Missouri University of Science & Technology, Rolla, MO, 65409, USA.
S&A Technologies, Rolla, MO, 65401, USA.
J Imaging Inform Med. 2024 Aug;37(4):1812-1823. doi: 10.1007/s10278-024-01000-5. Epub 2024 Feb 26.
Deep learning can exceed dermatologists' diagnostic accuracy in experimental image environments. However, inaccurate segmentation of images with multiple skin lesions can be seen with current methods. Thus, information present in multiple-lesion images, available to specialists, is not retrievable by machine learning. While skin lesion images generally capture a single lesion, there may be cases in which a patient's skin variation may be identified as skin lesions, leading to multiple false positive segmentations in a single image. Conversely, image segmentation methods may find only one region and may not capture multiple lesions in an image. To remedy these problems, we propose a novel and effective data augmentation technique for skin lesion segmentation in dermoscopic images with multiple lesions. The lesion-aware mixup augmentation (LAMA) method generates a synthetic multi-lesion image by mixing two or more lesion images from the training set. We used the publicly available International Skin Imaging Collaboration (ISIC) 2017 Challenge skin lesion segmentation dataset to train the deep neural network with the proposed LAMA method. As none of the previous skin lesion datasets (including ISIC 2017) has considered multiple lesions per image, we created a new multi-lesion (MuLe) segmentation dataset utilizing publicly available ISIC 2020 skin lesion images with multiple lesions per image. MuLe was used as a test set to evaluate the effectiveness of the proposed method. Our test results show that the proposed method improved the Jaccard score 8.3% from 0.687 to 0.744 and the Dice score 5% from 0.7923 to 0.8321 over a baseline model on MuLe test images. On the single-lesion ISIC 2017 test images, LAMA improved the baseline model's segmentation performance by 0.08%, raising the Jaccard score from 0.7947 to 0.8013 and the Dice score 0.6% from 0.8714 to 0.8766. The experimental results showed that LAMA improved the segmentation accuracy on both single-lesion and multi-lesion dermoscopic images. The proposed LAMA technique warrants further study.
深度学习在实验图像环境中可以超过皮肤科医生的诊断准确性。然而，当前的方法可以看到对具有多个皮肤病变的图像的不准确分割。因此，机器学习无法获取专家可获得的多病变图像中的信息。虽然皮肤病变图像通常仅捕获单个病变，但在某些情况下，患者的皮肤变异可能被识别为皮肤病变，从而导致单个图像中出现多个假阳性分割。相反，图像分割方法可能仅找到一个区域，并且可能无法捕获图像中的多个病变。为了解决这些问题，我们提出了一种新颖有效的用于多病变皮肤镜图像的皮肤病变分割的数据增强技术。病变感知混合增强（LAMA）方法通过混合来自训练集的两个或更多病变图像来生成合成的多病变图像。我们使用公开的国际皮肤成像协作（ISIC）2017 挑战赛皮肤病变分割数据集来训练具有所提出的 LAMA 方法的深度神经网络。由于以前的任何皮肤病变数据集（包括 ISIC 2017）都没有考虑每个图像的多个病变，因此我们利用每个图像都具有多个病变的公开的 ISIC 2020 皮肤病变图像创建了一个新的多病变（MuLe）分割数据集。MuLe 被用作测试集来评估所提出的方法的有效性。我们的测试结果表明，与基线模型相比，所提出的方法将 Jaccard 得分从 0.687 提高到 0.744，提高了 8.3%，将 Dice 得分从 0.7923 提高到 0.8321，提高了 5%。在 MuLe 测试图像上。在单病变 ISIC 2017 测试图像上，LAMA 将基线模型的分割性能提高了 0.08%，将 Jaccard 得分从 0.7947 提高到 0.8013，Dice 得分提高了 0.6%，从 0.8714 提高到 0.8766。实验结果表明，LAMA 提高了单病变和多病变皮肤镜图像的分割准确性。所提出的 LAMA 技术值得进一步研究。
J Imaging Inform Med. 2024-8
Comput Methods Programs Biomed. 2019-7-8
J Digit Imaging. 2023-8
Sensors (Basel). 2020-3-13
Comput Methods Programs Biomed. 2018-5-19
J Digit Imaging. 2023-8
CA Cancer J Clin. 2023-1
J Digit Imaging. 2020-8
Comput Methods Programs Biomed. 2020-4
Skin Res Technol. 2019-3-14
IEEE J Biomed Health Inform. 2019-1-4
Comput Biol Med. 2018-11-16
IEEE J Biomed Health Inform. 2018-2-16
Zotero 插件