Computer-aided diagnosis of proliferative diabetic retinopathy via modeling of the major temporal arcade in retinal fundus images

Automatic Grading of Retinal Blood Vessel in Deep Retinal Image Diagnosis

Automatic grading of retinal blood vessels from fundus image can be a useful tool for diagnosis, planning and treatment of eye. Automatic diagnosis of retinal images for early detection of glaucoma, stroke, and blindness is emerging in intelligent health care system. The method primarily depends on various abnormal signs, such as area of hard exudates, area of blood vessels, bifurcation points, texture, and entropies. The development of an automated screening system based on vessel width, tortuosity, and vessel branching are also used for grading. However, the automated method that directly can come to a decision by taking the fundus images got less attention. Detecting eye problems based on the tortuosity of the vessel from fundus images is a complicated task for opthalmologists. So automated grading algorithm using deep learning can be most valuable for grading retinal health. The aim of this work is to develop an automatic computer aided diagnosis system to solve the problem. This work approaches to achieve an automatic grading method that is opted using Convolutional Neural Network (CNN) model. In this work we have studied the state-of-the-art machine learning algorithms and proposed an attention network which can grade retinal images. The proposed method is validated on a public dataset EIARG1, which is only publicly available dataset for such task as per our knowledge.

Laterality Classification of Fundus Images Using Interpretable Deep Neural Network

In this paper, we aimed to understand and analyze the outputs of a convolutional neural network model that classifies the laterality of fundus images. Our model not only automatizes the classification process, which results in reducing the labors of clinicians, but also highlights the key regions in the image and evaluates the uncertainty for the decision with proper analytic tools. Our model was trained and tested with 25,911 fundus images (43.4% of macula-centered images and 28.3% each of superior and nasal retinal fundus images). Also, activation maps were generated to mark important regions in the image for the classification. Then, uncertainties were quantified to support explanations as to why certain images were incorrectly classified under the proposed model. Our model achieved a mean training accuracy of 99%, which is comparable to the performance of clinicians. Strong activations were detected at the location of optic disc and retinal blood vessels around the disc, which matches to the regions that clinicians attend when deciding the laterality. Uncertainty analysis discovered that misclassified images tend to accompany with high prediction uncertainties and are likely ungradable. We believe that visualization of informative regions and the estimation of uncertainty, along with presentation of the prediction result, would enhance the interpretability of neural network models in a way that clinicians can be benefitted from using the automatic classification system.

Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy

Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is the growth of abnormal new vessels. In this paper, an automated method for the detection of new vessels from retinal images is presented. This method is based on a dual classification approach. Two vessel segmentation approaches are applied to create two separate binary vessel map which each hold vital information. Local morphology features are measured from each binary vessel map to produce two separate 4-D feature vectors. Independent classification is performed for each feature vector using a support vector machine (SVM) classifier. The system then combines these individual outcomes to produce a final decision. This is followed by the creation of additional features to generate 21-D feature vectors, which feed into a genetic algorithm based feature selection approach with the objective of finding feature subsets that improve the performance of the classification. Sensitivity and specificity results using a dataset of 60 images are 0.9138 and 0.9600, respectively, on a per patch basis and 1.000 and 0.975, respectively, on a per image basis.

Real-time automated thickness measurement of the in vivo human tympanic membrane using optical coherence tomography

BACKGROUND

Otitis media (OM), an infection in the middle ear, is extremely common in the pediatric population. Current gold-standard methods for diagnosis include otoscopy for visualizing the surface features of the tympanic membrane (TM) and making qualitative assessments to determine middle ear content. OM typically presents as an acute infection, but can progress to chronic OM, and after numerous infections and antibiotic treatments over the course of many months, this disease is often treated by surgically inserting small tubes in the TM to relieve pressure, enable drainage, and provide aeration to the middle ear. Diagnosis and monitoring of OM is critical for successful management, but remains largely qualitative.

METHODS

We have developed an optical coherence tomography (OCT) system for high-resolution, depth-resolved, cross-sectional imaging of the TM and middle ear content, and for the quantitative assessment of in vivo TM thickness including the presence or absence of a middle ear biofilm. A novel algorithm was developed and demonstrated for automatic, real-time, and accurate measurement of TM thickness to aid in the diagnosis and monitoring of OM and other middle ear conditions. The segmentation algorithm applies a Hough transform to the OCT image data to determine the boundaries of the TM to calculate thickness.

RESULTS

The use of OCT and this segmentation algorithm is demonstrated first on layered phantoms and then during real-time acquisition of in vivo OCT from humans. For the layered phantoms, measured thicknesses varied by approximately 5 µm over time in the presence of large axial and rotational motion. In vivo data also demonstrated differences in thicknesses both spatially on a single TM, and across normal, acute, and chronic OM cases.

CONCLUSIONS

Real-time segmentation and thickness measurements of image data from both healthy subjects and those with acute and chronic OM demonstrate the use of OCT and this algorithm as a robust, quantitative, and accurate method for use during real-time in vivo human imaging.