Scientists have developed a new dermatology algorithm to improve the diagnosis of skin cancer and other types of skin lesions
The obvious concern with changes in the skin is whether the changes are a symptom of an underlying disorder or malignancy. A skin lesion refers to any area of the skin that has different characteristics from the surrounding skin. Changes may include:
- colour,
- shape,
- size, and
- texture.
Skin lesions are very common and often appear following damage such as sunburn, allergic contact or infection. Other changes may be the consequence of other conditions such as diabetes, autoimmune conditions, genetic disorders or excess alcohol 'liver spots'. The vast majority of skin lesions are benign and harmless, but some of them can be malignant or a sign of premalignancy, meaning they have the potential to evolve into skin cancer. An accurate diagnosis is therefore critical.
Better skin diagnostic accuracy
A new deep learning algorithm has been developed to help doctors identify the different types of skin lesions and improve diagnosis. Doctors who specialise in skin diseases (dermatologists) typically classify skin lesions based based on a range of different observations. These observations include:
- Clinical images,
- Microscopic images and
- Meta-data (such as the age and gender of the patient)
Algorithms that fuse the above information together can support this classification. An international research team has now developed an algorithm that classifies skin lesions more accurately than previous algorithms by using an improved data fusion process.
Deep learning algorithms can support the classification of skin lesions by fusing all the information together and evaluating it. Several such algorithms are already being developed. However, to apply these learning algorithms in the clinic, they need to be further improved to achieve higher diagnostic accuracy.
Fusing the data improves diagnostic accuracy
A research team led by PD Dr. Tobias Lasser (pictured) from the Technical University of Munich (TUM) has now developed a new learning algorithm - FusionM4Net - that displays higher average diagnostic accuracy than previous algorithms. The code for FusionM4Net is freely available (https://ciip.in.tum.de/software.html). The new algorithm uses a so-called multi-modal multi-stage data fusion process for multi-label skin lesion classification.
• Multi-modal: The learning algorithm includes three different types of data: Clinical images, microscopic images of the suspicious skin lesion, and patient metadata.
• Multi-label: The researchers trained the algorithm for multi-label skin classification, i.e. it can differentiate between five different categories of skin lesions.
• Multi-stage: The new algorithm first fuses together the available image data and then the patient’s metadata. This two-stage process allows image data and metadata to be weighted in the algorithm's decision-making process. This distinguishes FusionM4Net considerably from previous algorithms in this field, which merge all data at once.
outperforming all other state-of-the-art algorithms
To evaluate the diagnostic accuracy of an algorithm, it can be compared to the best existing classification for the used dataset, for which the value 100 percent is assigned. The average diagnostic accuracy of FusionM4Net improved to 78.5 percent through the multi-stage fusion process, outperforming all other state-of-the-art algorithms with which it was compared.
When will the new skin diagnostic test be available?
To foster reproducibility, a publicly available dataset was used to train the algorithm. However, in dermatology, datasets are not standardized everywhere. Depending on the clinic, different types of images and patient information may be available. Thus, for actual clinical deployment, the algorithm must be able to handle the type of data that is available at each specific clinic.
Together with the Department of Dermatology and Allergology at the University Hospital of LMU Munich, the research team is working intensely on making the algorithm operational for future clinical routine. To this end, the team is currently integrating numerous datasets that have been standardized for this clinic.
Dr Tobias Lasser says, “Future routine clinical use of algorithms with high diagnostic accuracy might help ensure that rare diseases are also detected by less experienced physicians and it might mitigate decisions affected by stress or fatigue”. In this way, learning algorithms could help improve the overall level of medical care.
