An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network

Abstract

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Automated grading of acne vulgaris by deep learning with convolutional neural networks

“…Some groups have reported promising results using neural networks for acne classification . One study classified acne into seven categories using a pre‐trained model .…”

Deep Neural Network Based Artificial Intelligence Assisted Diagnosis of Bone Scintigraphy for Cancer Bone Metastasis

“…Then, we proposed a multi-input convolutional neural network (CNN) which can accept multiple images as input. Previous studies indicate that fine-tuning with pre-trained networks is an effective method for training CNNs (16,17). In this study, several ImageNet pretrained networks are explored and ResNet-50 was been chosen to extract high-level features from input images.…”

AcneNet - A Deep CNN Based Classification Approach for Acne Classes

“…A Confusion Matrix [19] is a table that is often used to describe the performance of a classification model in test data for which the actual values are known. A confusion matrix [8] for a binary classifier reports the number of false positive (FP), false negative (FN), true positive (TP), and true negative (TN). In the case of multiple classes, there can be Confusion Matrix of n x n (n > 2) levels.…”

“…The traditional diagnosis method referred to as manual observation and acne calculation is labor-intensive, timeconsuming and subjective to the expert's experience and ability [8]. Also, a long training period is required in this method.…”