Q-space imaging based on Gaussian radial basis function with Laplace regularization.

PURPOSE: To introduce the diffusion signal characteristics presented by spherical harmonics (SH) basis into the q-space imaging method based on Gaussian radial basis function (GRBF) to robustly reconstruct ensemble average diffusion propagator (EAP) in diffusion MRI (dMRI). METHODS: We introduced the Laplacian regularization of the signal into the dMRI imaging method based on GRBF, and derived the relevant indicators of microstructure imaging and the orientation distribution function (ODF) providing fiber bundle direction information based on EAP. In addition, this method is combined with a multi-compartment model to calculate the diameter of fiber bundle axons. The evaluation of the results included qualitative comparisons and quantitative assessments of the signal fitting. RESULTS: The results show that the proposed method achieves the more significant accuracy improvement in reconstructing signal. Meanwhile, ODFs estimated by the proposed method show the sharper profiles and less spurious peaks, even under the sparse and noisy conditions. In the 36 sets of axon diameter estimation experiments, 34 and 30 sets of results showed that the proposed method reduced the mean and SD of axon diameter estimates, respectively. Moreover, compared with the current state-of-the-art method, the mean and SD of axon diameter estimated by the proposed method are mostly lower, with 32 and 29 of 36 groups. CONCLUSION: The proposed method outperforms the GRBF regarding signal fitting and the estimation of the EAP and ODF with multi-shell sparse samples. Moreover, it shows the potential to recover important features of microstructures with less uncertainty by using proposed method together with multi-compartment models.

DMAF-Net: deformable multi-scale adaptive fusion network for dental structure detection with panoramic radiographs.

OBJECTIVES: Panoramic radiography is one of the most commonly used diagnostic modalities in dentistry. Automatic recognition of panoramic radiography helps dentists in decision support. In order to improve the accuracy of the detection of dental structural problems in panoramic radiographs, we have improved the You Only Look Once (YOLO) network and verified the feasibility of this new method in aiding the detection of dental problems. METHODS: We propose a Deformable Multi-scale Adaptive Fusion Net (DMAF-Net) to detect 5 types of dental situations (impacted teeth, missing teeth, implants, crown restorations, and root canal-treated teeth) in panoramic radiography by improving the YOLO network. In DMAF-Net, we propose different modules to enhance the feature extraction capability of the network as well as to acquire high-level features at different scales, while using adaptively spatial feature fusion to solve the problem of scale mismatches of different feature layers, which effectively improves the detection performance. In order to evaluate the detection performance of the models, we compare the experimental results of different models in the test set and select the optimal results of the models by calculating the average of different metrics in each category as the evaluation criteria. RESULTS: About 1474 panoramic radiographs were divided into training, validation, and test sets in the ratio of 7:2:1. In the test set, the average precision and recall of DMAF-Net are 92.7% and 87.6%, respectively; the mean Average Precision (mAP0.5 and mAP[0.5:0.95]) are 91.8% and 63.7%, respectively. CONCLUSIONS: The proposed DMAF-Net model improves existing deep learning models and achieves automatic detection of tooth structure problems in panoramic radiographs. This new method has great potential for new computer-aided diagnostic, teaching, and clinical applications in the future.

CT classification model of pancreatic serous cystic neoplasm and mucinous cystic neoplasm based on deep transfer learning.

BACKGROUND: Pancreatic cancer is a highly lethal disease. The preoperative distinction between pancreatic serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN) remains a clinical challenge. OBJECTIVE: The goal of this study is to provide clinicians with supportive advice and avoid overtreatment by constructing a convolutional neural network (CNN) classifier to automatically identify pancreatic cancer using computed tomography (CT) images. METHODS: We construct a CNN model using a dataset of 6,173 CT images obtained from 107 pathologically confirmed pancreatic cancer patients at Shanghai Changhai Hospital from January 2017 to February 2022. We divide CT slices into three categories namely, SCN, MCN, and no tumor, to train the DenseNet201-based CNN model with multi-head spatial attention mechanism (MSAM-DenseNet201). The attention module enhances the network's attention to local features and effectively improves the network performance. The trained model is applied to process all CT image slices and finally realize the two categories classification of MCN and SCN patients through a joint voting strategy. RESULTS: Using a 10-fold cross validation method, this new MSAM-DenseNet201 model achieves a classification accuracy of 92.52%, a precision of 92.16%, a sensitivity of 92.16%, and a specificity of 92.86%, respectively. CONCLUSIONS: This study demonstrates the feasibility of using a deep learning network or classification model to help diagnose MCN and SCN cases. This, the new method has great potential for developing new computer-aided diagnosis systems and applying in future clinical practice.

A predictive model for early therapeutic efficacy of colorectal liver metastases using multimodal MRI data.

BACKGROUND: Liver metastases is a pivotal factor of death in patients with colorectal cancer. The longitudinal data of colorectal liver metastases (CRLM) during treatment can monitor and reflect treatment efficacy and outcomes. OBJECTIVE: The objective of this study is to establish a radiomic model based on longitudinal magnetic resonance imaging (MRI) to predict chemotherapy response in patients with CRLM. METHODS: This study retrospectively enrolled longitudinal MRI data of five modalities on 100 patients. According to Response Evaluation Criteria in Solid Tumors (RECIST 1.1), 42 and 58 patients were identified as responders and non-responders, respectively. First, radiomic features were computed from different modalities of image data acquired pre-treatment and early-treatment, as well as their differences (Δ). Next, the features were screened by a two-sample t-test, max-relevance and min-redundancy (mRMR), and least absolute shrinkage and selection operator (LASSO). Then, several ensemble radiomic models that integrate support vector machine (SVM), k-nearest neighbor (KNN), gradient boost decision tree (GBDT) and multi-layer perceptron (MLP) were established based on voting method to predict chemotherapy response. Data samples were divided into training and verification queues using a ratio of 8:2. Finally, we used the area under ROC curve (AUC) to evaluate model performance. RESULTS: Using the ensemble model developed using featue differences (Δ) computed from the longitudinal apparent diffusion coefficient (ADC) images, AUC is 0.9007±0.0436 for the training cohort. Applying to the testing cohort, AUC is 0.8958 and overall accuracy is 0.9. CONCLUSIONS: Study results demonstrate advantages and high performance of the ensemble radiomic model based on the radiomics feature difference of the longitudinal ADC images in predicting chemotherapy response, which has potential to assist treatment decision-making and improve clinical outcome.

PAPNet: Convolutional network for pancreatic cyst segmentation.

BACKGROUND: Automatic segmentation of the pancreas and its tumor region is a prerequisite for computer-aided diagnosis. OBJECTIVE: In this study, we focus on the segmentation of pancreatic cysts in abdominal computed tomography (CT) scan, which is challenging and has the clinical auxiliary diagnostic significance due to the variability of location and shape of pancreatic cysts. METHODS: We propose a convolutional neural network architecture for segmentation of pancreatic cysts, which is called pyramid attention and pooling on convolutional neural network (PAPNet). In PAPNet, we propose a new atrous pyramid attention module to extract high-level features at different scales, and a spatial pyramid pooling module to fuse contextual spatial information, which effectively improves the segmentation performance. RESULTS: The model was trained and tested using 1,346 CT slice images obtained from 107 patients with the pathologically confirmed pancreatic cancer. The mean dice similarity coefficient (DSC) and mean Jaccard index (JI) achieved using the 5-fold cross-validation method are 84.53% and 75.81%, respectively. CONCLUSIONS: The experimental results demonstrate that the proposed new method in this study enables to achieve effective results of pancreatic cyst segmentation.

Prediction of the activity of Crohn's disease based on CT radiomics combined with machine learning models.

PURPOSE: To investigate the value of a CT-based radiomics model in identification of Crohn's disease (CD) active phase and remission phase. METHODS: CT images of 101 patients diagnosed with CD were retrospectively collected, which included 60 patients in active phase and 41 patients in remission phase. These patients were randomly divided into training group and test group at a ratio of 7 : 3. First, the lesion areas were manually delineated by the physician. Meanwhile, radiomics features were extracted from each lesion. Next, the features were selected by t-test and the least absolute shrinkage and selection operator regression algorithm. Then, several machine learning models including random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), logistic regression (LR) and K-nearest neighbor (KNN) algorithms were used to construct CD activity classification models respectively. Finally, the soft-voting mechanism was used to integrate algorithms with better effects to perform two classifications of data, and the receiver operating characteristic curves were applied to evaluate the diagnostic value of the models. RESULTS: Both on the training set and the test set, AUC of the five machine learning classification models reached 0.85 or more. The ensemble soft-voting classifier obtained by using the combination of SVM, LR and KNN could better distinguish active CD from CD remission. For the test set, AUC was 0.938, and accuracy, sensitivity, and specificity were 0.903, 0.911, and 0.892, respectively. CONCLUSION: This study demonstrated that the established radiomics model could objectively and effectively diagnose CD activity. The integrated approach has better diagnostic performance.

[Fiber direction estimation using constrained spherical deconvolution based on multi-model response function].

Constrained spherical deconvolution can quantify white matter fiber orientation distribution information from diffusion magnetic resonance imaging data. But this method is only applicable to single shell diffusion magnetic resonance imaging data and will provide wrong fiber orientation information in white matter tissue which contains isotropic diffusion signals. To solve these problems, this paper proposes a constrained spherical deconvolution method based on multi-model response function. Multi-shell data can improve the stability of fiber orientation, and multi-model response function can attenuate isotropic diffusion signals in white matter, providing more accurate fiber orientation information. Synthetic data and real brain data from public database were used to verify the effectiveness of this algorithm. The results demonstrate that the proposed algorithm can attenuate isotropic diffusion signals in white matter and overcome the influence of partial volume effect on fiber direction estimation, thus estimate fiber direction more accurately. The reconstructed fiber direction distribution is stable, the false peaks are less, and the recognition ability of cross fiber is stronger, which lays a foundation for the further research of fiber bundle tracking technology.

Segmentation of corpus callosum based on tensor fuzzy clustering algorithm.

BACKGROUND: The corpus callosum in the midsagittal plane plays a crucial role in the early diagnosis of diseases. When the anisotropy of the diffusion tensor in the midsagittal plane is calculated, the anisotropy of corpus callosum is close to that of the fornix, which leads to blurred boundary of the segmentation region. OBJECTIVE: To apply a fuzzy clustering algorithm combined with new spatial information to achieve accurate segmentation of the corpus callosum in the midsagittal plane in diffusion tensor images. METHODS: In this algorithm, a fixed region of interest is selected from the midsagittal plane, and the anisotropic filtering algorithm based on tensor is implemented by replacing the gradient direction of the structural tensor with an eigenvector, thus filtering the diffusion tensor of region of interest. Then, the iterative clustering center based on K-means clustering is used as the initial clustering center of tensor fuzzy clustering algorithm. Taking filtered diffusion tensor as input data and different metrics as similarity measures, the neighborhood diffusion tensor voxel calculation method of Log Euclidean framework is introduced in the membership function calculation, and tensor fuzzy clustering algorithm is proposed. In this study, MGH35 data from the Human Connectome Project (HCP) are tested and the variance, accuracy and specificity of the experimental results are discussed. RESULTS: Segmentation results of three groups of subjects in MGH35 data are reported. The average segmentation accuracy is 97.34%, and the average specificity is 98.43%. CONCLUSIONS: When segmenting the corpus callosum of diffusion tensor imaging, our method cannot only effective denoise images, but also achieve high accuracy and specificity.

Hybrid diffusion tensor imaging feature-based AD classification.

BACKGROUND: Effective detection of Alzheimer's disease (AD) is still difficult in clinical practice. Therefore, establishment of AD detection model by means of machine learning is of great significance to assist AD diagnosis. OBJECTIVE: To investigate and test a new detection model aiming to help doctors diagnose AD more accurately. METHODS: Diffusion tensor images and the corresponding T1w images acquired from subjects (AD = 98, normal control (NC) = 100) are used to construct brain networks. Then, 9 types features (198×90×9 in total) are extracted from the 3D brain networks by a graph theory method. Features with low correction in both groups are selected through the Pearson correlation analysis. Finally, the selected features (198×33, 198×26, 198×30, 198×42, 198×36, 198×23, 198×29, 198×14, 198×25) are separately used into train 3 machine learning classifier based detection models in which 60% of study subjects are used for training, 20% for validation and 20% for testing. RESULTS: The best detection accuracy levels of 3 models are 90%, 98% and 90% with the corresponding sensitivity of 92%, 96%, and 72% and specificity of 88%, 100% and 94% when using a random forest classifier trained with the Shortest Path Length (SPL) features (198×14), a support vector machine trained with the Degree Centrality features (198×33), and a convolution neural network trained with SPL features, respectively. CONCLUSIONS: This study demonstrates that the new method and models not only improve the accuracy of detecting AD, but also avoid bias caused by the method of direct dimensionality reduction from high dimensional data.

Analysis of tectonic geochemical characteristics and leaching effects of typical pollutants in Kongyu gold mining area in Dadu River Basin, Kangding.

Kongyu Gold Mining Area is located in the northern margin of the Sichuan-Yunnan tectonic belt. This area has gone through two large tectonic cycles of Mesoproterozoic, Neoproterozoic and Phanerozoic. The strata are accompanied by a large number of tensile cracks, shear cracks and microfissures. The voidage, permeability and transitional effect of the rock are increased, and the transformation between surface water and groundwater is enhanced. On the other hand, tectonic movement controls the distributions and allocations of elements in the earth's crust, resulting in directional geochemical changes in crustal materials and rules. Driven by the tectonic force, the elements are reallocated. The ion content and ion compressibility of those elements increase and decrease inversely. The manifestations of rocks and minerals under directional pressure can be characterized by the flow and puncture of plastic minerals and the fragmentation of hard and brittle minerals. In the process of leaching, the pollutant elements precipitate from the deposits of different granular ores, and most are absorbed by the soil column; thus, the mass fraction of polluting elements in the soil column obviously increases. The variability is the largest when the leachate passes through the fine ore. The rate of change of the element mass fraction from high to low is Ni, Zn, Cu, Cd, Pb, As and Cr. A small part migrated from the soil column to the collection fluid, and the leaching effect is related to the rate of change of soil mass fraction, the ion radius of elements and the compressibility.

Fusion of 3-D medical image gradient domain based on detail-driven and directional structure tensor.

BACKGROUND: Multi-modal medical image fusion plays a crucial role in many areas of modern medicine like diagnosis and therapy planning. OBJECTIVE: Due to the factor that the structure tensor has the property of preserving the image geometry, we utilized it to construct the directional structure tensor and further proposed an improved 3-D medical image fusion method. METHOD: The local entropy metrics were used to construct the gradient weights of different source images, and the eigenvectors of traditional structure tensor were combined with the second-order derivatives of image to construct the directional structure tensor. In addition, the guided filtering was employed to obtain detail components of the source images and construct a fused gradient field with the enhanced detail. Finally, the fusion image was generated by solving the functional minimization problem. RESULTS AND CONCLUSION: Experimental results demonstrated that this new method is superior to the traditional structure tensor and multi-scale analysis in both visual effect and quantitative assessment.

Three-dimensional structure tensor based PET/CT fusion in gradient domain.

Gradient based image fusion can more effectively incorporate edge details using structure tensor, which is successfully used in 2D image fusion. In this study, we generalized and applied this gradient based image fusion method into 3D for non-small cell lung cancer PET/CT image fusion. According the characteristic of lung PET/CT images, we proposed a novel 3D structure tensor based feature, which can be used to construct a weighted structure tensor containing important local detail of both PET and CT images. The fusion gradient domain is deduced from a rank one tensor, which is the closest approximation of the weighted structure tensor in geometry. Based on the fusion gradient domain, final PET/CT fusion image is obtained by solving a Poisson equation. Comparing with the wavelet transform based fusion result, the average information entropy and average gradient measure of proposed fusion method increase 13.5% and 42.3%, respectively. The experimental results show that the proposed fusion method enables to effectively preserve lung vessel structure and sphere-like lesion detail while produces clear, stable and well consistent fusion images.

[A tooth cone beam computer tomography image segmentation method based on the local Gaussian distribution fitting].

Oral teeth image segmentation plays an important role in teeth orthodontic surgery and implant surgery. As the tooth roots are often surrounded by the alveolar, the molar's structure is complex and the inner pulp chamber usually exists in tooth, it is easy to over-segment or lead to inner edges in teeth segmentation process. In order to further improve the segmentation accuracy, a segmentation algorithm based on local Gaussian distribution fitting and edge detection is proposed to solve the above problems. This algorithm combines the local pixels' variance and mean values, which improves the algorithm's robustness by incorporating the gradient information. In the experiment, the root is segmented precisely in cone beam computed tomography (CBCT) teeth images. Segmentation results by the proposed algorithm are then compared with the classical algorithms' results. The comparison results show that the proposed method can distinguish the root and alveolar around the root. In addition, the split molars can be segmented accurately and there are no inner contours around the pulp chamber.

[Progress in the study of the imaging genomics of Alzheimer's disease].

With the exacerbation of aging population in China, the number of patients with Alzheimer's disease (AD) is increasing rapidly. AD is a chronic but irreversible neurodegenerative disease, which cannot be cured radically at present. In recent years, in order to intervene in the course of AD in advance, many researchers have explored how to detect AD as early as possible, which may be helpful for effective treatment of AD. Imaging genomics is a kind of diagnosis method developed in recent years, which combines the medical imaging and high-throughput genetic omics together. It studies changes in cognitive function in patients with AD by extracting effective information from high-throughput medical imaging data and genomic data, providing effective guidance for early detection and treatment of AD patients. In this paper, the association analysis of magnetic resonance image (MRI) with genetic variation are summarized, as well as the research progress on AD with this method. According to complexity, the objects in the association analysis are classified as candidate brain phenotype, candidate genetic variation, genome-wide genetic variation and whole brain voxel. Then we briefly describe the specific methods corresponding to phenotypic of the brain and genetic variation respectively. Finally, some unsolved problems such as phenotype selection and limited polymorphism of candidate genes are put forward.

Multiparametric MR imaging detects therapy efficacy of radioactive seeds brachytherapy in pancreatic ductal adenocarcinoma xenografts.

OBJECTIVE: To investigate the therapeutic efficacy of Iodine-125 (125I) seeds brachytherapy to pancreatic ductal adenocarcinoma (PDAC) xenografts via multiparametric magnetic resonance imaging (MRI) analysis. MATERIALS AND METHODS: Twenty mice were implanted subcutaneously with SW-1990 PDAC xenografts. The tumor-bearing mice were randomly divided into 125I seeds group (n = 10) and blank control group (n = 10). Treatment response was monitored by diffusion-weighted magnetic resonance imaging (DW-MRI) and dynamic contrast-enhanced MRI (DCE-MRI) obtained 1 day before, 14 and 60 days after treatment. Imaging results were correlated with histopathology. RESULTS: 125I seeds brachytherapy resulted in a significant increase in mean tumor apparent diffusion coefficient (ADC) values compared to the control at 14 and 60 days after treatment (p < 0.05). DCE-MRI showed a significant decrease in the perfusion parameters including Ktrans and Kep (p < 0.05). The mean ADCs within the peripheral region of the tumors were linearly proportional to the mean apoptotic cell density (p = 0.015; Spearman's coefficient = 0.945). The Ktrans and Kep were linearly proportional to microvessel density (MVD) (p = 0.043, 0.047; Spearman's coefficient = 0.891, 0.884). CONCLUSION: 125I seeds brachytherapy leads to effective inhibition of PDAC cell proliferation, higher degree of necrosis and necroptosis, and lower MVD. Both DW-MRI and DCE-MRI are feasible to monitor a response to 125I seeds brachytherapy in the PDAC xenografts. This paper shows an original project concerning about a possible palliative treatment not only in a murine model (preclinical setting) but also in humans.

A new adaptive-weighted total variation sparse-view computed tomography image reconstruction with local improved gradient information.

Inspired by the compressed sensing (CS) theory, introducing priori information of sparse image into sparse-view reconstruction algorithm of computed tomography (CT) can improve image quality. In recent years, as a special case of CS, total variation (TV) reconstruction algorithm that uses both image sparsity and prior information of edge direction have attracted much research interest in sparse-view image reconstruction due to its ability to preserve image edges. In this paper, we propose a new adaptive-weighted total variation (NAWTV) algorithm for CT image reconstruction, which is derived by considering local gradient direction continuity and the anisotropic edge property. The anisotropic edge property is used to consolidate the image sparsity, where the associated weights are expressed as a combination of exponential and cosine function. The weights can also be adjusted adaptively according the local image intensity gradient. The NAWTV algorithm is numerically implemented with gradient descent method. The typical Shepp-Logan phantom and FORBILD head phantom are employed to perform image reconstruction simulation. To evaluate performance of NAWTV algorithm, we compared it with TV and AwTV reconstruction algorithms in experiments. Numerical experimental results verified the effectiveness and feasibility of the proposed algorithm. Comparison results also showed that the NAWTV algorithm achieved a satisfactory performance in suppressing artifacts and preserving the edge structure details information of the reconstructed image.

[Research progress of details enhancement methods in medical images].

Effective medical image enhancement method can not only highlight the interested target and region, but also suppress the background and noise, thus improving the quality of the image and reducing the noise while keeping the original geometric structure, which contributes to easier diagnosis in disease based on the image enhanced. This article carries out research on strengthening methods of subtle structure in medical image nowadays, including images sharpening enhancement, rough sets and fuzzy sets, multi-scale geometrical analysis and differential operator. Finally, some commonly used quantitative evaluation criteria of image detail enhancement are given, and further research directions of fine structure enhancement of medical images are discussed.

[Research progress of disrupted brain connectivity in mild cognitive impairment:findings from graph theoretical studies of whole brain networks].

Mild cognitive impairment(MCI) is a clinical transition state between age-related cognitive decline and dementia. Researchers can use neuroimaging and neurophysiological techniques to obtain structural and functional information about the human brain. Using this information researchers can construct the brain network based on complex network theory. The literature on graph theory shows that the large-scale brain network of MCI patient exhibits small-world property, which ranges intermediately between Alzheimer's disease and that in the normal control group. But brain connectivity of MCI patients presents topologically structural disorder. The disorder is significantly correlated to the cognitive functions. This article reviews the recent findings on brain connectivity of MCI patients from the perspective of multimodal data. Specifically, the article focuses on the graph theory evidences of the whole brain structural and functional and the joint covariance network disorders. At last, the article shows the limitations and future research directions in this field.

[Research on brain white matter network in cerebral palsy infant].

Present study used diffusion tensor image and tractography to construct brain white matter networks of 15 cerebral palsy infants and 30 healthy infants that matched for age and gender. After white matter network analysis, we found that both cerebral palsy and healthy infants had a small-world topology in white matter network, but cerebral palsy infants exhibited abnormal topological organization: increased shortest path length but decreased normalize clustering coefficient, global efficiency and local efficiency. Furthermore, we also found that white matter network hub regions were located in the left cuneus, precuneus, and left posterior cingulate gyrus. However, some abnormal nodes existed in the frontal, temporal, occipital and parietal lobes of cerebral palsy infants. These results indicated that the white matter networks for cerebral palsy infants were disrupted, which was consistent with previous studies about the abnormal brain white matter areas. This work could help us further study the pathogenesis of cerebral palsy infants.

Retrospective reversal of extinction of conditioned fear by instruction.

In the present study, we examined the impact of verbal instruction during extinction of human fear-conditioning. We extended the study of Raes, De Houwer, Verschuere, and De Raedt (2011) by controlling for context conditioning and recording unconditioned stimulus expectancy online in a within-subject design. We informed participants of an alternative reason for the absence of the aversive unconditioned stimulus after extinction had been carried out, to see if such instruction could induce retrospective protection from extinction. The results demonstrated that both the expectancy of an aversive outcome and conditioned skin conductance were significantly increased for the conditioned stimulus targeted by the instruction. Thus extinction was reversed by the concurrent presence of an alternative cause for the absence of the unconditioned stimulus.