A Hybrid CNN Framework DLI-Net for Acne Detection with XAI
Acne is a prevalent skin condition that can significantly impact individuals’ psychological and physiological well-being. Detecting acne lesions is crucial for improving dermatological care and providing timely treatment. Numerous studies have explored the application of deep learning models to enha...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/4/115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850181011118227456 |
|---|---|
| author | Shaila Sharmin Fahmid Al Farid Md. Jihad Shakila Rahman Jia Uddin Rayhan Kabir Rafi Radia Hossan Hezerul Abdul Karim |
| author_facet | Shaila Sharmin Fahmid Al Farid Md. Jihad Shakila Rahman Jia Uddin Rayhan Kabir Rafi Radia Hossan Hezerul Abdul Karim |
| author_sort | Shaila Sharmin |
| collection | DOAJ |
| description | Acne is a prevalent skin condition that can significantly impact individuals’ psychological and physiological well-being. Detecting acne lesions is crucial for improving dermatological care and providing timely treatment. Numerous studies have explored the application of deep learning models to enhance the accuracy and speed of acne diagnoses. This study introduces a novel hybrid model that combines DeepLabV3 for precise image segmentation with InceptionV3 for classification, offering an enhanced solution for acne detection. The DeepLabV3 model isolates acne lesions and generates accurate segmentation masks, while InceptionV3 efficiently classifies the different types of acne, improving the overall diagnostic accuracy. The model was trained using a custom dataset and evaluated using advanced optimization techniques. The hybrid model achieved exceptional performances with a validation accuracy of 97%, a test accuracy of 97%, an F1 score of 0.97, a precision of 0.97, and a recall of 0.97, surpassing many of the existing baseline models. To enhance its interpretability further, Grad-CAM (Gradient-Weighted Class Activation Mapping) is utilized to visualize the regions of the image that the model focuses on during predictions, providing transparent insights into the decision-making process. This study underscores the transformative potential of AI in dermatology, offering a robust solution for acne detection and classification, which can significantly improve clinical decision making and patient outcomes. |
| format | Article |
| id | doaj-art-e986cacbf6c74a7eab4281b6dd8ba37a |
| institution | OA Journals |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-e986cacbf6c74a7eab4281b6dd8ba37a2025-08-20T02:17:59ZengMDPI AGJournal of Imaging2313-433X2025-04-0111411510.3390/jimaging11040115A Hybrid CNN Framework DLI-Net for Acne Detection with XAIShaila Sharmin0Fahmid Al Farid1Md. Jihad2Shakila Rahman3Jia Uddin4Rayhan Kabir Rafi5Radia Hossan6Hezerul Abdul Karim7Department of Computer Science, American International University-Bangladesh, Dhaka 1229, BangladeshCentre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, MalaysiaDepartment of Computer Science & Engineering, East West University, Dhaka 1212, BangladeshDepartment of Computer Science, American International University-Bangladesh, Dhaka 1229, BangladeshArtificial Intelligence and Big Data Department, Woosong University, Daejeon 34606, Republic of KoreaDepartment of Electrical and Electronic Engineering, American International University-Bangladesh, Dhaka 1229, BangladeshDepartment of Information Technology, University of Information Technology and Sciences, Dhaka 1212, BangladeshCentre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, MalaysiaAcne is a prevalent skin condition that can significantly impact individuals’ psychological and physiological well-being. Detecting acne lesions is crucial for improving dermatological care and providing timely treatment. Numerous studies have explored the application of deep learning models to enhance the accuracy and speed of acne diagnoses. This study introduces a novel hybrid model that combines DeepLabV3 for precise image segmentation with InceptionV3 for classification, offering an enhanced solution for acne detection. The DeepLabV3 model isolates acne lesions and generates accurate segmentation masks, while InceptionV3 efficiently classifies the different types of acne, improving the overall diagnostic accuracy. The model was trained using a custom dataset and evaluated using advanced optimization techniques. The hybrid model achieved exceptional performances with a validation accuracy of 97%, a test accuracy of 97%, an F1 score of 0.97, a precision of 0.97, and a recall of 0.97, surpassing many of the existing baseline models. To enhance its interpretability further, Grad-CAM (Gradient-Weighted Class Activation Mapping) is utilized to visualize the regions of the image that the model focuses on during predictions, providing transparent insights into the decision-making process. This study underscores the transformative potential of AI in dermatology, offering a robust solution for acne detection and classification, which can significantly improve clinical decision making and patient outcomes.https://www.mdpi.com/2313-433X/11/4/115image classificationdeep learningacne detectionimage segmentationexplainable AIDLI-Net |
| spellingShingle | Shaila Sharmin Fahmid Al Farid Md. Jihad Shakila Rahman Jia Uddin Rayhan Kabir Rafi Radia Hossan Hezerul Abdul Karim A Hybrid CNN Framework DLI-Net for Acne Detection with XAI Journal of Imaging image classification deep learning acne detection image segmentation explainable AI DLI-Net |
| title | A Hybrid CNN Framework DLI-Net for Acne Detection with XAI |
| title_full | A Hybrid CNN Framework DLI-Net for Acne Detection with XAI |
| title_fullStr | A Hybrid CNN Framework DLI-Net for Acne Detection with XAI |
| title_full_unstemmed | A Hybrid CNN Framework DLI-Net for Acne Detection with XAI |
| title_short | A Hybrid CNN Framework DLI-Net for Acne Detection with XAI |
| title_sort | hybrid cnn framework dli net for acne detection with xai |
| topic | image classification deep learning acne detection image segmentation explainable AI DLI-Net |
| url | https://www.mdpi.com/2313-433X/11/4/115 |
| work_keys_str_mv | AT shailasharmin ahybridcnnframeworkdlinetforacnedetectionwithxai AT fahmidalfarid ahybridcnnframeworkdlinetforacnedetectionwithxai AT mdjihad ahybridcnnframeworkdlinetforacnedetectionwithxai AT shakilarahman ahybridcnnframeworkdlinetforacnedetectionwithxai AT jiauddin ahybridcnnframeworkdlinetforacnedetectionwithxai AT rayhankabirrafi ahybridcnnframeworkdlinetforacnedetectionwithxai AT radiahossan ahybridcnnframeworkdlinetforacnedetectionwithxai AT hezerulabdulkarim ahybridcnnframeworkdlinetforacnedetectionwithxai AT shailasharmin hybridcnnframeworkdlinetforacnedetectionwithxai AT fahmidalfarid hybridcnnframeworkdlinetforacnedetectionwithxai AT mdjihad hybridcnnframeworkdlinetforacnedetectionwithxai AT shakilarahman hybridcnnframeworkdlinetforacnedetectionwithxai AT jiauddin hybridcnnframeworkdlinetforacnedetectionwithxai AT rayhankabirrafi hybridcnnframeworkdlinetforacnedetectionwithxai AT radiahossan hybridcnnframeworkdlinetforacnedetectionwithxai AT hezerulabdulkarim hybridcnnframeworkdlinetforacnedetectionwithxai |