Automated segmentation of macular edema for the diagnosis of ocular disease using deep learning method

Abstract

Macular edema is considered as a major cause of visual loss and blindness in patients with ocular fundus diseases. Optical coherence tomography (OCT) is a non-invasive imaging technique, which has been widely applied for diagnosing macular edema due to its non-invasive and high resolution properties. However, the practical applications remain challenges due to the distorted retinal morphology and blurred boundaries near macular edema. Herein, we developed a novel deep learning model for the segmentation of macular edema in OCT images based on DeepLab framework (OCT-DeepLab). In this model, we used atrous spatial pyramid pooling (ASPP) to detect macular edema at multiple features and used the fully connected conditional random field (CRF) to refine the boundary of macular edema. OCT-DeepLab model was compared against the traditional hand-crafted methods (C-V and SBG) and the end-to-end methods (FCN, PSPnet, and U-net) to estimate the segmentation performance. OCT-DeepLab showed great advantage over the hand-crafted methods (C-V and SBG) and end-to-end methods (FCN, PSPnet, and U-net) as shown by higher precision, sensitivity, specificity, and F1-score. The segmentation performance of OCT-DeepLab was comparable to that of manual label, with an average area under the curve (AUC) of 0.963, which was superior to other end-to-end methods (FCN, PSPnet, and U-net). Collectively, OCT-DeepLab model is suitable for the segmentation of macular edema and assist ophthalmologists in the management of ocular disease.

Figure 1

Flowchart of OCT-DeepLab method.

Figure 2

Flowchart of 2-level wavelet transform. (A) First level wavelet transform. (B) Second level wavelet transform.

Figure 3

Decomposing process of OCT image by 2-level wavelet transform.

Figure 4

Denoising flowchart of OCT image. (A) Original OCT image. (B) Low-frequency band of OCT image. (C) Low-frequency band of OCT image by reducing speckle noises. (D) Reconstitution of OCT image.

Figure 5

Principle for coarse segmentation of macular edema in OCT image. (A) Operating principle of residual learning block. (B) The workflow of conventional convolution and atrous convolution. Conventional convolution operation with 3 × 3 kernel size and 1 stride. Atrous convolution operation with 3 × 3 kernel size, 1 stride, and 2 rate. (C) Coarse segmentation of macular edema in OCT image.

Figure 6

Refine the segmentation results of macular edema by FC-CRF. (A) Sensitivity test for FC-CRF model. (B) Refined segmentation result of macular edema in OCT images.

Figure 7

Different segmentation results of macular edema by Deeplab with different setting.

Figure 8

Segmentation results of macular edema by different methods. Red line is the initial contour curve of segmentation; Green line is the segmentation result of macular edema.

Figure 9

Segmentation results of macular edema by different methods.

Figure 10

ROC curves from the segmentation of macular edema by different methods.