Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence

Huynh, Quan Thanh; Nguyen, Phuc; Le, Hieu Xuan; Ngo, Lua Thi; Trinh, Nhu‐Thuy; Tran, Mai Thi-Thanh; Nguyen, Hoan Tam; Vu, Nga Thi; Nguyen, Anh Tam; Suda, Kazuma; Tsuji, Kazuhiro; Ishii, Tsuyoshi; Ngo, Trung Xuan; Ngo, Hoan T.

doi:10.3390/diagnostics12081879

Cited by 24 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, image-based analysis is another prospect to detect face acne, which is possible by comparable severities checks where similar appearances are complex to examine, as shown in Figure 1. To overcome this situation, there is a need to adopt a complex network based on neurons, which consume more resources including computational cost and preservation [8,9]. Whereas the computational cost indicates the powerful graphical processing units that require a high-specification environment for deployment purposes.…”

Section: D-gan: An Automatic Acne Detection Severity and Assessment F...mentioning

confidence: 99%

“…On the other side, there are a few challenging prospects that effects the employment of DNN with other state-of-the-art methods for the better result of acne severity. Generative Adversarial Network (GAN) is associated with generative modeling, which is an unsupervised learning approach based on automation to discover learning and patterns of input values in accordance with the regulations [8,9,10]. In such a way that the model can be used to give output as a new example drawn from the original one.…”

Section: Figure 1 the Current Process Of Acne Detectionmentioning

confidence: 99%

See 1 more Smart Citation

D-GAN: An Automatic Acne Detection, Severity, and Assessment Framework using Generative Adversarial Network with Deep Neural Network

Khalid,

Chen,

Khan

et al. 2024

Preprint

View full text Add to dashboard Cite

With the robust development of Artificial Intelligence (AI), especially image processing has made information technology more efficient and effective in the sense to evaluate facial features, even though there has been masked on the face. However, the accuracy of acne detection and related severity analysis is becoming a significant prospect for the precise treatment of patients. Due to this, close severity is one of the features that need to be added first, while it is considered a highly challenging aspect for dermatologists because the similar appearance of acne in the face reduces the rate of accuracy when examining. It poses a serious problem in the domain of biomedical processing and controls. In this paper, we contribute to four different folds. Initially, this paper presents a novel framework that provides a platform in order to measure localization and segmentation. In this process, consultants receive better accuracy and efficiency during the process of acne detection and severity analysis. Second, this paper utilizes deep neural networks (DNNs) as a backend process to lightning the extraction of multi-scale features through a multi-hierarchy neural net for regionalized facial features to investigate distinction and localization. Third, a class-based segmentation approach customizes and integrates with the proposed framework to examine the background and facial skin separation to distinguish different classes to obtain severity marking. Fourth, the facial skin segmentation classes are built as a cluster segment using Generative Adversarial Network (GAN). It provides a high-resolution network that enhances severity masking awareness and related attentions, including shuffle and conditional channels like an update in weight block. Although, the simulation illustrates that the technological collaboration achieves promising results and elaborates on the accuracy and efficiency while the detection of acne as compared to other state-of-the-art baseline methods. In addition, the proposed framework illustrates good results in severity analysis for acne detection comparably far better than the previously published articles with a performance rate of 3.112% (accuracy), 1.131% (segmentation), 2.317% (localization), and 1.573% (GAN-based high-resolution network management), respectively.

show abstract

Section: D-gan: An Automatic Acne Detection Severity and Assessment F...mentioning

confidence: 99%

Section: Figure 1 the Current Process Of Acne Detectionmentioning

confidence: 99%

D-GAN: An Automatic Acne Detection, Severity, and Assessment Framework using Generative Adversarial Network with Deep Neural Network

Khalid,

Chen,

Khan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Yadav et al [5] identified candidate regions of acne presence on the face based on the HSV color space and then distinguished acne using classifiers trained with SVM or CNN. Rashataprucksa et al [6] and Hyunh et al [7] utilized object detection models such as faster-rcnn [8] and r-fcn [9] for acne detection. Min et al [10] employed a dual encoder based on CNN and Transformer to detect face acne.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Facial Acne Segmentation Using Bidirectional Copy-Paste

Kim,

Yoon,

Lee

2024

Preprint

View full text Add to dashboard Cite

Facial acne is a prevalent dermatological condition regularly observed in the general population. This study introduces a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy-paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrates improvement in performance, offering a novel direction for future acne analysis.

show abstract

“…Dermatology has become a hot topic in AI due to the visible clinical manifestations of skin diseases. In recent years, machine learning (ML) has played a large role in detecting and grading acne severity, distinguishing atopic dermatitis, classifying skin cancer, and detecting monkeypox with a level of accuracy comparable to a dermatologist 18–21 . However, the prospect of AI in deep skin fungal infection has not been investigated thus far.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, machine learning (ML) has played a large role in detecting and grading acne severity, distinguishing atopic dermatitis, classifying skin cancer, and detecting monkeypox with a level of accuracy comparable to a dermatologist. [18][19][20][21] However, the prospect of AI in deep skin fungal infection has not been investigated thus far. Therefore, it is A study was included in the study when it met all following criteria: (1) a study that showed skin lesion images for talaromycosis or cryptococcosis; (2) cases were diagnosed using the gold standard; and (3) the images were clearly visible.…”

mentioning

confidence: 99%

Application of deep learning algorithm in the recognition of cryptococcosis and talaromycosis skin lesions

Wei

Bao

et al. 2023

Mycoses

View full text Add to dashboard Cite

Fungal pathogens and infections are a growing global public health concern, with those most at risk being those with underlying health conditions or weakened immune systems. In recent years, the incidence and mortality of invasive fungal infections such as cryptococcus and talaromycosis have increased with the increase in HIV infection, the use of malignant tumours, organ transplantation and immunosuppressive age. 1,2 Cryptococcosis, an invasive fungus caused by Cryptococcus, is the third most common invasive fungal infection. 3,4 Approximately one million people are infected with Cryptococcus, and 630,000 people die each year worldwide. [5][6][7][8] Talaromycosis, also with a high case fatality rate, is an invasive fungal infection caused by Talaromyces marneffei infection, which causes

show abstract

Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence

Cited by 24 publications

References 19 publications

D-GAN: An Automatic Acne Detection, Severity, and Assessment Framework using Generative Adversarial Network with Deep Neural Network

D-GAN: An Automatic Acne Detection, Severity, and Assessment Framework using Generative Adversarial Network with Deep Neural Network

Semi-Supervised Facial Acne Segmentation Using Bidirectional Copy-Paste

Application of deep learning algorithm in the recognition of cryptococcosis and talaromycosis skin lesions

Contact Info

Product

Resources

About