Artificial intelligence (AI) models have been shown to surpass human experts in diagnosing ovarian cancer from ultrasound images, according to a groundbreaking international study led by researchers at Sweden’s Karolinska Institutet. The findings, published in Nature Medicine, highlight the potential of AI to revolutionize cancer diagnostics.
Superior Diagnostic Accuracy
The study evaluated neural network models trained on over 17,000 ultrasound images from 3,652 patients across 20 hospitals in eight countries. The AI achieved an accuracy rate of 86.3% in distinguishing between benign and malignant ovarian lesions, outperforming human experts (82.6%) and less experienced examiners (77.7%).
“These results suggest that AI can provide significant support in diagnosing ovarian cancer, particularly in complex cases or regions with a shortage of ultrasound experts,” said Professor Elisabeth Epstein, lead researcher from Karolinska Institutet and Stockholm South General Hospital.
Streamlining Patient Care
The AI models also demonstrated the ability to reduce the need for expert referrals. In a simulated triage scenario, AI assistance cut referrals by 63% and reduced misdiagnoses by 18%, paving the way for faster and more cost-effective care.
“This innovation could relieve pressure on healthcare systems while improving outcomes for patients with ovarian lesions,” said Filip Christiansen, doctoral student and co-author of the study.
Future Potential and Next Steps
Despite the promising results, the researchers emphasize the need for further studies to fully understand the AI models’ clinical applications and limitations. Ongoing prospective trials at Södersjukhuset aim to assess the AI tool’s real-world safety and effectiveness.
As reported by medicalxpress, future plans include a randomized multicenter study to evaluate the tool’s impact on patient management and healthcare costs. With continued research, the team believes AI-based diagnostic tools could become a cornerstone of modern healthcare, optimizing resources and supporting specialists worldwide.