AA-WGAN: Attention augmented Wasserstein generative adversarial network with application to fundus retinal vessel segmentation

Generative deep learning for the development of a type 1 diabetes simulator

BACKGROUND

Type 1 diabetes (T1D) simulators, crucial for advancing diabetes treatments, often fall short of capturing the entire complexity of the glucose-insulin system due to the imprecise approximation of the physiological models. This study introduces a simulation approach employing a conditional deep generative model. The aim is to overcome the limitations of existing T1D simulators by synthesizing virtual patients that more accurately represent the entire glucose-insulin system physiology.

METHODS

Our methodology utilizes a sequence-to-sequence generative adversarial network to simulate virtual T1D patients causally. Causality is embedded in the model by introducing shifted input-output pairs during training, with a 90-min shift capturing the impact of input insulin and carbohydrates on blood glucose. To validate our approach, we train and evaluate the model using three distinct datasets, each consisting of 27, 12, and 10 T1D patients, respectively. In addition, we subject the trained model to further validation for closed-loop therapy, employing a state-of-the-art controller.

RESULTS

The generated patients display statistical similarity to real patients when evaluated on the time-in-range results for each of the standard blood glucose ranges in T1D management along with means and variability outcomes. When tested for causality, authentic causal links are identified between the insulin, carbohydrates, and blood glucose levels of the virtual patients. The trained generative model demonstrates behaviours that are closer to reality compared to conventional T1D simulators when subjected to closed-loop insulin therapy using a state-of-the-art controller.

CONCLUSIONS

These results highlight our approach's capability to accurately capture physiological dynamics and establish genuine causal relationships, holding promise for enhancing the development and evaluation of therapies in diabetes.

ELTS-Net: An enhanced liver tumor segmentation network with augmented receptive field and global contextual information

The liver is one of the organs with the highest incidence rate in the human body, and late-stage liver cancer is basically incurable. Therefore, early diagnosis and lesion location of liver cancer are of important clinical value. This study proposes an enhanced network architecture ELTS-Net based on the 3D U-Net model, to address the limitations of conventional image segmentation methods and the underutilization of image spatial features by the 2D U-Net network structure. ELTS-Net expands upon the original network by incorporating dilated convolutions to increase the receptive field of the convolutional kernel. Additionally, an attention residual module, comprising an attention mechanism and residual connections, replaces the original convolutional module, serving as the primary components of the encoder and decoder. This design enables the network to capture contextual information globally in both channel and spatial dimensions. Furthermore, deep supervision modules are integrated between different levels of the decoder network, providing additional feedback from deeper intermediate layers. This constrains the network weights to the target regions and optimizing segmentation results. Evaluation on the LiTS2017 dataset shows improvements in evaluation metrics for liver and tumor segmentation tasks compared to the baseline 3D U-Net model, achieving 95.2% liver segmentation accuracy and 71.9% tumor segmentation accuracy, with accuracy improvements of 0.9% and 3.1% respectively. The experimental results validate the superior segmentation performance of ELTS-Net compared to other comparison models, offering valuable guidance for clinical diagnosis and treatment.

Global vision object detection using an improved Gaussian Mixture model based on contour

Object detection plays an important role in the field of computer vision. The purpose of object detection is to identify the objects of interest in the image and determine their categories and positions. Object detection has many important applications in various fields. This article addresses the problems of unclear foreground contour in moving object detection and excessive noise points in the global vision, proposing an improved Gaussian mixture model for feature fusion. First, the RGB image was converted into the HSV space, and a mixed Gaussian background model was established. Next, the object area was obtained through background subtraction, residual interference in the foreground was removed using the median filtering method, and morphological processing was performed. Then, an improved Canny algorithm using an automatic threshold from the Otsu method was used to extract the overall object contour. Finally, feature fusion of edge contours and the foreground area was performed to obtain the final object contour. The experimental results show that this method improves the accuracy of the object contour and reduces noise in the object.

Deep learning-based identification of eyes at risk for glaucoma surgery

To develop and evaluate the performance of a deep learning model (DLM) that predicts eyes at high risk of surgical intervention for uncontrolled glaucoma based on multimodal data from an initial ophthalmology visit. Longitudinal, observational, retrospective study. 4898 unique eyes from 4038 adult glaucoma or glaucoma-suspect patients who underwent surgery for uncontrolled glaucoma (trabeculectomy, tube shunt, xen, or diode surgery) between 2013 and 2021, or did not undergo glaucoma surgery but had 3 or more ophthalmology visits. We constructed a DLM to predict the occurrence of glaucoma surgery within various time horizons from a baseline visit. Model inputs included spatially oriented visual field (VF) and optical coherence tomography (OCT) data as well as clinical and demographic features. Separate DLMs with the same architecture were trained to predict the occurrence of surgery within 3 months, within 3-6 months, within 6 months-1 year, within 1-2 years, within 2-3 years, within 3-4 years, and within 4-5 years from the baseline visit. Included eyes were randomly split into 60%, 20%, and 20% for training, validation, and testing. DLM performance was measured using area under the receiver operating characteristic curve (AUC) and precision-recall curve (PRC). Shapley additive explanations (SHAP) were utilized to assess the importance of different features. Model prediction of surgery for uncontrolled glaucoma within 3 months had the best AUC of 0.92 (95% CI 0.88, 0.96). DLMs achieved clinically useful AUC values (> 0.8) for all models that predicted the occurrence of surgery within 3 years. According to SHAP analysis, all 7 models placed intraocular pressure (IOP) within the five most important features in predicting the occurrence of glaucoma surgery. Mean deviation (MD) and average retinal nerve fiber layer (RNFL) thickness were listed among the top 5 most important features by 6 of the 7 models. DLMs can successfully identify eyes requiring surgery for uncontrolled glaucoma within specific time horizons. Predictive performance decreases as the time horizon for forecasting surgery increases. Implementing prediction models in a clinical setting may help identify patients that should be referred to a glaucoma specialist for surgical evaluation.

MAG-Net : Multi-fusion network with grouped attention for retinal vessel segmentation

Retinal vessel segmentation plays a vital role in the clinical diagnosis of ophthalmic diseases. Despite convolutional neural networks (CNNs) excelling in this task, challenges persist, such as restricted receptive fields and information loss from downsampling. To address these issues, we propose a new multi-fusion network with grouped attention (MAG-Net). First, we introduce a hybrid convolutional fusion module instead of the original encoding block to learn more feature information by expanding the receptive field. Additionally, the grouped attention enhancement module uses high-level features to guide low-level features and facilitates detailed information transmission through skip connections. Finally, the multi-scale feature fusion module aggregates features at different scales, effectively reducing information loss during decoder upsampling. To evaluate the performance of the MAG-Net, we conducted experiments on three widely used retinal datasets: DRIVE, CHASE and STARE. The results demonstrate remarkable segmentation accuracy, specificity and Dice coefficients. Specifically, the MAG-Net achieved segmentation accuracy values of 0.9708, 0.9773 and 0.9743, specificity values of 0.9836, 0.9875 and 0.9906 and Dice coefficients of 0.8576, 0.8069 and 0.8228, respectively. The experimental results demonstrate that our method outperforms existing segmentation methods exhibiting superior performance and segmentation outcomes.

A Review on Retinal Blood Vessel Enhancement and Segmentation Techniques for Color Fundus Photography

The retinal image is a trusted modality in biomedical image-based diagnosis of many ophthalmologic and cardiovascular diseases. Periodic examination of the retina can help in spotting these abnormalities in the early stage. However, to deal with today's large population, computerized retinal image analysis is preferred over manual inspection. The precise extraction of the retinal vessel is the first and decisive step for clinical applications. Every year, many more articles are added to the literature that describe new algorithms for the problem at hand. The majority of the review article is restricted to a fairly small number of approaches, assessment indices, and databases. In this context, a comprehensive review of different vessel extraction methods is inevitable. It includes the development of a first-hand classification of these methods. A bibliometric analysis of these articles is also presented. The benefits and drawbacks of the most commonly used techniques are summarized. The primary challenges, as well as the scope of possible changes, are discussed. In order to make a fair comparison, numerous assessment indices are considered. The findings of this survey could provide a new path for researchers for further work in this domain.

Bio-Inspired Spotted Hyena Optimizer with Deep Convolutional Neural Network-Based Automated Food Image Classification

Food image classification, an interesting subdomain of Computer Vision (CV) technology, focuses on the automatic classification of food items represented through images. This technology has gained immense attention in recent years thanks to its widespread applications spanning dietary monitoring and nutrition studies to restaurant recommendation systems. By leveraging the developments in Deep-Learning (DL) techniques, especially the Convolutional Neural Network (CNN), food image classification has been developed as an effective process for interacting with and understanding the nuances of the culinary world. The deep CNN-based automated food image classification method is a technology that utilizes DL approaches, particularly CNNs, for the automatic categorization and classification of the images of distinct kinds of foods. The current research article develops a Bio-Inspired Spotted Hyena Optimizer with a Deep Convolutional Neural Network-based Automated Food Image Classification (SHODCNN-FIC) approach. The main objective of the SHODCNN-FIC method is to recognize and classify food images into distinct types. The presented SHODCNN-FIC technique exploits the DL model with a hyperparameter tuning approach for the classification of food images. To accomplish this objective, the SHODCNN-FIC method exploits the DCNN-based Xception model to derive the feature vectors. Furthermore, the SHODCNN-FIC technique uses the SHO algorithm for optimal hyperparameter selection of the Xception model. The SHODCNN-FIC technique uses the Extreme Learning Machine (ELM) model for the detection and classification of food images. A detailed set of experiments was conducted to demonstrate the better food image classification performance of the proposed SHODCNN-FIC technique. The wide range of simulation outcomes confirmed the superior performance of the SHODCNN-FIC method over other DL models.

MDF-Net for abnormality detection by fusing X-rays with clinical data

This study investigates the effects of including patients' clinical information on the performance of deep learning (DL) classifiers for disease location in chest X-ray images. Although current classifiers achieve high performance using chest X-ray images alone, consultations with practicing radiologists indicate that clinical data is highly informative and essential for interpreting medical images and making proper diagnoses. In this work, we propose a novel architecture consisting of two fusion methods that enable the model to simultaneously process patients' clinical data (structured data) and chest X-rays (image data). Since these data modalities are in different dimensional spaces, we propose a spatial arrangement strategy, spatialization, to facilitate the multimodal learning process in a Mask R-CNN model. We performed an extensive experimental evaluation using MIMIC-Eye, a dataset comprising different modalities: MIMIC-CXR (chest X-ray images), MIMIC IV-ED (patients' clinical data), and REFLACX (annotations of disease locations in chest X-rays). Results show that incorporating patients' clinical data in a DL model together with the proposed fusion methods improves the disease localization in chest X-rays by 12% in terms of Average Precision compared to a standard Mask R-CNN using chest X-rays alone. Further ablation studies also emphasize the importance of multimodal DL architectures and the incorporation of patients' clinical data in disease localization. In the interest of fostering scientific reproducibility, the architecture proposed within this investigation has been made publicly accessible( https://github.com/ChihchengHsieh/multimodal-abnormalities-detection ).

Generative adversarial networks based skin lesion segmentation

Skin cancer is a serious condition that requires accurate diagnosis and treatment. One way to assist clinicians in this task is using computer-aided diagnosis tools that automatically segment skin lesions from dermoscopic images. We propose a novel adversarial learning-based framework called Efficient-GAN (EGAN) that uses an unsupervised generative network to generate accurate lesion masks. It consists of a generator module with a top-down squeeze excitation-based compound scaled path, an asymmetric lateral connection-based bottom-up path, and a discriminator module that distinguishes between original and synthetic masks. A morphology-based smoothing loss is also implemented to encourage the network to create smooth semantic boundaries of lesions. The framework is evaluated on the International Skin Imaging Collaboration Lesion Dataset. It outperforms the current state-of-the-art skin lesion segmentation approaches with a Dice coefficient, Jaccard similarity, and accuracy of 90.1%, 83.6%, and 94.5%, respectively. We also design a lightweight segmentation framework called Mobile-GAN (MGAN) that achieves comparable performance as EGAN but with an order of magnitude lower number of training parameters, thus resulting in faster inference times for low compute resource settings.

Optimal Feature Analysis for Identification Based on Intracranial Brain Signals with Machine Learning Algorithms

Biometrics, e.g., fingerprints, the iris, and the face, have been widely used to authenticate individuals. However, most biometrics are not cancellable, i.e., once these traditional biometrics are cloned or stolen, they cannot be replaced easily. Unlike traditional biometrics, brain biometrics are extremely difficult to clone or forge due to the natural randomness across different individuals, which makes them an ideal option for identity authentication. Most existing brain biometrics are based on an electroencephalogram (EEG), which typically demonstrates unstable performance due to the low signal-to-noise ratio (SNR). Thus, in this paper, we propose the use of intracortical brain signals, which have higher resolution and SNR, to realize the construction of a high-performance brain biometric. Significantly, this is the first study to investigate the features of intracortical brain signals for identification. Specifically, several features based on local field potential are computed for identification, and their performance is compared with different machine learning algorithms. The results show that frequency domain features and time-frequency domain features are excellent for intra-day and inter-day identification. Furthermore, the energy features perform best among all features with 98% intra-day and 93% inter-day identification accuracy, which demonstrates the great potential of intracraial brain signals to be biometrics. This paper may serve as a guidance for future intracranial brain researches and the development of more reliable and high-performance brain biometrics.