Deep Learning Classifier with Patient’s Metadata of Dermoscopic Images in Malignant Melanoma Detection

Abstract

Background: Incidence of skin cancer is one of the global burdens of malignancies that increase each year, with melanoma being the deadliest one. Imaging-based automated skin cancer detection still remains challenging owing to variability in the skin lesions and limited standard dataset availability. Recent research indicates the potential of deep convolutional neural networks (CNN) in predicting outcomes from simple as well as highly complicated images. However, its implementation requires high-class computational facility, that is not feasible in low resource and remote areas of health care. There is potential in combining image and patient's metadata, but the study is still lacking. Objective: We want to develop malignant melanoma detection based on dermoscopic images and patient's metadata using an artificial intelligence (AI) model that will work on low-resource devices. Methods:We used an open-access dermatology repository of International Skin Imaging Collaboration (ISIC) Archive dataset consist of 23,801 biopsy-proven dermoscopic images. We tested performance for binary classification malignant melanomas vs nonmalignant melanomas. From 1200 sample images, we split the data for training (72%), validation (18%), and testing (10%). We compared CNN with image data only (CNN model) vs CNN for image data combined with an artificial neural network (ANN) for patient's metadata (CNN+ANN model). Results: The balanced accuracy for CNN+ANN model was higher (92.34%) than the CNN model (73.69%). Combination of the patient's metadata using ANN prevents the overfitting that occurs in the CNN model using dermoscopic images only. This small size (24 MB) of this model made it possible to run on a medium class computer without the need of cloud computing, suitable for deployment on devices with limited resources. Conclusion:The CNN+ANN model can increase the accuracy of classification in malignant melanoma detection even with limited data and is promising for development as a screening device in remote and low resources health care.

Web-Based Skin Cancer Assessment and Classification Using Machine Learning and Mobile Computerized Adaptive Testing in a Rasch Model: Development Study

“…For instance, a report that sniffer dogs are able to detect MM at a curable stage was first described in the United Kingdom by William et al [53]. Thereafter, studies focusing on the utility of dog olfaction for screening or diagnosing different medical conditions, such as COVID-19, malignancies, diabetes, Parkinson disease, seizures, certain hormonal and enzymatic defects [54][55][56][57][58][59][60][61][62][63][64][65][66][67], and melanoma [53], ensued. Machine learning models based on CNNs were applied to extract the region of interest of the skin lesion data set and showed that training CNN models with the region of interest-extracted data set could improve the accuracy of the prediction [55][56][57].…”

Recent Advances in Diagnosis of Skin Lesions Using Dermoscopic Images Based on Deep Learning

“…It consists of 10,015 dermoscopic dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive [120]. A dermo- [103] 12,500 D 7 P [24], [29], [48], [58], [59], [104]-[107] ISIC 2017 [108] ∼2,000 D 3 P [46], [85], [104], [109] ISBI 2016 [110] 1,279 D 2 P [28], [76], [77], [90], [101], [111]- [113] ISIC Archive(2018) [114] 23,665 D 7 P [44], [49], [63], [115]- [119] HAM 10000 [120] 10,015 The interactive atlas of dermoscopy [132] (Atlas) dataset has 1,011 dermoscopic images (252 melanoma and 759 nevi cases), with 7-point checklist criteria. There are also 1,011 clinical color images corresponding to dermoscopic images.…”

Editorial: The Emerging Role of Artificial Intelligence in Dermatology

“…However, potential errors, poor/inconsistent image quality and insufficient data protection of AI still pose important barriers. Recently, ML and convolutional neural network (CNN) models that classify melanoma on histopathological or clinical images demonstrated ability to achieve exceedingly high sensitivities and diagnostic accuracies (20)(21)(22)(23)(24). ML models are also being trained using substantial data sets including more racially diverse data, making AI more accessible for use in remote and resourcelimited healthcare settings (20,25).…”

“…Recently, ML and convolutional neural network (CNN) models that classify melanoma on histopathological or clinical images demonstrated ability to achieve exceedingly high sensitivities and diagnostic accuracies (20)(21)(22)(23)(24). ML models are also being trained using substantial data sets including more racially diverse data, making AI more accessible for use in remote and resourcelimited healthcare settings (20,25). There is also a rise in smartphone applications with classifying the risk of photographed lesions or detecting malignant/premalignant lesions on histopathological images (26,27).…”