A novel computer aided quantification method of focal arteriolar narrowing using colour retinal image

The Use of Texture Features to Extract and Analyze Useful Information from Retinal Images

Background:

The analysis of retinal images can help to detect retinal abnormalities that are caused by cardiovascular and retinal disorders.

Objective:

In this paper, we propose methods based on texture features for mining and analyzing information from retinal images.

Methods:

The recognition of the retinal mask region is a prerequisite for retinal image processing. However, there is no way to automatically recognize the retinal region. By quantifying and analyzing texture features, a method is proposed to automatically identify the retinal region. The boundary of the circular retinal region is detected based on the image texture contrast feature, followed by the filling of the closed circular area, and then the detected circular retinal mask region can be obtained.

Results:

The experimental results show that the method based on the image contrast feature can be used to detect the retinal region automatically. The average accuracy of retinal mask region detection of images from the Digital Retinal Images for Vessel Extraction (DRIVE) database was 99.34%.

Conclusion:

This is the first time these texture features of retinal images are analyzed, and texture features are used to recognize the circular retinal region automatically.

Research on FAE Cloud Image Processing Method Based on Background Subtraction and Region Growing

After the first initiation, the Fuel Air Explosive (FAE) cloud formed through fuel explosion dispersal and it will generate tremendous damaging power after being detonated the second time. As the damaging power is closely related to the determination of reinitiation time, it is of great significance to study the growth principle of FAE cloud by means of analyzing FAE cloud images. Combining with background subtraction and region growing, an improved region growing image processing method was proposed, in which the seeds of region growing abstracted through background subtraction method and the growing criterion was modified. With this method, the integrate area of cloud can be obtained for extracting geometric parameters. Experiments were carried out on both cloudy and sunny days, and image overlap score was used to quantitatively evaluate the accuracy of images segmentation. The result indicated that this image processing method has advantages of high precision and robustness. In addition, the computation burden is reduced significantly compared with traditional region growing method.

Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network

BACKGROUND

Ocular images play an essential role in ophthalmological diagnoses. Having an imbalanced dataset is an inevitable issue in automated ocular diseases diagnosis; the scarcity of positive samples always tends to result in the misdiagnosis of severe patients during the classification task. Exploring an effective computer-aided diagnostic method to deal with imbalanced ophthalmological dataset is crucial.

METHODS

In this paper, we develop an effective cost-sensitive deep residual convolutional neural network (CS-ResCNN) classifier to diagnose ophthalmic diseases using retro-illumination images. First, the regions of interest (crystalline lens) are automatically identified via twice-applied Canny detection and Hough transformation. Then, the localized zones are fed into the CS-ResCNN to extract high-level features for subsequent use in automatic diagnosis. Second, the impacts of cost factors on the CS-ResCNN are further analyzed using a grid-search procedure to verify that our proposed system is robust and efficient.

RESULTS

Qualitative analyses and quantitative experimental results demonstrate that our proposed method outperforms other conventional approaches and offers exceptional mean accuracy (92.24%), specificity (93.19%), sensitivity (89.66%) and AUC (97.11%) results. Moreover, the sensitivity of the CS-ResCNN is enhanced by over 13.6% compared to the native CNN method.

CONCLUSION

Our study provides a practical strategy for addressing imbalanced ophthalmological datasets and has the potential to be applied to other medical images. The developed and deployed CS-ResCNN could serve as computer-aided diagnosis software for ophthalmologists in clinical application.

Hypertension and the eye

PURPOSE OF REVIEW

Hypertension is the primary risk factor for cardiovascular disease and mortality that consists a major public health issue worldwide. Hypertension triggers a series of pathophysiological ocular modifications affecting significantly the retinal, choroidal, and optic nerve circulations that result in a range of ocular effects.The retina is the only place in the body where microvasculature can be directly inspected, providing valuable information on hypertension related systemic risks.The aim of this review is to provide an update on latest advances regarding the detection and significance of hypertension related eye signs.

RECENT FINDINGS

It's been shown that measurable retinal microvascular changes may precede progression of systemic microvascular disease.Last years, there are emerging advances in the field retinal imaging and computer software analysis that have enabled the objective and accurate assessment of retinal vascular caliber, while in association with latest epidemiological studies several other retinal vascular features have been recognized, such as vascular length-to-diameter ratio, and wall-to-lumen ratio that may also be associated to hypertension.Additionally, recent genetic studies have provided some insight to vascular pathophysiological processes having correlated new chromosome's loci to hypertensive retinopathy signs.

SUMMARY

Assessment of hypertensive retinopathy signs may convey additional prognostic information on the risk of end-organ damage and may alert for urgent systemic management or even preventive systemic therapies. Further development of retinal vascular imaging and computerized system may provide a significant tool to improve the diagnosis, prognosis, and management of hypertension in clinical practice.