AI Matches Dermatologists in Assessing Squamous Cell Carcinoma Aggressiveness in Sweden

Every year, more than 10,000 people in Sweden are diagnosed with squamous cell carcinoma, the second most common type of skin cancer in the country. Its incidence is rapidly increasing and usually appears in sun-exposed areas such as the head and neck, particularly affecting people with skin damaged by UV radiation accumulated over the years.

AI Shows Promise as Noninvasive Tool for Pre-Surgical Skin Cancer Evaluation in Sweden

Now, a study led by dermatologist and associate professor Sam Polesie of the University of Gothenburg shows that artificial intelligence (AI) could become a key tool for assessing the aggressiveness of these tumors before surgery.

Although the clinical diagnosis of this cancer is usually straightforward, the real challenge lies in the preoperative evaluation. Determining whether a tumor is more or less aggressive directly influences surgical treatment: aggressive tumors require more extensive and rapid interventions, while less aggressive tumors can be treated with less invasive procedures.

Currently, in Sweden—and many other countries—biopsies are not routinely performed to confirm tumor type and aggressiveness before surgery. This highlights the value of noninvasive tools, such as AI-powered image analysis , that can provide reliable information without the need to remove tissue.

Artificial intelligence at the level of experts

The research team trained an AI system with 1,829 close-up clinical images of confirmed squamous cell carcinomas. They then evaluated its ability to classify tumors into three levels of aggressiveness, comparing its results with the assessments of seven experienced dermatologists.

The findings, published in the Journal of the American Academy of Dermatology International, reveal that the AI ​​performed almost identically to the physician group. However, the agreement between the dermatologists’ own assessments was only moderate, highlighting the difficulty of these types of clinical decisions.

The study also identified two key features associated with more aggressive tumors: an ulcerated skin surface and flat lesions. These signals doubled the likelihood that the tumor belonged to the highest levels of aggressiveness. Despite the enthusiasm for AI in medicine, Polesie cautions that its practical impact on healthcare remains limited. The key, he says, is accurately identifying the cases where these technologies can make a real difference.

“We believe one of these areas is the preoperative evaluation of suspected skin cancer cases, where a more nuanced assessment can influence decision-making,” explains Polesie. Although the model still requires further testing and fine-tuning , the researcher sees it as a promising step toward a more useful and responsible integration of artificial intelligence into the Swedish healthcare system.

__

(Featured image by Miraxh Tereziu via Unsplash)

DISCLAIMER: This article was written by a third party contributor and does not reflect the opinion of Born2Invest, its management, staff or its associates. Please review our disclaimer for more information.

This article may include forward-looking statements. These forward-looking statements generally are identified by the words “believe,” “project,” “estimate,” “become,” “plan,” “will,” and similar expressions. These forward-looking statements involve known and unknown risks as well as uncertainties, including those discussed in the following cautionary statements and elsewhere in this article and on this site. Although the Company may believe that its expectations are based on reasonable assumptions, the actual results that the Company may achieve may differ materially from any forward-looking statements, which reflect the opinions of the management of the Company only as of the date hereof. Additionally, please make sure to read these important disclosures.

First published in GACETA MEDICA. A third-party contributor translated and adapted the article from the original. In case of discrepancy, the original will prevail.

Although we made reasonable efforts to provide accurate translations, some parts may be incorrect. Born2Invest assumes no responsibility for errors, omissions or ambiguities in the translations provided on this website. Any person or entity relying on translated content does so at their own risk. Born2Invest is not responsible for losses caused by such reliance on the accuracy or reliability of translated information. If you wish to report an error or inaccuracy in the translation, we encourage you to contact us.