RETRACTED: Enhancing online health consultations through fuzzy logic-integrated attribute-based encryption system

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

Plus Disease in Retinopathy of Prematurity: Convolutional Neural Network Performance Using a Combined Neural Network and Feature Extraction Approach

Purpose

Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed by clinical ophthalmoscopic examinations or reading retinal images. Plus disease, defined as abnormal tortuosity and dilation of the posterior retinal blood vessels, is the most important feature to determine treatment-requiring ROP. We aimed to create a complete, publicly available and feature-extraction-based pipeline, I-ROP ASSIST, that achieves convolutional neural network (CNN)-like performance when diagnosing plus disease from retinal images.

Methods

We developed two datasets containing 100 and 5512 posterior retinal images, respectively. After segmenting retinal vessels, we detected the vessel centerlines. Then, we extracted features relevant to ROP, including tortuosity and dilation measures, and used these features in the classifiers including logistic regression, support vector machine and neural networks to assess a severity score for the input. We tested our system with fivefold cross-validation and calculated the area under the curve (AUC) metric for each classifier and dataset.

Results

For predicting plus versus not-plus categories, we achieved 99% and 94% AUC on the first and second datasets, respectively. For predicting pre-plus or worse versus normal categories, we achieved 99% and 88% AUC on the first and second datasets, respectively. The CNN method achieved 98% and 94% for predicting two categories on the second dataset.

Conclusions

Our system combining automatic retinal vessel segmentation, tracing, feature extraction and classification is able to diagnose plus disease in ROP with CNN-like performance.

Translational Relevance

The high performance of I-ROP ASSIST suggests potential applications in automated and objective diagnosis of plus disease.

Comprehensive Retinal Image Analysis for Aggressive Posterior Retinopathy of Prematurity

Computer aided analysis plays a nontrivial role in assisting the diagnosis of various eye pathologies. In this paper, we propose a framework to help diagnose the presence of Aggressive Posterior Retinopathy Of Prematurity (APROP), a pathology that is characterised by rapid onset and increased tortuosity of blood vessels close to the optic disc (OD). We quantify vessel characteristics that are of clinical relevance to APROP such as tortuosity and the extent of branching i.e., vessel segment count in the defined diagnostic region. We have adapted three vessel segmentation techniques: matched filter response, scale space theory and morphology with local entropy based thresholding. The proposed feature set equips us to build a linear discriminant classifier to discriminate APROP images from clinically healthy images. We have studied 36 images from 21 APROP subjects against a control group of 15 clinically healthy age matched infants. All subjects are age matched ranging from 33−40 weeks of post menstrual age. Experimental results show that we attain 100% recall and 95.45% precision, when the vessel network obtained from morphology is used for feature extraction.

Automated retinal vessel recognition and measurements on large datasets

The characteristics of the retinal vascular network have been prospectively associated with many systemic and vascular diseases. QUARTZ is a fully automated software that has been developed to localize and quantify the morphological characteristics of blood vessels in retinal images for use in epidemiological studies. This software was used to analyse a dataset containing 16,000 retinal images from the EPIC-Norfolk cohort study. The objective of this paper is to both assess the suitability of this dataset for computational analysis and to further evaluate the QUARTZ software.

Decision support systems and applications in ophthalmology: literature and commercial review focused on mobile apps

The growing importance that mobile devices have in daily life has also reached health care and medicine. This is making the paradigm of health care change and the concept of mHealth or mobile health more relevant, whose main essence is the apps. This new reality makes it possible for doctors who are not specialist to have easy access to all the information generated in different corners of the world, making them potential keepers of that knowledge. However, the new daily information exceeds the limits of the human intellect, making Decision Support Systems (DSS) necessary for helping doctors to diagnose diseases and also help them to decide the attitude that has to be taken towards these diagnoses. These could improve the health care in remote areas and developing countries. All of this is even more important in diseases that are more prevalent in primary care and that directly affect the people's quality of life, this is the case in ophthalmological problems where in first patient care a specialist in ophthalmology is not involved. The goal of this paper is to analyse the state of the art of DSS in Ophthalmology. Many of them focused on diseases affecting the eye's posterior pole. For achieving the main purpose of this research work, a literature review and commercial apps analysis will be done. The used databases and systems will be IEEE Xplore, Web of Science (WoS), Scopus, and PubMed. The search is limited to articles published from 2000 until now. Later, different Mobile Decision Support System (MDSS) in Ophthalmology will be analyzed in the virtual stores for Android and iOS. 37 articles were selected according their thematic (posterior pole, anterior pole, Electronic Health Records (EHRs), cloud, data mining, algorithms and structures for DSS, and other) from a total of 600 found in the above cited databases. Very few mobile apps were found in the different stores. It can be concluded that almost all existing mobile apps are focused on the eye's posterior pole. Among them, the most intended are for diagnostic of diabetic retinopathy. The primary market niche of the commercial apps is the general physicians.

Blood vessel segmentation methodologies in retinal images--a survey

Retinal vessel segmentation algorithms are a fundamental component of automatic retinal disease screening systems. This work examines the blood vessel segmentation methodologies in two dimensional retinal images acquired from a fundus camera and a survey of techniques is presented. The aim of this paper is to review, analyze and categorize the retinal vessel extraction algorithms, techniques and methodologies, giving a brief description, highlighting the key points and the performance measures. We intend to give the reader a framework for the existing research; to introduce the range of retinal vessel segmentation algorithms; to discuss the current trends and future directions and summarize the open problems. The performance of algorithms is compared and analyzed on two publicly available databases (DRIVE and STARE) of retinal images using a number of measures which include accuracy, true positive rate, false positive rate, sensitivity, specificity and area under receiver operating characteristic (ROC) curve.

An automated computational framework for retinal vascular network labeling and branching order analysis

Changes in retinal vascular morphology are well known as predictive clinical signs of many diseases such as hypertension, diabetes and so on. Computer-aid image processing and analysis for retinal vessels in fundus images are effective and efficient in clinical diagnosis instead of tedious manual labeling and measurement. An automated computational framework for retinal vascular network labeling and analysis is presented in this work. The framework includes 1) detecting and locating the optic disc; 2) tracking the vessel centerline from detected seed points and linking the breaks after tracing; 3) extracting all the retinal vascular trees and identifying all the significant points; and 4) classifying terminal points into starting points and ending points based on the information of optic disc location, and finally assigning branch order for each extracted vascular tree in the image. All the modules in the framework are fully automated. Based on the results, morphological analysis is then applied to achieve geometrical and topological features based on branching order for one individual vascular tree or for the vascular network through the retinal vascular network in the images. Validation and experiments on the public DRIVE database have demonstrated that the proposed framework is a novel approach to analyze and study the vascular network pattern, and may offer new insights to the diagnosis of retinopathy.

Quantitative imaging of retinal pigment epithelial detachments using spectral-domain optical coherence tomography

PURPOSE

To evaluate the reproducibility of area and volume measurements of retinal pigment epithelium detachments (PEDs) in eyes of patients with age-related macular degeneration using spectral-domain optical coherence tomography imaging and a novel automated, quantitative algorithm.

DESIGN

Prospective study to evaluate a diagnostic technology.

METHODS

Patients with PEDs associated with age-related macular degeneration underwent spectral-domain optical coherence tomography imaging. Each eye was imaged 5 times, and each scan consisted of a raster pattern comprising 40 000 uniformly spaced A-scans organized as a 200 × 200 A-scan array. Each raster scan covered a retinal area of 6 × 6 mm encompassing the entire PED. A novel algorithm was used to create PED maps that permitted both qualitative and quantitative assessment of PED area and volume. Test-retest standard deviations of PED area and volume measurements were calculated for each eye.

RESULTS

Sixty-three eyes of 58 patients were enrolled in this study. The qualitative appearance and the quantitative measurements of PED area and volume were highly reproducible over the 5 different datasets obtained from each eye. The intraclass correlation coefficient was more than 0.99 for both area and volume measurements obtained using the entire dataset.

CONCLUSIONS

A novel algorithm for the qualitative and quantitative assessment of PEDs imaged using spectral-domain optical coherence tomography was shown to be highly reproducible. The ability to measure PED area and volume reliably represents a novel strategy for following disease progression, especially when assessing the response of vascularized PEDs to antiangiogenic therapy.

Comparison of autophotomontage software programs in eyes with CMV retinitis

PURPOSE

Automated mosaic software programs are used to stitch together overlapping retinal fundus photographs. The performance of these programs in eyes with retinal diseases has not been independently evaluated. This study compares the quality of the mosaic products of three autophotomontage software programs, using digital fundus photographs of eyes with cytomegalovirus (CMV) retinitis.

METHODS

Photographs of 99 eyes with CMV retinitis of 94 patients with HIV were taken at Maharaj Nakorn Chiang Mai Hospital in Chiang Mai, Thailand. Automated mosaic images were created for each of the 99 eyes by three different commercially available programs: IMAGEnet (Topcon, Oakland, NJ), i2k Retina (DualAlign LLC, Clifton Park, NY), and AutoMontage (OIS, Sacramento, CA). Three masked graders ranked each set of mosaics for each eye. The graders also assessed the overall image quality and documented mosaic artifacts in each image.

RESULTS

i2k Retina was ranked as the best program (70%-88%) more often than AutoMontage (10%-33%, P < 0.001) or IMAGEnet (0%-4%, P < 0.001) for creating automontages from digital fundus photographs of eyes with CMV retinitis. Acceptable quality mosaic images were reported most commonly for i2k Retina (93%-94%) and AutoMontage (91%-95%), followed by IMAGEnet (27%-56%, P < 0.001). IMAGEnet had a significantly higher percentage of mosaic errors than did either i2k Retina or AutoMontage (P < 0.001).

CONCLUSIONS

In eyes with CMV retinitis, both the i2k Retina and AutoMontage software packages appear to create higher quality mosaics than does IMAGEnet. Automated retinal mosaic imaging may be valuable in diagnosing CMV retinitis and observing disease progression.

Development, implementation, and multicenter clinical validation of the TeleDICOM--advanced, interactive teleconsultation system

There is a need to make medical diagnosis available to critically ill patients on-site, without the necessity of time-consuming and risky transportation to larger reference hospitals. The teleconsultation of medical images is possible with the use of Internet-based TeleDICOM software developed in Krakow, Poland. Interactive consultation between two or more centers offers real-time voice communication, visualization of synchronized Digital Imaging and Communications in Medicine images, and use of interactive pointers and specific calculation tools. If direct interaction between physicians is not needed, the system can also be used in "offline" mode. In 2006, TeleDICOM was successfully deployed in the John Paul II Hospital in Krakow as well as a dozen other cooperating medical centers throughout southeast Poland. It is used for routine referral for cardiosurgical procedures. Aims of the study were to evaluate the image quality, software stability, constant availability, data transmission speed, and quality of real-time synchronized viewing of the images during the TeleDICOM teleconsultation; to evaluate the clinical utility of the TeleDICOM system; and to analyze the compatibility of TeleDICOM with the storage data formats of various imaging machine manufacturers. The analysis of angiographic offline teleconsultations was based on 918 patients referred remotely for coronary artery bypass grafting (CABG). The echocardiographic teleconsultations were performed during 63 live interactive consultations, several of them were presented to live during medical conferences. Measurement tools of the TeleDICOM software were tested against original measurement tools of echocardiographic machines from four different manufacturers. As a result of TeleDICOM consultation, a CABG decision was made in 806 of 918 patients consulted (87.8%). In remaining 12 patients, medical therapy or percutaneous angioplasty was recommended. CABG was performed in 98.6% of the admitted patients. Treatment decisions were changed after admission in 1.4% of patients-however, in all cases, it was not related to analysis of angiography data but rather to the change of clinical condition of the patients. All medical personnel involved in both offline and interactive teleconsultations judged the system positively in all assessed aspects. Lesser scores were observed only in the centers connected by slower networks. Measurements performed in the ECHO-TeleDICOM module were accurate as compared with those performed on a standard echo-machine (correlation r > 0.980, p < 0.001), independently of the echocardiograph model.

CONCLUSION

This study demonstrates that telemedicine can improve patients' management using a clinically effective teleconsultation system. The TeleDICOM system is suited for professional use in the field of cardiovascular disease. It is also prepared for remote live demonstrations of clinical cases during large medical meetings.

An integrated software solution for multi-modal mapping of morphological and functional ocular data

Various morphological and functional techniques for retina examination have been established in the recent years. Although many examination results are spatially resolved and can be mapped onto data originating from other modalities, usually only data from one modality is analyzed by a clinician at a time. This is mainly because there is no software available to the public that enables the registration of structure and function in the clinical setting. Therefore we developed an integrated mapping application that allows the registration and analysis of morphological data (fundus photography, optical coherence tomography, scanning laser ophthalmoscopy images, and GDx thickness profiles) and functional data (multifocal electroretinography, multifocal pattern electroretinography, perimetry, and microperimetry). To obtain quantitative data that can be used for clinical trials and statistical analyses, extraction routines for morphological parameters - such as retinal layer thicknesses and measures of the vascular network - have been integrated. Global, regional and point-specific data from registered modalities can be extracted and exported for statistical analyses. In this article we present the implementation and examples of use of the developed software.