Université Paris Cité, Paris, France.
Ophthalmology Department, AP-HP, Hôpital Lariboisière, Paris, France.
PLoS One. 2024 Aug 7;19(8):e0306794. doi: 10.1371/journal.pone.0306794. eCollection 2024.
To develop and test VMseg, a new image processing algorithm performing automatic segmentation of retinal non-perfusion in widefield OCT-Angiography images, in order to estimate the non-perfusion index in diabetic patients.
We included diabetic patients with severe non-proliferative or proliferative diabetic retinopathy. We acquired images using the PlexElite 9000 OCT-A device with a photomontage of 5 images of size 12 x 12 mm. We then developed VMseg, a Python algorithm for non-perfusion detection, which binarizes a variance map calculated through convolution and morphological operations. We used 70% of our data set (development set) to fine-tune the algorithm parameters (convolution and morphological parameters, binarization thresholds) and evaluated the algorithm performance on the remaining 30% (test set). The obtained automatic segmentations were compared to a ground truth corresponding to manual segmentation from a retina expert and the inference processing time was estimated.
We included 51 eyes of 30 patients (27 severe non-proliferative, 24 proliferative diabetic retinopathy). Using the optimal parameters found on the development set to tune the algorithm, the mean dice for the test set was 0.683 (sd = 0.175). We found a higher dice coefficient for images with a higher area of retinal non-perfusion (rs = 0.722, p < 10-4). There was a strong correlation (rs = 0.877, p < 10-4) between VMseg estimated non-perfusion indexes and indexes estimated using the ground truth segmentation. The Bland-Altman plot revealed that 3 eyes (5.9%) were significantly under-segmented by VMseg.
We developed VMseg, an automatic algorithm for retinal non-perfusion segmentation on 12 x 12 mm OCT-A widefield photomontages. This simple algorithm was fast at inference time, segmented images in full-resolution and for the OCT-A format, was accurate enough for automatic estimation of retinal non-perfusion index in diabetic patients with diabetic retinopathy.
开发并测试 VMseg，这是一种新的图像处理算法，用于对广角 OCT-Angiography 图像中的视网膜无灌注进行自动分割，以便估计糖尿病患者的无灌注指数。
我们纳入了患有严重非增生性或增生性糖尿病视网膜病变的糖尿病患者。我们使用 PlexElite 9000 OCT-A 设备采集图像，该设备具有大小为 12x12mm 的 5 张图像的光片。然后，我们开发了 VMseg，这是一种用于无灌注检测的 Python 算法，它通过卷积和形态学操作计算的方差图进行二值化。我们使用数据集的 70%（开发集）来微调算法参数（卷积和形态学参数、二值化阈值），并在剩余的 30%（测试集）上评估算法性能。将获得的自动分割与来自视网膜专家的手动分割的真实分割进行比较，并估计推断处理时间。
我们纳入了 30 名患者的 51 只眼（27 只严重非增生性，24 只增生性糖尿病视网膜病变）。使用在开发集上找到的最佳参数来调整算法，测试集的平均骰子系数为 0.683（标准差=0.175）。我们发现，对于具有更高视网膜无灌注面积的图像，骰子系数更高（rs=0.722，p<10-4）。VMseg 估计的无灌注指数与使用真实分割估计的指数之间存在很强的相关性（rs=0.877，p<10-4）。Bland-Altman 图显示，VMseg 有 3 只眼（5.9%）明显被低估。
我们开发了 VMseg，这是一种用于 12x12mm OCT-A 广角光片的视网膜无灌注自动分割的算法。这种简单的算法在推断时间上很快，能够以全分辨率分割图像，并且对于 OCT-A 格式来说，足够准确，可以自动估计糖尿病视网膜病变的糖尿病患者的视网膜无灌注指数。
