Identification of important gene signatures in schizophrenia through feature fusion and genetic algorithm.

Schizophrenia is a debilitating psychiatric disorder that can significantly affect a patient's quality of life and lead to permanent brain damage. Although medical research has identified certain genetic risk factors, the specific pathogenesis of the disorder remains unclear. Despite the prevalence of research employing magnetic resonance imaging, few studies have focused on the gene level and gene expression profile involving a large number of screened genes. However, the high dimensionality of genetic data presents a great challenge to accurately modeling the data. To tackle the current challenges, this study presents a novel feature selection strategy that utilizes heuristic feature fusion and a multi-objective optimization genetic algorithm. The goal is to improve classification performance and identify the key gene subset for schizophrenia diagnostics. Traditional gene screening techniques are inadequate for accurately determining the precise number of key genes associated with schizophrenia. Our innovative approach integrates a filter-based feature selection method to reduce data dimensionality and a multi-objective optimization genetic algorithm for improved classification tasks. By combining the filtering and wrapper methods, our strategy leverages their respective strengths in a deliberate manner, leading to superior classification accuracy and a more efficient selection of relevant genes. This approach has demonstrated significant improvements in classification results across 11 out of 14 relevant datasets. The performance on the remaining three datasets is comparable to the existing methods. Furthermore, visual and enrichment analyses have confirmed the practicality of our proposed method as a promising tool for the early detection of schizophrenia.

Improving the performance of rapid lifetime determination for wide-field time-gated imaging in live cells.

In biological research, rapid wide-field fluorescence lifetime imaging has become an important imaging tool. However, the biological samples with weak fluorescence signals and lower sensitivity often suffer from very low precision in lifetime determinations which restricts its widespread utilization in many bioimaging applications. To address this issue, a method is presented in this paper to substantially enhance the precision of rapid lifetime determination (RLD). It expedites the discrimination of fluorescence lifetimes, even for the weak signals coming from the cells, stained with long-lived biocompatible AIS/ZnS QDs. The proposed method works in two phases. The first phase deals with the systematic noise analysis based on the signal and contrast of the images in a time-gated imaging system, wherein acquiring the high-quality imaging data through optimization of hardware parameters improves the overall system performance. In the second phase, the chosen images are treated using total variation denoising method combined with the Max/Min filtering method for extracting the region of interest to reconstruct the intensity images for RLD. We performed several experiments on live cells to demonstrate the improvements in imaging performance by the systematic optimizations and data treatment. Obtained results demonstrated a great enhancement in signal-to-noise and contrast-to-noise ratios beside witnessing an obvious improvement in RLD for weak signals. This approach can be used not only to improve the quality of time-gated imaging data but also for efficient fluorescence lifetime imaging of live biological samples without compromising imaging speed and light exposure.

DNL-Net: deformed non-local neural network for blood vessel segmentation.

BACKGROUND: The non-local module has been primarily used in literature to capturing long-range dependencies. However, it suffers from prohibitive computational complexity and lacks the interactions among positions across the channels. METHODS: We present a deformed non-local neural network (DNL-Net) for medical image segmentation, which has two prominent components; deformed non-local module (DNL) and multi-scale feature fusion. The former optimizes the structure of the non-local block (NL), hence, reduces the problem of excessive computation and memory usage, significantly. The latter is derived from the attention mechanisms to fuse the features of different levels and improve the ability to exchange information across channels. In addition, we introduce a residual squeeze and excitation pyramid pooling (RSEP) module that is like spatial pyramid pooling to effectively resample the features at different scales and improve the network receptive field. RESULTS: The proposed method achieved 96.63% and 92.93% for Dice coefficient and mean intersection over union, respectively, on the intracranial blood vessel dataset. Also, DNL-Net attained 86.64%, 96.10%, and 98.37% for sensitivity, accuracy and area under receiver operation characteristic curve, respectively, on the DRIVE dataset. CONCLUSIONS: The overall performance of DNL-Net outperforms other current state-of-the-art vessel segmentation methods, which indicates that the proposed network is more suitable for blood vessel segmentation, and is of great clinical significance.

Novel multi-site graph convolutional network with supervision mechanism for COVID-19 diagnosis from X-ray radiographs.

The novel Coronavirus disease 2019 (COVID-2019) has become a global pandemic and affected almost all aspects of our daily life. The total number of positive COVID-2019 cases has exponentially increased in the last few months due to the easy transmissibility of the virus. It can be detected using the nucleic acid test or the antibodies blood test which are not always available and take several hours to get the results. Therefore, researchers proposed computer-aided diagnosis systems using the state-of-the-art artificial intelligence techniques to learn imaging biomarkers from chest computed tomography and X-ray radiographs to effectively diagnose COVID-19. However, previous methods either adopted transfer learning from a pre-trained model on natural images or were trained on limited datasets. Either cases may lead to accuracy deficiency or overfitting. In addition, feature space suffers from noise and outliers when collecting X-ray images from multiple datasets. In this paper, we overcome the previous limitations by firstly collecting a large-scale X-ray dataset from multiple resources. Our dataset includes 11,312 images collected from 10 different data repositories. To alleviate the effect of the noise, we suppress it in the feature space of our new dataset. Secondly, we introduce a supervision mechanism and combine it with the VGG-16 network to consider the differences between the COVID-19 and healthy cases in the feature space. Thirdly, we propose a multi-site (center) COVID-19 graph convolutional network (GCN) that exploits dataset information, the status of training samples, and initial scores to effectively classify the disease status. Extensive experiments using different convolutional neural network-based methods with and without the supervision mechanism and different classifiers are performed. Results demonstrate the effectiveness of the proposed supervision mechanism in all models and superior performance with the proposed GCN.

Alzheimer's disease diagnosis framework from incomplete multimodal data using convolutional neural networks.

Alzheimer's disease (AD) is a severe irreversible neurodegenerative disease that has great sufferings on patients and eventually leads to death. Early detection of AD and its prodromal stage, mild cognitive impairment (MCI) which can be either stable (sMCI) or progressive (pMCI), is highly desirable for effective treatment planning and tailoring therapy. Recent studies recommended using multimodal data fusion of genetic (single nucleotide polymorphisms, SNPs) and neuroimaging data (magnetic resonance imaging (MRI) and positron emission tomography (PET)) to discriminate AD/MCI from normal control (NC) subjects. However, missing multimodal data in the cohort under study is inevitable. In addition, data heterogeneity between phenotypes and genotypes biomarkers makes learning capability of the models more challenging. Also, the current studies mainly focus on identifying brain disease classification and ignoring the regression task. Furthermore, they utilize multistage for predicting the brain disease progression. To address these issues, we propose a novel multimodal neuroimaging and genetic data fusion for joint classification and clinical score regression tasks using the maximum number of available samples in one unified framework using convolutional neural network (CNN). Specifically, we initially perform a technique based on linear interpolation to fill the missing features for each incomplete sample. Then, we learn the neuroimaging features from MRI, PET, and SNPs using CNN to alleviate the heterogeneity among genotype and phenotype data. Meanwhile, the high learned features from each modality are combined for jointly identifying brain diseases and predicting clinical scores. To validate the performance of the proposed method, we test our method on 805 subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Also, we verify the similarity between the synthetic and real data using statistical analysis. Moreover, the experimental results demonstrate that the proposed method can yield better performance in both classification and regression tasks. Specifically, our proposed method achieves accuracy of 98.22%, 93.11%, and 97.35% for NC vs. AD, NC vs. sMCI, and NC vs. pMCI, respectively. On the other hand, our method attains the lowest root mean square error and the highest correlation coefficient for different clinical scores regression tasks compared with the state-of-the-art methods.

Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review.

BACKGROUND: Machine learning (ML) has become a vital part of medical imaging research. ML methods have evolved over the years from manual seeded inputs to automatic initializations. The advancements in the field of ML have led to more intelligent and self-reliant computer-aided diagnosis (CAD) systems, as the learning ability of ML methods has been constantly improving. More and more automated methods are emerging with deep feature learning and representations. Recent advancements of ML with deeper and extensive representation approaches, commonly known as deep learning (DL) approaches, have made a very significant impact on improving the diagnostics capabilities of the CAD systems. OBJECTIVE: This review aimed to survey both traditional ML and DL literature with particular application for breast cancer diagnosis. The review also provided a brief insight into some well-known DL networks. METHODS: In this paper, we present an overview of ML and DL techniques with particular application for breast cancer. Specifically, we search the PubMed, Google Scholar, MEDLINE, ScienceDirect, Springer, and Web of Science databases and retrieve the studies in DL for the past 5 years that have used multiview mammogram datasets. RESULTS: The analysis of traditional ML reveals the limited usage of the methods, whereas the DL methods have great potential for implementation in clinical analysis and improve the diagnostic capability of existing CAD systems. CONCLUSIONS: From the literature, it can be found that heterogeneous breast densities make masses more challenging to detect and classify compared with calcifications. The traditional ML methods present confined approaches limited to either particular density type or datasets. Although the DL methods show promising improvements in breast cancer diagnosis, there are still issues of data scarcity and computational cost, which have been overcome to a significant extent by applying data augmentation and improved computational power of DL algorithms.

Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder.

OBJECTIVE: In this paper, we aim to investigate the effect of computer-aided triage system, which is implemented for the health checkup of lung lesions involving tens of thousands of chest X-rays (CXRs) that are required for diagnosis. Therefore, high accuracy of diagnosis by an automated system can reduce the radiologist's workload on scrutinizing the medical images. METHOD: We present a deep learning model in order to efficiently detect abnormal levels or identify normal levels during mass chest screening so as to obtain the probability confidence of the CXRs. Moreover, a convolutional sparse denoising autoencoder is designed to compute the reconstruction error. We employ four publicly available radiology datasets pertaining to CXRs, analyze their reports, and utilize their images for mining the correct disease level of the CXRs that are to be submitted to a computer aided triaging system. Based on our approach, we vote for the final decision from multi-classifiers to determine which three levels of the images (i.e. normal, abnormal, and uncertain cases) that the CXRs fall into. RESULTS: We only deal with the grade diagnosis for physical examination and propose multiple new metric indices. Combining predictors for classification by using the area under a receiver operating characteristic curve, we observe that the final decision is related to the threshold from reconstruction error and the probability value. Our method achieves promising results in terms of precision of 98.7 and 94.3% based on the normal and abnormal cases, respectively. CONCLUSION: The results achieved by the proposed framework show superiority in classifying the disease level with high accuracy. This can potentially save the radiologists time and effort, so as to allow them to focus on higher-level risk CXRs.

Non-iterative geometric approach for inverse kinematics of redundant lead-module in a radiosurgical snake-like robot.

BACKGROUND: Snake-like robot is an emerging form of serial-link manipulator with the morphologic design of biological snakes. The redundant robot can be used to assist medical experts in accessing internal organs with minimal or no invasion. Several snake-like robotic designs have been proposed for minimal invasive surgery, however, the few that were developed are yet to be fully explored for clinical procedures. This is due to lack of capability for full-fledged spatial navigation. In rare cases where such snake-like designs are spatially flexible, there exists no inverse kinematics (IK) solution with both precise control and fast response. METHODS: In this study, we proposed a non-iterative geometric method for solving IK of lead-module of a snake-like robot designed for therapy or ablation of abdominal tumors. The proposed method is aimed at providing accurate and fast IK solution for given target points in the robot's workspace. n-1 virtual points (VPs) were geometrically computed and set as coordinates of intermediary joints in an n-link module. Suitable joint angles that can place the end-effector at given target points were then computed by vectorizing coordinates of the VPs, in addition to coordinates of the base point, target point, and tip of the first link in its default pose. The proposed method is applied to solve IK of two-link and redundant four-link modules. RESULTS: Both two-link and four-link modules were simulated with Robotics Toolbox in Matlab 8.3 (R2014a). Implementation result shows that the proposed method can solve IK of the spatially flexible robot with minimal error values. Furthermore, analyses of results from both modules show that the geometric method can reach 99.21 and 88.61% of points in their workspaces, respectively, with an error threshold of 1 mm. The proposed method is non-iterative and has a maximum execution time of 0.009 s. CONCLUSIONS: This paper focuses on solving IK problem of a spatially flexible robot which is part of a developmental project for abdominal surgery through minimal invasion or natural orifices. The study showed that the proposed geometric method can resolve IK of the snake-like robot with negligible error offset. Evaluation against well-known methods shows that the proposed method can reach several points in the robot's workspace with high accuracy and shorter computational time, simultaneously.

Robust kernelized local information fuzzy C-means clustering for brain magnetic resonance image segmentation.

Brain tissue segmentation from magnetic resonance (MR) images is an importance task for clinical use. The segmentation process becomes more challenging in the presence of noise, grayscale inhomogeneity, and other image artifacts. In this paper, we propose a robust kernelized local information fuzzy C-means clustering algorithm (RKLIFCM). It incorporates local information into the segmentation process (both grayscale and spatial) for more homogeneous segmentation. In addition, the Gaussian radial basis kernel function is adopted as a distance metric to replace the standard Euclidean distance. The main advantages of the new algorithm are: efficient utilization of local grayscale and spatial information, robustness to noise, ability to preserve image details, free from any parameter initialization, and with high speed as it runs on image histogram. We compared the proposed algorithm with 7 soft clustering algorithms that run on both image histogram and image pixels to segment brain MR images. Experimental results demonstrate that the proposed RKLIFCM algorithm is able to overcome the influence of noise and achieve higher segmentation accuracy with low computational complexity.

TDFFM: Transformer and Deep Forest Fusion Model for Predicting Coronavirus 3C-Like Protease Cleavage Sites.

COVID-19, caused by the highly contagious SARS-CoV-2 virus, is distinguished by its positive-sense, single-stranded RNA genome. A thorough understanding of SARS-CoV-2 pathogenesis is crucial for halting its proliferation. Notably, the 3C- like protease of the coronavirus (denoted as 3CLpro) is instrumental in the viral replication process. Precise delineation of 3CLpro cleavage sites is imperative for elucidating the transmission dynamics of SARS-CoV-2. While machine learning tools have been deployed to identify potential 3CLpro cleavage sites, these existing methods often fall short in terms of accuracy. To improve the performances of these predictions, we propose a novel analytical framework, the Transformer and Deep Forest Fusion Model (TDFFM). Within TDFFM, we utilize the AAindex and the BLOSUM62 matrix to encode protein sequences. These encoded features are subsequently input into two distinct components: a Deep Forest, which is an effective decision tree ensemble methodology, and a Transformer equipped with a Multi-Level Attention Model (TMLAM). The integration of the attention mechanism allows our model to more accurately identify positive samples, thus enhancing the overall predictive performance. Evaluation on a test set demonstrates that our TDFFM achieves an accuracy of 0.955, an AUC of 0.980, and an F1-score of 0.367, substantiating the model's superior prediction capabilities.

UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-scale Generation and Registration Enhancement.

Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies. The code is accessible at https://github.com/Tinysqua/UWAFA-GAN.

Fusing Multimodal and Anatomical Volumes of Interest Features Using Convolutional Auto-Encoder and Convolutional Neural Networks for Alzheimer's Disease Diagnosis.

Alzheimer's disease (AD) is an age-related disease that affects a large proportion of the elderly. Currently, the neuroimaging techniques [e.g., magnetic resonance imaging (MRI) and positron emission tomography (PET)] are promising modalities for AD diagnosis. Since not all brain regions are affected by AD, a common technique is to study some region-of-interests (ROIs) that are believed to be closely related to AD. Conventional methods used ROIs, identified by the handcrafted features through Automated Anatomical Labeling (AAL) atlas rather than utilizing the original images which may induce missing informative features. In addition, they learned their framework based on the discriminative patches instead of full images for AD diagnosis in multistage learning scheme. In this paper, we integrate the original image features from MRI and PET with their ROIs features in one learning process. Furthermore, we use the ROIs features for forcing the network to focus on the regions that is highly related to AD and hence, the performance of the AD diagnosis can be improved. Specifically, we first obtain the ROIs features from the AAL, then we register every ROI with its corresponding region of the original image to get a synthetic image for each modality of every subject. Then, we employ the convolutional auto-encoder network for learning the synthetic image features and the convolutional neural network (CNN) for learning the original image features. Meanwhile, we concatenate the features from both networks after each convolution layer. Finally, the highly learned features from the MRI and PET are concatenated for brain disease classification. Experiments are carried out on the ADNI datasets including ADNI-1 and ADNI-2 to evaluate our method performance. Our method demonstrates a higher performance in brain disease classification than the recent studies.

Parkinson's Disease Classification and Clinical Score Regression via United Embedding and Sparse Learning From Longitudinal Data.

Parkinson's disease (PD) is known as an irreversible neurodegenerative disease that mainly affects the patient's motor system. Early classification and regression of PD are essential to slow down this degenerative process from its onset. In this article, a novel adaptive unsupervised feature selection approach is proposed by exploiting manifold learning from longitudinal multimodal data. Classification and clinical score prediction are performed jointly to facilitate early PD diagnosis. Specifically, the proposed approach performs united embedding and sparse regression, which can determine the similarity matrices and discriminative features adaptively. Meanwhile, we constrain the similarity matrix among subjects and exploit the l2,p norm to conduct sparse adaptive control for obtaining the intrinsic information of the multimodal data structure. An effective iterative optimization algorithm is proposed to solve this problem. We perform abundant experiments on the Parkinson's Progression Markers Initiative (PPMI) data set to verify the validity of the proposed approach. The results show that our approach boosts the performance on the classification and clinical score regression of longitudinal data and surpasses the state-of-the-art approaches.

Attention-Guided Multi-Branch Convolutional Neural Network for Mitosis Detection From Histopathological Images.

Mitotic count is an important indicator for assessing the invasiveness of breast cancers. Currently, the number of mitoses is manually counted by pathologists, which is both tedious and time-consuming. To address this situation, we propose a fast and accurate method to automatically detect mitosis from the histopathological images. The proposed method can automatically identify mitotic candidates from histological sections for mitosis screening. Specifically, our method exploits deep convolutional neural networks to extract high-level features of mitosis to detect mitotic candidates. Then, we use spatial attention modules to re-encode mitotic features, which allows the model to learn more efficient features. Finally, we use multi-branch classification subnets to screen the mitosis. Compared to existing related methods in literature, our method obtains the best detection results on the dataset of the International Pattern Recognition Conference (ICPR) 2012 Mitosis Detection Competition. Code has been made available at: https://github.com/liushaomin/MitosisDetection.

TA-Net: Triple attention network for medical image segmentation.

The automatic segmentation of medical images has made continuous progress due to the development of convolutional neural networks (CNNs) and attention mechanism. However, previous works usually explore the attention features of a certain dimension in the image, thus may ignore the correlation between feature maps in other dimensions. Therefore, how to capture the global features of various dimensions is still facing challenges. To deal with this problem, we propose a triple attention network (TA-Net) by exploring the ability of the attention mechanism to simultaneously recognize global contextual information in the channel domain, spatial domain, and feature internal domain. Specifically, during the encoder step, we propose a channel with self-attention encoder (CSE) block to learn the long-range dependencies of pixels. The CSE effectively increases the receptive field and enhances the representation of target features. In the decoder step, we propose a spatial attention up-sampling (SU) block that makes the network pay more attention to the position of the useful pixels when fusing the low-level and high-level features. Extensive experiments were tested on four public datasets and one local dataset. The datasets include the following types: retinal blood vessels (DRIVE and STARE), cells (ISBI 2012), cutaneous melanoma (ISIC 2017), and intracranial blood vessels. Experimental results demonstrate that the proposed TA-Net is overall superior to previous state-of-the-art methods in different medical image segmentation tasks with high accuracy, promising robustness, and relatively low redundancy.

Diagnosis of early Alzheimer's disease based on dynamic high order networks.

Machine learning methods have been widely used for early diagnosis of Alzheimer's disease (AD) via functional connectivity networks (FCNs) analysis from neuroimaging data. The conventional low-order FCNs are obtained by time-series correlation of the whole brain based on resting-state functional magnetic resonance imaging (R-fMRI). However, FCNs overlook inter-region interactions, which limits application to brain disease diagnosis. To overcome this drawback, we develop a novel framework to exploit the high-level dynamic interactions among brain regions for early AD diagnosis. Specifically, a sliding window approach is employed to generate some R-fMRI sub-series. The correlations among these sub-series are then used to construct a series of dynamic FCNs. High-order FCNs based on the topographical similarity between each pair of the dynamic FCNs are then constructed. Afterward, a local weight clustering method is used to extract effective features of the network, and the least absolute shrinkage and selection operation method is chosen for feature selection. A support vector machine is employed for classification, and the dynamic high-order network approach is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Our experimental results demonstrate that the proposed approach not only achieves promising results for AD classification, but also successfully recognizes disease-related biomarkers.

GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images.

Brain tumors are one of the major common causes of cancer-related death, worldwide. Growth prediction of these tumors, particularly gliomas which are the most dominant type, can be quite useful to improve treatment planning, quantify tumor aggressiveness, and estimate patients' survival time towards precision medicine. Studying tumor growth prediction basically requires multiple time points of single or multimodal medical images of the same patient. Recent models are based on complex mathematical formulations that basically rely on a system of partial differential equations, e.g. reaction diffusion model, to capture the diffusion and proliferation of tumor cells in the surrounding tissue. However, these models usually have small number of parameters that are insufficient to capture different patterns and other characteristics of the tumors. In addition, such models consider tumor growth independently for each subject, not being able to get benefit from possible common growth patterns existed in the whole population under study. In this paper, we propose a novel data-driven method via stacked 3D generative adversarial networks (GANs), named GP-GAN, for growth prediction of glioma. Specifically, we use stacked conditional GANs with a novel objective function that includes both l1 and Dice losses. Moreover, we use segmented feature maps to guide the generator for better generated images. Our generator is designed based on a modified 3D U-Net architecture with skip connections to combine hierarchical features and thus have a better generated image. The proposed method is trained and tested on 18 subjects with 3 time points (9 subjects from collaborative hospital and 9 subjects from BRATS 2014 dataset). Results show that our proposed GP-GAN outperforms state-of-the-art methods for glioma growth prediction and attain average Jaccard index and Dice coefficient of 78.97% and 88.26%, respectively.

Glioma Growth Prediction via Generative Adversarial Learning from Multi-Time Points Magnetic Resonance Images.

Gliomas are the most dominant and lethal type of brain tumors. Growth prediction is significant to quantify tumor aggressiveness, improve therapy planning, and estimate patients' survival time. This is commonly addressed in literature using mathematical models guided by multi-time point scans of multi/single-modal data for the same subject. However, these models are mechanism-based and heavily rely on complicated mathematical formulations of partial differential equations with few parameters that are insufficient to capture different patterns and other characteristics of gliomas. In this paper, we propose a 3D generative adversarial networks (GANs) for glioma growth prediction. Specifically, we stack 2 GANs with conditional initialization of segmented feature maps. Furthermore, we employ Dice loss in our objective function and devised 3D U-Net architecture for better image generation. The proposed method is trained and validated using 3D patch-based strategy on real magnetic resonance images of 9 subjects with 3 time points. Experimental results show that the proposed method can be successfully used for glioma growth prediction with satisfactory performance.

AMD-GAN: Attention encoder and multi-branch structure based generative adversarial networks for fundus disease detection from scanning laser ophthalmoscopy images.

The scanning laser ophthalmoscopy (SLO) has become an important tool for the determination of peripheral retinal pathology, in recent years. However, the collected SLO images are easily interfered by the eyelash and frame of the devices, which heavily affect the key feature extraction of the images. To address this, we propose a generative adversarial network called AMD-GAN based on the attention encoder (AE) and multi-branch (MB) structure for fundus disease detection from SLO images. Specifically, the designed generator consists of two parts: the AE and generation flow network, where the real SLO images are encoded by the AE module to extract features and the generation flow network to handle the random Gaussian noise by a series of residual block with up-sampling (RU) operations to generate fake images with the same size as the real ones, where the AE is also used to mine features for generator. For discriminator, a ResNet network using MB is devised by copying the stage 3 and stage 4 structures of the ResNet-34 model to extract deep features. Furthermore, the depth-wise asymmetric dilated convolution is leveraged to extract local high-level contextual features and accelerate the training process. Besides, the last layer of discriminator is modified to build the classifier to detect the diseased and normal SLO images. In addition, the prior knowledge of experts is utilized to improve the detection results. Experimental results on the two local SLO datasets demonstrate that our proposed method is promising in detecting the diseased and normal SLO images with the experts labeling.

Adaptive sparse learning using multi-template for neurodegenerative disease diagnosis.

Neurodegenerative diseases are excessively affecting millions of patients, especially elderly people. Early detection and management of these diseases are crucial as the clinical symptoms take years to appear after the onset of neuro-degeneration. This paper proposes an adaptive feature learning framework using multiple templates for early diagnosis. A multi-classification scheme is developed based on multiple brain parcellation atlases with various regions of interest. Different sets of features are extracted and then fused, and a feature selection is applied with an adaptively chosen sparse degree. In addition, both linear discriminative analysis and locally preserving projections are integrated to construct a least square regression model. Finally, we propose a feature space to predict the severity of the disease by the guidance of clinical scores. Our proposed method is validated on both Alzheimer's disease neuroimaging initiative and Parkinson's progression markers initiative databases. Extensive experimental results suggest that the proposed method outperforms the state-of-the-art methods, such as the multi-modal multi-task learning or joint sparse learning. Our method demonstrates that accurate feature learning facilitates the identification of the highly relevant brain regions with significant contribution in the prediction of disease progression. This may pave the way for further medical analysis and diagnosis in practical applications.