Presentation of a Segmentation Method for a Diabetic Retinopathy Patient's Fundus Region Detection Using a Convolutional Neural Network

AI-assisted Segmentation Tool for Brain Tumor MR Image Analysis

TumorPrism3D software was developed to segment brain tumors with a straightforward and user-friendly graphical interface applied to two- and three-dimensional brain magnetic resonance (MR) images. The MR images of 185 patients (103 males, 82 females) with glioblastoma multiforme were downloaded from The Cancer Imaging Archive (TCIA) to test the tumor segmentation performance of this software. Regions of interest (ROIs) corresponding to contrast-enhancing lesions, necrotic portions, and non-enhancing T2 high signal intensity components were segmented for each tumor. TumorPrism3D demonstrated high accuracy in segmenting all three tumor components in cases of glioblastoma multiforme. They achieved a better Dice similarity coefficient (DSC) ranging from 0.83 to 0.91 than 3DSlicer with a DSC ranging from 0.80 to 0.84 for the accuracy of segmented tumors. Comparative analysis with the widely used 3DSlicer software revealed TumorPrism3D to be approximately 37.4% faster in the segmentation process from initial contour drawing to final segmentation mask determination. The semi-automated nature of TumorPrism3D facilitates reproducible tumor segmentation at a rapid pace, offering the potential for quantitative analysis of tumor characteristics and artificial intelligence-assisted segmentation in brain MR imaging.

Automatic Detection of Microaneurysms in Fundus Images Using an Ensemble-Based Segmentation Method

In this study, a novel method for automatic microaneurysm detection in color fundus images is presented. The proposed method is based on three main steps: (1) image breakdown to smaller image patches, (2) inference to segmentation models, and (3) reconstruction of the predicted segmentation map from output patches. The proposed segmentation method is based on an ensemble of three individual deep networks, such as U-Net, ResNet34-UNet and UNet++. The performance evaluation is based on the calculation of the Dice score and IoU values. The ensemble-based model achieved higher Dice score (0.95) and IoU (0.91) values compared to other network architectures. The proposed ensemble-based model demonstrates the high practical application potential for detection of early-stage diabetic retinopathy in color fundus images.

Object tracking in infrared images using a deep learning model and a target-attention mechanism

Small object tracking in infrared images is widely utilized in various fields, such as video surveillance, infrared guidance, and unmanned aerial vehicle monitoring. The existing small target detection strategies in infrared images suffer from submerging the target in heavy cluttered infrared (IR) maritime images. To overcome this issue, we use the original image and the corresponding encoded image to apply our model. We use the local directional number patterns algorithm to encode the original image to represent more unique details. Our model is able to learn more informative and unique features from the original and encoded image for visual tracking. In this study, we explore the best convolutional filters to obtain the best possible visual tracking results by finding those inactive to the backgrounds while active in the target region. To this end, the attention mechanism for the feature extracting framework is investigated comprising a scale-sensitive feature generation component and a discriminative feature generation module based on the gradients of regression and scoring losses. Comprehensive experiments have demonstrated that our pipeline obtains competitive results compared to recently published papers.

Three-Dimensional Semantic Segmentation of Diabetic Retinopathy Lesions and Grading Using Transfer Learning

Diabetic retinopathy (DR) is a drastic disease. DR embarks on vision impairment when it is left undetected. In this article, learning-based techniques are presented for the segmentation and classification of DR lesions. The pre-trained Xception model is utilized for deep feature extraction in the segmentation phase. The extracted features are fed to Deeplabv3 for semantic segmentation. For the training of the segmentation model, an experiment is performed for the selection of the optimal hyperparameters that provided effective segmentation results in the testing phase. The multi-classification model is developed for feature extraction using the fully connected (FC) MatMul layer of efficient-net-b0 and pool-10 of the squeeze-net. The extracted features from both models are fused serially, having the dimension of N × 2020, amidst the best N × 1032 features chosen by applying the marine predictor algorithm (MPA). The multi-classification of the DR lesions into grades 0, 1, 2, and 3 is performed using neural network and KNN classifiers. The proposed method performance is validated on open access datasets such as DIARETDB1, e-ophtha-EX, IDRiD, and Messidor. The obtained results are better compared to those of the latest published works.

Investigation of Effectiveness of Shuffled Frog-Leaping Optimizer in Training a Convolution Neural Network

One of the leading algorithms and architectures in deep learning is Convolution Neural Network (CNN). It represents a unique method for image processing, object detection, and classification. CNN has shown to be an efficient approach in the machine learning and computer vision fields. CNN is composed of several filters accompanied by nonlinear functions and pooling layers. It enforces limitations on the weights and interconnections of the neural network to create a good structure for processing spatial and temporal distributed data. A CNN can restrain the numbering of free parameters of the network through its weight-sharing property. However, the training of CNNs is a challenging approach. Some optimization techniques have been recently employed to optimize CNN's weight and biases such as Ant Colony Optimization, Genetic, Harmony Search, and Simulated Annealing. This paper employs the well-known nature-inspired algorithm called Shuffled Frog-Leaping Algorithm (SFLA) for training a classical CNN structure (LeNet-5), which has not been experienced before. The training method is investigated by employing four different datasets. To verify the study, the results are compared with some of the most famous evolutionary trainers: Whale Optimization Algorithm (WO), Bacteria Swarm Foraging Optimization (BFSO), and Ant Colony Optimization (ACO). The outcomes demonstrate that the SFL technique considerably improves the performance of the original LeNet-5 although using this algorithm slightly increases the training computation time. The results also demonstrate that the suggested algorithm presents high accuracy in classification and approximation in its mechanism.