DME-DeepLabV3+: a lightweight model for diabetic macular edema extraction based on DeepLabV3+ architecture

Yun Bai; Jing Li; Lianjun Shi; Qin Jiang; Biao Yan; Zhenhua Wang

doi:10.3389/fmed.2023.1150295

DME-DeepLabV3+: a lightweight model for diabetic macular edema extraction based on DeepLabV3+ architecture

Front Med (Lausanne). 2023 Sep 8:10:1150295. doi: 10.3389/fmed.2023.1150295. eCollection 2023.

Authors

Yun Bai¹, Jing Li¹, Lianjun Shi², Qin Jiang², Biao Yan³, Zhenhua Wang¹

Affiliations

¹ College of Information Science, Shanghai Ocean University, Shanghai, China.
² The Affiliated Eye Hospital, Nanjing Medical University, Nanjing, China.
³ Eye Institute, Eye and ENT Hospital, Shanghai Medical College, Fudan University, Shanghai, China.

Abstract

Introduction: Diabetic macular edema (DME) is a major cause of vision impairment in the patients with diabetes. Optical Coherence Tomography (OCT) is an important ophthalmic imaging method, which can enable early detection of DME. However, it is difficult to achieve high-efficiency and high-precision extraction of DME in OCT images because the sources of OCT images are diverse and the quality of OCT images is not stable. Thus, it is still required to design a model to improve the accuracy of DME extraction in OCT images.

Methods: A lightweight model (DME-DeepLabV3+) was proposed for DME extraction using a DeepLabV3+ architecture. In this model, MobileNetV2 model was used as the backbone for extracting low-level features of DME. The improved ASPP with sawtooth wave-like dilation rate was used for extracting high-level features of DME. Then, the decoder was used to fuse and refine low-level and high-level features of DME. Finally, 1711 OCT images were collected from the Kermany dataset and the Affiliated Eye Hospital. 1369, 171, and 171 OCT images were randomly selected for training, validation, and testing, respectively.

Conclusion: In ablation experiment, the proposed DME-DeepLabV3+ model was compared against DeepLabV3+ model with different setting to evaluate the effects of MobileNetV2 and improved ASPP on DME extraction. DME-DeepLabV3+ had better extraction performance, especially in small-scale macular edema regions. The extraction results of DME-DeepLabV3+ were close to ground truth. In comparative experiment, the proposed DME-DeepLabV3+ model was compared against other models, including FCN, UNet, PSPNet, ICNet, and DANet, to evaluate DME extraction performance. DME-DeepLabV3+ model had better DME extraction performance than other models as shown by greater pixel accuracy (PA), mean pixel accuracy (MPA), precision (Pre), recall (Re), F1-score (F1), and mean Intersection over Union (MIoU), which were 98.71%, 95.23%, 91.19%, 91.12%, 91.15%, and 91.18%, respectively.

Discussion: DME-DeepLabV3+ model is suitable for DME extraction in OCT images and can assist the ophthalmologists in the management of ocular diseases.

Keywords: DeepLabV3+; deep learning; diabetic macular edema; extraction model; optical coherence tomography.