Wyniki wyszukiwania - BazTech

1

Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images

Xu Yanan, Fan Yingle

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 2

695--706

EN

The morphological properties of retinal vessels are closely related to the diagnosis of ophthalmic diseases. However, many problems in retinal images, such as complicated directions of vessels and difficult recognition of capillaries, bring challenges to the accurate segmentation of retinal blood vessels. Thus, we propose a new retinal blood vessel segmentation method based on a dual-channel asymmetric convolutional neural network (CNN). First, we construct the thick and thin vessel extraction module based on the morphological differences in retinal vessels. A two-dimensional (2D) Gabor filter is used to perceive the scale characteristics of blood vessels after selecting the direction of blood vessels; thereby, adaptively extracting the thick vessel features characterizing the overall characteristics and the thin vessel features preserving the capillaries from fundus images. Then, considering that the single-channel network is unsuitable for the unified characterization of thick and thin vessels, we develop a dual-channel asymmetric CNN based on the U-Net model. The MainSegment-Net uses the step-by-step connection mode to achieve rapid positioning and segmentation of thick vessels; the FineSegment-Net combines dilated convolution and the skip connection to achieve the fine extraction of thin vessels. Finally, the output of the dual-channel asymmetric CNN is fused and coded to combine the segmentation results of thick and thin vessels. The performance of our method is evaluated and tested by DRIVE and CHASE_DB1. The results show that the accuracy (Acc), sensitivity (SE), and specificity (SP) of our method on the DRIVE database are 0.9630, 0.8745, and 0.9823, respectively. The evaluation indexes Acc, SE, and SP of the CHASE_DB1 database are 0.9694, 0.8916, and 0.9794, respectively. Additionally, our method combines the biological vision mechanism with deep learning to achieve rapid and automatic segmentation of retinal vessels, providing a new idea for diagnosing and analyzing subsequent medical images.

2

A deep learning framework for the detection of Plus disease in retinal fundus images of preterm infants

Ramachandran Sivakumar, Niyas Punnakadan, Vinekar Anand, John Renu

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

362--375

EN

Retinopathy of prematurity (ROP) is an eye disorder that mainly affects fundus vasculature of immature infants. The effect of this disease can be mild with no observable impairments or may become severe with neovascularization, leading to retinal detachment and possibly childhood blindness. Avital sign for initiating treatment for ROP is the detection of Plus disease, which is clinically diagnosed by identifying certain morphological changes to the blood vessels present in the retina of preterm infants. The main goal of this study is to develop a diagnostic method that can distinguish between Plus-diseased and healthy infant retinal images. This work utilizes a fully convolutional deep learning architecture for achieving the desired objective. We use a semi-supervised learning technique for training the network. The proposed technique accurately predicts bounding boxes over the tortuous vessel segments present in an infant retinal image. The count of bounding boxes serve as a measure to quantify tortuosity. We also compare the proposed technique with a recently introduced ROP diagnostic method employing U-COSFIRE filters. We show the efficacy of the proposed methodology on a proprietary data set of 289 infant retinal images (89 with ROP, and 200 healthy), obtained from KIDROP Bangalore, India. We obtain sensitivity (true positive rate) and specificity (true negative rate) equal to 0.99 and 0.98, respectively in the experimented data set. The results obtained in this study show the robustness of the proposed pipeline, as a computer aided diagnostic tool, that can augment medical experts in the early diagnosis of ROP.

3

Retinal vasculature segmentation and measurement framework for color fundus and SLO images

Pachade Samiksha, Porwal Prasanna, Kokare Manesh, Giancardo Luca, Meriaudeau Fabrice

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

865--900

EN

The change in vascular geometry is an indicator of various health issues linked with vision and cardiovascular risk factors. Early detection and diagnosis of these changes can help patients to select an appropriate treatment option when the disease is in its primary phase. Automatic segmentation and quantification of these vessels would decrease the cost and eliminate inconsistency related to manual grading. However, automatic detection of the vessels is challenging in the presence of retinal pathologies and non-uniform illumination, two common occurrences in clinical settings. This paper presents a novel framework to address the issue of retinal blood vessel detection and width measurement under these challenging circumstances and also on two different imaging modalities: color fundus imaging and Scanning Laser Ophthalmoscopy (SLO). In this framework, initially, vessel enhancement is done using linear recursive filtering. Then, a unique combination of morphological operations, background estimation, and iterative thresholding are applied to segment the blood vessels. Further, vessel diameter is estimated in two steps: firstly, vessel centerlines are extracted using the graph-based algorithm. Then, vessel edges are localized from the image profiles, by utilizing spline fitting to obtain vascular orientations and then finding the zero-crossings. Extensive experiments have been carried out on several publicly accessible datasets for vessel segmentation and diameter measurement, i.e., DRIVE, STARE, IOSTAR, RC-SLO and REVIEW dataset. Results demonstrate the competitive and comparable performance than earlier methods. The encouraging quantitative and visual performance of the proposed framework makes it an important component of a decision support system for retinal images.

4

Fast, accurate and robust retinal vessel segmentation system

Jiang Z., Yepez J., An S., Ko S.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

412--421

EN

The accurate segmentation of the retinal vessel tree has become the prerequisite step for automatic ophthalmological and cardiovascular diagnosis systems. Aside from accuracy, robustness and processing speed are also considered crucial for medical purposes. In order to meet those requirements, this work presents a novel approach to extract blood vessels from the retinal fundus, by using morphology-based global thresholding to draw the retinal venule structure and centerline detection method for capillaries. The proposed system is tested on DRIVE and STARE databases and has an average accuracy of 95.88% for single-database test and 95.27% for the cross-database test. Meanwhile, the system is designed to minimize the computing complexity and processes multiple independent procedures in parallel, thus having an execution time of 1.677 s per image on CPU platform.

5

Zastosowanie metody zbiorów poziomicowych do wyodrębniania struktur naczyniowych w obrębie nerki w celu minimalizacji inwazyjności zabiegów onkologicznych

Bugajska K., Skalski A., Drewniak T., Gajda J.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 5

68-71

PL

W artykule zaproponowano zastosowanie algorytmów przetwarzania obrazów w celu wyodrębnienia struktur naczyniowych zlokalizowanych w obrębie nerki. Możliwość identyfikacji tętnic odżywiających guza nerki pozwala na jego usunięcie bez ryzyka wystąpienia urazu niedokrwiennego i przyczynia się do maksymalnego zabezpieczenia czynności nerki. Minimalizacja inwazyjności zabiegu usunięcia guza jest także korzystna dla pacjenta. Badania rozpoczęto od segmentacji struktur naczyniowych preparatów anatomicznych. Do ich wyodrębnienia zastosowano progowanie z histerezą, co pozwoliło na otrzymanie funkcji inicjalizującej dla metody zbiorów poziomicowych. Otrzymane wyniki potwierdziły skuteczność doboru metody - wizualnie ciągłość tych struktur była lepiej odtworzona względem samej binaryzacji, a granice obiektów były odpowiednio odwzorowane. Dodatkowo, analiza ilościowa polegająca na porównaniu otrzymanych wyników działania algorytmu z ręcznymi obrysami okazała się zadawalająca, co skłania do kontynuacji badań mogących stanowić o renoprotekcji.

EN

In the article we have proposed an application of several image processing algorithms to extract renal vessels. Earlier identification of the tumor feeding arteries facilitates conducting a zero-ischemia partial nephrectomy and preservation of renal function. This minimally invasive procedure is also beneficial for a patient. The study began with vascular structures segmentation of anatomical preparations. To do this hysteresis thresholding was applied to three dimensional computer tomography images. It allowed to obtain an initialization function for subsequently applied segmentation method – i.e. the level set method. The results confirmed the effectiveness of described methods - visually, in comparison to initial binarization, the acquired structures continuity had been found better and the objects boundaries were properly mapped. In addition, quantitative analysis involving the comparison of segmentation results with manual ones had been found satisfactory, that encourages to continue further research.