Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence
Skin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI syst...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/8/1879 |
| _version_ | 1797446063089516544 |
|---|---|
| author | Quan Thanh Huynh Phuc Hoang Nguyen Hieu Xuan Le Lua Thi Ngo Nhu-Thuy Trinh Mai Thi-Thanh Tran Hoan Tam Nguyen Nga Thi Vu Anh Tam Nguyen Kazuma Suda Kazuhiro Tsuji Tsuyoshi Ishii Trung Xuan Ngo Hoan Thanh Ngo |
| author_facet | Quan Thanh Huynh Phuc Hoang Nguyen Hieu Xuan Le Lua Thi Ngo Nhu-Thuy Trinh Mai Thi-Thanh Tran Hoan Tam Nguyen Nga Thi Vu Anh Tam Nguyen Kazuma Suda Kazuhiro Tsuji Tsuyoshi Ishii Trung Xuan Ngo Hoan Thanh Ngo |
| author_sort | Quan Thanh Huynh |
| collection | DOAJ |
| description | Skin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI system called AcneDet for automatic acne object detection and acne severity grading using facial images captured by smartphones. AcneDet includes two models for two tasks: (1) a Faster R-CNN-based deep learning model for the detection of acne lesion objects of four types, including blackheads/whiteheads, papules/pustules, nodules/cysts, and acne scars; and (2) a LightGBM machine learning model for grading acne severity using the Investigator’s Global Assessment (IGA) scale. The output of the Faster R-CNN model, i.e., the counts of each acne type, were used as input for the LightGBM model for acne severity grading. A dataset consisting of 1572 labeled facial images captured by both iOS and Android smartphones was used for training. The results show that the Faster R-CNN model achieves a mAP of 0.54 for acne object detection. The mean accuracy of acne severity grading by the LightGBM model is 0.85. With this study, we hope to contribute to the development of artificial intelligent systems to help acne patients better understand their conditions and support doctors in acne diagnosis. |
| first_indexed | 2024-03-09T13:34:52Z |
| format | Article |
| id | doaj.art-32199646643e4185a2ccf33e85551078 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T13:34:52Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-32199646643e4185a2ccf33e855510782023-11-30T21:13:06ZengMDPI AGDiagnostics2075-44182022-08-01128187910.3390/diagnostics12081879Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial IntelligenceQuan Thanh Huynh0Phuc Hoang Nguyen1Hieu Xuan Le2Lua Thi Ngo3Nhu-Thuy Trinh4Mai Thi-Thanh Tran5Hoan Tam Nguyen6Nga Thi Vu7Anh Tam Nguyen8Kazuma Suda9Kazuhiro Tsuji10Tsuyoshi Ishii11Trung Xuan Ngo12Hoan Thanh Ngo13Medical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamRohto Pharmaceutical Co., Ltd., Basic Research Division, Research Village Kyoto, 6-5-4 Kunimidai, Kizugawa, Kyoto 619-0216, JapanRohto Pharmaceutical Co., Ltd., Regulatory Affairs Promotion Division, 1-8-1 Tatsumi-nishi, Ikuno-ku, Osaka 544-8666, JapanRohto Pharmaceutical Co., Ltd., Basic Research Division, Research Village Kyoto, 6-5-4 Kunimidai, Kizugawa, Kyoto 619-0216, JapanRohto Pharmaceutical Co., Ltd., Basic Research Division, Research Village Kyoto, 6-5-4 Kunimidai, Kizugawa, Kyoto 619-0216, JapanMedical AI Co., Ltd., Ho Chi Minh City 700000, VietnamSkin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI system called AcneDet for automatic acne object detection and acne severity grading using facial images captured by smartphones. AcneDet includes two models for two tasks: (1) a Faster R-CNN-based deep learning model for the detection of acne lesion objects of four types, including blackheads/whiteheads, papules/pustules, nodules/cysts, and acne scars; and (2) a LightGBM machine learning model for grading acne severity using the Investigator’s Global Assessment (IGA) scale. The output of the Faster R-CNN model, i.e., the counts of each acne type, were used as input for the LightGBM model for acne severity grading. A dataset consisting of 1572 labeled facial images captured by both iOS and Android smartphones was used for training. The results show that the Faster R-CNN model achieves a mAP of 0.54 for acne object detection. The mean accuracy of acne severity grading by the LightGBM model is 0.85. With this study, we hope to contribute to the development of artificial intelligent systems to help acne patients better understand their conditions and support doctors in acne diagnosis.https://www.mdpi.com/2075-4418/12/8/1879deep learningsmartphone imageacne gradingacne object detection |
| spellingShingle | Quan Thanh Huynh Phuc Hoang Nguyen Hieu Xuan Le Lua Thi Ngo Nhu-Thuy Trinh Mai Thi-Thanh Tran Hoan Tam Nguyen Nga Thi Vu Anh Tam Nguyen Kazuma Suda Kazuhiro Tsuji Tsuyoshi Ishii Trung Xuan Ngo Hoan Thanh Ngo Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence Diagnostics deep learning smartphone image acne grading acne object detection |
| title | Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence |
| title_full | Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence |
| title_fullStr | Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence |
| title_full_unstemmed | Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence |
| title_short | Automatic Acne Object Detection and Acne Severity Grading Using Smartphone Images and Artificial Intelligence |
| title_sort | automatic acne object detection and acne severity grading using smartphone images and artificial intelligence |
| topic | deep learning smartphone image acne grading acne object detection |
| url | https://www.mdpi.com/2075-4418/12/8/1879 |
| work_keys_str_mv | AT quanthanhhuynh automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT phuchoangnguyen automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT hieuxuanle automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT luathingo automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT nhuthuytrinh automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT maithithanhtran automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT hoantamnguyen automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT ngathivu automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT anhtamnguyen automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT kazumasuda automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT kazuhirotsuji automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT tsuyoshiishii automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT trungxuanngo automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence AT hoanthanhngo automaticacneobjectdetectionandacneseveritygradingusingsmartphoneimagesandartificialintelligence |