JLE

European Journal of Dermatology

MENU

Unveiling the power of convolutional neural networks in melanoma diagnosis Volume 33, issue 5, September-October 2023

Figures


  • Figure 1.

  • Figure 2.

  • Figure 3.

  • Figure 4.

  • Figure 5.

  • Figure 6.

  • Figure 7.

  • Figure 8.

  • Figure 9.
Authors
1 Faculty of Medicine and Health Sciences, University of Antwerp, Wilrijk, Belgium
2 Operations Research Center, Massachusetts Institute of Technology, Boston, Massachusetts, USA
3 Faculty of Electrical Engineering and Computer Science, Technical University of Berlin, Berlin, Germany
4 Faculty of Medicine, Katholieke Universiteit Leuven, Leuven, Belgium
5 Faculty of Medicine and Dental Medicine, UCLouvain, Brussels, Belgium
6 Department of Plastic, Reconstructive and Aesthetic Surgery, Antwerp University Hospital, Antwerp, Belgium
7 Vascularized Composite Allotransplantation Laboratory, Center for Transplantation Sciences, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
8 Shriners Hospitals for Children-Boston, Boston, Massachusetts, USA
9 Division of Plastic and Reconstructive Surgery, Massachusetts General Hospital, Boston, Massachusetts, USA
* Reprints: Alexandre G. LellouchLoïc Van Dieren

Background

Convolutional neural networks are a type of deep learning algorithm. They are mostly applied in visual recognition and can be used for the identification of melanomas. Multiple studies have evaluated the performance of convolutional neural networks, and most algorithms match or even surpass the accuracy of dermatologists. However, only 23.8% of dermatologists have good or excellent knowledge of the topic. We believe that the lack of knowledge physicians experience regarding artificial intelligence is an obstacle to its clinical implementation.

Objectives

We describe how a convolutional neural network differentiates a benign from a malignant lesion.

Materials & Methods

We systematically searched the Web of Science, Medline (PubMed), and The Cochrane Library on the 9th February, 2022. We focused on articles describing the role and use of artificial intelligence in melanoma recognition between 2017 and 2022, using the following MeSH terms: “melanoma,” “diagnosis,” and “artificial intelligence”.

Results

Traditional machine learning algorithms comprise different parts which must preprocess, segment, extract features and classify the lesion into benign or malignant. Deep learning algorithms can perform these steps simultaneously, which significantly enhances efficiency. Convolutional neural networks include a convolutional layer, a pooling layer, and a fully connected layer. Convolutional and pooling layers extract features from the lesion and reduce computational power, whereas fully connected layers classify the image into two or more categories.

Conclusion

Additionally, we suggest that further studies should be performed to accelerate the clinical implementation of artificial intelligence, to create comprehensive datasets and to generate explainable algorithms.