Decker, S. (2020, January 16–19). Deepcovidexplainer: Explainable COVID-19 diagnosis from chest X-ray images. Proceedings of the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Seoul, Republic of Korea.10.1109/BIBM49941.2020.9313304 ↗
48. Wang, H., Wang, Z., Du, M., Yang, F., Zhang, Z., Ding, S., Mardziel, P., and Hu, X. (2020, January 14–19). Score-cam: Score-weighted visual explanations for convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00020 ↗
49. Desai, S., and Ramaswamy, H.G. (2020, January 1–5). Ablation-cam: Visual explanations for deep convolutional network via gradient-free localization. Proceedings of the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass, CO, USA.10.1109/WACV45572.2020.9093360 ↗
50. Assessment of convolutional neural networks for automated classification of chest radiographs10.1148/radiol.2018181422 ↗
51. Park, J., Kwak, I.-Y., and Lim, C. (2021). A deep learning model with self-supervised learning and attention mechanism for COVID-19 diagnosis using chest X-ray images. Electronics, 10.10.3390/electronics10161996 ↗
52. Wang, K., Zhang, X., and Huang, S. (2019, January 18–21). Kgznet: Knowledge-guided deep zoom neural networks for thoracic disease classification. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine, San Diego, CA, USA.10.1109/BIBM47256.2019.8982943 ↗
53. Learning to detect chest radiographs containing pulmonary lesions using visual attention networks10.1016/j.media.2018.12.007 ↗
54. Huang, Z., and Fu, D. (2019, January 24–26). Diagnose chest pathology in X-ray images by learning multi-attention convolutional neural network. Proceedings of the IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China.10.1109/ITAIC.2019.8785431 ↗
55. Guan, Q., Huang, Y., Zhong, Z., Zheng, Z., Zheng, L., and Yang, Y. (2018). Diagnose like a radiologist: Attention guided convolutional neural network for thorax disease classification. arXiv.
56. Ypsilantis, P.-P., and Montana, G. (2017). Learning what to look in chest X-rays with a recurrent visual attention model. arXiv.
57. Ahsan, M.M., Nazim, R., Siddique, Z., and Huebner, P. (2021). Detection of COVID-19 patients from ct scan and chest X-ray data using modified mobilenetv2 and lime. Healthcare, 9.10.3390/healthcare9091099 ↗
58. Kamal, M.S., Chowdhury, L., Dey, N., Fong, S.J., and Santosh, K. (2021, January 17–20). Explainable AI to Analyze Outcomes of Spike Neural Network in COVID-19 Chest X-rays. Proceedings of the 2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Melbourne, Australia.10.1109/SMC52423.2021.9658745 ↗
59. Dixit, A., Mani, A., and Bansal, R. (2021, January 7–8). Covidetect-desvm: Explainable framework using differential evolution algorithm with svm classifier for the diagnosis of COVID-19. Proceedings of the 2021 4th International Conference on Recent Developments in Control, Automation Power Engineering (RDCAPE), Noida, India.10.1109/RDCAPE52977.2021.9633679 ↗
60. Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks10.1007/s10489-020-01900-3 ↗
61. Teixeira, L., Pereira, R.M., Bertolini, D., Oliveira, L.S., Nanni, L., Cavalcanti, G., and Costa, Y. (2021). Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images. Sensors, 21.10.3390/s21217116 ↗
62. A ensemble methodology for automatic classification of chest X-rays using deep learning10.1016/j.compbiomed.2022.105442 ↗
63. COVID-19 symptoms detection based on nasnetmobile with explainable ai using various imaging modalities
64. Bassi, P.R., and Cavalli, A. (2022). ISNet: Costless and Implicit Image Segmentation for Deep Classifiers, with Application in COVID-19 Detection. arXiv.10.21203/rs.3.rs-1390236/v1 ↗
65. Samsom, Q. (2021). Generating explanations for chest medical scan pneumonia predictions. Covid Inf. Commons Stud. Pap. Chall., Available online: https://academiccommons.columbia.edu/doi/10.7916/d8-t9np-xk59.
66. A deep convolutional neural network for COVID-19 detection using chest X-rays10.1007/s42600-021-00132-9 ↗
67. Pedro, B., and de Faissol, A.R. (2021). COVID-19 detection using chest X-rays: Is lung segmentation important for generalization?. arXiv.
68. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., and Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE, 10.10.1371/journal.pone.0130140 ↗
69. Explaining nonlinear classification decisions with deep taylor decomposition10.1016/j.patcog.2016.11.008 ↗
70. Layer-wise relevance propagation: An overview
71. Lu, J., Xiong, C., Parikh, D., and Socher, R. (2017, January 21–26). Knowing when to look: Adaptive attention via A visual sentinel for image captioning. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.345 ↗
72. Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., and Zhang, L. (2018, January 18–22). Bottom-up and top-down attention for image captioning and VQA. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00636 ↗
73. Fang, H., Gupta, S., Iandola, F.N., Srivastava, R.K., Deng, L., Dollár, P., Gao, J., He, X., Mitchell, M., and Platt, J.C. (2015, January 7–12). From captions to visual concepts and back. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298754 ↗
74. Zhang, Z., Chen, P., Sapkota, M., and Yang, L. (2017). Tandemnet: Distilling knowledge from medical images using diagnostic reports as optional semantic references. Medical Image Computing and Computer Assisted Intervention—MICCAI 2017, Springer International Publishing.10.1007/978-3-319-66179-7_37 ↗
75. Wang, X., Peng, Y., Lu, L., Lu, Z., and Summers, R.M. (2018, January 18–22). Tienet: Text-image embedding network for common thorax disease classification and reporting in chest X-rays. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00943 ↗
76. Lee, H., Kim, S.T., and Ro, Y.M. (2019, January 17). Generation of multimodal justification using visual word constraint model for explainable computer-aided diagnosis. Proceedings of the Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support, Shenzhen, China.10.1007/978-3-030-33850-3_3 ↗
77. Kim, B., Wattenberg, M., Gilmer, J., Cai, C.J., Wexler, J., Viégas, F.B., and Sayres, R. (2018, January 10–15). Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmaessan, Stockholm, Sweden.
78. Clough, J.R., Öksüz, I., Puyol-Antón, E., Ruijsink, B., King, A.P., and Schnabel, J.A. (2019, January 13–17). Global and local interpretability for cardiac mri classification. Proceedings of the 22nd International Conference MICCAI, Shenzhen, China.10.1007/978-3-030-32251-9_72 ↗
79. Kingma, D.P., and Welling, M. (2014). Auto-encoding variational bayes. arXiv.
80. Understanding and interpreting machine learning in medical image computing applications
81. Concept attribution: Explaining cnn decisions to physicians10.1016/j.compbiomed.2020.103865 ↗
82. An interpretable deep hierarchical semantic convolutional neural network for lung nodule malignancy classification10.1016/j.eswa.2019.01.048 ↗
83. Schneider, J., and Vlachos, M. (2020). Reflective-net: Learning from explanations. arXiv.
84. Improving deep learning performance by using explainable artificial intelligence (xai) approaches10.1007/s44163-021-00008-y ↗
85. Zhou, J., Gandomi, A.H., Chen, F., and Holzinger, A. (2021). Evaluating the quality of machine learning explanations: A survey on methods and metrics. Electronics, 10.10.3390/electronics10050593 ↗