Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 1739 2024-02-26 09:33:01 |
2 layout Meta information modification 1739 2024-02-26 09:56:47 |

Video Upload Options

Do you have a full video?


Are you sure to Delete?
If you have any further questions, please contact Encyclopedia Editorial Office.
Arshed, M.A.; Rehman, H.A.; Ahmed, S.; Dewi, C.; Christanto, H.J. Deep Learning and Human Monkeypox. Encyclopedia. Available online: (accessed on 21 April 2024).
Arshed MA, Rehman HA, Ahmed S, Dewi C, Christanto HJ. Deep Learning and Human Monkeypox. Encyclopedia. Available at: Accessed April 21, 2024.
Arshed, Muhammad Asad, Hafiz Abdul Rehman, Saeed Ahmed, Christine Dewi, Henoch Juli Christanto. "Deep Learning and Human Monkeypox" Encyclopedia, (accessed April 21, 2024).
Arshed, M.A., Rehman, H.A., Ahmed, S., Dewi, C., & Christanto, H.J. (2024, February 26). Deep Learning and Human Monkeypox. In Encyclopedia.
Arshed, Muhammad Asad, et al. "Deep Learning and Human Monkeypox." Encyclopedia. Web. 26 February, 2024.
Deep Learning and Human Monkeypox

The DNA virus responsible for monkeypox, transmitted from animals to humans, exhibits two distinct genetic lineages in central and eastern Africa. Beyond the zoonotic transmission involving direct contact with the infected animals’ bodily fluids and blood, the spread of monkeypox can also occur through skin lesions and respiratory secretions among humans. Both monkeypox and chickenpox involve skin lesions and can also be transmitted through respiratory secretions, but they are caused by different viruses. The key difference is that monkeypox is caused by an orthopox-virus, while chickenpox is caused by the varicella-zoster virus.

monkeypox chickenpox patches vision transformer deep learning skin color images

1. Introduction

After the third wave of COVID-19, which started in January 2022, the condition of the pandemic got progressively less severe in the first half of the year 2022. Sadly, a new threat appeared in just a few weeks and quickly spread around the world, with the risk of becoming a pandemic. This sickness, called human monkeypox, although not a new one [1], was first found in 1970, and over the next ten years, more and more cases were found. Notably, this is not the first time that human monkeypox has spread. The 2003 Midwest monkeypox outbreak and the 2017–2019 Nigeria monkeypox outbreak are evidence of this [2]. There have also been rare cases of the disease in places like the UK, Singapore, and different parts of the US [3]. On the other hand, over the past nine months, the 2022 monkeypox outbreak has spread to more than 100 countries and regions [4]. Although this virus is comparatively less contagious due to its mode of transmission [5], the imperative for the development of a cost-effective and expeditious detection system remains paramount, given its continued spread. Understanding the genetic diversity and transmission patterns of the monkeypox virus is crucial for public health efforts, outbreak control, and vaccine development.
  • Genetic Diversity: The monkeypox virus has genetic variety, similarly to other viruses. Mutations that occur during viral replication and recombination activities give rise to this variety. Various strains of MPXV with different genetic compositions have been identified through genomic investigations. These variations may have an effect on host range, transmissibility, and pathogenicity. Through genome sequencing and analysis, researchers are able to follow the evolution of the virus, gaining insight into its epidemiology.
  • Transmission Patterns: Non-human primates, especially African rodents, are the main reservoir hosts for monkeypox infections. Direct contact with diseased animals or their body fluids, as well as contact with contaminated objects or surfaces, can result in human diseases. Although it happens less frequently, human-to-human transmission can happen when skin lesions or respiratory droplets come into contact with one another. Human behavior, healthcare practices, vaccine coverage, and population density are some of the factors that affect the spread of the disease.
  • Globalization and Travel: Globalization and increased travel facilitate the spread of infectious diseases, including monkeypox. The importation of infected animals or humans can introduce the virus to new regions. Surveillance systems at ports of entry help detect and contain imported cases, preventing local transmission.
Belonging to the Poxyviridae family [6], this virus finds its natural hosts among mammalian species, including squirrels, rats, and various primates. The disease caused by this virus exhibits an infectious course, lasting from two to four weeks, typically manifesting its initial symptoms approximately five to twenty-one days after exposure. As of now, the known symptoms include fever, muscle and joint pain, chills, swollen lymph nodes, and the appearance of blistering spots. [7]. These rashes usually show up in three days, primarily appearing on the face, hands, and bottoms of the feet. There is also potential for these rashes to extend to other areas, such as the mouth, eyes, and genital region. Subsequently, the disease progresses to a phase characterized by skin eruptions, which evolve through four distinct stages. At first, lesions have flat bases and are called macules. Later, they get raised, harden, and are then called papules. After that, these papules fill with pus and turn into pustules, which then turn into solid crusts [8].
The duration of monkeypox symptoms typically spans a period of 2 to 4 weeks, and it is noteworthy that severe cases can manifest. A study from the World Health Organization (WHO) says that the latest case fatality rate is somewhere between 3% and 6%. Monkeypox usually takes between 6 and 13 days to incubate, but it is important to know that it can take anywhere from 5 to 21 days. The spread happens over two separate time periods. During the first few weeks after the attack, patients often had back pain, fever, swollen lymph nodes, severe headaches, muscle aches, and a general lack of energy. The next phase usually starts one to three days after the fever starts, and this is when the familiar skin sores show up. These skin lesions show up on the face in about 95% of the cases, on the palms and soles of the feet in about 75% of the cases, on the inside of the mouth about 70% of the time, on the external sexual organs in about 30% of the cases, and on the conjunctivae, including the eyeball, in about 20% of the cases [9]. Transmitting the virus mostly happens through close touch between people or through bedding and clothes that have been contaminated [9]. According to [10], it is anticipated that more cases will be detected. However, it is important to note that the availability of polymerase chain reactions (PCR) and other biochemical tests is currently limited in terms of sufficient quantities, as indicated by [11].
Multiplex polymerase chain reaction (PCR) testing is the most common way to detect human monkeypox. However, the accuracy of the results obtained through this test can be compromised, often yielding inconclusive outcomes due to the virus’s transient presence in the bloodstream, as highlighted by [12]. This method of diagnosis also needs extra details, like the current stage of the rashes, the patient’s age, and the exact times when the fever and rash started. Furthermore, PCR tests are not widely utilized because they require a lot of resources, which causes them to be unavailable in most rural or remote places. In light of these challenges, there is a compelling case for the development of an alternative diagnostic system which operates independently of these metrics and leverages real-time data while utilizing readily accessible devices. Such an approach holds the potential to offer a near-perfect diagnostic solution for monkeypox, significantly enhancing both its effectiveness and efficiency.
Utilizing artificial intelligence (AI) and its various parts has been used in healthcare for a long time [12][13]. When it comes to healthcare, employing deep neural networks, especially for computer vision tasks, opens up a whole new world of possibilities. This method can harness the huge amount of healthcare data that is available to train convolutional neural networks (CNNs). These networks can then use current devices to solve new healthcare challenges [14]. A similar deep learning model based on patches has been proposed to identify monkeypox and chickenpox using skin images. This model utilizes RGB images of skin lesions captured using the cameras commonly found on smartphones.

2. Monkeypox Affecting Humans

The first recorded instance of monkeypox affecting humans was documented in 1970, marking the inception of human monkeypox studies in the scientific literature [15][16]. Over recent years, the research on human monkeypox has gained momentum, prompted by the alarming global spread of monkeypox infections. In fact, some researchers [17][18] have explicitly noted the pressing need for further investigation in this area.
Despite the historical presence of human monkeypox cases, the application of computer vision for early disease diagnosis is a relatively recent development. Currently, there is a dearth of comprehensive studies on this subject. Ahsan et al. [19], researchers collected image data of monkeypox-infected cases from Google called “Monkeypox2022” and conducted an in-depth analysis using advanced deep learning techniques. Specifically, they harnessed a modified VGG16 network for this purpose. Their model had great performance measures; its accuracy, sensitivity, recall, and f1-score all reached an amazing 97%. Ali et al. [11] involved the creation of a dedicated database of human monkeypox images, subsequently subjecting them to classification. In their classification efforts, the researchers employed four distinct deep learning networks, namely VGG16, ResNet50, InceptionV3, and Ensemble.
A lot of experts have used deep learning to figure out how to diagnose the monkeypox (Mpox) virus. In a different study, Abdelhamid et al. [20] used the AI-Biruni Earth Radius Optimization method, along with GoogLeNet, to pull out features for their Mpox diagnosis. They got a maximum accuracy rate of 98.8% by using different deep learning methods. The f1-score, sensitivity, and recall reached 62.5%, 99.8%, and 76%, respectively.
To make it easier for people to get medical help, a mobile app was made that can diagnose Mpox from pictures of skin lesions [21]. The creation process used Java and Android technologies, which led to an excellent maximum accuracy rate of 91.11%. The sensitivity score was 85%, the memory score was 94%, and the f1-score was 89%. A study by Islam et al. [22] used deep learning methods and a dataset with pictures of measles, mumps, chickenpox, smallpox, cowpox, and typhus. They utilized seven different classifiers, and the results were 83% for accuracy, 85% for sensitivity, 94% for recall, and 89% for the f1-score. Finally, Sitaula et al. [23] used eight different deep learning models that had already been trained to tell the difference between four groups and identify a case of mumps. They got an f1-score of 85%, an accuracy rate of 87.13%, a sensitivity rate of 85%.
Alakus et al. [24] used wart DNA segments and deep learning models to tell the difference between warts and monkeypox in a distinctive way. This classification process involved three stages and achieved an impressive maximum accuracy of 96.08%. Given the potential for monkeypox to emerge as a significant global health concern, efficient resource utilization is imperative. Disease diagnosis is one of the many areas in which artificial intelligence (AI) is essential. This research advances our knowledge of and ability to treat monkeypox by using a variety of transfer learning models to classify images of the illness. The objectives of this research are as follows:
  • The implementation of augmentation techniques was considered essential to ensure the model proper and consistent training with balanced class representation.
  • A state-of-the-art vision transformer model was employed, utilizing a transfer learning approach to detect instances of monkeypox from skin images.
  • An empirical exploration and adjustment of hyperparameters related to the proposed model and its training process were carried out to optimize performance.
  • The proposed model’s performance was systematically compared with that of other deep learning models and relevant studies. This comparative analysis aimed to derive insights into the significance of the proposed model within the broader research context.


  1. Rizk, J.; Lippi, G.; Henry, B.; Forthal, D.; Rizk, R. Prevention and treatment of monkeypox. Drugs 2022, 82, 957–963.
  2. Yinka-Ogunleye, A.; Aruna, O.; Dalhat, M.; Ogoina, D.; McCollum, A.; Disu, Y.; Mamadu, I.; Akinpelu, A.; Ahmad, A.; Burga, J.; et al. Outbreak of human monkeypox in Nigeria in 2017–18: A clinical and epidemiological report. Lancet Infect. Dis. 2019, 19, 872–879.
  3. Zachary, K.C.; Shenoy, E.S. Transmission following exposure in healthcare facilities in nonendemic settings: Low risk but limited literature. Infect. Control. Hosp. Epidemiol. 2022, 43, 920–924.
  4. Chadha, J.; Khullar, L.; Gulati, P.; Chhibber, S.; Harjai, K. Insights into the monkeypox virus: Making of another pandemic within the pandemic? Environ. Microbiol. 2022, 24, 4547–4560.
  5. Uwishema, O.; Adekunbi, O.; Peñamante, C.A.; Bekele, B.K.; Khoury, C.; Mhanna, M.; Nicholas, A.; Adanur, I.; Dost, B.; Onyeaka, H. The burden of monkeypox virus amidst the Covid-19 pandemic in Africa: A double battle for Africa. Ann. Med. Surg. 2022, 80, 104197.
  6. Nayak, T.; Chadaga, K.; Sampathila, N.; Mayrose, H.; Gokulkrishnan, N.; Prabhu, S.; Umakanth, S. Deep learning based detection of monkeypox virus using skin lesion images. Med. Nov. Technol. Devices 2023, 18, 100243.
  7. De Baetselier, I.; Van Dijck, C.; Kenyon, C.; Coppens, J.; Michiels, J.; de Block, T.; Smet, H.; Coppens, S.; Vanroye, F.; Bugert, J.J.; et al. Retrospective detection of asymptomatic monkeypox virus infections among male sexual health clinic attendees in Belgium. Nat. Med. 2022, 28, 2288–2292.
  8. Altindis, M.; Puca, E.; Shapo, L. Diagnosis of monkeypox virus—An overview. Travel. Med. Infect. Dis. 2022, 50, 102459.
  9. Multi-Country Monkeypox Outbreak in Non-Endemic Countries: Update. Available online: (accessed on 23 November 2023).
  10. Zumla, A.; Valdoleiros, S.R.; Haider, N.; Asogun, D.; Ntoumi, F.; Petersen, E.; Kock, R. Monkeypox outbreaks outside endemic regions: Scientific and social priorities. Lancet Infect. Dis. 2022, 22, 929–931.
  11. Ali, S.N.; Ahmed, M.T.; Paul, J.; Jahan, T.; Sani, S.M.; Noor, N.; Hasan, T. Monkeypox Skin Lesion Detection Using Deep Learning Models: A Feasibility Study. arXiv 2022, arXiv:2207.03342. Available online: (accessed on 23 November 2023).
  12. Paniz-Mondolfi, A.; Guerra, S.; Munoz, M.; Luna, N.; Hernandez, M.M.; Patino, L.H.; Reidy, J.; Banu, R.; Shrestha, P.; Liggayu, B.; et al. Evaluation and validation of an RT-PCR assay for specific detection of monkeypox virus (MPXV). J. Med. Virol. 2022, 95, e28247.
  13. Chadaga, K.; Prabhu, S.; Sampathila, N.; Nireshwalya, S.; Katta, S.S.; Tan, R.S.; Acharya, U.R. Application of artificial intelligence techniques for monkeypox: A systematic review. Diagnostics 2023, 13, 824.
  14. Norgeot, B.; Glicksberg, B.S.; Butte, A.J. A call for deep-learning healthcare. Nat. Med. 2023, 25, 14–15.
  15. Bulletin of the World Health Organization. Available online: (accessed on 23 November 2023).
  16. Heymann, D.L.; Szczeniowski, M.; Esteves, K. Re-emergence of monkeypox in Africa: A review of the past six years. Br. Med. Bull. 1998, 54, 693–702.
  17. Bragazzi, N.L.; Kong, J.D.; Mahroum, N.; Tsigalou, C.; Khamisy-Farah, R.; Converti, M.; Wu, J. Epidemiological trends and clinical features of the ongoing monkeypox epidemic: A preliminary pooled data analysis and literature review. J. Med. Virol. 2023, 95, e27931.
  18. Wilson, M.E.; Hughes, J.M.; McCollum, A.M.; Damon, I.K. Human Monkeypox. Clin. Infect. Dis. 2014, 58, 260–267.
  19. Ahsan, M.M.; Uddin, M.R.; Farjana, M.; Sakib, A.N.; Al Momin, K.; Luna, S.A. Image Data collection and implementation of deep learning-based model in detecting Monkeypox disease using modified VGG16. arXiv 2022, arXiv:2206.0186. Available online: (accessed on 23 November 2023).
  20. Abdelhamid, A.A.; El-Kenawy, E.S.M.; Khodadadi, N.; Mirjalili, S.; Khafaga, D.S.; Alharbi, A.H.; Ibrahim, A.; Eid, M.M.; Saber, M. Classification of monkeypox images based on transfer learning and the Al-Biruni Earth Radius Optimization algorithm. Mathematics 2022, 10, 3614.
  21. Sahin, V.H.; Oztel, I.; Yolcu Oztel, G. Human monkeypox classification from skin lesion images with deep pre-trained network using mobile application. J. Med. Syst. 2022, 46, 79.
  22. Hussain, M.A.; Islam, T.; Chowdhury, F.U.H.; Islam, B.R. Can Artificial Intelligence Detect Monkeypox from Digital Skin Images? bioRxiv 2022.
  23. Sitaula, C.; Shahi, T.B. Monkeypox Virus Detection Using Pre-trained Deep Learning-based Approaches. J. Med. Syst. 2022, 46, 78.
  24. Alakus, T.B.; Baykara, M. Comparison of Monkeypox and wart DNA sequences with deep learning model. Appl. Sci. 2022, 12, 10216.
Subjects: Others
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to : , , , ,
View Times: 57
Revisions: 2 times (View History)
Update Date: 27 Feb 2024