Huynh Quan Thanh, Nguyen Phuc Hoang, 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 Thanh
Medical AI Co., Ltd., Ho Chi Minh City 700000, Vietnam.
School of Biomedical Engineering, International University, Vietnam National University-HCMC, Ho Chi Minh City 700000, Vietnam.
Diagnostics (Basel). 2022 Aug 3;12(8):1879. doi: 10.3390/diagnostics12081879.
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.
利用人工智能（AI）进行皮肤图像分析最近引起了广泛的研究兴趣，特别是在分析移动设备拍摄的皮肤图像方面。痤疮是最常见的皮肤疾病之一，严重时会产生深远影响。在本研究中，我们开发了一个名为AcneDet的人工智能系统，用于使用智能手机拍摄的面部图像自动检测痤疮目标并对痤疮严重程度进行分级。AcneDet包括用于两项任务的两个模型：（1）基于Faster R-CNN的深度学习模型，用于检测四种类型的痤疮病变目标，包括黑头/白头、丘疹/脓疱、结节/囊肿和痤疮疤痕；（2）基于LightGBM的机器学习模型，用于使用研究者整体评估（IGA）量表对痤疮严重程度进行分级。Faster R-CNN模型的输出，即每种痤疮类型的数量，被用作LightGBM模型进行痤疮严重程度分级的输入。一个由iOS和安卓智能手机拍摄的1572张带标签面部图像组成的数据集用于训练。结果表明，Faster R-CNN模型在痤疮目标检测方面的平均精度均值（mAP）为0.54。LightGBM模型对痤疮严重程度分级的平均准确率为0.85。通过这项研究，我们希望为人工智能系统的发展做出贡献，以帮助痤疮患者更好地了解自己的病情，并为医生的痤疮诊断提供支持。
