Ros-NET: A deep convolutional neural network for automatic identification of rosacea lesions
Ros-NET: A deep convolutional neural network for automatic identification of rosacea lesions
复制标题
DOI：
10.1111/srt.12817
复制
发表时间：
2019-12-17
影响因子：
2.2
通讯作者：
Gurcan, Metin N.
中科院分区：
文献类型：
--
作者：
Binol, Hamidullah;Plotner, Alisha;Gurcan, Metin N.
背景酒渣鼻是最常见的皮肤病之一，主要表现为面部潮红、红斑、丘疹、脓疱、毛细血管扩张和鼻肿胀。酒渣鼻的诊断主要是通过身体检查和一致的病史。然而，定性的人类评估通常是主观的，并且在评估患者结果时遭受相对高的观察者内和观察者间的变化。材料与方法为了克服这些问题，我们提出了一个定量和可重复的计算机辅助诊断系统，Ros-NET，它集成了来自不同图像尺度和分辨率的信息，以识别酒渣鼻病变。这涉及到Inception-ResNet-v2和ResNet-101的适配，以从面部图像中提取酒渣鼻特征。此外，我们建议通过面部地标为基础的区域（即，人体测量地标）作为感兴趣的区域（ROI），重点是在脸上的酒渣鼻发生的典型区域，以完善检测结果。结果使用留一患者交叉验证方案，在Inception-ResNet-v2和ResNet-101中，所有患者（N = 41）的256 x 256图像块的加权平均Dice系数（百分比）分别为89.8 +/- 2.6%和87.8 +/- 2.4%。结论本研究的结果支持通过迁移学习训练的预训练网络可以有益于识别酒渣鼻病变。我们未来的工作将涉及将工作扩展到具有不同程度疾病特征的病例的更大数据库。
Background Rosacea is one of the most common cutaneous disorder characterized primarily by facial flushing, erythema, papules, pustules, telangiectases, and nasal swelling. Diagnosis of rosacea is principally done by a physical examination and a consistent patient history. However, qualitative human assessment is often subjective and suffers from a relatively high intra- and inter-observer variability in evaluating patient outcomes. Materials and Methods To overcome these problems, we propose a quantitative and reproducible computer-aided diagnosis system, Ros-NET, which integrates information from different image scales and resolutions in order to identify rosacea lesions. This involves adaption of Inception-ResNet-v2 and ResNet-101 to extract rosacea features from facial images. Additionally, we propose to refine the detection results by means of facial-landmarks-based zones (ie, anthropometric landmarks) as regions of interest (ROI), which focus on typical areas of rosacea occurrence on a face. Results Using a leave-one-patient-out cross-validation scheme, the weighted average Dice coefficients, in percentages, across all patients (N = 41) with 256 x 256 image patches are 89.8 +/- 2.6% and 87.8 +/- 2.4% with Inception-ResNet-v2 and ResNet-101, respectively. Conclusion The findings from this study support that pre-trained networks trained via transfer learning can be beneficial in identifying rosacea lesions. Our future work will involve expanding the work to a larger database of cases with varying degrees of disease characteristics.