The iSeg AI platform matches or outperforms physicians in segmenting lung tumors on CT scans, aiding radiation therapy planning.
Key Details
- 1iSeg was developed by Northwestern Medicine researchers for lung tumor segmentation.
- 2Tested on CT scans, iSeg matched or exceeded physician performance in outlining tumor margins.
- 3In some cases, the AI identified tumor regions missed by doctors.
- 4iSeg was trained and validated on a multi-institutional dataset from nine centers, featuring hundreds of CT scans plus manual segmentations.
- 5Experts believe this tool could enhance precision in radiation therapy.
Why It Matters
Accurate tumor segmentation is critical for effective radiation therapy planning. AI solutions like iSeg may improve treatment precision, reduce physician workload, and uncover areas potentially overlooked by human experts.
Source
Health Imaging
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.