Collaborative Deep Learning for Privacy Preserving Diabetic Retinopathy Detection.

Convolutional Neural Networks (CNNs) are an emerging research area for detection of Diabetic Retinopathy (DR) development in fundus images with highly reliable results. However, its accuracy depends on the availability of big datasets to train such a deep network. Due to the privacy concerns, the strict rules on medical data limit accessibility of images in publicly available datasets. In this paper, we propose a collaborative learning approach to train CNN models with multiple datasets while preserving the privacy of datasets in a distributed learning environment without sharing them. First, CNN networks are trained with private datasets, and tested with the same publicly available images. Based on their initial accuracies, the CNN model with the lowest performance among datasets is forwarded to second lowest performed dataset to retrain it using the transfer learning approach. Then, the retrained network is forwarded to next dataset. This procedure is repeated for each dataset from the lowest performed dataset to the highest. With this ascending chain order fashion, the network is retrained again and again using different datasets and its performance is improved over the time. Based on our experimental results on five different retina image datasets, DR detection accuracy is increased to 93.5% compared with the accuracies of merged datasets (84%) and individual datasets (73%, 78%, 83%, 85%).

Deep Learning Frameworks for Diabetic Retinopathy Detection with Smartphone-based Retinal Imaging Systems.

Diabetic Retinopathy (DR) may result in various degrees of vision loss and even blindness if not diagnosed in a timely manner. Therefore, having an annual eye exam helps early detection to prevent vision loss in earlier stages, especially for diabetic patients. Recent technological advances made smartphone-based retinal imaging systems available on the market to perform small-sized, low-powered, and affordable DR screening in diverse environments. However, the accuracy of DR detection depends on the field of view and image quality. Since smartphone-based retinal imaging systems have much more compact designs than a traditional fundus camera, captured images are likely to be the low quality with a smaller field of view. Our motivation in this paper is to develop an automatic DR detection model for smartphone-based retinal images using the deep learning approach with the ResNet50 network. This study first utilized the well-known AlexNet, GoogLeNet, and ResNet50 architectures, using the transfer learning approach. Second, these frameworks were retrained with retina images from several datasets including EyePACS, Messidor, IDRiD, and Messidor-2 to investigate the effect of using images from the single, cross, and multiple datasets. Third, the proposed ResNet50 model is applied to smartphone-based synthetic images to explore the DR detection accuracy of smartphone-based retinal imaging systems. Based on the vision-threatening diabetic retinopathy detection results, the proposed approach achieved a high classification accuracy of 98.6%, with a 98.2% sensitivity and a 99.1% specificity while its AUC was 0.9978 on the independent test dataset. As the main contributions, DR detection accuracy was improved using the deep transfer learning approach for the ResNet50 network with publicly available datasets and the effect of the field of view in smartphone-based retinal imaging was studied. Although a smaller number of images were used in the training set compared with the existing studies, considerably acceptable high accuracies for validation and testing data were obtained.

Comparison of smartphone-based retinal imaging systems for diabetic retinopathy detection using deep learning.

BACKGROUND: Diabetic retinopathy (DR), the most common cause of vision loss, is caused by damage to the small blood vessels in the retina. If untreated, it may result in varying degrees of vision loss and even blindness. Since DR is a silent disease that may cause no symptoms or only mild vision problems, annual eye exams are crucial for early detection to improve chances of effective treatment where fundus cameras are used to capture retinal image. However, fundus cameras are too big and heavy to be transported easily and too costly to be purchased by every health clinic, so fundus cameras are an inconvenient tool for widespread screening. Recent technological developments have enabled to use of smartphones in designing small-sized, low-power, and affordable retinal imaging systems to perform DR screening and automated DR detection using image processing methods. In this paper, we investigate the smartphone-based portable retinal imaging systems available on the market and compare their image quality and the automatic DR detection accuracy using a deep learning framework. RESULTS: Based on the results, iNview retinal imaging system has the largest field of view and better image quality compared with iExaminer, D-Eye, and Peek Retina systems. The overall classification accuracy of smartphone-based systems are sorted as 61%, 62%, 69%, and 75% for iExaminer, D-Eye, Peek Retina, and iNview images, respectively. We observed that the network DR detection performance decreases as the field of view of the smartphone-based retinal systems get smaller where iNview is the largest and iExaminer is the smallest. CONCLUSIONS: The smartphone-based retina imaging systems can be used as an alternative to the direct ophthalmoscope. However, the field of view of the smartphone-based retina imaging systems plays an important role in determining the automatic DR detection accuracy.

Correction to: Imaging features of immune-mediated genitourinary disease.

The authors regret that they neglected to cite their conference report on the technical part of a 'preliminary study' presented at, and published in, the Biomedical Sciences and Engineering Conference (BSEC), 2010, May 25-26 (Fully automated segmentation and characterization of the dendritic trees of retinal horizontal neurons -DOI: 10.1109/BSEC.2010.5510843 ), as it related to the larger dataset presented as validation of the method in the Neurochemical Research article (Automated Tracing of Horizontal Neuron Processes During Retinal Development- Neurochem Res. 2011 Apr;36(4):583-93). This resulted in the lack of transparency on the re-use and duplication of introductory text, which should have been cited. No figures or tables were reproduced, but rather larger confirmatory data and different set of results were reported. Appropriate authors were cited in both papers.

Leading-process actomyosin coordinates organelle positioning and adhesion receptor dynamics in radially migrating cerebellar granule neurons.

BACKGROUND: During brain development, neurons migrate from germinal zones to their final positions to assemble neural circuits. A unique saltatory cadence involving cyclical organelle movement (e.g., centrosome motility) and leading-process actomyosin enrichment prior to nucleokinesis organizes neuronal migration. While functional evidence suggests that leading-process actomyosin is essential for centrosome motility, the role of the actin-enriched leading process in globally organizing organelle transport or traction forces remains unexplored. RESULTS: We show that myosin ii motors and F-actin dynamics are required for Golgi apparatus positioning before nucleokinesis in cerebellar granule neurons (CGNs) migrating along glial fibers. Moreover, we show that primary cilia are motile organelles, localized to the leading-process F-actin-rich domain and immobilized by pharmacological inhibition of myosin ii and F-actin dynamics. Finally, leading process adhesion dynamics are dependent on myosin ii and F-actin. CONCLUSIONS: We propose that actomyosin coordinates the overall polarity of migrating CGNs by controlling asymmetric organelle positioning and cell-cell contacts as these cells move along their glial guides.

Analysis of tight junction formation and integrity.

In this paper, we study segmentation of tight junctions and analyze the formation and integrity of tight junctions in large-scale confocal image stacks, a challenging biological problem because of the low spatial resolution images and the presence of breaks in tight junction structure. We present an automated, three-step processing approach for tight junction analysis. In our approach, we first localize each individual nucleus in the image by using thresholding, morphological filters and active contours. By using each nucleus position as a seed point, we automatically segment the cell body based on the active contour. We then use an intensity-based skeletonization algorithm to generate the boundary regions for each cell, and features are extracted from tight junctions associated with each cell to assess tight junction continuity. Based on qualitative results and quantitative comparisons, we show that we are able to automatically segment tight junctions and compute relevant features that provide a quantitative measure of tight junction formation to which the permeability of the cell monolayer can ultimately be correlated.

Retinoblastoma (Rb) regulates laminar dendritic arbor reorganization in retinal horizontal neurons.

Neuronal differentiation with respect to the acquisition of synaptic competence needs to be regulated precisely during neurogenesis to ensure proper formation of circuits at the right place and time in development. This regulation is particularly important for synaptic triads among photoreceptors, horizontal cells (HCs), and bipolar cells in the retina, because HCs are among the first cell types produced during development, and bipolar cells are among the last. HCs undergo a dramatic transition from vertically oriented neurites that form columnar arbors to overlapping laminar dendritic arbors with differentiation. However, how this process is regulated and coordinated with differentiation of photoreceptors and bipolar cells remains unknown. Previous studies have suggested that the retinoblastoma (Rb) tumor suppressor gene may play a role in horizontal cell differentiation and synaptogenesis. By combining genetic mosaic analysis of individual synaptic triads with neuroanatomic analyses and multiphoton live imaging of developing HCs, we found that Rb plays a cell-autonomous role in the reorganization of horizontal cell neurites as they differentiate. Aberrant vertical processes in Rb-deficient HCs form ectopic synapses with rods in the outer nuclear layer but lack bipolar dendrites. Although previous reports indicate that photoreceptor abnormalities can trigger formation of ectopic synapses, our studies now demonstrate that defects in a postsynaptic partner contribute to the formation of ectopic photoreceptor synapses in the mammalian retina.

Automated tracing of horizontal neuron processes during retinal development.

In the developing mammalian retina, horizontal neurons undergo a dramatic reorganization of their processes shortly after they migrate to their appropriate laminar position. This is an important process because it is now understood that the apical processes are important for establishing the regular mosaic of horizontal cells in the retina and proper reorganization during lamination is required for synaptogenesis with photoreceptors and bipolar neurons. However, this process is difficult to study because the analysis of horizontal neuron anatomy is labor intensive and time-consuming. In this paper, we present a computational method for automatically tracing the three-dimensional (3-D) dendritic structure of horizontal retinal neurons in two-photon laser scanning microscope (TPLSM) imagery. Our method is based on 3-D skeletonization and is thus able to preserve the complex structure of the dendritic arbor of these cells. We demonstrate the effectiveness of our approach by comparing our tracing results against two sets of semi-automated traces over a set of 10 horizontal neurons ranging in age from P1 to P5. We observe an average agreement level of 81% between our automated trace and the manual traces. This automated method will serve as an important starting point for further refinement and optimization.