Segmentation of laser induced retinal lesions using deep learning (December 2021).
Segmentation of laser induced retinal lesions using deep learning (December 2021).
复制标题
DOI：
10.1002/lsm.23578
复制
发表时间：
2022-10
影响因子：
2.4
通讯作者：
中科院分区：
文献类型：
--
作者：
视网膜激光损伤的检测对于评估高功率激光源的损伤程度和验证涉及激光损伤放置的治疗都是必要的。然而，单独使用彩色眼底照相机难以检测到这样的病变。基于深度学习的分割可以通过突出图像中的潜在病变来解决这个问题。在过去的30年里，空军研究实验室收集了一个独特的图像数据库，用于训练深度学习模型，对病变图像进行分类，并进行后续分割。我们研究了从学习分类的模型中转移权重是否会提高分割模型的性能。我们使用Pearson在初始和最终训练阶段之间的相关系数来揭示网络如何传递特征。分割模型能够有效分割广泛的病变和成像条件基于深度学习的病变分割可以有效突出激光病变，使其成为辅助临床医生的有用工具。
Detection of retinal laser lesions is necessary in both the evaluation of the extent of damage from high power laser sources, and in validating treatments involving the placement of laser lesions. However, such lesions are difficult to detect using Color Fundus cameras alone. Deep learning-based segmentation can remedy this, by highlighting potential lesions in the image. A unique database of images collected at the Air Force Research Laboratory over the past 30 years was used to train deep learning models for classifying images with lesions and for subsequent segmentation. We investigate whether transferring weights from models that learned classification would improve performance of the segmentation models. We use Pearson’s correlation coefficient between the initial and final training phases to reveal how the networks are transferring features. The segmentation models are able to effectively segment a broad range of lesions and imaging conditions Deep learning-based segmentation of lesions can effectively highlight laser lesions, making this a useful tool for aiding clinicians.