A visual framework to create photorealistic retinal vessels for diagnosis purposes

Diabetic and Hypertensive Retinopathy Screening in Fundus Images Using Artificially Intelligent Shallow Architectures

Retinal blood vessels are considered valuable biomarkers for the detection of diabetic retinopathy, hypertensive retinopathy, and other retinal disorders. Ophthalmologists analyze retinal vasculature by manual segmentation, which is a tedious task. Numerous studies have focused on automatic retinal vasculature segmentation using different methods for ophthalmic disease analysis. However, most of these methods are computationally expensive and lack robustness. This paper proposes two new shallow deep learning architectures: dual-stream fusion network (DSF-Net) and dual-stream aggregation network (DSA-Net) to accurately detect retinal vasculature. The proposed method uses semantic segmentation in raw color fundus images for the screening of diabetic and hypertensive retinopathies. The proposed method's performance is assessed using three publicly available fundus image datasets: Digital Retinal Images for Vessel Extraction (DRIVE), Structured Analysis of Retina (STARE), and Children Heart Health Study in England Database (CHASE-DB1). The experimental results revealed that the proposed method provided superior segmentation performance with accuracy (Acc), sensitivity (SE), specificity (SP), and area under the curve (AUC) of 96.93%, 82.68%, 98.30%, and 98.42% for DRIVE, 97.25%, 82.22%, 98.38%, and 98.15% for CHASE-DB1, and 97.00%, 86.07%, 98.00%, and 98.65% for STARE datasets, respectively. The experimental results also show that the proposed DSA-Net provides higher SE compared to the existing approaches. It means that the proposed method detected the minor vessels and provided the least false negatives, which is extremely important for diagnosis. The proposed method provides an automatic and accurate segmentation mask that can be used to highlight the vessel pixels. This detected vasculature can be utilized to compute the ratio between the vessel and the non-vessel pixels and distinguish between diabetic and hypertensive retinopathies, and morphology can be analyzed for related retinal disorders.

A high resolution representation network with multi-path scale for retinal vessel segmentation

BACKGROUND AND OBJECTIVES

Automatic retinal vessel segmentation (RVS) in fundus images is expected to be a vital step in the early image diagnosis of ophthalmologic diseases. However, it is a challenging task to detect the retinal vessel accurately mainly due to the vascular intricacies, lesion areas and optic disc edges in retinal fundus images.

METHODS

In this paper, we propose a high resolution representation network with multi-path scale (MPS-Net) for RVS aiming to improve the performance of extracting the retinal blood vessels. In the MPS-Net, there exist one high resolution main road and two lower resolution branch roads where the proposed multi-path scale modules are embedded to enhance the representation ability of network. Besides, in order to guide the network focus on learning the features of hard examples in retinal images, we design a hard-focused cross-entropy loss function.

RESULTS

We evaluate our network structure on DRIVE, STARE, CHASE and synthetic images and the quantitative comparisons with respect to the existing methods are presented. The experimental results show that our approach is superior to most methods in terms of F1-score, sensitivity, G-mean and Matthews correlation coefficient.

CONCLUSIONS

The promising segmentation performances reveal that our method has potential in real-world applications and can be exploited for other medical images with further analysis.

Image formation by a biological curved mirror array of the fisheye in the deep-sea environment

In this paper, we present the imaging formation process of the piecewise mirror eyes of the deep-sea spookfish, which has a strange combination of refractive and reflective eyes. The biological reflective eye structure is formulated to the curved surface's flat mirror array. Zemax is utilized to evaluate optical features such as the modulation transfer function, distortion, and imaging performances. However, the natural images are highly distorted, and the resolution is lower than expected. Therefore, we increase the number of piecewise mirrors of the fisheye to see higher quality images, which can be improved entirely by the mirror shapes. Finally, the fisheye's imaging analysis reveals the deep-sea creature's resolution limit and also shows the possibility of artificial and biomimetic camera applications.

Edge-Based Missing Data Imputation in Large-Scale Environments

Smart cities leverage large amounts of data acquired in the urban environment in the context of decision support tools. These tools enable monitoring the environment to improve the quality of services offered to citizens. The increasing diffusion of personal Internet of things devices capable of sensing the physical environment allows for low-cost solutions to acquire a large amount of information within the urban environment. On the one hand, the use of mobile and intermittent sensors implies new scenarios of large-scale data analysis; on the other hand, it involves different challenges such as intermittent sensors and integrity of acquired data. To this effect, edge computing emerges as a methodology to distribute computation among different IoT devices to analyze data locally. We present here a new methodology for imputing environmental information during the acquisition step, due to missing or otherwise out of order sensors, by distributing the computation among a variety of fixed and mobile devices. Numerous experiments have been carried out on real data to confirm the validity of the proposed method.

Exudates as Landmarks Identified through FCM Clustering in Retinal Images

The aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient’s status through a noninvasive approach. In the field of diabetic retinopathy detection, we considered four public domain datasets (DIARETDB0/1, IDRID, and e-optha) as benchmarks. In order to refine the final results, a specialist ophthalmologist manually segmented a random selection of DIARETDB0/1 fundus images that presented exudates. An innovative pipeline of morphological procedures and fuzzy C-means clustering was integrated in order to extract exudates with a pixel-wise approach. Our methodology was optimized, and verified and the parameters were fine-tuned in order to define both suitable values and to produce a more accurate segmentation. The method was used on 100 tested images, resulting in averages of sensitivity, specificity, and accuracy equal to 83.3%, 99.2%, and 99.1%, respectively.

Parallel Raster Scan for Euclidean Distance Transform

Distance transform (DT) and Voronoi diagrams (VDs) have found many applications in image analysis. Euclidean distance transform (EDT) can generate forms that do not vary with the rotation, because it is radially symmetrical, which is a desirable characteristic in distance transform applications. Recently, parallel architectures have been very accessible and, particularly, GPU-based architectures are very promising due to their high performance, low power consumption and affordable prices. In this paper, a new parallel algorithm is proposed for the computation of a Euclidean distance map and Voronoi diagram of a binary image that mixes CUDA multi-thread parallel image processing with a raster propagation of distance information over small fragments of the image. The basic idea is to exploit the throughput and the latency in each level of memory in the NVIDIA GPU; the image is set in the global memory, and can be accessed via texture memory, and we divide the problem into blocks of threads. For each block we copy a portion of the image and each thread applies a raster scan-based algorithm to a tile of m×m pixels. Experiment results exhibit that our proposed GPU algorithm can improve the efficiency of the Euclidean distance transform in most cases, obtaining speedup factors that even reach 3.193.

ACDC: Automated Cell Detection and Counting for Time-Lapse Fluorescence Microscopy

Advances in microscopy imaging technologies have enabled the visualization of live-cell dynamic processes using time-lapse microscopy imaging. However, modern methods exhibit several limitations related to the training phases and to time constraints, hindering their application in the laboratory practice. In this work, we present a novel method, named Automated Cell Detection and Counting (ACDC), designed for activity detection of fluorescent labeled cell nuclei in time-lapse microscopy. ACDC overcomes the limitations of the literature methods, by first applying bilateral filtering on the original image to smooth the input cell images while preserving edge sharpness, and then by exploiting the watershed transform and morphological filtering. Moreover, ACDC represents a feasible solution for the laboratory practice, as it can leverage multi-core architectures in computer clusters to efficiently handle large-scale imaging datasets. Indeed, our Parent-Workers implementation of ACDC allows to obtain up to a 3.7× speed-up compared to the sequential counterpart. ACDC was tested on two distinct cell imaging datasets to assess its accuracy and effectiveness on images with different characteristics. We achieved an accurate cell-count and nuclei segmentation without relying on large-scale annotated datasets, a result confirmed by the average Dice Similarity Coefficients of 76.84 and 88.64 and the Pearson coefficients of 0.99 and 0.96, calculated against the manual cell counting, on the two tested datasets.