Fig 2 - available via license: Creative Commons Attribution-NoDerivatives 4.0 International
Content may be subject to copyright.
Example skin images of Monkeypox, Chickenpox, Smallpox, Cowpox, Measles, and healthy cases (first to sixth rows, respectively) from our database.
Source publication
Monkeypox has emerged as a fast-spreading disease around the world and an outbreak has been reported in 42 countries so far. Although the clinical attributes of Monkeypox are similar to that of Smallpox, skin lesions and rashes caused by Monkeypox often resemble that of other pox types, e.g., Chickenpox and Cowpox. This scenario makes an early diag...
Context in source publication
Context 1
... for several pox classes, we hardly find images under "Creative Commons licenses," thus collected images that fall under "Commercial & other licenses." Therefore, we include a list as supplementary material that includes the uniform resource locator (URL) of the source, access date, and photo credit (if any) for all our collected images. In Fig. 2, we show some example images from our ...
Similar publications
An outbreak of Monkeypox has been reported in 75 countries so far, and it is spreading in fast pace around the world. The clinical attributes of Monkeypox resemble those of Smallpox, while skin lesions and rashes of Monkeypox often resemble those of other poxes, for example, Chickenpox and Cowpox. These similarities make Monkeypox detection challen...
Citations
... Additionally, a novel binary hybrid algorithm was proposed by Abdelhamid et al. [30], which utilizes meta-heuristic optimization algorithms for feature selection, significantly improving the classification accuracy of monkeypox images. The project presented in [31] aimed to build the Monkeypox Skin Image Dataset 2022, addressing the scarcity of monkeypox skin image data that creates a bottleneck in using machine learning for monkeypox detection. Moreover, to enable accurate diagnoses and treatment, Alakus et al. [32] analyzed DNA sequences of MPV (causing monkeypox) and HPV (causing warts) and performed their classification using deep learning. ...
Background/Objectives:The emergence of monkeypox outside its endemic region in Africa has raised significant concerns within the public health community due to its rapid global dissemination. Early clinical differentiation of monkeypox from similar diseases, such as chickenpox and measles, presents a challenge. The Monkeypox Skin Lesion Dataset (MSLD) used in this study comprises monkeypox skin lesions, which were collected primarily from publicly accessible sources. The dataset contains 770 original images captured from 162 unique patients. The MSLD includes four distinct class labels: monkeypox, measles, chickenpox, and normal. Methods: This paper presents an ensemble model for classifying the monkeypox dataset, which includes transformer models and support vector machine (SVM). The model development process begins with an evaluation of seven convolutional neural network (CNN) architectures. The proposed model is developed by selecting the top four models based on evaluation metrics for performance. The top four CNN architectures, namely EfficientNetB0, ResNet50, MobileNet, and Xception, are used for feature extraction. The high-dimensional feature vectors extracted from each network are then concatenated and optimized before being inputted into the SVM classifier. Results: The proposed ensemble model, in conjunction with the SVM classifier, achieves an accuracy of 95.45b%. Furthermore, the model demonstrates high precision (95.51%), recall (95.45%), and F1 score (95.46%), indicating its effectiveness in identifying monkeypox lesions. Conclusions: The results of the study show that the proposed hybrid framework achieves robust diagnostic performance in monkeypox detection, offering potential utility for enhanced disease monitoring and outbreak management. The model’s high diagnostic accuracy and computational efficiency indicate that it can be used as an additional tool for clinical decision support.
... The highest performing Xception and DenseNet169 DL models were combined using the majority vote approach to create an ensemble model with 87.13% accuracy. Islam et al. [32,33] addressed data limitations by web scraping, curating the Monkeypox Skin Image Dataset 2022. Their analysis of skin images in six categories resulted in ShuffleNet-V2 achieving the highest success with 79% accuracy. ...
... A mobile application was introduced in [14] to classify monkeypox from other diseases; two datasets were applied with different images for these classes: the first dataset had 228 images; 102 were monkeypox images, whereas the others were different [10]. The second dataset was in the form of images with 770 images, of which 279 were monkeypox images, and the remaining 491 were other data with division of training set as 60%, validation set as 20%, and testing set as 20% [15]. They employed nine layers and used values in the units where the first layer consisted of 1024, and the last consisted of 4 only. ...
... As depicted in [15], the presented web scraping allows any user to find and use a detailed database of images of skin conditions and healthy skin. Pictures of contaminated skin include six similar diseases: infectious disease, like the classic symptoms of monkeypox and caused by the orthopoxvirus. ...
... Dataset untuk penelitian ini diambil dari website Kaggle(https://www.kaggle.com/datasets/nazmussadat 013/monkey-pox-dataset), sebuah platform yang menyediakan berbagai dataset untuk keperluan analisis dan penelitian [19]. Dataset yang digunakan terdiri dari 900 gambar yang menunjukkan gejala penyakit cacar monyet dan 900 gambar penyakit dengan gejala yang hampir serupa dengan cacar monyet, namun bukan penyakit cacar monyet. ...
... Arafat Hussain et al. [19] used web scraping to gather images of skin infected with monkeypox, chickenpox, smallpox, cowpox, measles, and healthy skin [20]. The dataset is publicly available on Kaggle by the name of "Monkeypox Skin Image Dataset 2022". ...
... Madhukar Dwivedi et al. [13] proposed pre-trained models like ResNet50, EfficientNetB3 and EfficientNetB7 to work with the Monkeypox Skin Image Dataset 2022 [20]. The Effi-cientNetB3 model produced the best results with an accuracy of 0.87 and an F1-score of 0.9. ...
In the midst of the continuing difficulties presented by the COVID-19 pandemic, the possible emergence of illnesses such as monkeypox places an additional and significant load on public health services that are already under pressure. Conventional diagnostic methods for monkeypox, reliant on polymerase chain reaction tests and biochemical assays on lesion swabs suffer from drawbacks such as patient discomfort and resource limitations, particularly in economically distressed areas of Western and Central Africa. This work investigates the application of deep learning techniques, specifically transfer learning using three trained CNN frameworks (ResNet50V2, MobileNetV2, and Xception), to accurately identify monkeypox. Utilizing the "Monkeypox Skin Lesion Dataset," images of patients’ skin lesions are augmented and incorporated into the training and validation of the models. Additional layers for classifying monkeypox and non-monkeypox images are introduced. Evaluation metrics, with a focus on accuracy and F1-score, showcase the superior performance of the ResNet50V2-based model (0.9874 accuracy, F1-score of 0.99), followed by Xception (0.9546 accuracy, F1-score of 0.95), and MobileNetV2 (0.9452 accuracy, F1-score of 0.94). Comparative analysis with previous works in the field underscores the improved results achieved in this research. The proposed models offer a promising avenue for early monkeypox detection, contributing to effective preventive measures against its spread. Looking ahead, we aim to deploy the developed MobileNetV2-based model as a web application, leveraging its lightweight architecture and notable accuracy. This initiative is intended to provide people in rural areas with a cost-effective and easily accessible solution for the early detection of monkeypox, contributing to improved healthcare in resource-constrained settings.
... • Monkeypox Skin Image Dataset 2022: Islam et al. (2022) Ahsan et al. (2022) generated this dataset also through webscraping from websites, newspapers, and online portals and publicly shared samples using internet search engines. This dataset contains 171 original web-scrapped images, including 43 monkeypox images, 47 chickenpox images, 17 measles images, and 54 healthy-skin images. ...
Under the Autonomous Mobile Clinics (AMCs) initiative, the AI Clinics on Mobile (AICOM) project is developing, open sourcing, and standardising health AI technologies on low-end mobile devices to enable health-care access in least-developed countries (LDCs). As the first step, we introduce AICOM-MP, an AI-based monkeypox detector specially aiming for handling images taken from resource-constrained devices. We have developed AICOM-MP with the following principles: minimisation of gender, racial, and age bias; ability to conduct binary classification without over-relying on computing power; capacity to produce accurate results irrespective of images' background, resolution, and quality. AICOM-MP has achieved state-of-the-art (SOTA) performance. We have hosted AICOM-MP as a web service to allow universal access to monkeypox screening technology, and open-sourced both the source code and the dataset of AICOM-MP to allow health AI professionals to integrate AICOM-MP into their services.
... In addition, the Monkeypox Skin Lesion Dataset (MSLD) [13] has become an abstract reaction to the recent outbreak of monkeypox. It is a dataset that contains Web-scrapped images of monkeypox and non-monkeypox cases (measles and chickenpox), as well as images of various body parts (face, neck, hand, arm, leg). ...
... This resulted in the MobileNetV2 model having the best accuracy compared with the other modules. Islam et al. [13] proposed a web-scraping-based data collection system for a monkeypox skin lesion. In the classification task, ResNet50, Inception-V3, DenseNet121, MnasNet-A1, MobileNet-V2, ShuffleNet-V2, and SqueezeNet models were used. ...
The recent outbreak of monkeypox has raised significant concerns in the field of public health, primarily because it has quickly spread to over 40 countries outside of Africa. Detecting monkeypox in its early stages can be quite challenging because its symptoms can resemble those of chickenpox and measles. However, there is hope that potential use of computer-assisted tools may be used to identify monkeypox cases rapidly and efficiently. A promising approach involves the use of technology, specifically deep learning methods, which have proven effective in automatically detecting skin lesions when sufficient training examples are available. To improve monkeypox diagnosis through mobile applications, we have employed a particular neural network called MobileNetV2, which falls under the category of Fully Connected Convolutional Neural Networks (FCCNN). It enables us to identify suspected monkeypox cases accurately compared to classical machine learning approaches. The proposed approach was evaluated using the recall, precision, F score, and accuracy. The experimental results show that our architecture achieves an accuracy of 0.99%, a Recall of 1.0%, an F-score of 0.98%, and a Precision of 0.95%. We believe that such experimental evaluation will contribute to the medical domain and many use cases.
... Towhidul Islam et al (T. Islam, Hussain, Uddin, et al., 2022) conducted research using web scraping to create a thorough database of skin images affected by Measles, Cowpox, ChickenPox, Monkey Pox, and Smallpox. Their database has the most actual photos per class and the most enhanced images per class when compared to other comparable data sets. To verify the disease in the photo, they used the pr ...
In May 2022, it has received by WHO reports from non-endemic countries on cases of monkey pox disease. Monkey pox is a rare zoonotic disease caused by infection with the monkeypox virus that belongs to the genus orthopoxvirus and the family poxviridae, and also the variola virus. This study aims to classify patients who have contracted the monkey pox virus. We modeled an analysis of monkey pox disease and conducted comparisons utilizing a dataset from Kaggle consisting of a CSV file with records for 25,000 patients. The monkey pox dataset was analyzed using the correlation coefficient and the number of target variables. Machine learning (ML) methods are used for classification by utilizing the K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) algorithms. This study resulted in the highest classifier Gradient Boosting (GB) algorithm with an accuracy value of 71%. then the accuracy obtained by Support Vector Machine (SVM) is 69%, Random Forest (RF) accuracy is 68%, and finally K-Nearest Neighbor (KNN) obtains 63% accuracy. This ML method is expected to analyze monkey pox disease so that it helps the country and government, especially the health field in assessing, identifying, and being able to take appropriate action against monkey pox disease.
... Symptoms of measles, cowpox, chickenpox, smallpox, and monkeypox can be seen in photographs of afflicted skin [31]. The Monkeypox Skin Lesion Dataset was assembled by the authors of [32] using images of measles, chickenpox, and monkeypox skin lesions (MSLD). Most of these images originated from web pages that were open to the public. ...
While the world is working quietly to repair the damage caused by COVID-19’s widespread transmission, the monkeypox virus threatens to become a global pandemic. There are several nations that report new monkeypox cases daily, despite the virus being less deadly and contagious than COVID-19. Monkeypox disease may be detected using artificial intelligence techniques. This paper suggests two strategies for improving monkeypox image classification precision. Based on reinforcement learning and parameter optimization for multi-layer neural networks, the suggested approaches are based on feature extraction and classification: the Q-learning algorithm determines the rate at which an act occurs in a particular state; Malneural networks are binary hybrid algorithms that improve the parameters of neural networks. The algorithms are evaluated using an openly available dataset. In order to analyze the proposed optimization feature selection for monkeypox classification, interpretation criteria were utilized. In order to evaluate the efficiency, significance, and robustness of the suggested algorithms, a series of numerical tests were conducted. There were 95% precision, 95% recall, and 96% f1 scores for monkeypox disease. As compared to traditional learning methods, this method has a higher accuracy value. The overall macro average was around 0.95, and the overall weighted average was around 0.96. When compared to the benchmark algorithms, DDQN, Policy Gradient, and Actor–Critic, the Malneural network had the highest accuracy (around 0.985). In comparison with traditional methods, the proposed methods were found to be more effective. Clinicians can use this proposal to treat monkeypox patients and administration agencies can use it to observe the origin and current status of the disease.
... In August 2022, the preprint "A Web-scraped Skin Image Database of Monkeypox, Chickenpox, Smallpox, Cowpox, and Measles" was uploaded to BiorXiv publication repository. In this case, one of the authors is affiliated with Boston Children's Hospital, Harvard Medical School [34]. At first glance, it is easy to wonder whether the diagnosis relevance of the images was validated by medical doctors or not. ...
The self-proclaimed first publicly available dataset of Monkeypox skin images consists of medically irrelevant images extracted from Google and photography repositories through a process denominated web-scrapping. Yet, this did not stop other researchers from employing it to build Machine Learning (ML) solutions aimed at computer-aided diagnosis of Monkeypox and other viral infections presenting skin lesions. Neither did it stop the reviewers or editors from publishing these subsequent works in peer-reviewed journals. Several of these works claimed extraordinary performance in the classification of Monkeypox, Chickenpox and Measles, employing ML and the aforementioned dataset. In this work, we analyse the initiator work that has catalysed the development of several ML solutions, and whose popularity is continuing to grow. Further, we provide a rebuttal experiment that showcases the risks of such methodologies, proving that the ML solutions do not necessarily obtain their performance from the features relevant to the diseases at issue.
