Explainable Artificial Intelligence (XAI) for Oncological Ultrasound Image Analysis: A Systematic Review
Source abstract
Abstract
This review provides an overview of explainable AI (XAI) methods for oncological ultrasound image analysis and compares their performance evaluations. A systematic search of Medline Embase and Scopus between 25 March and 14 April 2024 identified 17 studies describing 14 XAI methods, including visualization, semantics, example-based, and hybrid functions. These methods primarily provided specific, local, and post hoc explanations. Performance evaluations focused on AI model performance, with limited assessment of explainability impact. Standardized evaluations incorporating clinical end-users are generally lacking. Enhanced XAI transparency may facilitate AI integration into clinical workflows. Future research should develop real-time methodologies and standardized quantitative evaluative metrics.
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
Image-Guided Surgery, Department of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands
Technical Medicine, Faculty of Mechanical, Maritime, and Materials Engineering, Delft University of Technology, Mekelweg 2, 2628 CD Delft, The Netherlands
References (55)
Show source-provided references
1. Grand View Research (2024, July 01). AI In Healthcare Market Size, Share & Trends Analysis Report by Component (Hardware, Services), by Application, by End-Use, by Technology, by Region, and Segment Forecasts, 2024–2030. Available online: https://www.grandviewresearch.com/industry-analysis/artificial-intelligence-ai-healthcare-market.
2. Sanskrutisathe (2024, September 03). AI in Healthcare Market Size and Growth. Available online: https://medium.com/@sanskrutisathe01/ai-in-healthcare-market-size-and-growth-2ae9b8463121.
3. World Health Organization (2024, September 03). Global Strategy on Human Resources for Health: Workforce 2030, Available online: https://apps.who.int/iris/bitstream/handle/10665/250368/9789241511131-eng.pdf.
4. Choi, M., Sempungu, J.K., Lee, E.H., and Lee, Y.H. (2024). Living longer but in poor health: Healthcare system responses to ageing populations in industrialised countries based on the Findings from the Global Burden of Disease Study 2019. BMC Public Health, 24.10.1186/s12889-024-18049-0 ↗
5. Atkinson, S., and Jackson, C. (2024, September 03). Three in Five Globally Say Their Healthcare System Is Overstretched. Available online: https://www.ipsos.com/en/three-five-globally-say-their-healthcare-system-overstretched.
6. Page, B., Irving, D., Amalberti, R., and Vincent, C. (2023). Health services under pressure: A scoping review and development of a taxonomy of adaptive strategies. BMJ Qual. Saf.10.1136/bmjqs-2023-016686 ↗
7. Bohr, A., and Memarzadeh, K. (2020). Chapter 2—The rise of artificial intelligence in healthcare applications. Artificial Intelligence in Healthcare, Academic Press.10.1016/B978-0-12-818438-7.00002-2 ↗
8. Machine Learning and AI in Cancer Prognosis, Prediction, and Treatment Selection: A Critical Approach10.2147/JMDH.S410301 ↗
9. The Economic Impact of Artificial Intelligence in Health Care: Systematic Review10.2196/16866 ↗
10. Pinto-Coelho, L. (2023). How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications. Bioengineering, 10.10.20944/preprints202311.1366.v1 ↗
11. Explainable AI in medical imaging: An overview for clinical practitioners—Saliency-based XAI approaches10.1016/j.ejrad.2023.110787 ↗
12. Explaining explainability: The role of XAI in medical imaging10.1016/j.ejrad.2024.111389 ↗
13. Singh, A., Sengupta, S., and Lakshminarayanan, V. (2020). Explainable Deep Learning Models in Medical Image Analysis. J. Imaging, 6.10.3390/jimaging6060052 ↗
14. On the Interpretability of Artificial Intelligence in Radiology: Challenges and Opportunities10.1148/ryai.2020190043 ↗
15. Hacker, P., and Passoth, J.H. (2022). Varieties of AI Explanations under the Law. From the GDPR to the AIA, and Beyond. xxAI—Beyond Explainable AI, Lecture Notes in Artificial Intelligence, Springer International Publishing.10.2139/ssrn.3911324 ↗
16. Antoniadi, A.M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B.A., and Mooney, C. (2021). Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review. Appl. Sci., 11.10.3390/app11115088 ↗
17. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI10.1016/j.inffus.2019.12.012 ↗
18. Linardatos, P., Papastefanopoulos, V., and Kotsiantis, S. (2020). Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy, 23.10.3390/e23010018 ↗
19. (2024, July 01). Next Move Strategy Consulting Explainable AI (XAI) Market. Available online: https://www.nextmsc.com/report/explainable-ai-market.
20. Jacovi, A. (2024, July 01). Trends in Explainable AI (XAI) Literature. Available online: https://medium.com/@alonjacovi/trends-in-explainable-ai-xai-literature-a1db485e871.
21. Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions10.1016/j.inffus.2024.102301 ↗
22. Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence10.1016/j.inffus.2023.101805 ↗
23. World Health Organization (2024, September 03). Global Cancer Burden Growing, Amidst Mounting Need for Services, Available online: https://www.who.int/news/item/01-02-2024-global-cancer-burden-growing--amidst-mounting-need-for-services.
24. Artificial Intelligence Applications for Biomedical Cancer Research: A Review
25. Jaber, N. (2022). Can Artificial Intelligence Help See Cancer in New, and Better, Ways?, National Cancer Institute.
26. Wijkhuizen, M., van Karnenbeek, L., Geldof, F., Ruers, T.J., and Dashtbozorg, B. (2024). Ultrasound tumor detection using an adapted Mask-RCNN with a continuous objectness score. Medical Imaging with Deep Learning, Available online: https://openreview.net/forum?id=IHmvNgX34A.
27. Natali, T., Wijkhuizen, M., Kurucz, L., Fusaglia, M., van Leeuwen, P.J., Ruers, T.J., and Dashtbozorg, B. (2024). Automatic real-time prostate detection in transabdominal ultrasound images. Medical Imaging with Deep Learning, Available online: https://openreview.net/forum?id=jh1KZ4cyWA.
28. Toward automatic surgical margin assessment using ultrasound imaging during breast cancer surgery10.1016/j.ejso.2022.11.323 ↗
29. Veluponnar, D., de Boer, L.L., Geldof, F., Jong, L.J.S., Da Silva Guimaraes, M., Vrancken Peeters, M.J.T., van Duijnhoven, F., Ruers, T., and Dashtbozorg, B. (2023). Toward intraoperative margin assessment using a deep learning-based approach for automatic tumor segmentation in breast lumpectomy ultrasound images. Cancers, 15.10.3390/cancers15061652 ↗
30. Geldof, F., Pruijssers, C.W., Jong, L.J.S., Veluponnar, D., Ruers, T.J., and Dashtbozorg, B. (2023). Tumor Segmentation in Colorectal Ultrasound Images Using an Ensemble Transfer Learning Model: Towards Intra-Operative Margin Assessment. Diagnostics, 13.10.3390/diagnostics13233595 ↗
31. Weld, A., Dixon, L., Anichini, G., Dyck, M., Ranne, A., Camp, S., and Giannarou, S. (2023). Identifying Visible Tissue in Intraoperative Ultrasound Images during Brain Surgery: A Method and Application. arXiv.
32. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis10.1016/j.media.2022.102470 ↗
33. (2024, September 03). Medline Embase Database. Available online: https://www.embase.com.
34. (2024, September 03). Scopus Bibliographic Database. Available online: https://www.scopus.com.
35. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews10.1186/s13643-021-01626-4 ↗
36. Visani, G. (2024, September 03). Explainable Machine Learning, XAI Review: Model Agnostic Tools. Available online: https://towardsdatascience.com/explainable-machine-learning-9d1ca0547ae0.
37. SThy-Net: A feature fusion-enhanced dense-branched modules network for small thyroid nodule classification from ultrasound images10.1007/s00371-023-02984-x ↗
38. RadFormer: Transformers with global–local attention for interpretable and accurate Gallbladder Cancer detection10.1016/j.media.2022.102676 ↗
39. Explaining a Deep Learning Based Breast Ultrasound Image Classifier with Saliency Maps10.15557/JoU.2022.0013 ↗
40. One step further into the blackbox: A pilot study of how to build more confidence around an AI-based decision system of breast nodule assessment in 2D ultrasound10.1007/s00330-020-07561-7 ↗
41. Multitask network for thyroid nodule diagnosis based on TI-RADS10.1002/mp.15724 ↗
42. Prostate cancer classification from ultrasound and MRI images using deep learning based Explainable Artificial Intelligence10.1016/j.future.2021.09.030 ↗
43. Karimzadeh, M., Vakanski, A., Xian, M., and Zhang, B. (2023, January 17–20). Post-Hoc Explainability of BI-RADS Descriptors in a Multi-Task Framework for Breast Cancer Detection and Segmentation. Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP), Rome, Italy.10.1109/MLSP55844.2023.10286006 ↗
44. A human-interpretable machine learning pipeline based on ultrasound to support leiomyosarcoma diagnosis10.1016/j.artmed.2023.102697 ↗
45. Martizzi, D., Huang, Y., Malik, B., and Ray, P.D. (2021, January 15–19). Breast mass detection and classification using PRISM™ eXplainable Network based Machine Learning (XNML™) platform for Quantitative Transmission (QT) ultrasound tomography. Proceedings of the Medical Imaging 2021: Ultrasonic Imaging and Tomography, Online.10.1117/12.2580975 ↗
46. Morris, J., Liu, Z., Liang, H., Nagala, S., and Hong, X. (2023, January 21–25). ThyExp: An explainable AI-assisted Decision Making Toolkit for Thyroid Nodule Diagnosis based on Ultra-sound Images. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, Birmingham, UK.10.1145/3583780.3615131 ↗
47. Prospective assessment of breast cancer risk from multimodal multiview ultrasound images via clinically applicable deep learning10.1038/s41551-021-00711-2 ↗
48. Explainable Ensemble Machine Learning for Breast Cancer Diagnosis Based on Ultrasound Image Texture Features10.3390/forecast4010015 ↗
49. Song, D., Yao, J., Jiang, Y., Shi, S., Cui, C., Wang, L., Wang, L., Wu, H., Tian, H., and Ye, X. (2023). A new xAI framework with feature explainability for tumors decision-making in Ultrasound data: Comparing with Grad-CAM. Comput. Methods Programs Biomed., 235.10.1016/j.cmpb.2023.107527 ↗
50. Tasnim, J., and Hasan, M.K. (2024). CAM-QUS guided self-tuning modular CNNs with multi-loss functions for fully automated breast lesion classification in ultrasound images. Phys. Med. Biol., 69.10.1088/1361-6560/ad1319 ↗
51. AIBx, Artificial Intelligence Model to Risk Stratify Thyroid Nodules10.1089/thy.2019.0752 ↗
52. Zhang, B., Vakanski, A., and Xian, M. (2021, January 25–28). Bi-Rads-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images. Proceedings of the 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), Gold Coast, QLD, Australia.10.1109/MLSP52302.2021.9596314 ↗
53. Enhancing gastrointestinal submucosal tumor recognition in endoscopic ultrasonography: A novel multi-attribute guided contextual attention network10.1016/j.eswa.2023.122725 ↗
54. Zhang, Y., Gu, S., Song, J., Pan, B., Bai, G., and Zhao, L. (2023). XAI Benchmark for Visual Explanation. arXiv.
55. Amann, J., Blasimme, A., Vayena, E., Frey, D., and Madai, V.I. (2020). Explainability for artificial intelligence in healthcare: A multidisciplinary perspective. BMC Med Inform. Decis. Mak., 20.10.1186/s12911-020-01332-6 ↗