High Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data (original) (raw)
Related papers
Towards Synthetic Generation of Clinical Rosacea Images with GAN Models
2022 33rd Irish Signals and Systems Conference (ISSC)
Computer-aided skin disease diagnosis has recently attracted much attention in the scientific and medical research community due to advances in computer vision and machine learning algorithms. These methodologies essentially rely on large datasets collected from hospitals and medical professionals. Data scarcity is a vital problem in the medical domain, especially facial skin conditions, due to privacy concerns. For instance, some facial skin conditions, e.g. Rosacea, require observation of the entire face, which reveals the patient's identity. Rosacea is a lamentably neglected skin condition in the computer-aided diagnosis research community, due to the limited availability of Rosacea datasets. Hence, there is a need for exploring alternative ways to deal with the limited available data for Rosacea. A common approach to expanding small datasets is to utilise augmentation techniques. One of the most powerful augmentation methods in machine learning is Generative Adversarial Networks (GANs). Recently, GANs, principally the variants of StyleGAN, have successfully generated synthetic facial images. In this paper, a small dataset of a particular skin disease, Rosacea, with 300 images is used to examine the potential of a variant of StyleGAN known as StyleGAN2-ADA. The preliminary experiments and evaluations show promising signs towards addressing the data scarcity for computer-aided Rosacea diagnosis.
Generative Adversarial Networks for anonymous Acneic face dataset generation
arXiv (Cornell University), 2022
It is well known that the performance of any classification model is effective if the dataset used for the training process and the test process satisfy some specific requirements. In other words, the more the dataset size is large, balanced, and representative, the more one can trust the proposed model's effectiveness and, consequently, the obtained results. Unfortunately, large-size anonymous datasets are generally not publicly available in biomedical applications, especially those dealing with pathological human face images. This concern makes using deep-learning-based approaches challenging to deploy and difficult to reproduce or verify some published results. In this paper, we suggest an efficient method to generate a realistic anonymous synthetic dataset of human faces with the attributes of acne disorders corresponding to three levels of severity (i.e. Mild, Moderate and Severe). Therefore, a specific hierarchy StyleGAN-based algorithm trained at distinct levels is considered. To evaluate the performance of the proposed scheme, we consider a CNN-based classification system, trained using the generated synthetic acneic face images and tested using authentic face images. Consequently, we show that an accuracy of 97,6% is achieved using InceptionResNetv2. As a result, this work allows the scientific community to employ the generated synthetic dataset for any data processing application without restrictions on legal or ethical concerns. Moreover, this approach can also be extended to other applications requiring the generation of synthetic medical images. We can make the code and the generated dataset accessible for the scientific community.
Synthetic Skin Cancer Image Data Generation Using Generative Adversarial Neural Network
International Journal of Multidisciplinary Studies and Innovative Technologies, 2021
In this study, synthetic data generating method using generative adversarial neural network (GAN) for the skin cancer types malignant melanoma and basal-cell carcinoma is presented. GAN is a neural network where two synthetic networks compete. The generator attempts to generate data similar to those measured and the discriminator attempts to classify data as dummy or real. Using medical data in studies is a difficult task due to legal and ethical restrictions. Most of the available data is classified because of patient consent and available data in most cases is not labeled, low quality and/or low quantity. Recent GAN systems can generate labeled high quantity data without any personal discriminative information. In this paper, we used skin cancer images in The International Skin Imaging Collaboration (ISIC) database that have been used for discriminator training. To test our generated images applicability in the medical field studies we have conducted a Turing test with medical experts in various medical fields. Our results indicate that the generated data obtained with our method is a valuable alternative for real medical data.
Multi-Class Skin Problem Classification Using Deep Generative Adversarial Network (DGAN)
Computational Intelligence and Neuroscience, 2022
The lack of annotated datasets makes the automatic detection of skin problems very difficult, which is also the case for most other medical applications. The outstanding results achieved by deep learning techniques in developing such applications have improved the diagnostic accuracy. Nevertheless, the performance of these models is heavily dependent on the volume of labelled data used for training, which is unfortunately not available. To address this problem, traditional data augmentation is usually adopted. Recently, the emergence of a generative adversarial network (GAN) seems a more plausible solution, where synthetic images are generated. In this work, we have developed a deep generative adversarial network (DGAN) multi-class classifier, which can generate skin problem images by learning the true data distribution from the available images. Unlike the usual two-class classifier, we have developed a multi-class solution, and to address the class-imbalanced dataset, we have take...
IEEE Access
Skin cancer, particularly the malignant melanoma subtype, is widely recognized as a highly lethal form of cancer characterized by abnormal melanocyte cell growth. However, diagnosing and classifying skin lesions, as well as automatically recognizing malignant tumors from dermoscopy images, present significant challenges. To address this challenge, our study employs variants of Convolutional Neural Networks (CNNs) to effectively diagnose and classify various skin lesion types using the latest benchmark datasets ISIC 2019 and 2020. The dataset underwent rigorous preprocessing, which involves employing advanced Generative Artificial Intelligence (AI) techniques i.e., Generative Adversarial Networks (GANs) and Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN), for augmentation. These generative techniques are carefully evaluated and compared for their effectiveness. Our CNN-based approach involves aggregating results from multiple transfer learning models, including VGG16, VGG19, SVM along with a hybrid model in combination of VGG19 and SVM. On ISIC 2019, we have achieved promising accuracies of 92% for VGG16 and 93% for VGG19. Notably, the hybrid VGG19+SVM model exhibits the highest accuracy of 96%. On ISIC 2020, VGG16, VGG19, and SVM achieves accuracies of 90%, 92%, and 92%, respectively. Our findings underscore the potential of generative AI for augmentation, and the efficacy of CNN-based transfer learning models in improving skin cancer classification accuracy.
Biomolecules
Corneal diseases are the most common eye disorders. Deep learning techniques are used to perform automated diagnoses of cornea. Deep learning networks require large-scale annotated datasets, which is conceded as a weakness of deep learning. In this work, a method for synthesizing medical images using conditional generative adversarial networks (CGANs), is presented. It also illustrates how produced medical images may be utilized to enrich medical data, improve clinical decisions, and boost the performance of the conventional neural network (CNN) for medical image diagnosis. The study includes using corneal topography captured using a Pentacam device from patients with corneal diseases. The dataset contained 3448 different corneal images. Furthermore, it shows how an unbalanced dataset affects the performance of classifiers, where the data are balanced using the resampling approach. Finally, the results obtained from CNN networks trained on the balanced dataset are compared to those ...
Skin Disease Analysis With Limited Data in Particular Rosacea: A Review and Recommended Framework
IEEE Access
Recently, the rapid advancements in Deep Learning and Computer Vision technologies have introduced a new and exciting era in the field of skin disease analysis. However, there are certain challenges in the roadmap towards developing such technologies for real-life applications that must be investigated. This study considers one of the key challenges in data acquisition and computation, viz. data scarcity. Data scarcity is a central problem in acquiring medical images and applying machine learning techniques to train Convolutional Neural Networks for disease diagnosis. The main objective of this study is to explore the possible methods to deal with the data scarcity problem and to improve diagnosis with small datasets. The challenges in data acquisition for a few lamentably neglected skin conditions such as rosacea are an excellent instance to explore the possibilities of improving computer-aided skin disease diagnosis. With data scarcity in mind, the possible techniques explored and discussed include Generative Adversarial Networks, Meta-Learning, Few-Shot classification, and 3D face modelling. Furthermore, the existing studies are discussed based on skin conditions considered, data volume and implementation choices. Some future research directions are recommended.
Acne Detection Through AI Model For Nothern Indian Region
The eighth most prevalent skin condition worldwide, acne is normally assessed by dermatologists in a clinical setting.There's a huge number of people in Northern India who are suffering with this acne problem , so for providing a solution to it we collaborated with Chandigarh University to create a deep learning model that can evaluate the severity of acne from selfie photographs as precisely as dermatologists and give the results accordingly. The model was made available as a Smartphone application (android and Ios both) , giving patients a simple way to evaluate and monitor the effectiveness of their acne therapy. It is common knowledge that any classification model will perform well if the datasets used for training and testing meet certain criteria. The more one can trust the effectiveness of the given model and, accordingly, the more the dataset size is large, balanced, and representative Sadly, large-scale anonymous datasets are rarely made publically accessible in biomedical applications, especially those that work with diseased photographs of the human face. This issue makes it tricky to adopt deep learning-based methods and difficult to replicate or confirm some reported results. In this study, we propose a quick technique for creating a collection of anonymous, realistic human faces with attributes of three different severity levels of acne diseases and also we have created our own dataset for the skin images of different types of people having different types of acne specially from Northern India. To reduce extraneous background, we used OpenCV models to detect facial landmarks, which were subsequently used to extract important skin patches from selfie photographs. We present a new picture rolling augmentation strategy to address CNN models' spatial sensitivity. Conceptually, causes acne lesions to show in more locations in the training photos and improves the generalization of the CNN model on test images. As a result, this study enables the scientific community to use the developed synthetic dataset for any data processing application without regard for legal or ethical problems. Furthermore, this approach can be expanded to other applications that need the production of synthetic medical pictures. We can make the code and generated dataset available to the scientific community. This is, to the best of our knowledge, the first deep learning-based solution for acne assessment using selfie photos.
Contrast Media & Molecular Imaging
Skin cancer is one of the most serious forms of the disease, and it can spread to other parts of the body if not detected early. Therefore, it is crucial to diagnose and treat skin cancer patients at an early stage. Due to the fact that a manual diagnosis of skin cancer is both time-consuming and expensive, an incorrect diagnosis is made due to the high degree of similarity between the various skin lesions. Improved categorization of multi-class skin lesions requires the development of automated diagnostic systems. We offer a fully automated method for classifying several skin lesions by fine-tuning the deep learning models, namely VGG16, ResNet50, and ResNet101. Prior to model creation, the training dataset should undergo data augmentation using traditional image transformation techniques and generative adversarial networks (GANs) to prevent class imbalance issues that may lead to model overfitting. In this study, we investigate the feasibility of creating dermoscopic images that h...
IRJET, 2020
Skin problems not only injure physical health but also induce psychological problems, especially for patients whose faces have been damaged or even disgorged. Using smart devices, most of the people are able to obtain convenient clinical images of their face skin condition. On the other hand, the convolution neural networks (CNNs) have achieved near or even better performance than human beings in the imaging field. Therefore, this paper studied different CNN algorithms for face skin disease classification based on the clinical images. First, from Xiangya_Derm, which is, to the best of our knowledge, China's largest clinical image dataset of skin diseases, we established a dataset that contains 2656 face images belonging to six common skin diseases [seborrhoea kurtosis (SK), actinic kurtosis (AK), rosacea (ROS), lupus erythematosus (LE), basal cell carcinoma (BCC), and squamous cell carcinoma (SCC)].We performed studies using five mainstream network algorithms to classify these diseases in the dataset and compared the results. Then, we performed studies using an independent dataset of the same disease types, but from other body parts, to perform transfer learning on our models. Comparing the performances, the models that used transfer learning achieved a higher average precision and recall for almost all structures. In the test dataset, which included 388 facial images, the best model achieved 92.9%, 89.2%, and 84.3% recalls for the LE, BCC, and SK, respectively, and the mean recall and precision reached 77.0% and 70.8%. INDEX TERMS: Deep learning, CNN, facial skin disease, medical image processing.