Algorithm that performs as accurately as dermatologists

February 12, 2021

A study has now been presented that boosts the evidence for using AI solutions in skin cancer diagnostics. With an algorithm they devised themselves, scientists at the University of Gothenburg show the capacity of technology to perform at the same level as dermatologists in assessing the severity of skin melanoma.

The study, published in the Journal of the American Academy of Dermatology, and its results are the work of a research group at the Department of Dermatology and Venereology at Sahlgrenska Academy, University of Gothenburg.

The study was conducted at Sahlgrenska University Hospital in Gothenburg. Its purpose was, through machine learning (ML), to train an algorithm to determine whether skin melanoma is invasive and there is a risk of it spreading (metastatizing), or whether it remains at a growth stage in which it is confined to the epidermis, with no risk of metastasis.

The algorithm was trained and validated on 937 dermatoscopic images of melanoma, and subsequently tested on 200 cases. All the cases included were diagnosed by a dermatopathologist.

The majority of melanomas are found by patients rather than doctors. This suggests that, in most cases, diagnosis is relatively easy. Before surgery, however, it is often much more difficult to determine the stage the melanoma has reached.

To make the classifications more accurate, dermatologists use dermatoscopes -- instruments that combine a type of magnifying glass with bright illumination. In recent years, interest in using ML for skin tumor classifications has increased, and several publications have shown that ML algorithms can perform on par with, or even better than, experienced dermatologists.

The current study is now giving a further boost to research in this field. When the same classification task was performed by the algorithm on the one hand and seven independent dermatologists on the other, the result was a draw.

"None of the dermatologists significantly outperformed the ML algorithm," states Sam Polesie, a researcher at the University of Gothenburg and specialist doctor at Sahlgrenska University Hospital, who is the corresponding author of the study.

In a developed form, the algorithm could serve as support in the task of assessing the severity of skin melanoma before surgery. The classification affects how extensive an operation needs to be, and is therefore important for both the patient and the surgeon.

"The results of the study are interesting, and the hope is that the algorithm can be used as clinical decision support in the future. But it needs refining further, and prospective studies that monitor patients over time are necessary, too," Polesie concludes.
Title: Discrimination between Invasive and In situ Melanomas Using a Convolutional Neural Network,

Title (supplementary text about the ML algorithm): Supplemental material -- Discrimination between Invasive and In situ Melanomas Using a Convolutional Neural Network,

University of Gothenburg

Related Melanoma Articles from Brightsurf:

Boosting treatments for metastatic melanoma
University of Cincinnati clinician-scientist Soma Sengupta, MD, PhD, says that new findings from her and Daniel Pomeranz Krummel's, PhD, team might have identified a treatment-boosting drug to enhance effectiveness of therapies for metastatic cancer and make them less toxic, giving patients a fighting chance at survival and improved quality of life.

A promising new tool in the fight against melanoma
An Edith Cowan University (ECU) study has revealed that a key blood marker of cancer could be used to select the most effective treatment for melanoma.

New targets for melanoma treatment
A collaborative study led by Monash University's Biomedicine Discovery Institute and the Olivia Newton-John Cancer Research Institute (ONJCRI) has uncovered new markers (HLA-associated peptides) that are uniquely present on melanoma tumours and could pave the way for therapeutic vaccines to be developed in the fight against melanoma.

Innovative smartphone-camera adaptation images melanoma and non-melanoma
An article published in the Journal of Biomedical Optics (JBO), ''Point-of-care, multispectral, smartphone-based dermascopes for dermal lesion screening and erythema monitoring,'' shows that standard smartphone technology can be adapted to image skin lesions, providing a low-cost, accessible medical diagnostic tool for skin cancer.

Antihistamines may help patients with malignant melanoma
Can a very common allergy medicine improve survival among patients suffering from the serious skin cancer, malignant melanoma?

Blood test for deadly eye melanoma
A simple blood test could soon become the latest monitoring tool for the early detection of melanoma in the eye.

Analysis of melanoma in US by age groups
This study used registry data to determine annual rates of melanoma in pediatric, adolescent, young adult and adult age groups, and the findings suggest an apparent decrease among adolescent and young adults between 2006 and 2015 but increases in older adults.

Vitamin D dials down the aggression in melanoma cells
Vitamin D influences the behaviour of melanoma cells in the lab by making them less aggressive, Cancer Research UK scientists have found.

B cells linked to immunotherapy for melanoma
Immunotherapy uses our body's own immune system to fight cancer.

Five things to know about melanoma
'Five things to know about ... melanoma' in CMAJ (Canadian Medical Association Journal) provides a brief overview of this malignant skin cancer for physicians and patients.

Read More: Melanoma News and Melanoma Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to