CCA-Net: Clinical-awareness attention network for nuclear cataract classification in AS-OCT

Zhang, Xiaoqing; Xiao, Zunjie; Hu, Lingxi; Xu, Gelei; Higashita, Risa; Chen, Wan; Yuan, Jing; Liu, Jiang

doi:10.1016/j.knosys.2022.109109

Cited by 9 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 5 offers representative AS-OCT images of three NC severity levels. This paper adopts the same dataset splitting method used in [57]. Thus, we divide the AS-OCT dataset into three subsets based on the participant-level: training, validation, and testing.…”

Section: As-oct Datasetmentioning

confidence: 99%

Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition

Xiao-qing

Xiao

et al. 2023

CAAI Trans on Intel Tech

Self Cite

View full text Add to dashboard Cite

Eye health has become a global health concern and attracted broad attention. Over the years, researchers have proposed many state‐of‐the‐art convolutional neural networks (CNNs) to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely. However, most existing methods were dedicated to constructing sophisticated CNNs, inevitably ignoring the trade‐off between performance and model complexity. To alleviate this paradox, this paper proposes a lightweight yet efficient network architecture, mixed‐decomposed convolutional network (MDNet), to recognise ocular diseases. In MDNet, we introduce a novel mixed‐decomposed depthwise convolution method, which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low‐resolution and high‐resolution patterns by using fewer computations and fewer parameters. We conduct extensive experiments on the clinical anterior segment optical coherence tomography (AS‐OCT), LAG, University of California San Diego, and CIFAR‐100 datasets. The results show our MDNet achieves a better trade‐off between the performance and model complexity than efficient CNNs including MobileNets and MixNets. Specifically, our MDNet outperforms MobileNets by 2.5% of accuracy by using 22% fewer parameters and 30% fewer computations on the AS‐OCT dataset.

show abstract

Section: As-oct Datasetmentioning

confidence: 99%