mapping-regional-homogeneity-functional-connectivity-visual-cortex

Mapping Regional Homogeneity and Functional Connectivity of the Visual Cortex in Resting-State fMRI

A combined regional homogeneity (ReHo) and functional connectivity (FC) method, a type of noninvasive functional magnetic resonance imaging (fMRI) method, ...

Renmin hospital of Wuhan university

With the emergence of unmanned plane, autonomous vehicles, face recognition, and language processing, the artificial intelligence (AI) has remarkably revolutionized our lifestyle. Recent studies indicate that AI has astounding potential to perform much better than human beings in some tasks, especially in the image recognition field. As the amount of image data in imaging center of ophthalmology is increasing dramatically, analyzing and processing these data is in urgent need. AI has been tried to apply to decipher medical data and has made extraordinary progress in intelligent diagnosis. In this paper, we presented the basic workflow for building an AI model and systematically reviewed applications of AI in the diagnosis of eye diseases. Future work should focus on setting up systematic AI platforms to diagnose general eye diseases based on multimodal data in the real world.

Applications of Artificial Intelligence in Ophthalmology: General Overview.

To develop a new intelligent system based on deep learning for automatically optical coherence tomography (OCT) images categorization.

Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images.

There is increasing evidence that patients with retinal vein occlusion exhibit cerebral vascular changes and are at an increased risk of stroke. However, it remains unknown whether patients with retinal vein occlusion exhibit changes in intrinsic brain activity.

Assessment of cerebral low-frequency oscillations in patients with retinal vein occlusion: a preliminary functional MRI study.

There is increasing neuroimaging evidence that type 2 diabetes patients with retinal microvascular complications show abnormal brain functional and structural architecture and are at an increased risk of cognitive decline and dementia. However, changes in the topological properties of the functional brain connectome in diabetic retinopathy (DR) patients remain unknown. The aim of this study was to explore the topological organization of the brain connectome in DR patients using graph theory approaches.

Disrupted topological organization of human brain connectome in diabetic retinopathy patients.

In clinical ophthalmology, a variety of image-related diagnostic techniques have begun to offer unprecedented insights into eye diseases based on morphological datasets with millions of data points. Artificial intelligence (AI), inspired by the human multilayered neuronal system, has shown astonishing success within some visual and auditory recognition tasks. In these tasks, AI can analyze digital data in a comprehensive, rapid and non-invasive manner. Bioinformatics has become a focus particularly in the field of medical imaging, where it is driven by enhanced computing power and cloud storage, as well as utilization of novel algorithms and generation of data in massive quantities. Machine learning (ML) is an important branch in the field of AI. The overall potential of ML to automatically pinpoint, identify and grade pathological features in ocular diseases will empower ophthalmologists to provide high-quality diagnosis and facilitate personalized health care in the near future. This review offers perspectives on the origin, development, and applications of ML technology, particularly regarding its applications in ophthalmic imaging modalities.

Application of machine learning in ophthalmic imaging modalities.

Diabetic retinopathy (DR) patients are at an increased risk of cognitive decline and dementia. There is accumulating evidence that specific functional and structural architecture changes in the brain are related to cognitive impairment in DR patients. However, little is known regarding whether the functional architecture of resting-state networks (RSNs) changes in DR patients. The purpose of this study was to investigate the intranetwork functional connectivity (FC) and functional network connectivity (FNC) of RSN changes in DR patients using independent component analysis (ICA). Thirty-four DR patients (18 men and 16 women; mean age, 53.53 ± 8.67 years) and 38 nondiabetic healthy controls (HCs) (15 men and 23 women; mean age, 48.63 ± 11.83 years), closely matched for age, sex, and education, underwent resting-state magnetic resonance imaging scans. ICA was applied to extract the nine RSNs. Then, two-sample -tests were conducted to investigate different intranetwork FCs within nine RSNs between the two groups. The FNC toolbox was used to assess interactions among RSNs. Pearson correlation analysis was conducted to explore the relationship between intranetwork FCs and clinical variables in the DR group. A receiver operating characteristic (ROC) curve was conducted to assess the ability of the intranetwork FCs of RSNs in discriminating between the two groups. Compared to the HC group, DR patients showed significant decreased intranetwork FCs within the basal ganglia network (BGN), visual network (VN), ventral default mode network (vDMN), right executive control network (rECN), salience network (SN), left executive control network (lECN), auditory network (AN), and dorsal default mode network (dDMN). In addition, FNC analysis showed increased VN-BGN, VN-vDMN, VN-dDMN, vDMN-lECN, SN-BGN, lECN-dDMN, and AN-BGN FNCs in the DR group, relative to the HC group. Furthermore, altered intranetwork FCs of RSNs were significantly correlated with the glycosylated hemoglobin (HbA1c) level in DR patients. A ROC curve showed that these specific intranetwork FCs of RSNs discriminated between the two groups with a high degree of sensitivity and specificity. Our study highlighted that DR patients had widespread deficits in both low-level perceptual and higher-order cognitive networks. Our results offer important insights into the neural mechanisms of visual loss and cognitive decline in DR patients.

Large-Scale Neuronal Network Dysfunction in Diabetic Retinopathy.

Previous neuroimaging studies have shown that patients with diabetic retinopathy (DR) were accompanied by abnormalities in cerebral functional and structural architecture, whereas the resting cerebral blood flow (CBF) alterations in patients with DR are not well understood.

Altered resting cerebral blood flow specific to patients with diabetic retinopathy revealed by arterial spin labeling perfusion magnetic resonance imaging.

Previous neuroimaging studies demonstrated that visual deprivation triggers significant crossmodal plasticity in the functional and structural architecture of the brain. However, prior neuroimaging studies focused on the static brain activity in blindness. It remains unknown whether alterations of dynamic intrinsic brain activity occur in late blindness (LB). This study investigated dynamic intrinsic brain activity changes in individuals with late blindness by assessing the dynamic amplitude of low-frequency fluctuations (dALFFs) using sliding-window analyses. Forty-one cases of late blindness (LB) (29 males and 12 females, mean age: 39.70 ± 12.66 years) and 48 sighted controls (SCs) (17 males and 31 females, mean age: 43.23 ± 13.40 years) closely matched in age, sex, and education level were enrolled in this study. The dALFF with sliding-window analyses was used to compare the difference in dynamic intrinsic brain activity between the two groups. Compared with SCs, individuals with LB exhibited significantly lower dALFF values in the bilateral lingual gyrus (LING)/calcarine (CAL) and left thalamus (THA). LB cases also showed considerably decreased dFC values between the bilateral LING/CAL and the left middle frontal gyrus (MFG) and between the left THA and the right LING/cerebelum_6 (CER) (two-tailed, voxel-level  < 0.01, Gaussian random field (GRF) correction, cluster-level  < 0.05). Our study demonstrated that LB individuals showed lower-temporal variability of dALFF in the visual cortices and thalamus, suggesting lower flexibility of visual thalamocortical activity, which might reflect impaired visual processing in LB individuals. These findings indicate that abnormal dynamic intrinsic brain activity might be involved in the neurophysiological mechanisms of LB.

Altered Temporal Dynamic Intrinsic Brain Activity in Late Blindness.

Retinopathy of prematurity (ROP) is a leading cause of childhood blindness worldwide but can be a treatable retinal disease with appropriate and timely diagnosis. This study was performed to develop a robust intelligent system based on deep learning to automatically classify the severity of ROP from fundus images and detect the stage of ROP and presence of plus disease to enable automated diagnosis and further treatment.

Automated identification of retinopathy of prematurity by image-based deep learning.

 This study used the regional homogeneity (ReHo) technique to explore whether spontaneous brain activity is altered in patients with iridocyclitis.  Twenty-six patients with iridocyclitis (14 men and 12 women) and 26 healthy volunteers (15 men and 11 women) matched for sex and age were enrolled in this study. The ReHo technique was used to comprehensively assess changes in whole-brain synchronous neuronal activity. The diagnostic ability of the ReHo method was evaluated by means of receive operating characteristic (ROC) curve analysis. Moreover, associations of average ReHo values in different brain areas and clinical characteristics were analyzed using correlation analysis.  Compared with healthy volunteers, reduced ReHo values were observed in patients with iridocyclitis in the following brain regions: the right inferior occipital gyrus, bilateral calcarine, right middle temporal gyrus, right postcentral gyrus, left superior occipital gyrus, and left precuneus. In contrast, ReHo values were significantly enhanced in the right cerebellum, left putamen, left supplementary motor area, and left inferior frontal gyrus in patients with iridocyclitis, compared with healthy volunteers (false discovery rate correction,  < 0.05).  Patients with iridocyclitis exhibited disturbed synchronous neural activities in specific brain areas, including the visual, motor, and somatosensory regions, as well as the default mode network. These findings offer a novel image-guided research strategy that might aid in exploration of neuropathological or compensatory mechanisms in patients with iridocyclitis.

Disrupted Neural Activity in Individuals With Iridocyclitis Using Regional Homogeneity: A Resting-State Functional Magnetic Resonance Imaging Study.

 Growing evidence demonstrate that diabetic retinopathy (DR) patients have a high risk of cognitive decline and exhibit abnormal brain activity. However, neuroimaging studies thus far have focused on static cerebral activity changes in DR patients. The characteristics of dynamic cerebral activity in patients with DR are poorly understood.  The purpose of the study was to investigate the dynamic cerebral activity changes in patients with DR using the dynamic amplitude of low-frequency fluctuation (dALFF) method.  Thirty-four DR patients (18 men and 16 women) and 38 healthy controls (HCs) (18 males and 20 females) closely matched in age, sex, and education were enrolled in this study. The dALFF method was used to investigate dynamic intrinsic brain activity differences between the DR and HC groups.  Compared with HCs, DR patients exhibited increased dALFF variability in the right brainstem, left cerebellum_8, left cerebellum_9, and left parahippocampal gyrus. In contrast, DR patients exhibited decreased dALFF variability in the left middle occipital gyrus and right middle occipital gyrus.  Our study highlighted that DR patients showed abnormal variability of dALFF in the visual cortices, cerebellum, and parahippocampal gyrus. These findings suggest impaired visual and motor and memory function in DR individuals. Thus, abnormal dynamic spontaneous brain activity might be involved in the pathophysiology of DR.

Dynamic Changes of Amplitude of Low-Frequency Fluctuations in Patients With Diabetic Retinopathy.

However, whether the whole-brain functional network hub changes occur in diabetic retinopathy patients remains unknown.

Abnormal intrinsic functional network hubs in diabetic retinopathy patients.

Several studies demonstrated that patients with iridocyclitis were associated with vision loss and cognitive decline, whereas alterations in spontaneous brain activity occur in iridocyclitis patients remains unknown. The study aimed to explore spontaneous brain activity changes in iridocyclitis patients. Twenty-six patients with iridocyclitis and 26 healthy controls were finally included in our study. Resting-state MRI (rs-MRI) scan was conducted on both groups and the whole brain amplitude of low-frequency fluctuations (ALFFs) value was collected to assess differences in spontaneous brain activity. A receiver operating characteristic (ROC) curve was analyzed to distinguish between the fMRI data of patients with iridocyclitis and healthy controls. Patients with iridocyclitis showed significantly lower ALFF values in the right inferior parietal lobule, right calcarine, right superior temporal gyrus and right precentral gyrus compared to healthy controls and significantly higher ALFF values in the left superior frontal gyrus (P < 0.01, false discovery rate correction). The ROC curve analysis of different brain areas showed that the accuracies of ALFF value specificity between the iridocyclitis and healthy controls of the area under the curve were over 0.8. Our study highlighted an altered spontaneous activity in multiple brain regions, including the visual cortex, default-mode network, auditory area and sensorimotor areas in iridocyclitis. This may provide valuable information about underlying pathogenic mechanisms of iridocyclitis. These findings also indicate that rs-fMRI serves as a potential tool in the disease detection and evaluation of neurologic impairment in iridocyclitis.

Assessment of spontaneous brain activity patterns in patients with iridocyclitis: a resting-state study.

To explore the intrinsic functional connectivity (FC) alteration of the primary visual cortex (V1) between individuals with iridocyclitis and healthy controls (HCs) by the resting-state functional magnetic resonance imaging (fMRI) technique, and to investigate whether FC findings be used to differentiate patients with iridocyclitis from HCs.

Altered Functional Connectivity of the Primary Visual Cortex in Patients With Iridocyclitis and Assessment of Its Predictive Value Using Machine Learning.

The purpose of the study was to find the differences in intrinsic functional connectivity (FC) patterns of the primary visual area (V1) among diabetic retinopathy (DR), diabetes mellitus (DM), and healthy controls (HCs) applying resting-state functional magnetic resonance imaging (rs-fMRI).

Article	Year
Applications of Artificial Intelligence in Ophthalmology: General Overview. Journal of ophthalmology\| PubMed ID: 30581604	2018
Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities From Optical Coherence Tomography Images. Translational vision science & technology\| PubMed ID: 30619661	2018
Assessment of cerebral low-frequency oscillations in patients with retinal vein occlusion: a preliminary functional MRI study. Acta radiologica (Stockholm, Sweden : 1987)\| PubMed ID: 31604375	2020
Disrupted topological organization of human brain connectome in diabetic retinopathy patients. Neuropsychiatric disease and treatment\| PubMed ID: 31695385	2019
Application of machine learning in ophthalmic imaging modalities. Eye and vision (London, England)\| PubMed ID: 32322599	2020
Large-Scale Neuronal Network Dysfunction in Diabetic Retinopathy. Neural plasticity\| PubMed ID: 32399026	2020
Altered resting cerebral blood flow specific to patients with diabetic retinopathy revealed by arterial spin labeling perfusion magnetic resonance imaging. Acta radiologica (Stockholm, Sweden : 1987)\| PubMed ID: 32551803	2021
Altered Temporal Dynamic Intrinsic Brain Activity in Late Blindness. BioMed research international\| PubMed ID: 32685447	2020
Automated identification of retinopathy of prematurity by image-based deep learning. Eye and vision (London, England)\| PubMed ID: 32766357	2020
Disrupted Neural Activity in Individuals With Iridocyclitis Using Regional Homogeneity: A Resting-State Functional Magnetic Resonance Imaging Study. Frontiers in neurology\| PubMed ID: 33643195	2021
Dynamic Changes of Amplitude of Low-Frequency Fluctuations in Patients With Diabetic Retinopathy. Frontiers in neurology\| PubMed ID: 33643197	2021
Abnormal intrinsic functional network hubs in diabetic retinopathy patients. Neuroreport\| PubMed ID: 33657077	2021
Assessment of spontaneous brain activity patterns in patients with iridocyclitis: a resting-state study. Neuroreport\| PubMed ID: 33789337	2021
Altered Functional Connectivity of the Primary Visual Cortex in Patients With Iridocyclitis and Assessment of Its Predictive Value Using Machine Learning. Frontiers in immunology\| PubMed ID: 34025659	2021
Altered Functional Connectivity Strength of Primary Visual Cortex in Subjects with Diabetic Retinopathy. Diabetes, metabolic syndrome and obesity : targets and therapy\| PubMed ID: 34285528	2021

Yan Tong

Biography

JoVE Journal Publications

Other Publications