Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan.
Department of Health Science and Technology, Aalborg University, 9220, Aalborg, Denmark.
Sci Rep. 2022 Mar 10;12(1):3948. doi: 10.1038/s41598-022-07885-y.
In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness.
在皮肤病变分割的计算机辅助诊断（CAD）系统中，病变形状和大小的变化使得分割任务更加具有挑战性。病变分割是 CAD 方案的初始步骤，因为它导致对皮肤病变的结构、边界和比例的定量分析错误率较低。当前最先进的深度学习分割技术提供的皮肤病变分割结果的主观临床评估不符合专家皮肤科医生的观察者间协议。本研究提出了一种新的基于深度学习的皮肤病变分割全自动方法，包括复杂的预处理和后处理方法。我们使用了三种深度学习模型，包括 UNet、深度残差 U-Net（ResUNet）和改进的 ResUNet（ResUNet++）。预处理阶段将形态滤波器与填充算法相结合，从皮肤镜图像中消除不必要的毛发结构。最后，我们在后处理阶段使用测试时间增强（TTA）和条件随机场（CRF）来提高分割准确性。该方法在 ISIC-2016 和 ISIC-2017 皮肤病变数据集上进行了训练和评估。当分别训练时，它在 ISIC-2016 和 ISIC-2017 数据集上的平均 Jaccard 指数分别达到 85.96%和 80.05%。当在组合数据集（ISIC-2016 和 ISIC-2017）上进行训练时，该方法在 ISIC-2017 和 ISIC-2016 测试数据集上的平均 Jaccard 指数分别达到 80.73%和 90.02%。由于其高可扩展性和鲁棒性，所提出的方法框架可用于设计全自动计算机辅助皮肤病变诊断系统。
