Multimodal transformer graph convolution attention isomorphism network (MTCGAIN): a novel deep network for detection of insomnia disorder.

Background: In clinic, the subjectivity of diagnosing insomnia disorder (ID) often leads to misdiagnosis or missed diagnosis, as ID may have the same symptoms as those of other health problems. Methods: A novel deep network, the multimodal transformer graph convolution attention isomorphism network (MTGCAIN) is proposed in this study. In this network, graph convolution attention (GCA) is first employed to extract the graph features of brain connectivity and achieve good spatial interpretability. Second, the MTGCAIN comprehensively utilizes multiple brain network atlases and a multimodal transformer (MT) to facilitate coded information exchange between the atlases. In this way, MTGCAIN can be used to more effectively identify biomarkers and arrive at accurate diagnoses. Results: The experimental results demonstrated that more accurate and objective diagnosis of ID can be achieved using the MTGCAIN. According to fivefold cross-validation, the accuracy reached 81.29% and the area under the receiver operating characteristic curve (AUC) reached 0.8760. A total of nine brain regions were detected as abnormal, namely right supplementary motor area (SMA.R), right temporal pole: superior temporal gyrus (TPOsup.R), left temporal pole: superior temporal gyrus (TPOsup.L), right superior frontal gyrus, dorsolateral (SFGdor.R), right middle temporal gyrus (MTG.R), left middle temporal gyrus (MTG.L), right inferior temporal gyrus (ITG.R), right median cingulate and paracingulate gyri (DCG.R), left median cingulate and paracingulate gyri (DCG.L). Conclusions: The brain regions in the default mode network (DMN) of patients with ID show significant impairment (occupies four-ninths). In addition, the functional connectivity (FC) between the right middle occipital gyrus and inferior temporal gyrus (ITG) has an obvious correlation with comorbid anxiety (P=0.008) and depression (P=0.005) among patients with ID.

[Automatic detection method of intracranial aneurysms on maximum intensity projection images based on SE-CaraNet].

Conventional maximum intensity projection (MIP) images tend to ignore some morphological features in the detection of intracranial aneurysms, resulting in missed detection and misdetection. To solve this problem, a new method for intracranial aneurysm detection based on omni-directional MIP image is proposed in this paper. Firstly, the three-dimensional magnetic resonance angiography (MRA) images were projected with the maximum density in all directions to obtain the MIP images. Then, the region of intracranial aneurysm was prepositioned by matching filter. Finally, the Squeeze and Excitation (SE) module was used to improve the CaraNet model. Excitation and the improved model were used to detect the predetermined location in the omni-directional MIP image to determine whether there was intracranial aneurysm. In this paper, 245 cases of images were collected to test the proposed method. The results showed that the accuracy and specificity of the proposed method could reach 93.75% and 93.86%, respectively, significantly improved the detection performance of intracranial aneurysms in MIP images.

Investigation of the correlation between brain functional connectivity and ESRD based on low-order and high-order feature analysis of rs-fMRI.

BACKGROUND: The lack of analysis of brain networks in individuals with end-stage renal disease (ESRD) is an obstacle to detecting and preventing neurological complications of ESRD. PURPOSE: This study aims to explore the correlation between brain activity and ESRD based on a quantitative analysis of the dynamic functional connectivity (dFC) of brain networks. It provides insights into differences in brain functional connectivity between healthy individuals and ESRD patients and aims to identify the brain activities and regions most relevant to ESRD. METHODS: Differences in brain functional connectivity between healthy individuals and ESRD patients were analyzed and quantitatively evaluated in this study. Blood oxygen level-dependent (BOLD) signals obtained through resting-state functional magnetic resonance imaging (rs-fMRI) were used as information carriers. First, a connectivity matrix of dFC was constructed for each subject using Pearson correlation. Then a high-order connectivity matrix was built by applying the "correlation's correlation" method. Second, sparsification of the high-order connectivity matrix was performed using the graphical least absolute shrinkage and selection operator (gLASSO) model. The discriminative features of the sparse connectivity matrix were extracted and sifted using central moments and t-tests, respectively. Finally, feature classification was conducted using a support vector machine (SVM). RESULTS: The experiment showed that functional connectivity was reduced to some degree in certain brain regions of ESRD patients. The sensorimotor, visual, and cerebellum subnetworks had the highest numbers of abnormal functional connectivities. It is inferred that these three subnetworks most likely have a direct relationship to ESRD. CONCLUSIONS: The low-order and high-order dFC features can identify the positions where brain damage occurs in ESRD patients. In contrast to healthy individuals, the damaged brain regions and the disruption of functional connectivity in ESRD patients were not limited to specific regions. This indicates that ESRD has a severe impact on brain function. Abnormal functional connectivity was mainly associated with the three functional brain regions responsible for visual processing, emotional, and motor control. The findings presented here have the potential for use in the detection, prevention, and prognostic evaluation of ESRD.

Fiber connectivity density mapping in end-stage renal disease patients: a preliminary study.

Abnormal brain structural connectivity of end-stage renal disease(ESRD) is associated with cognitive impairment. However, the characteristics of cortical structural connectivity have not been investigated in ESRD patients. Here, we study structural connectivity of the entire cerebral cortex using a fiber connectivity density(FiCD) mapping method derived from diffusion tensor imaging(DTI) data of 25 ESRD patients and 20 healthy controls, and between-group differences were compared in a vertexwise manner. We also investigated the associations between these abnormal cortical connectivities and the clinical variables using Pearson correlation analysis and multifactor linear regression analysis. Our results demonstrated that the mean global FiCD value was significantly decreased in ESRD patients. Notably, FiCD values were significantly changed(decreased or increased) in certain cortical regions, which mainly involved the bilateral dorsolateral prefrontal cortex(DLPFC), inferior parietal cortex, lateral temporal cortex and middle occipital cortex. In ESRD patients, we found a trend of negative correlation between the increased FiCD values of bilateral middle frontal gyrus and serum creatinine, urea, parathyroid hormone(PTH) levels and dialysis duration. Only the white matter hyperintensity(WMH) scores were significantly negatively correlated with the global FiCD value in multifactor regression analysis. Our results suggested that ESRD patients exhibited extensive impaired cortical structural connectivity, which was related to the severity of WMHs. A compensation mechanism of cortical structural recombination may play a role in how the brain adapts to maintain optimal network function. Additionally, the serum creatinine, urea and PTH levels may be risk factors for brain structural network decompensation in ESRD patients.

[An algorithm for three-dimensional plumonary parenchymal segmentation by integrating surfacelet transform with pulse coupled neural network].

In order to overcome the difficulty in lung parenchymal segmentation due to the factors such as lung disease and bronchial interference, a segmentation algorithm for three-dimensional lung parenchymal is presented based on the integration of surfacelet transform and pulse coupled neural network (PCNN). First, the three-dimensional computed tomography of lungs is decomposed into surfacelet transform domain to obtain multi-scale and multi-directional sub-band information. The edge features are then enhanced by filtering sub-band coefficients using local modified Laplacian operator. Second, surfacelet inverse transform is implemented and the reconstructed image is fed back to the input of PCNN. Finally, iteration process of the PCNN is carried out to obtain final segmentation result. The proposed algorithm is validated on the samples of public dataset. The experimental results demonstrate that the proposed algorithm has superior performance over that of the three-dimensional surfacelet transform edge detection algorithm, the three-dimensional region growing algorithm, and the three-dimensional U-NET algorithm. It can effectively suppress the interference coming from lung lesions and bronchial, and obtain a complete structure of lung parenchyma.

Body region localization in whole-body low-dose CT images of PET/CT scans using virtual landmarks.

PURPOSE: Radiological imaging and image interpretation for clinical decision making are mostly specific to each body region such as head and neck, thorax, abdomen, pelvis, and extremities. In this study, we present a new solution to trim automatically the given axial image stack into image volumes satisfying the given body region definition. METHODS: The proposed approach consists of the following steps. First, a set of reference objects is selected and roughly segmented. Virtual landmarks (VLs) for the objects are then identified by using principal component analysis and recursive subdivision of the object via the principal axes system. The VLs can be defined based on just the binary objects or objects with gray values also considered. The VLs may lie anywhere with respect to the object, inside or outside, and rarely on the object surface, and are tethered to the object. Second, a classic neural network regressor is configured to learn the geometric mapping relationship between the VLs and the boundary locations of each body region. The trained network is then used to predict the locations of the body region boundaries. In this study, we focus on three body regions - thorax, abdomen, and pelvis, and predict their superior and inferior axial locations denoted by TS(I), TI(I), AS(I), AI(I), PS(I), and PI(I), respectively, for any given volume image I. Two kinds of reference objects - the skeleton and the lungs and airways, are employed to test the localization performance of the proposed approach. RESULTS: Our method is tested by using low-dose unenhanced computed tomography (CT) images of 180 near whole-body 18 F-fluorodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) scans (including 34 whole-body scans) which are randomly divided into training and testing sets with a ratio of 85%:15%. The procedure is repeated six times and three times for the case of lungs and skeleton, respectively, with different divisions of the entire data set at this proportion. For the case of using skeleton as a reference object, the overall mean localization error for the six locations expressed as number of slices (nS) and distance (dS) in mm, is found to be nS: 3.4, 4.7, 4.1, 5.2, 5.2, and 3.9; dS: 13.4, 18.9, 16.5, 20.8, 20.8, and 15.5 mm for binary objects; nS: 4.1, 5.7, 4.3, 5.9, 5.9, and 4.0; dS: 16.2, 22.7, 17.2, 23.7, 23.7, and 16.1 mm for gray objects, respectively. For the case of using lungs and airways as a reference object, the corresponding results are, nS: 4.0, 5.3, 4.1, 6.9, 6.9, and 7.4; dS: 15.0, 19.7, 15.3, 26.2, 26.2, and 27.9 mm for binary objects; nS: 3.9, 5.4, 3.6, 7.2, 7.2, and 7.6; dS: 14.6, 20.1, 13.7, 27.3, 27.3, and 28.6 mm for gray objects, respectively. CONCLUSIONS: Precise body region identification automatically in whole-body or body region tomographic images is vital for numerous medical image analysis and analytics applications. Despite its importance, this issue has received very little attention in the literature. We present a solution to this problem in this study using the concept of virtual landmarks. The method achieves localization accuracy within 2-3 slices, which is roughly comparable to the variation found in localization by experts. As long as the reference objects can be roughly segmented, the method with its learned VLs-to-boundary location relationship and predictive ability is transferable from one image modality to another.

Automatic thoracic body region localization.

Radiological imaging and image interpretation for clinical decision making are mostly specific to each body region such as head & neck, thorax, abdomen, pelvis, and extremities. For automating image analysis and consistency of results, standardizing definitions of body regions and the various anatomic objects, tissue regions, and zones in them becomes essential. Assuming that a standardized definition of body regions is available, a fundamental early step needed in automated image and object analytics is to automatically trim the given image stack into image volumes exactly satisfying the body region definition. This paper presents a solution to this problem based on the concept of virtual landmarks and evaluates it on whole-body positron emission tomography/computed tomography (PET/CT) scans. The method first selects a (set of) reference object(s), segments it (them) roughly, and identifies virtual landmarks for the object(s). The geometric relationship between these landmarks and the boundary locations of body regions in the cranio-caudal direction is then learned through a neural network regressor, and the locations are predicted. Based on low-dose unenhanced CT images of 180 near whole-body PET/CT scans (which includes 34 whole-body PET/CT scans), the mean localization error for the boundaries of superior of thorax (TS) and inferior of thorax (TI), expressed as number of slices (slice spacing ≈ 4mm)), and using either the skeleton or the pleural spaces as reference objects, is found to be 3,2 (using skeleton) and 3, 5 (using pleural spaces) respectively, or in mm 13, 10 mm (using skeleton) and 10.5, 20 mm (using pleural spaces), respectively. Improvements of this performance via optimal selection of objects and virtual landmarks and other object analytics applications are currently being pursued. and the skeleton and pleural spaces used as a reference objects.

Virtual Landmarks.

Much has been published on finding landmarks on object surfaces in the context of shape modeling. While this is still an open problem, many of the challenges of past approaches can be overcome by removing the restriction that landmarks must be on the object surface. The virtual landmarks we propose may reside inside, on the boundary of, or outside the object and are tethered to the object. Our solution is straightforward, simple, and recursive in nature, proceeding from global features initially to local features in later levels to detect landmarks. Principal component analysis (PCA) is used as an engine to recursively subdivide the object region. The object itself may be represented in binary or fuzzy form or with gray values. The method is illustrated in 3D space (although it generalizes readily to spaces of any dimensionality) on four objects (liver, trachea and bronchi, and outer boundaries of left and right lungs along pleura) derived from 5 patient computed tomography (CT) image data sets of the thorax and abdomen. The virtual landmark identification approach seems to work well on different structures in different subjects and seems to detect landmarks that are homologously located in different samples of the same object. The approach guarantees that virtual landmarks are invariant to translation, scaling, and rotation of the object/image. Landmarking techniques are fundamental for many computer vision and image processing applications, and we are currently exploring the use virtual landmarks in automatic anatomy recognition and object analytics.

A novel level set model with automated initialization and controlling parameters for medical image segmentation.

In this paper, a level set model without the need of generating initial contour and setting controlling parameters manually is proposed for medical image segmentation. The contribution of this paper is mainly manifested in three points. First, we propose a novel adaptive mean shift clustering method based on global image information to guide the evolution of level set. By simple threshold processing, the results of mean shift clustering can automatically and speedily generate an initial contour of level set evolution. Second, we devise several new functions to estimate the controlling parameters of the level set evolution based on the clustering results and image characteristics. Third, the reaction diffusion method is adopted to supersede the distance regularization term of RSF-level set model, which can improve the accuracy and speed of segmentation effectively with less manual intervention. Experimental results demonstrate the performance and efficiency of the proposed model for medical image segmentation.