A lightweight deep learning model for retinal optical coherence tomography image classification

Automated retinal disease detection and grading is one of the most researched areas in medical image analysis. In recent years, Deep Learning models have attracted much attention in this field. Hence, in this paper, we present a Deep Learning-based, lightweight, fully automated end-to-end diagnostic system for the detection of the two major retinal diseases, namely diabetic macular oedema (DME) and drusen macular degeneration (DMD). Early detection of these diseases is important to prevent vision impairment. Optical coherence tomography (OCT) is the main imaging technique for detecting these diseases. The model proposed in this work is based on residual blocks and channel attention modules. The performance of the model is evaluated using the publicly available Mendeley OCT dataset and the Duke dataset. We were able to achieve a classification accuracy of 99.5% in the Mendeley test dataset and 94.9% in the Duke dataset with the proposed model. For the application, we performed an extensive evaluation of pre-trained models (LeNet, AlexNet, VGG-16, ResNet50 and SE-ResNet). The proposed model has a much smaller number of trainable parameters and shows superior performance compared to existing methods.     

Enhancement of intrinsic optical signal recording with split spectrum optical coherence tomography

Functional optical coherence tomography (OCT) of stimulus-evoked intrinsic optical signal (IOS) promises to be a new methodology for high-resolution mapping of retinal neural dysfunctions. However, its practical applications for non-invasive examination of retinal function have been hindered by the low signal-to-noise ratio (SNR) and small magnitude of IOSs. Split spectrum amplitude-decorrelation has been demonstrated to improve the image quality of OCT angiography. In this study, we exploited split spectrum strategy to improve the sensitivity of IOS recording. The full OCT spectrum was split into multiple spectral bands and IOSs from each sub-band were calculated separately and then combined to generate a single IOS image sequence. The algorithm was tested on in vivo images of frog retinas. It significantly improved both IOS magnitude and SNR, which are essential for practical applications of functional IOS imaging.     

Attenuating noise from computed tomography medical images using a coefficients‐driven total variation denoising algorithm

The aim of image denoising is to recover a visually accepted image from its noisy observation with as much detail as possible. The noise exists in computed tomography images due to hardware errors, software faults and/or low radiation dose. Because of noise, the analysis and extraction of accurate medical information is a challenging task for specialists. Therefore, a novel modification on the total variational denoising algorithm is proposed in this article to attenuate the noise from CT images and provide a better visual quality. The newly developed algorithm can properly detect noise from the other image components using four new noise distinguishing coefficients and reduce it using a novel minimization function. Moreover, the proposed algorithm has a fast computation speed, a simple structure, a relatively low computational cost and preserves the small image details while reducing the noise efficiently. Evaluating the performance of the proposed algorithm is achieved through the use of synthetic and real noisy images. Likewise, the synthetic images are appraised by three advanced accuracy methods –Gradient Magnitude Similarity Deviation (GMSD), Structural Similarity (SSIM) and Weighted Signal‐to‐Noise Ratio (WSNR). The empirical results exhibited significant improvement not only in noise reduction but also in preserving the minor image details. Finally, the proposed algorithm provided satisfying results that outperformed all the comparative methods.     

Determining elastic properties of skin by measuring surface waves from an impulse mechanical stimulus using phase-sensitive optical coherence tomography

The mechanical properties of skin are important tissue parameters that are useful for understanding skin patho-physiology, which can aid disease diagnosis and treatment. This paper presents an innovative method that employs phase-sensitive spectral-domain optical coherence tomography (PhS-OCT) to characterize the biomechanical properties of skin by measuring surface waves induced by short impulses from a home-made shaker. Experiments are carried out on single and double-layer agar–agar phantoms, of different concentrations and thickness, and on in vivo human skin, at the forearm and the palm. For each experiment, the surface wave phase-velocity dispersion curves were calculated, from which the elasticity of each layer of the sample was determined. It is demonstrated that the experimental results agree well with previous work. This study provides a novel combination of PhS-OCT technology with a simple and an inexpensive mechanical impulse surface wave stimulation that can be used to non-invasively evaluate the mechanical properties of skin in vivo, and may offer potential use in clinical situations.