In brief

Optoacoustic mesoscopy in combination with machine learning analytical tools detect atopic dermatitis non-invasively with up to 97% accuracy.

© Pexels

Machine learning gets under the skin

24 Mar 2023

Researchers develop machine learning models for accurately diagnosing an inflammatory skin condition.

Bumps, flare-ups and redness—we identify skin conditions such as dermatitis as their symptoms manifest on the skin. However, researchers say tomorrow’s dermatological technologies could make more accurate diagnostics by ‘listening’ for changes beneath the surface of the skin.

Raster-scanning optoacoustic mesoscopy, or RSOM, is a painless way of extracting more information from the skin than conventional light-based techniques. “The acoustic pressure wave is detected by a transducer that is placed just above the skin surface,” explained Malini Olivo, who heads the Laboratory of Bio-optical Imaging at A*STAR’s Institute of Bioengineering and Bioimaging (IBB). These sound waves travel through the tissue and are picked up as electrical signals before being processed into images.

Next, machine learning (ML) tools can be used by dermatologists to survey thousands of RSOM image data points to distinguish healthy and diseased skin. “ML models can extract important image features automatically and use these features for subsequent processing,” Olivo said, adding that this approach could benefit patients with difficult-to-diagnose conditions such as atopic dermatitis (AD).

Together with researchers from the National Skin Centre and A*STAR’s Bioinformatics Institute (BII), Olivo spearheaded a project that integrated ML analytical tools with RSOM for detecting atopic dermatitis efficiently and accurately. To build their training dataset, the team recruited over 70 participants, including healthy individuals and those with AD. The researchers captured three-dimensional images of the participants’ skin with RSOM, which were graded based on AD severity by an experienced dermatologist.

The dataset with dermatologist scores was then used to train three ML models: random forest (RF), support vector machine (SVM), and convolutional neural network (CNN). These models span a variety of computational capabilities, with CNN performing the most comprehensive analysis (at the cost of additional computational time). Parameters such as blood volume, epidermal thickness and the ratio of bigger and smaller vasculature were also implemented in the training to optimise accuracy.

The group found that all three models could tell AD apart from healthy skin with up to 97% accuracy. Additionally, the random forest model could classify images from AD patients as being either mild or moderate to severe, with an accuracy of about 65%.

A bigger, more balanced training dataset could help improve these metrics, said Hwee Kuan Lee, a Senior Principal Investigator at BII’s Imaging Informatics division. “The limited data set is our main challenge, especially the unbalanced data of different AD severities which can easily lead to overfitting,” Lee added, explaining that while 26 patients had moderate AD, only eight patients had severe AD, throwing off the data balance.

The team is working on improving the sensitivity of their ML models and expanding the application landscape to include other inflammatory skin diseases. “We will also explore other deep learning frameworks to realise automatically useful feature extraction and high accuracy classifications,” Olivo shared.

The A*STAR-affiliated researchers contributing to this research are from the Institute of Bioengineering and Bioimaging (IBB) and the Bioinformatics Institute (BII).

Want to stay up to date with breakthroughs from A*STAR? Follow us on Twitter and LinkedIn!


Park, S., Saw, S.N., Li, X., Paknezhad, M., Coppola, D., et al. Model learning analysis of 3D optoacoustic mesoscopy images for the classification of atopic dermatitis, Biomedical Optics Express 12, 3671-3683 (2021) | article

About the Researchers

View articles

Malini Olivo

Distinguished Principal Scientist

A*STAR Skin Research Labs (A*SRL)
Malini Olivo is a Distinguished Principal Scientist at A*STAR Skin Research Labs (A*SRL) where she leads the Translational Biophotonics Laboratory. Concurrently, she is also an Adjunct Professor at the Lee Kong Chian School of Medicine, NTU; Department of Obstetrics & Gynaecology, National University Health System, NUS, Singapore; and Royal College of Surgeons Ireland, Dublin, Ireland. She obtained a PhD degree in Bio-Medical Physics in 1990 from University Malaya/University College London (UCL) and did her post-doctoral training between 1991 and 1995 at UCL, UK and both McMaster University and University of Toronto, Canada. Her current research interest is in medtech and nano-biophotonics and its applications in translational medicine. Her efforts include bridging the gap between cutting edge optical technologies and unmet clinical needs by developing in-house photonics-based devices for various industries. She has succeeded in obtaining competitive research funding of over USD 25 million to support her research in Singapore and overseas. She has published over 500 papers, three books and 20 book chapters, and filed close to 50 patents on technology platforms and devices. She is also the co- founder of three medtech companies. Furthermore, she holds many advisory international roles and is well recognised internationally for her research in biophotonics for her pioneering research contributions. She has conferred as the Fellow of Optical Society of America (OSA), Fellow of American Institute of Medical Bioengineering (AIMBE) and Fellow of Institute of Physics, UK.
View articles

Hwee Kuan Lee

Deputy Director (Talent & Training), Senior Principal Investigator

Bioinformatics Institute (BII)
Hwee Kuan Lee’s current research work involves the development of Artificial Intelligence (AI) research for clinical and biological applications. His laboratory focus on diverse research activities, including more basic AI centric research as well as AI applications. Theoretical AI development activities in Lee’s laboratory is mostly inspired by impactful clinical use cases. Clinical application areas include diagnostics in cancers, cardiology, dermatology and interventional radiology. In the area of biology, Lee’s laboratory develops bioinformatics pipelines in spatial omics and single cell analysis, and in the development of AI in protein science and drug discovery.

This article was made for A*STAR Research by Wildtype Media Group