Observer study: impact of case complexities and physician characteristics on AI-assisted treatment response assessment in bladder cancer
This study explores the impact of physician experience, specialty, and institutional background on the performance of AI-assisted assessment of treatment responses in bladder cancer patients. Utilizing pre- and post-chemotherapy CTU scans from 123 patients, 17 physicians with varying levels of experience and from different specialties and institutions assessed 157 lesion pairs. The lesion pairs were divided into easy and difficult cases to evaluate the AI system's effectiveness in different scenarios. The study revealed that AI assistance significantly improved diagnostic accuracy in easy cases for both experienced and inexperienced physicians, with a great benefit observed in radiologists and oncologists. In difficult cases, the AI's impact was present but less pronounced, indicating that while AI can enhance performance in challenging situations, its effectiveness is more limited in complex cases. Additionally, the study found that institutional background influenced the effectiveness of AI assistance, suggesting that certain training or cultural factors may affect physicians’ trust in AI recommendations. The findings underscore the potential of AI to support clinical decision-making in bladder cancer treatment response assessment, particularly in less complex cases. However, they also highlight the need for tailored implementation and user training of AI systems to maximize their effectiveness across different medical specialties and institutions. By aligning AI tools with the specific needs and expertise of physicians, their confidence and efficacy in using AI in complex medical scenarios can be enhanced.
Authors
- D. H. Sun (ORCID: https://orcid.org/0000-0001-6578-5142)
- Wesley T. Kerr (ORCID: https://orcid.org/0000-0002-5546-5951)
- Alon Z. Weizer (ORCID: https://orcid.org/0000-0002-0504-2969)
- Elaine M. Caoili (ORCID: https://orcid.org/0000-0001-5303-8844)
- Sean Woolen (ORCID: https://orcid.org/0000-0003-4951-2173)
- Heang‐Ping Chan (ORCID: https://orcid.org/0000-0001-7777-9006)
- Lauren Pomerantz (ORCID: https://orcid.org/0000-0002-2917-961X)
- Monika Joshi (ORCID: https://orcid.org/0000-0003-4286-8492)
- Prasad R. Shankar (ORCID: https://orcid.org/0000-0002-6488-8382)
- Martha M. Matuszak (ORCID: https://orcid.org/0000-0002-4129-1030)
- Ajjai Alva (ORCID: https://orcid.org/0000-0002-1898-3522)
- Yousef Zakharia (ORCID: https://orcid.org/0000-0001-9480-2626)
- Nathaniel B. Meyer (ORCID: https://orcid.org/0000-0002-9600-0288)
- Isaac R. Francis (ORCID: https://orcid.org/0000-0003-1953-7740)
- Rohan Garje (ORCID: https://orcid.org/0000-0002-7244-5602)
- Galina Kirova-Nedyalkova (ORCID: https://orcid.org/0000-0002-0158-8972)
- Daniel Barkmeier (ORCID: https://orcid.org/0000-0002-0061-6994)
- Matthew S. Davenport (ORCID: https://orcid.org/0000-0001-7943-7851)
- Dean Elhag
- Kimberly L. Shampain (ORCID: https://orcid.org/0000-0002-6094-1676)
- Richard H. Cohan (ORCID: https://orcid.org/0000-0003-3156-7037)
- Phillip L. Palmbos (ORCID: https://orcid.org/0000-0002-3134-2965)
- Lubomir M. Hadjiiski (ORCID: https://orcid.org/0000-0003-2069-8066)
- Chuan Zhou (ORCID: https://orcid.org/0000-0002-0609-1658)
Institutions
- University of Iowa (US)
- Pennsylvania State University (US)
- University of Michigan (US)
- Tokuda Hospital (BG)
- Michigan United (US)
- University of Pittsburgh Medical Center (US)
Publication Details
- Published
- 2025-04-04
- DOI
- https://doi.org/10.1117/12.3049033
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00