By Stephen Beech
Artificial intelligence is better than doctors at spotting ovarian cancer, according to new research.
Scientists say state-of-the-art robot technology can outperform human experts at identifying killer diseases in ultrasound images.
Researchers based in Sweden have developed and validated neural network models able to differentiate between benign and malignant ovarian lesions.
The team trained and tested the AI on more than 17,000 ultrasound images from 3,652 patients across 20 hospitals in eight countries.
They then compared the models’ diagnostic capacity with a large group of experts and less experienced ultrasound examiners.
The findings, published in the journal Nature Medicine, showed that the AI models outperformed both expert and non-expert examiners at identifying ovarian cancer, achieving an accuracy rate of 86.3%, compared to 82.6% and 77.7% for the expert and non-expert examiners respectively.
Dr. Elisabeth Epstein, of the Karolinska Institutet, said: “Ovarian tumors are common and are often detected by chance.
“There is a serious shortage of ultrasound experts in many parts of the world, which has raised concerns of unnecessary interventions and delayed cancer diagnoses.
“We therefore wanted to find out if AI can complement human experts.”
She said the findings suggest that neural network models can offer “valuable support in the diagnosis of ovarian cancer, especially in difficult-to-diagnose cases and in settings where there’s a shortage of ultrasound experts.”
Researchers say the AI models can also reduce the need for expert referrals.
In a simulated triage situation, the AI support cut the number of referrals by 63% and the misdiagnosis rate by 18% which can lead to faster and more cost-effective care for patients with ovarian lesions.
Despite the promising results, the research team stressed that further studies are needed before the full potential of the neural network models and their clinical limitations are fully understood.
Study joint first author Filip Christiansen, a doctoral student in Dr. Epstein’s research group at Karolinska Institute, said: “With continued research and development, AI-based tools can be an integral part of tomorrow’s healthcare, relieving experts and optimizing hospital resources.
“But we need to make sure that they can be adapted to different clinical environments and patient groups.”
The team is now conducting prospective clinical studies to evaluate the everyday clinical safety and usefulness of the AI tool.
