New AI system may be able to identify lung cancer type

NEW YORK: A new artificial intelligence (AI) system can accurately identify lung cancer types by analysing patients' tumours, scientists say.

The system, described in the journal Nature Medicine, could distinguish with 97 per cent accuracy between adenocarcinoma and squamous cell carcinoma -- two lung cancer types that experienced pathologists at times struggle to parse without confirmatory tests.

"Our study provides strong evidence that an AI approach will be able to instantly determine cancer subtype and mutational profile to get patients started on targeted therapies sooner," said Aristotelis Tsirigos, an associate professor at New York University (NYU) in the US.


The AI tool was also able to determine whether abnormal versions of 6 genes linked to lung cancer -- including EGFR, KRAS, and TP53 -- were present in cells, with an accuracy that ranged from 73 to 86 per cent depending on the gene.

Such genetic changes or mutations often cause the abnormal growth seen in cancer, but can also change a cell's shape and interactions with its surroundings, providing visual clues for automated analysis.


Determining which genes are changed in each tumour has become vital with the increased use of targeted therapies that work only against cancer cells with specific mutations, researchers said.

About 20 per cent of patients with adenocarcinoma, for instance, are known to have mutations in the gene epidermal growth factor receptor or EGFR, which can now be treated with approved drugs.

However, the genetic tests currently used to confirm the presence of mutations can take weeks to return results, researchers said.

The study found that about half of the small percentage of tumour images misclassified by the study AI programme were also misclassified by the pathologists, highlighting the difficulty in distinguishing between the two lung cancer types.

On the other hand, 45 out of 54 of the images misclassified by at least one of the pathologist in the study were assigned to the correct cancer type by the machine learning programme, suggesting that AI could offer a useful second opinion.

"In our study, we were excited to improve on pathologist-level accuracies, and to show that AI can discover previously unknown patterns in the visible features of cancer cells and the tissues around them," said Narges Razavian, an assistant professor at NYU.

The team plans to keep training its AI programme with data until it can determine which genes are mutated in a given cancer with more than 90 per cent accuracy, at which point they will begin seeking government approval to use the technology clinically, and in the diagnosis of several cancer types.