'Jack-of-all-trades' AI model outperforms numerous others in CT-related tasks

Researchers have developed a single artificial intelligence model that can handle multiple medical imaging tasks simultaneously—a breakthrough that challenges the prevailing industry assumption that specialized AI systems always outperform generalist ones. The model, tested on CT scans, matched or exceeded the performance of narrowly focused competitors while requiring significantly less computational power and training data. If the approach scales beyond radiology, it could fundamentally reshape how hospitals deploy AI, consolidating dozens of specialized systems into a handful of versatile ones.

Radiology Business·Mar 8