scholarly journals Automated feature-based grading and progression analysis of diabetic retinopathy

Eye ◽  
2021 ◽  
Author(s):  
Lutfiah Al-Turk ◽  
James Wawrzynski ◽  
Su Wang ◽  
Paul Krause ◽  
George M. Saleh ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Diabetic Macular Oedema ◽  
Large Datasets ◽  
Image Analysis System ◽  
Learning Approaches ◽  
External Evaluation ◽  
Severity Scale ◽  
Grading Systems ◽  
Feature Based ◽  
Analysis System

Abstract Background In diabetic retinopathy (DR) screening programmes feature-based grading guidelines are used by human graders. However, recent deep learning approaches have focused on end to end learning, based on labelled data at the whole image level. Most predictions from such software offer a direct grading output without information about the retinal features responsible for the grade. In this work, we demonstrate a feature based retinal image analysis system, which aims to support flexible grading and monitor progression. Methods The system was evaluated against images that had been graded according to two different grading systems; The International Clinical Diabetic Retinopathy and Diabetic Macular Oedema Severity Scale and the UK’s National Screening Committee guidelines. Results External evaluation on large datasets collected from three nations (Kenya, Saudi Arabia and China) was carried out. On a DR referable level, sensitivity did not vary significantly between different DR grading schemes (91.2–94.2.0%) and there were excellent specificity values above 93% in all image sets. More importantly, no cases of severe non-proliferative DR, proliferative DR or DMO were missed. Conclusions We demonstrate the potential of an AI feature-based DR grading system that is not constrained to any specific grading scheme.

scholarly journals Impact of baseline Diabetic Retinopathy Severity Scale scores on visual outcomes in the VIVID-DME and VISTA-DME studies

2017 ◽  
Vol 102 (7) ◽  
pp. 954-958 ◽  
Author(s):  
Giovanni Staurenghi ◽  
Nicolas Feltgen ◽  
Jennifer J Arnold ◽  
Todd A Katz ◽  
Carola Metzig ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Group Versus ◽  
Diabetic Macular Oedema ◽  
Severity Scale ◽  
Treatment Benefit ◽  
Treatment Groups ◽  
Link Type ◽  
Intravitreal Aflibercept ◽  
Scale Scores ◽  
Consistent Treatment

Background/aimsTo evaluate intravitreal aflibercept versus laser in subgroups of patients with baseline Diabetic Retinopathy Severity Scale (DRSS) scores ≤43, 47, and ≥53 in VIVID-DME and VISTA-DME.MethodsPatients with diabetic macular oedema were randomised to receive intravitreal aflibercept 2 mg every 4 weeks (2q4), intravitreal aflibercept 2 mg every 8 weeks after five initial monthly doses (2q8), or macular laser photocoagulation at baseline with sham injections at every visit. These post hoc analyses evaluate outcomes based on baseline DRSS scores in patients in the integrated dataset. The 2q4 and 2q8 treatment groups were also pooled.Results748 patients had a baseline DRSS score based on fundus photographs (≤43, n=301; 47, n=153; ≥53, n=294). At week 100, the least squares mean difference between treatment groups (effect of intravitreal aflibercept above that of laser, adjusting for baseline best-corrected visual acuity) was 8.9 (95% CI 5.99 to 11.81), 9.7 (95% CI 5.54 to 13.91), and 11.0 (95% CI 7.96 to 14.1) letters in those with baseline DRSS scores ≤43, 47, and ≥53, respectively. The proportions of patients with ≥2 step DRSS score improvement were greater in the intravitreal aflibercept group versus laser, respectively, for those with baseline DRSS scores of ≤43 (13% vs 5.9%), 47 (25.8% vs 4.5%), and ≥53 (64.5% vs 28.4%).ConclusionsRegardless of baseline DRSS score, functional outcomes were superior in intravitreal aflibercept-treated patients, demonstrating consistent treatment benefit across various baseline levels of retinopathy.Trial registration numbersNCT01331681 and NCT01363440, Post-results.

scholarly journals Automated Method for Optic Disc Detection and Elimination in Digital Fundus Images

2019 ◽  
Vol 8 (4) ◽  
pp. 12558-12563
Keyword(s):  
Diabetic Retinopathy ◽  
Optic Disc ◽  
Retinal Diseases ◽  
Image Analysis System ◽  
Fundus Images ◽  
Connected Component ◽  
Automated Method ◽  
Novel Method ◽  
Disc Region ◽  
Analysis System

Localizing, segmenting and eliminating the optic disc region of a fundus image is a prerequisite task in the automatic investigation of a number of retinal diseases such as Diabetic retinopathy, Glaucoma, Macular Edema, etc. Accurate detection of optic disc is a challenging task due to a number of reasons. Optic disc in most fundus images does not exhibit clear disc boundaries and there are number of blood vessels crossing it. An important task in automated retinal image analysis system is the detection and elimination of optic disc because the lesion regions in diabetic retinopathy closely resemble the color and texture of an optic disc. Hence, eliminating the optic disc region can improve the performance of diabetic retinopathy detection. The proposed work presents a novel method for optic disc segmentation which is not restricted by the location of the optic disc on the retina. The proposed algorithm localizes the position of the optic disc that is independent of its location and dynamically finds its center. The proposed method is tested on images from DRISHTI-GS, DIARETDB1, DRIONS-DB and DRIVE databases based on morphological operation and finding the largest connected component. The precision values of segmentation for digital fundus images from DRISHTI-GS, DIARETDB1, DRIONS-DB, and DRIVE databases are 0.98, 0.99, 0.98 and 0.99 respectively using the proposed method. The algorithm has yielded consistent high values of precision and recall indicating its robustness and efficiency.

Digital Processing of STEM Images

1981 ◽  
Vol 39 ◽  
pp. 236-237
Author(s):  
A. V. Crewe ◽  
M. Ohtsuki
Keyword(s):  
High Resolution ◽  
Low Dose ◽  
Assembly Language ◽  
Processing System ◽  
Principal Component ◽  
Digital Processing ◽  
Image Analysis System ◽  
Black And White ◽  
Analysis System ◽  
Dose Imaging

We have assembled an image processing system for use with our high resolution STEM for the particular purpose of working with low dose images of biological specimens. The system is quite flexible, however, and can be used for a wide variety of images.The original images are stored on magnetic tape at the microscope using the digitized signals from the detectors. For low dose imaging, these are “first scan” exposures using an automatic montage system. One Nova minicomputer and one tape drive are dedicated to this task.The principal component of the image analysis system is a Lexidata 3400 frame store memory. This memory is arranged in a 640 x 512 x 16 bit configuration. Images are displayed simultaneously on two high resolution monitors, one color and one black and white. Interaction with the memory is obtained using a Nova 4 (32K) computer and a trackball and switch unit provided by Lexidata.The language used is BASIC and uses a variety of assembly language Calls, some provided by Lexidata, but the majority written by students (D. Kopf and N. Townes).

Chemical Classification and Particle Sizing of Foundry Sands

1985 ◽  
Vol 43 ◽  
pp. 388-389
Author(s):  
D.S. DeMiglio
Keyword(s):  
Image Analysis ◽  
Energy Dispersive Spectrometer ◽  
Image Analysis System ◽  
Representative Sampling ◽  
Foundry Sands ◽  
Large Atomic Number ◽  
Backscattered Electron ◽  
Sand Particles ◽  
Analysis System ◽  
Reclamation System

Much progress has been made in recent years towards the development of closed-loop foundry sand reclamation systems. However, virtually all work to date has determined the effectiveness of these systems to remove surface clay and metal oxide scales by a qualitative inspection of a representative sampling of sand particles. In this investigation, particles from a series of foundry sands were sized and chemically classified by a Lemont image analysis system (which was interfaced with an SEM and an X-ray energy dispersive spectrometer) in order to statistically document the effectiveness of a reclamation system developed by The Pangborn Company - a subsidiary of SOHIO.The following samples were submitted: unreclaimed sand; calcined sand; calcined & mechanically scrubbed sand and unused sand. Prior to analysis, each sample was sprinkled onto a carbon mount and coated with an evaporated film of carbon. A backscattered electron photomicrograph of a field of scale-covered particles is shown in Figure 1. Due to a large atomic number difference between sand particles and the carbon mount, the backscattered electron signal was used for image analysis since it had a uniform contrast over the shape of each particle.

Цифровая морфометрия разнокачественности семян овощных культур

2018 ◽  
Author(s):  
F.B. Musaev ◽  
N.S. Priyatkin ◽  
M.V. Arkhipov ◽  
P.A. Shchukina ◽  
A.F. Bukharov ◽  
...  
Keyword(s):  
Seed Quality ◽  
Image Analysis System ◽  
Flatbed Scanner ◽  
The Future ◽  
Scanned Images ◽  
Computer Morphometry ◽  
Analysis System ◽  
Matrix Heterogeneity ◽  
Relationship Of ◽  
Selection Of

Приведено описание разработанной авторами методики цифровой компьютерной морфометрии семян овощных культур на основе системы анализа изображений, состоящей из планшетного сканера и программного обеспечения для автоматических измерений. В основу метода положено представление о разнокачественности семян, обусловленной генетической неоднородностью самих семенных растений, используемых в промышленном семеноводстве. Физические свойства семян (их форма и линейные размеры) – основные параметры при определении их качества. Цифровые изображения семян получены при помощи планшетного сканера HP Sсanjet 200 на базе Агрофизического НИИ с использованием серийного программного обеспечения «Argus-BIO», производства ООО «АргусСофт» (г. Санкт-Петербург). Метод состоит из подбора контрастной подложки (фона) для сканирования семян с минимальными теневыми эффектами, калибровку программного обеспечения для привязки к истинным размерным величинам, подбор параметров измерений и автоматическое распознавание цифровых сканированных изображений семян. Представлены экспериментальные данные по морфометрии экологически разнокачественных семян фасоли овощной, матрикально разнокачественных семян укропа, пастернака и лука Кристофа. Семена укропа и пастернака, собранные из разных порядков ветвления семенного растения, значительно различались по величине линейных параметров. Наиболее показательный линейный параметр семян – площадь проекции. Предложенная авторами методика цифровой морфометрии, уже использована на практике и в перспективе может быть задействована в исследованиях экологической и матрикальной разнокачественности семян овощных культур. Так, она прошла апробацию на разнокачественных семенах пяти сортов фасоли овощной (Настена, Магура, Миробела, Морена, Бажена) полученных в пяти контрастных эколого-географических условиях среды (Москва, Белгород, Ставрополь, Омск, Горки) в 2011–2012 годах. В дальнейшем методика может быть использована для улучшения качества цифровых изображений семян, изучения разнокачественности семян в том числе и для совершенствования контроля за селекционным процессом. Кроме того, она применима для изучения взаимосвязи совокупности морфометрических характеристик семян и их посевных качеств.The description of the method of digital computer morphometry of vegetable seeds developed by the authors on the basis of the image analysis system consisting of a flatbed scanner and software for automatic measurements is given. The method is based on the idea of seed quality, due to the genetic heterogeneity of the seed plants used in industrial seed production. Physical properties of seeds (their shape and linear dimensions) are the main parameters in determining their quality. Digital image of the seed obtained using the flatbed scanner, HP Sсanjet 200 on the basis of the Agrophysical research Institute with serial software “Argus-BIO”, produced by LLC “Argussoft” (Saint-Petersburg). The method consists of selection of a contrast substrate (background) for scanning seeds with minimal shadow effects, calibration of software for binding to true size values, selection of measurement parameters and automatic recognition of digital scanned images of seeds. Experimental data on the morphometry of ecologically different-quality seeds of vegetable beans, matrix seeds of dill, Pasternak and Christoph onion are presented. Seeds of dill and parsnip, collected from different orders of branching of the seed plant, significantly differed in size of linear parameters. The most revealing linear parameter seed – area projection. The method of digital morphometry proposed by the authors has already been used in practice and in the future can be used in studies of ecological and matrix heterogeneity of vegetable seeds. So, it was tested on different quality seeds of five varieties of vegetable beans (Nastena, Magura, Mirobelа, Morena, Bazhenf) obtained in five contrasting environmental and geographical conditions (Moscow, Belgorod, Stavropol, Omsk, Gorki) in 2011-2012. In the future, the technique can be used to improve the quality of digital images of seeds, study of seed diversity, including to improve the control of the breeding process. In addition, it is applicable to study the relationship of the set of morphometric characteristics of seeds and their sowing qualities.

Sign in / Sign up

Export Citation Format

Share Document