Akademiliv

Sahlgrenska akademins nyheter

På Svenska
University of Gothenburg Logotype
  • News
  • Notices
  • Grants
  • About Akademiliv

Melanoma thickness equally hard for algorithms and dermatologists to judge

20 July, 2022

NEW STUDY. Assessing the thickness of melanoma is difficult, whether done by an experienced dermatologist or a well-trained machine-learning algorithm. A study from the University of Gothenburg shows that the algorithm and the dermatologists had an equal success rate in interpreting dermoscopic images.

In diagnosing melanoma, dermatologists evaluate whether it is an aggressive form (invasive melanoma), where the cancer cells grow down into the dermis and there is a risk of spreading to other parts of the body, or a milder form (melanoma in situ, MIS) that develops in the outer skin layer, the epidermis, only. Invasive melanomas that grow deeper than one millimeter into the skin are considered thick and, as such, more aggressive.

Importance of thickness

Melanomas are assessed by investigation with a dermatoscope — a type of magnifying glass fitted with a bright light. Diagnosing melanoma is often relatively simple, but estimating its thickness is a much greater challenge.

Sam Polesie, Institute of Clinical Sciences, Sahlgrenska Academy at the University of Gothenburg.
Photo: Private.

“As well as providing valuable prognostic information, the thickness may affect the choice of surgical margins for the first operation and how promptly it needs to be performed,” says Sam Polesie, associate professor (docent) of dermatology and venereology at Sahlgrenska Academy, University of Gothenburg, Polesie is also a dermatologist at Sahlgrenska University Hospital and the study’s first author.

Tie between man and machine

Using a web platform, 438 international dermatologists assessed nearly 1,500 melanoma images captured with a dermatoscope. The dermatologists’ results were then compared with those from a machine-learning algorithm trained in classifying melanoma depth.

Among the dermatologists, overall accuracy was 63% for correct classification of MIS, and 71% for that of invasive melanomas.

“Interestingly, professional background and experience in dermoscopy had no bearing on diagnostic accuracy in predicting melanoma thickness.

The area under the curve, which is a measurement ranging from 0 to 1 on performance was 0.83 for the pretrained machine learning algorithm and 0.85 for the combined AUC of the individual readers’. Collectively, the dermatologists’ assessment performed on par with an algorithm trained in distinguishing MIS and invasive melanomas,” Polesie says.

Hard to assess

Artificial Intelligence (AI) is making major leaps forward in health care. This technology is, in particular, expected to be capable of development as support for medical imaging ­­— that is, for doctors who assess and interpret images, such as X-rays and pictures of the retina and skin changes. The technology is also applicable to areas other than image recognition.

“Our study highlights the difficulties of correctly assessing melanoma thickness on the basis of dermoscopic images,” Polesie adds.

“In future studies, we aim to explore the usefulness of predefined dermoscopic structures for distinguishing . We also want to test whether clinical decision-making in this situation can be improved by means of machine-learning algorithms.”

The results are published in the Journal of the European Academy of Dermatology and Venereology (JEADV). The study was conducted in collaboration with researchers at the Medical University of Vienna, Austria.

Title: Assessment of melanoma thickness based on dermoscopy images: an open, web-based, international, diagnostic study

BY: ELIN LINDSTRÖM / MARGARETA GUSTAFSSON KUBISTA

By: Elin Lindström
Tagged With: cancer

HAPPY SUMMER!

The newsletter from Akademiliv will return on Wednesday, August 21st.

Contact your institute to add your event to the calendar in the Staff Portal

  • Biomedicine: Kristian Kvint: kalender@biomedicine.gu.se
  • Core Facilities: Amelie Karlsson: amelie.karlsson.2@gu.se
  • Clinical Sciences: Katarina Olinder Eriksson: klinvet@gu.se
  • Medicine: Nina Raun; kommunikation@medicine.gu.se
  • Neuroscience and Physiology: Josefin Bergenholtz; kommunikation@neuro.gu.se
  • Odontology: Johan Thompson; info@odontologi.gu.se
  • Sahlgrenska Academy’s Office and faculty-wide calendar events Åsa Ekvall; info@sahlgrenska.gu.se
  • Health and Care Sciences: Karin Mossberg; vardvetenskap@fhs.gu.se

Information from Sahlgrenska Academy Research Support Office

[UPDATED JUNE 2024]
The Sahlgrenska Academy Research Support Office provides an overview of upcoming and current calls, nominations and events in an information letter. This letter is updated on a monthly basis.
Current and previous newsletters are also available in the Staff Portal.

’20 minutes for researchers’ is back – see full spring program

During 20 minutes over Zoom, the Biomedical Library gives tips on tools and services that can facilitate your research everyday life.

More news

En personlig död (A Personal Death) – a chance to win Björn Fagerberg’s new book

27 May, 2024

NEW BOOK. During his career as a physician specializing in internal medicine, Björn Fagerberg has been involved in many end-of-life situations, …  

She is doing her residency in the US with a medical degree from Gothenburg

21 May, 2024

STUDENT. Doing a “residency” in orthopedics in the United States is an unattainable dream for many newly qualified American doctors. Now Janina Ka …  

Alba Corell reports from a high-level brain tumor meeting

20 May, 2024

COLUMN. The recent gathering of the Scandinavian Society of Neuro-oncology (SNOG) in Gothenburg has concluded. Professor Asgeir Jakola hosted and …  

From South Africa to Sweden: Collaborative Research Efforts Improving Pregnant Women’s Health

17 May, 2024

GLOBAL HEALTH. In the bustling Tygerberg University Hospital in Cape Town, a dedicated research team led by Lina Bergman, is on a mission to …  

Sara Bjursten and Anna Wenger are the recipients of the Assar Gabrielsson Prize 2024

17 May, 2024

AWARD. The Assar Gabrielsson Foundation has named Anna Wenger as the winner in the basic science research category and Sara Bjursten as the …  

A full day for PhD students focused on mental health

16 May, 2024

PHD STUDENTS. For the sixth time, PhD students at Sahlgrenska Academy were invited to PhD Day, organized by the Doctoral Student Council. The day …  

Kaj Blennow ranked highest in Sweden in neuroscience

16 May, 2024

AWARD. In this year's edition of the researcher ranking from Research.com in the field of neuroscience, Kaj Blennow is ranked 17th …  

Linda Wass is doing a postdoc at Stanford with ALF funding

14 May, 2024

ALF FUNDING. Biomedical Scientist Linda Wass has just settled in Stanford, California, where she will spend two years as a postdoc. She is the …  

Karin Nilsson wrote the Thesis of the Year at Sahlgrenska Academy in 2023

14 May, 2024

AWARD. Karin Nilsson, currently a postdoc at the Department of Internal Medicine and Clinical Nutrition, receives the faculty-wide Thesis of the …  

Some answers from the proposed members of the next Faculty Board

14 May, 2024

FACULTY ELECTIONS. The eight proposed members of the next Faculty Board hereby give some brief answers on how they want to contribute to the work …  

More news...

Sahlgrenska Academy

© University of Gothenburg
PO-Box 100, S-405 30 Gothenburg, Sweden
Phone: 00 46 31 786 0000

About the website

Elin Lindström is editor for Akademiliv.
Please feel free to send your ideas and comments to akademiliv@gu.se

Sign up for the Akademiliv newsletter:

Send you tips to Akademiliv

Do you have a suggestion for news, grants, seminars or an education?
Send an email to Elin Lindström Claessen