Finetuning pre-trained deep neural networks (DNN) delicately designed for large-scale natural images may not be suitable for medical images due to the intrinsic difference between the datasets. We propose a strategy to modify DNNs, which improves their performance on retinal optical coherence tomography (OCT) images. Deep features of pre-trained DNN are high-level features of natural images. These features harm the training of transfer learning. Our strategy is to remove some deep convolutional layers of the state-of-the-art pre-trained networks: GoogLeNet, ResNet and DenseNet. We try to find the optimized deep neural networks on small-scale and large-scale OCT datasets, respectively, in our experiments. Results show that optimized deep neural networks not only reduce computational burden, but also improve classification accuracy.
Optical coherence tomography (OCT) is an optical high-resolution imaging technique for ophthalmic diagnosis. In this paper, we take advantages of multi-scale input, multi-scale side output and dual attention mechanism and present an enhanced nested U-Net architecture (MDAN-UNet), a new powerful fully convolutional network for automatic end-to-end segmentation of OCT images. We have evaluated two versions of MDAN-UNet (MDAN-UNet-16 and MDAN-UNet-32) on two publicly available benchmark datasets which are the Duke Diabetic Macular Edema (DME) dataset and the RETOUCH dataset, in comparison with other state-of-the-art segmentation methods. Our experiment demonstrates that MDAN-UNet-32 achieved the best performance, followed by MDAN-UNet-16 with smaller parameter, for multi-layer segmentation and multi-fluid segmentation respectively.
Macular diseases have received widespread attention in recent years, and age-related macular degeneration (AMD) and diabetic macular edema (DME) are two common diseases that cause severe vision loss and blindness, especially in adults. Optical coherence tomography (OCT) is an imaging technology that measures the backward scattered light intensity of objects.1 Since the structure of the retina can be clearly visualized with micron resolution using OCT, some eye diseases such as AMD and DME can be diagnosed based on OCT images.2,3 In clinical diagnosis, ophthalmologists make diagnostic decisions of retina edema diseases based mainly on the observation and analysis of OCT images. Spectral-domain OCT (SD-OCT) has been capable of generating 3D datasets since its inception and is widely used in clinics. One retinal OCT volume usually contains dozens or even hundreds of B-scans, and ophthalmologists need to manually identify retina lesions at each cross-section of the OCT volume and then make diagnostic decisions related to ocular diseases. This greatly increases the analysis burden of the eye specialist, and this manual interrogation requires expert graders, which is inefficient and prone to yielding subjective results. Consequently, high-performance automatic 3-D OCT image analysis is critical for the diagnosis of retinal disease.
1 August 2019 in Computers in Biology and Medicine
Commonly used convolutional neural networks (CNNs) usually compress high‐resolution input images. Although it reduces the computation requirements into a reasonable range, the downsampling operation causes information loss, which affects the accuracy of image classification. How to adopt high‐resolution image inputs to improve the quality of input information and thus improve the classification accuracy without changing the overall structure of the pre‐defined CNN model or increasing the model parameters is an important issue. Here, a CNN model with wavelet domain inputs is proposed to provide a solving scheme. Specifically, the proposed method applies wavelet packet transform or dual‐tree complex wavelet transform to extract information from input images with higher resolutions in the image pre‐processing stage. Some subband image channels are selected as the inputs of conventional CNNs where the first several convolutional layers are removed, so that the networks directly learn in the wavelet domain. Experiment results on the Caltech‐256 dataset and the Describable Textures Dataset with the ResNet‐50 show that the classification accuracy of our method can have a maximum improvement of 2.15% and 10.26%, respectively. These validate the effectiveness of our proposed scheme. This code is publicly available at https://github.com/BeBeBerr/wavelet‐cnn .
We present an automatic method based on transfer learning for the identification of dry age-related macular degeneration (AMD) and diabetic macular edema (DME) from retinal optical coherence tomography (OCT) images. The algorithm aims to improve the classification performance of retinal OCT images and shorten the training time. Firstly, we remove the last several layers from the pre-trained Inception V3 model and regard the remaining part as a fixed feature extractor. Then, the features are used as input of a convolutional neural network (CNN) designed to learn the feature space shifts. The experimental results on two different retinal OCT images datasets demonstrate the effectiveness of the proposed method.