An effective and robust lattice Boltzmann model guided by atlas for hippocampal subregions segmentation.

BACKGROUND: Given the varying vulnerability of the rostral and caudal regions of the hippocampus to neuropathology in the Alzheimer's disease (AD) continuum, accurately assessing structural changes in these subregions is crucial for early AD detection. The development of reliable and robust automatic segmentation methods for hippocampal subregions (HS) is of utmost importance. OBJECTIVE: Our aim is to propose and validate a HS segmentation model that is both training-free and highly generalizable. This method should exhibit comparable accuracy and efficiency to state-of-the-art techniques. The segmented HS can serve as a biomarker for studying the progression of AD. METHODS: We utilized the functional magnetic resonance imaging of the Brain's Integrated Registration and Segmentation Tool (FIRST) to segment the entire hippocampus. By intersecting the segmentation results with the Brainnetome (BN) atlas, we obtained coarse segmentation of the four HS regions. This coarse segmentation was then employed as a shape prior term in the lattice Boltzmann (LB) model, as well as for initializing contours. Additionally, image gradients and local gray levels were integrated into the external force terms of the LB model to refine the coarse segmentation results. We assessed the segmentation accuracy of the model using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and evaluated the potential of the segmentation results as AD biomarkers on both the ADNI and Xuanwu datasets. RESULTS: The median Dice similarity coefficients (DSC) for the left caudal, right caudal, left rostral, and right rostral hippocampus were 0.87, 0.88, 0.88, and 0.89, respectively. The proportion of segmentation results with a DSC exceeding 0.8 was 77%, 78%, 77%, and 94% for the respective regions. In terms of volume, the correlation coefficients between the segmentation results of the four HS regions and the gold standard were 0.95, 0.93, 0.96, and 0.96, respectively. Regarding asymmetry, the correlation coefficient between the segmentation result's right caudal minus left caudal and the corresponding gold standard was 0.91, while for right rostral minus left rostral, it was 0.93. Over time, we observed a decline in the volumes of the four HS regions and the total hippocampal volume of mild cognitive impairment (MCI) converters. Analysis of inter-group differences revealed that, except for the right rostral region in the ADNI dataset, the p-values for the four HS regions in the normal controls (NC), MCI, and AD groups from both datasets were all below 0.05. The right caudal hippocampal volume demonstrated correlation coefficients of 0.47 and 0.43 with the mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA), respectively. Similarly, the left rostral hippocampal volume showed correlation coefficients of 0.50 and 0.58 with MMSE and MoCA, respectively. CONCLUSIONS: Our framework allows for direct application to different brain magnetic resonance (MR) datasets without the need for training. It eliminates the requirement for complex image preprocessing steps while achieving segmentation accuracy comparable to deep learning (DL) methods even with small sample sizes. Compared to traditional active contour models (ACM) and atlas-based methods, our approach exhibits significant speed advantages. The segmented HS regions hold promise as potential biomarkers for studying the progression of AD.

Multimodal cross enhanced fusion network for diagnosis of Alzheimer's disease and subjective memory complaints.

Deep learning methods using multimodal imagings have been proposed for the diagnosis of Alzheimer's disease (AD) and its early stages (SMC, subjective memory complaints), which may help to slow the progression of the disease through early intervention. However, current fusion methods for multimodal imagings are generally coarse and may lead to suboptimal results through the use of shared extractors or simple downscaling stitching. Another issue with diagnosing brain diseases is that they often affect multiple areas of the brain, making it important to consider potential connections throughout the brain. However, traditional convolutional neural networks (CNNs) may struggle with this issue due to their limited local receptive fields. To address this, many researchers have turned to transformer networks, which can provide global information about the brain but can be computationally intensive and perform poorly on small datasets. In this work, we propose a novel lightweight network called MENet that adaptively recalibrates the multiscale long-range receptive field to localize discriminative brain regions in a computationally efficient manner. Based on this, the network extracts the intensity and location responses between structural magnetic resonance imagings (sMRI) and 18-Fluoro-Deoxy-Glucose Positron Emission computed Tomography (FDG-PET) as an enhancement fusion for AD and SMC diagnosis. Our method is evaluated on the publicly available ADNI datasets and achieves 97.67% accuracy in AD diagnosis tasks and 81.63% accuracy in SMC diagnosis tasks using sMRI and FDG-PET. These results achieve state-of-the-art (SOTA) performance in both tasks. To the best of our knowledge, this is one of the first deep learning research methods for SMC diagnosis with FDG-PET.

MFCNet: A multi-modal fusion and calibration networks for 3D pancreas tumor segmentation on PET-CT images.

In clinical diagnosis, positron emission tomography and computed tomography (PET-CT) images containing complementary information are fused. Tumor segmentation based on multi-modal PET-CT images is an important part of clinical diagnosis and treatment. However, the existing current PET-CT tumor segmentation methods mainly focus on positron emission tomography (PET) and computed tomography (CT) feature fusion, which weakens the specificity of the modality. In addition, the information interaction between different modal images is usually completed by simple addition or concatenation operations, but this has the disadvantage of introducing irrelevant information during the multi-modal semantic feature fusion, so effective features cannot be highlighted. To overcome this problem, this paper propose a novel Multi-modal Fusion and Calibration Networks (MFCNet) for tumor segmentation based on three-dimensional PET-CT images. First, a Multi-modal Fusion Down-sampling Block (MFDB) with a residual structure is developed. The proposed MFDB can fuse complementary features of multi-modal images while retaining the unique features of different modal images. Second, a Multi-modal Mutual Calibration Block (MMCB) based on the inception structure is designed. The MMCB can guide the network to focus on a tumor region by combining different branch decoding features using the attention mechanism and extracting multi-scale pathological features using a convolution kernel of different sizes. The proposed MFCNet is verified on both the public dataset (Head and Neck cancer) and the in-house dataset (pancreas cancer). The experimental results indicate that on the public and in-house datasets, the average Dice values of the proposed multi-modal segmentation network are 74.14% and 76.20%, while the average Hausdorff distances are 6.41 and 6.84, respectively. In addition, the experimental results show that the proposed MFCNet outperforms the state-of-the-art methods on the two datasets.

Ultrafast Ultrasound Localization Microscopy by Conditional Generative Adversarial Network.

Ultrasound localization microscopy (ULM) overcomes the acoustic diffraction limit and enables the visualization of microvasculature at subwavelength resolution. However, challenges remain in ultrafast ULM implementation, where short data acquisition time, efficient data processing speed, and high imaging resolution need to be considered simultaneously. Recently, deep learning (DL)-based methods have exhibited potential in speeding up ULM imaging. Nevertheless, a certain number of ultrasound (US) data ( L frames) are still required to accumulate enough localized microbubble (MB) events, leading to an acquisition time within a time span of tens of seconds. To further speed up ULM imaging, in this article, we present a new DL-based method, termed as ULM-GAN. By using a modified conditional generative adversarial network (cGAN) framework, ULM-GAN is able to reconstruct a superresolution image directly from a temporal mean low-resolution (LR) image generated by averaging l -frame raw US images with l being significantly smaller than L . To evaluate the performance of ULM-GAN, a series of numerical simulations and phantom experiments are both implemented. The results of the numerical simulations demonstrate that when performing ULM imaging, ULM-GAN allows  âˆ¼ 40 -fold reduction in data acquisition time and  âˆ¼ 61 -fold reduction in computational time compared with the conventional Gaussian fitting method, without compromising spatial resolution according to the resolution scaled error (RSE). For the phantom experiments, ULM-GAN offers an implementation of ULM with ultrafast data acquisition time (  âˆ¼ 0.33 s) and ultrafast data processing speed (  âˆ¼ 0.60 s) that makes it promising to observe rapid biological activities in vivo.

Classifying Chinese Medicine Constitution Using Multimodal Deep-Learning Model.

OBJECTIVE: To develop a multimodal deep-learning model for classifying Chinese medicine constitution, i.e., the balanced and unbalanced constitutions, based on inspection of tongue and face images, pulse waves from palpation, and health information from a total of 540 subjects. METHODS: This study data consisted of tongue and face images, pulse waves obtained by palpation, and health information, including personal information, life habits, medical history, and current symptoms, from 540 subjects (202 males and 338 females). Convolutional neural networks, recurrent neural networks, and fully connected neural networks were used to extract deep features from the data. Feature fusion and decision fusion models were constructed for the multimodal data. RESULTS: The optimal models for tongue and face images, pulse waves and health information were ResNet18, Gate Recurrent Unit, and entity embedding, respectively. Feature fusion was superior to decision fusion. The multimodal analysis revealed that multimodal data compensated for the loss of information from a single mode, resulting in improved classification performance. CONCLUSIONS: Multimodal data fusion can supplement single model information and improve classification performance. Our research underscores the effectiveness of multimodal deep learning technology to identify body constitution for modernizing and improving the intelligent application of Chinese medicine.

Development of a Machine Learning Model to Discriminate Mild Cognitive Impairment Subjects from Normal Controls in Community Screening.

Background: Mild cognitive impairment (MCI) is a transitional stage between normal aging and probable Alzheimer's disease. It is of great value to screen for MCI in the community. A novel machine learning (ML) model is composed of electroencephalography (EEG), eye tracking (ET), and neuropsychological assessments. This study has been proposed to identify MCI subjects from normal controls (NC). Methods: Two cohorts were used in this study. Cohort 1 as the training and validation group, includes184 MCI patients and 152 NC subjects. Cohort 2 as an independent test group, includes 44 MCI and 48 NC individuals. EEG, ET, Neuropsychological Tests Battery (NTB), and clinical variables with age, gender, educational level, MoCA-B, and ACE-R were selected for all subjects. Receiver operating characteristic (ROC) curves were adopted to evaluate the capabilities of this tool to classify MCI from NC. The clinical model, the EEG and ET model, and the neuropsychological model were compared. Results: We found that the classification accuracy of the proposed model achieved 84.5 ± 4.43% and 88.8 ± 3.59% in Cohort 1 and Cohort 2, respectively. The area under curve (AUC) of the proposed tool achieved 0.941 (0.893-0.982) in Cohort 1 and 0.966 (0.921-0.988) in Cohort 2, respectively. Conclusions: The proposed model incorporation of EEG, ET, and neuropsychological assessments yielded excellent classification performances, suggesting its potential for future application in cognitive decline prediction.

Reducing instability of inter-subject covariance of FDG uptake networks using structure-weighted sparse estimation approach.

PURPOSE: Sparse inverse covariance estimation (SICE) is increasingly utilized to estimate inter-subject covariance of FDG uptake (FDGcov) as proxy of metabolic brain connectivity. However, this statistical method suffers from the lack of robustness in the connectivity estimation. Patterns of FDGcov were observed to be spatially similar with patterns of structural connectivity as obtained from DTI imaging. Based on this similarity, we propose to regularize the sparse estimation of FDGcov using the structural connectivity. METHODS: We retrospectively analyzed the FDG-PET and DTI data of 26 healthy controls, 41 patients with Alzheimer's disease (AD), and 30 patients with frontotemporal lobar degeneration (FTLD). Structural connectivity matrix derived from DTI data was introduced as a regularization parameter to assign individual penalties to each potential metabolic connectivity. Leave-one-out cross validation experiments were performed to assess the differential diagnosis ability of structure weighted SICE approach. A few approaches of structure weighted were compared with the standard SICE. RESULTS: Compared to the standard SICE, structural weighting has shown more stable performance in the supervised classification, especially in the differentiation AD vs. FTLD (accuracy of 89-90%, while unweighted SICE only 85%). There was a significant positive relationship between the minimum number of metabolic connection and the robustness of the classification accuracy (r = 0.57, P < 0.001). Shuffling experiments showed significant differences between classification score derived with true structural weighting and those obtained by randomized structure (P < 0.05). CONCLUSION: The structure-weighted sparse estimation can enhance the robustness of metabolic connectivity, which may consequently improve the differentiation of pathological phenotypes.

Prognostic Evaluation Based on Dual-Time 18F-FDG PET/CT Radiomics Features in Patients with Locally Advanced Pancreatic Cancer Treated by Stereotactic Body Radiation Therapy.

Background: 18F-FDG PET/CT is widely used in the prognosis evaluation of tumor patients. The radiomics features can provide additional information for clinical prognostic assessment. Purpose: Purpose is to explore the prognostic value of radiomics features from dual-time 18F-FDG PET/CT images for locally advanced pancreatic cancer (LAPC) patients treated with stereotactic body radiation therapy (SBRT). Materials and Methods: This retrospective study included 70 LAPC patients who received early and delayed 18F-FDG PET/CT scans before SBRT treatment. A total of 1188 quantitative imaging features were extracted from dual-time PET/CT images. To avoid overfitting, the univariate analysis and elastic net were used to obtain a sparse set of image features that were applied to develop a radiomics score (Rad-score). Then, the Harrell consistency index (C-index) was used to evaluate the prognosis model. Results: The Rad-score from dual-time images contains six features, including intensity histogram, morphological, and texture features. In the validation cohort, the univariate analysis showed that the Rad-score was the independent prognostic factor (p < 0.001, hazard ratio [HR]: 3.2). And in the multivariate analysis, the Rad-score was the only prognostic factor (p < 0.01, HR: 4.1) that was significantly associated with the overall survival (OS) of patients. In addition, according to cross-validation, the C-index of the prognosis model based on the Rad-score from dual-time images is better than the early and delayed images (0.720 vs. 0.683 vs. 0.583). Conclusion: The Rad-score based on dual-time 18F-FDG PET/CT images is a promising noninvasive method with better prognostic value.

Non-Invasive Glucose Metabolism Quantification Method Based on Unilateral ICA Image Derived Input Function by Hybrid PET/MR in Ischemic Cerebrovascular Disease.

The non-invasive quantification of the cerebral metabolic rate for glucose (CMRGlc) and the characterization of cerebral metabolism in the cerebrovascular territories are helpful in understanding ischemic cerebrovascular disease (ICVD). Firstly, we investigated a non-invasive quantification approach based on an image-derived input function (IDIF) in ICVD. Second, we studied the metabolic changes in CMRGlc after surgical intervention. We evaluated the hypothesis that the IDIF method based on the unilateral internal carotid artery could address challenges in ICVD quantification. The CMRGlc and standardized uptake value ratio (SUVR) were used to measure glucose metabolism activity. Healthy controls showed no significant differences in CMRGlc values between bilateral and unilateral IDIF measurements (intraclass correlation coefficient [ICC]: 0.91-0.98). Patients with ICVD showed significantly increased CMRGlc values after surgical intervention for all territories (percentage changes: 7.4%-22.5%). In contrast, SUVR showed minor differences between postoperative and preoperative patients, indicating that it was a poor biomarker for the diagnosis of ICVD. A significant association between CMRGlc and the National Institutes of Health Stroke Scale (NIHSS) scores was observed (r=-0.54). Our findings suggested that IDIF could be a valuable tool for CMRGlc quantification in patients with ICVD and may advance personalized precision interventions.

Multi-Task Joint Learning Model for Chinese Word Segmentation and Syndrome Differentiation in Traditional Chinese Medicine.

Evidence-based treatment is the basis of traditional Chinese medicine (TCM), and the accurate differentiation of syndromes is important for treatment in this context. The automatic differentiation of syndromes of unstructured medical records requires two important steps: Chinese word segmentation and text classification. Due to the ambiguity of the Chinese language and the peculiarities of syndrome differentiation, these tasks pose a daunting challenge. We use text classification to model syndrome differentiation for TCM, and use multi-task learning (MTL) and deep learning to accomplish the two challenging tasks of Chinese word segmentation and syndrome differentiation. Two classic deep neural networks­bidirectional long short-term memory (Bi-LSTM) and text-based convolutional neural networks (TextCNN)­are fused into MTL to simultaneously carry out these two tasks. We used our proposed method to conduct a large number of comparative experiments. The experimental comparisons showed that it was superior to other methods on both tasks. Our model yielded values of accuracy, specificity, and sensitivity of 0.93, 0.94, and 0.90, and 0.80, 0.82, and 0.78 on the Chinese word segmentation task and the syndrome differentiation task, respectively. Moreover, statistical analyses showed that the accuracies of the non-joint and joint models were both within the 95% confidence interval, with pvalue < 0.05. The experimental comparison showed that our method is superior to prevalent methods on both tasks. The work here can help modernize TCM through intelligent differentiation.

TongueCaps: An Improved Capsule Network Model for Multi-Classification of Tongue Color.

Tongue color is an important part of tongue diagnosis. The change of tongue color is affected by pathological state of body, blood rheology, and other factors. Therefore, physicians can understand a patient's condition by observing tongue color. Currently, most studies use machine learning, which is time consuming and labor intensive. Other studies use deep learning based on convolutional neural network (CNN), but the affine transformation of CNN is less robust and easily loses the spatial relationship between features. Recently, Capsule Networks (CapsNet) have been proposed to overcome these problems. In our work, CapsNet is used for tongue color research for the first time, and improved model TongueCaps is proposed, which combines the advantage of CapsNet and residual block structure to achieve end to end tongue color classification. We conduct experiments on 1371 tongue images; TongueCaps achieve accuracy is 0.8456, sensitivity is 0.8474, and specificity is 0.9586. In addition, the size of TongueCaps is 8.11 M, and FLOPs is 1,335,342, which are smaller than CNN in comparison models. Experiments have confirmed that the CapsNet can be used for tongue color research, and improved model TongueCaps, in this paper, is superior to other comparison models in terms of accuracy, specificity and sensitivity, computational complexity, and size of model.

BMNet: A New Region-Based Metric Learning Method for Early Alzheimer's Disease Identification With FDG-PET Images.

18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, existing FDG-PET-based researches are still insufficient for the identification of early MCI (EMCI) and late MCI (LMCI). Compared with methods based other modalities, current methods with FDG-PET are also inadequate in using the inter-region-based features for the diagnosis of early AD. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing the embedding space. To validate the proposed method, we collect 898 FDG-PET images from Alzheimer's disease neuroimaging initiative (ADNI) including 263 normal control (NC) patients, 290 EMCI patients, 147 LMCI patients, and 198 AD patients. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive fivefold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module. In addition, the accuracy of classification between EMCI and LMCI achieves 79.64% using imbalanced FDG-PET images, which illustrates that the proposed method yields a state-of-the-art result of the classification accuracy between EMCI and LMCI based on PET images.

Classification of fissured tongue images using deep neural networks.

BACKGROUND: Tongue inspection is vital in traditional Chinese medicine. Fissured tongue is an important feature in tongue diagnosis, and primarily corresponds to three Chinese medicine syndromes: syndrome-related hotness, blood deficiency, and insufficiency of the spleen. Diagnosis of the syndrome is significantly affected by the experience of clinicians, and it is difficult for young doctors to perform accurate diagnoses. OBJECTIVE: The syndrome not only depends on the local features based on fissured regions but also on the global features of the whole tongue; therefore, a syndrome diagnosis framework combining the global and local features of a fissured tongue image was developed in the present study to achieve a quantitative and objective diagnosis. METHODS: First, we detected the fissured region of a tongue image using a single-shot multibox detector. Second, we extracted the global and local features from a whole tongue image and a fissured region using TongueNet (developed in-house). Third, we developed a classifier to determine the final syndrome. RESULTS: Based on an experiment involving 721 fissured tongue images, we discovered that TongueNet affords better feature extraction. The accuracy of TongueNet was 4% (p< 0.05) and 3% (p< 0.05) higher than that of InceptionV3 and ResNet18, respectively, for whole tongue images. Meanwhile, at local fissured regions, the accuracy of TongueNet was 3% (p< 0.05) higher than that of InceptionV3 and equal to that of ResNet18. Finally, the fusion features outperformed the global and local features with a 78% accuracy. CONCLUSIONS: Our findings indicate that TongueNet designed with batch normalization and dropout is more suitable for uncomplicated images than InceptionV3 and ResNet18. In addition, compared with the global features, the fusion features supplement the detailed information of the fissures and improve classification accuracy.

FMRNet: A fused network of multiple tumoral regions for breast tumor classification with ultrasound images.

PURPOSE: Recent studies have illustrated that the peritumoral regions of medical images have value for clinical diagnosis. However, the existing approaches using peritumoral regions mainly focus on the diagnostic capability of the single region and ignore the advantages of effectively fusing the intratumoral and peritumoral regions. In addition, these methods need accurate segmentation masks in the testing stage, which are tedious and inconvenient in clinical applications. To address these issues, we construct a deep convolutional neural network that can adaptively fuse the information of multiple tumoral-regions (FMRNet) for breast tumor classification using ultrasound (US) images without segmentation masks in the testing stage. METHODS: To sufficiently excavate the potential relationship, we design a fused network and two independent modules to extract and fuse features of multiple regions simultaneously. First, we introduce two enhanced combined-tumoral (EC) region modules, aiming to enhance the combined-tumoral features gradually. Then, we further design a three-branch module for extracting and fusing the features of intratumoral, peritumoral, and combined-tumoral regions, denoted as the intratumoral, peritumoral, and combined-tumoral module. Especially, we design a novel fusion module by introducing a channel attention module to adaptively fuse the features of three regions. The model is evaluated on two public datasets including UDIAT and BUSI with breast tumor ultrasound images. Two independent groups of experiments are performed on two respective datasets using the fivefold stratified cross-validation strategy. Finally, we conduct ablation experiments on two datasets, in which BUSI is used as the training set and UDIAT is used as the testing set. RESULTS: We conduct detailed ablation experiments about the proposed two modules and comparative experiments with other existing representative methods. The experimental results show that the proposed method yields state-of-the-art performance on both two datasets. Especially, in the UDIAT dataset, the proposed FMRNet achieves a high accuracy of 0.945 and a specificity of 0.945, respectively. Moreover, the precision (PRE = 0.909) even dramatically improves by 21.6% on the BUSI dataset compared with the existing method of the best result. CONCLUSION: The proposed FMRNet shows good performance in breast tumor classification with US images, and proves its capability of exploiting and fusing the information of multiple tumoral-regions. Furthermore, the FMRNet has potential value in classifying other types of cancers using multiple tumoral-regions of other kinds of medical images.

Classification of microcalcification clusters in digital breast tomosynthesis using ensemble convolutional neural network.

BACKGROUND: The classification of benign and malignant microcalcification clusters (MCs) is an important task for computer-aided diagnosis (CAD) of digital breast tomosynthesis (DBT) images. Influenced by imaging method, DBT has the characteristic of anisotropic resolution, in which the resolution of intra-slice and inter-slice is quite different. In addition, the sharpness of MCs in different slices of DBT is quite different, among which the clearest slice is called focus slice. These characteristics limit the performance of CAD algorithms based on standard 3D convolution neural network (CNN). METHODS: To make full use of the characteristics of the DBT, we proposed a new ensemble CNN, which consists of the 2D ResNet34 and the anisotropic 3D ResNet to extract the 2D focus slice features and 3D contextual features of MCs, respectively. Moreover, the anisotropic 3D convolution is used to build 3D ResNet to avoid the influence of DBT anisotropy. RESULTS: The proposed method was evaluated on 495 MCs in DBT images of 275 patients, which are collected from our collaborative hospital. The area under the curve (AUC) of receiver operating characteristic (ROC) and accuracy of classifying benign and malignant MCs using decision-level ensemble strategy were 0.8837 and 82.00%, which were significantly higher than the experimental results of 2D ResNet34 (AUC: 0.8264, ACC: 76.00%) and anisotropic 3D ResNet (AUC: 0.8455, ACC: 76.00%). Compared with the results of 3D features classification in the radiomics, the AUC of the deep learning method with decision-level ensemble strategy was improved by 0.0435, and the F1 score was improved from 79.37 to 85.71%. More importantly, the sensitivity increased from 78.13 to 84.38%, and the specificity increased from 66.67 to 77.78%, which effectively reduced the false positives of diagnosis CONCLUSION: The results fully prove that the ensemble CNN can effectively integrate 2D features and 3D features, improve the classification performance of benign and malignant MCs in DBT, and reduce the false positives.

Parametric estimation of reference signal intensity in the quantification of amyloid-beta deposition: an 18F-AV-45 study.

BACKGROUND: Positron emission tomography (PET) with the radiotracer florbetapir (18F-AV-45) allows the pathophysiology of Alzheimer's disease (AD) to be tracked in vivo. The semi-quantification of amyloid-beta (Aß) has been extensively evaluated with the standardized uptake value ratio (SUVR) but is susceptible to disturbance from the candidate reference region and the partial volume effect (PVE). In the present study, we applied the parametric estimation of reference signal intensity (PERSI) method to 18F-AV-45 PET images for intensity normalization. METHODS: We enrolled 479 people with 18F-AV-45 images from the Alzheimer's Disease Neuroimaging Initiative database: 261 healthy controls (HCs), 102 patients with mild cognitive impairment (MCI), and 116 AD patients. We used white matter post-processed by PERSI (PERSI-WM) as the reference region and compared our proposed method with the traditional method for semi-quantification. SUVRs were calculated for eight regions of interest: the frontal lobe, the parietal lobe, the temporal lobe, the occipital lobe, the anterior cingulate cortex, the posterior cingulate cortex, the precuneus, and the global cortex. The SUVRs derived from PERSI-WM and other reference regions were evaluated by effect size and receiver-operator characteristic curve analyses. RESULTS: The SUVRs derived from PERSI-WM showed significantly higher trace retention in the frontal, parietal, temporal, and occipital lobes, as well as in the anterior cingulate, posterior cingulate, precuneus, and global cortex in the AD Aß-positive (+) group (mean: +43.3%±5.4%, P<0.01) and MCI Aß+ group (mean: +29.6%±5.3%, P<0.01). For the global cortex, PERSI-WM had the greatest Cohen's d effect size compared with the HC Aß-negative (-) group (AD Aß+ and MCI Aß+: 3.02, AD Aß+: 3.56, MCI Aß+: 2.34), and the highest area under the curve (AUC) between the HC Aß- and AD Aß+ groups (AUC: 0.983, 95% confidence interval: 0.978-0.998). CONCLUSIONS: PERSI-WM could mitigate the influence of PVE and improve the semi-quantification of 18F-AV-45 images; therefore, it could be used for large-scale clinical application in the nuclear medicine domain.

A Novel Metabolic Connectome Method to Predict Progression to Mild Cognitive Impairment.

OBJECTIVE: Glucose-based positron emission tomography (PET) imaging has been widely used to predict the progression of mild cognitive impairment (MCI) into Alzheimer's disease (AD) clinically. However, existing discriminant methods are unsubtle to reveal pathophysiological changes. Therefore, we present a novel metabolic connectome-based predictive modeling to predict progression from MCI to AD accurately. METHODS: In this study, we acquired fluorodeoxyglucose PET images and clinical assessments from 420 MCI patients with 36 months follow-up. Individual metabolic network based on connectome analysis was constructed, and the metabolic connectivity in this network was extracted as predictive features. Three different classification strategies were implemented to interrogate the predictive performance. To verify the effectivity of selected features, specific brain regions associated with MCI conversion were identified based on these features and compared with prior knowledge. RESULTS: As a result, 4005 connectome features were obtained, and 153 in which were selected as efficient features. Our proposed feature extraction method had achieved 85.2% accuracy for MCI conversion prediction (sensitivity: 88.1%; specificity: 81.2%; and AUC: 0.933). The discriminative brain regions associated with MCI conversion were mainly located in the precentral gyrus, precuneus, lingual, and inferior frontal gyrus. CONCLUSION: Overall, the results suggest that our proposed individual metabolic connectome method has great potential to predict whether MCI patients will progress to AD. The metabolic connectome may help to identify brain metabolic dysfunction and build a clinically applicable biomarker to predict the MCI progression.

A Combined Deep-Learning and Lattice Boltzmann Model for Segmentation of the Hippocampus in MRI.

Segmentation of the hippocampus (HC) in magnetic resonance imaging (MRI) is an essential step for diagnosis and monitoring of several clinical situations such as Alzheimer's disease (AD), schizophrenia and epilepsy. Automatic segmentation of HC structures is challenging due to their small volume, complex shape, low contrast and discontinuous boundaries. The active contour model (ACM) with a statistical shape prior is robust. However, it is difficult to build a shape prior that is general enough to cover all possible shapes of the HC and that suffers the problems of complicated registration of the shape prior and the target object and of low efficiency. In this paper, we propose a semi-automatic model that combines a deep belief network (DBN) and the lattice Boltzmann (LB) method for the segmentation of HC. The training process of DBN consists of unsupervised bottom-up training and supervised training of a top restricted Boltzmann machine (RBM). Given an input image, the trained DBN is utilized to infer the patient-specific shape prior of the HC. The specific shape prior is not only used to determine the initial contour, but is also introduced into the LB model as part of the external force to refine the segmentation. We used a subset of OASIS-1 as the training set and the preliminary release of EADC-ADNI as the testing set. The segmentation results of our method have good correlation and consistency with the manual segmentation results.

[A Method for Fluorescent Diffuse Optical Tomography Based on Lattice Boltzmann Forward Model on GPU Parallelization].

Fluorescent Diffuse Optical Tomography (FDOT) is an emerging imaging method with great prospects in fields of biology and medicine. However, the current solutions to the forward problem in FDOT are time consuming, which greatly limit the application. We proposed a method for FDOT based on Lattice Boltzmann forward model on GPU to greatly improve the computational efficiency. The Lattice Boltzmann Method (LBM) was used to construct the optical transmission model. This method separated the LBM into collision, streaming and boundary processing processes on GPUs to perform the LBM efficiently, which were local computational and inefficient on CPU. The feasibility of the proposed method was verified by the numerical phantom and the physical phantom experiments. The experimental results showed that the proposed method achieved the best performance of a 118-fold speed up under the precondition of simulation accuracy, comparing to the diffusion equation implemented by Finite Element Method (FEM) on CPU. Thus, the LBM on the GPU may efficiently solve the forward problem in FDOT.

Individual brain metabolic connectome indicator based on Kullback-Leibler Divergence Similarity Estimation predicts progression from mild cognitive impairment to Alzheimer's dementia.

PURPOSE: Positron emission tomography (PET) with 18F-fluorodeoxyglucose (FDG) reveals altered cerebral metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's dementia (AD). Previous metabolic connectome analyses derive from groups of patients but do not support the prediction of an individual's risk of conversion from present MCI to AD. We now present an individual metabolic connectome method, namely the Kullback-Leibler Divergence Similarity Estimation (KLSE), to characterize brain-wide metabolic networks that predict an individual's risk of conversion from MCI to AD. METHODS: FDG-PET data consisting of 50 healthy controls, 332 patients with stable MCI, 178 MCI patients progressing to AD, and 50 AD patients were recruited from ADNI database. Each individual's metabolic brain network was ascertained using the KLSE method. We compared intra- and intergroup similarity and difference between the KLSE matrix and group-level matrix, and then evaluated the network stability and inter-individual variation of KLSE. The multivariate Cox proportional hazards model and Harrell's concordance index (C-index) were employed to assess the prediction performance of KLSE and other clinical characteristics. RESULTS: The KLSE method captures more pathological connectivity in the parietal and temporal lobes relative to the typical group-level method, and yields detailed individual information, while possessing greater stability of network organization (within-group similarity coefficient, 0.789 for sMCI and 0.731 for pMCI). Metabolic connectome expression was a superior predictor of conversion than were other clinical assessments (hazard ratio (HR) = 3.55; 95% CI, 2.77-4.55; P < 0.001). The predictive performance improved further upon combining clinical variables in the Cox model, i.e., C-indices 0.728 (clinical), 0.730 (group-level pattern model), 0.750 (imaging connectome), and 0.794 (the combined model). CONCLUSION: The KLSE indicator identifies abnormal brain networks predicting an individual's risk of conversion from MCI to AD, thus potentially constituting a clinically applicable imaging biomarker.