Effects of deep brain stimulation on dopamine D2 receptor binding in patients with treatment-refractory depression.

BACKGROUND: Depression is a chronic psychiatric disorder related to diminished dopaminergic neurotransmission. Deep brain stimulation (DBS) has shown effectiveness in treating patients with treatment-refractory depression (TRD). This study aimed to evaluate the effect of DBS on dopamine D2 receptor binding in patients with TRD. METHODS: Six patients with TRD were treated with bed nucleus of the stria terminalis (BNST)-nucleus accumbens (NAc) DBS were recruited. Ultra-high sensitivity [11C]raclopride dynamic total-body positron emission tomography (PET) imaging was used to assess the brain D2 receptor binding. Each patient underwent a [11C]raclopride PET scan for 60-min under DBS OFF and DBS ON, respectively. A simplified reference tissue model was used to generate parametric images of binding potential (BPND) with the cerebellum as reference tissue. RESULTS: Depression and anxiety symptoms improved after 3-6 months of DBS treatment. Compared with two-day-nonstimulated conditions, one-day BNST-NAc DBS decreased [11C]raclopride BPND in the amygdala (15.9 %, p < 0.01), caudate nucleus (15.4 %, p < 0.0001) and substantia nigra (10.8 %, p < 0.01). LIMITATIONS: This study was limited to the small sample size and lack of a healthy control group. CONCLUSIONS: Chronic BNST-NAc DBS improved depression and anxiety symptoms, and short-term stimulation decreased D2 receptor binding in the amygdala, caudate nucleus, and substantia nigra. The findings suggest that DBS relieves depression and anxiety symptoms possibly by regulating the dopaminergic system.

Patlak-Ki derived from ultra-high sensitivity dynamic total body [18F]FDG PET/CT correlates with the response to induction immuno-chemotherapy in locally advanced non-small cell lung cancer patients.

PURPOSE: This study aimed to investigate the predictive value of metabolic features in response to induction immuno-chemotherapy in patients with locally advanced non-small cell cancer (LA-NSCLC), using ultra-high sensitivity dynamic total body [18F]FDG PET/CT. METHODS: The study analyzed LA-NSCLC patients who received two cycles of induction immuno-chemotherapy and underwent a 60-min dynamic total body [18F]FDG PET/CT scan before treatment. The primary tumors (PTs) were manually delineated, and their metabolic features, including the Patlak-Ki, Patlak-Intercept, maximum SUV (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) were evaluated. The overall response rate (ORR) to induction immuno-chemotherapy was evaluated according to RECIST 1.1 criteria. The Patlak-Ki of PTs was calculated from the 20-60 min frames using the Patlak graphical analysis. The best feature was selected using Laplacian feature importance scores, and an unsupervised K-Means method was applied to cluster patients. ROC curve was used to examine the effect of selected metabolic feature in predicting tumor response to treatment. The targeted next generation sequencing on 1021 genes was conducted. The expressions of CD68, CD86, CD163, CD206, CD33, CD34, Ki67 and VEGFA were assayed through immunohistochemistry. The independent samples t test and the Mann-Whitney U test were applied in the intergroup comparison. Statistical significance was considered at P < 0.05. RESULTS: Thirty-seven LA-NSCLC patients were analyzed between September 2020 and November 2021. All patients received two cycles of induction chemotherapy combined with Nivolumab/ Camrelizumab. The Laplacian scores showed that the Patlak-Ki of PTs had the highest importance for patient clustering, and the unsupervised K-Means derived decision boundary of Patlak-Ki was 2.779 ml/min/100 g. Patients were categorized into two groups based on their Patlak-Ki values: high FDG Patlak-Ki (H-FDG-Ki, Patlak-Ki > 2.779 ml/min/100 g) group (n = 23) and low FDG Patlak-Ki (L-FDG-Ki, Patlak-Ki ≤ 2.779 ml/min/100 g) group (n = 14). The ORR to induction immuno-chemotherapy was 67.6% (25/37) in the whole cohort, with 87% (20/23) in H-FDG-Ki group and 35.7% (5/14) in L-FDG-Ki group (P = 0.001). The sensitivity and specificity of Patlak-Ki in predicting the treatment response were 80% and 75%, respectively [AUC = 0.775 (95%CI 0.605-0.945)]. The expression of CD3+/CD8+ T cells and CD86+/CD163+/CD206+ macrophages were higher in the H-FDG-Ki group, while Ki67, CD33+ myeloid cells, CD34+ micro-vessel density (MVD) and tumor mutation burden (TMB) were comparable between the two groups. CONCLUSIONS: The total body [18F]FDG PET/CT scanner performed a dynamic acquisition of the entire body and clustered LA-NSCLC patients into H-FDG-Ki and L-FDG-Ki groups based on the Patlak-Ki. Patients with H-FDG-Ki demonstrated better response to induction immuno-chemotherapy and higher levels of immune cell infiltration in the PTs compared to those with L-FDG-Ki. Further studies with a larger patient cohort are required to validate these findings.

First Total-Body Kinetic Modeling and Parametric Imaging of Dynamic 68Ga-FAPI-04 PET in Pancreatic and Gastric Cancer.

Fibroblast activation protein inhibitor (FAPI) is an ideal diagnostic and therapeutic target in malignant tumors. However, the knowledge of kinetic modeling and parametric imaging of 68Ga-FAPI is limited. Purpose: The purpose of this study was to explore the pharmacokinetics of 68Ga-FAPI-04 PET/CT in pancreatic cancer and gastric cancer and to conduct parametric imaging of dynamic total-body data compared with SUV imaging. Methods: Dynamic total-body 68Ga-FAPI-04 PET/CT was performed on 13 patients. The lesion time-activity curves were fitted by 3-compartment models and multigraphical models. The kinetics parameters derived from the 2-tissue reversible compartment model (2T4K) and multigraphical models were analyzed. Parametric [Formula: see text] imaging was generated using the 2T4K and Logan models, and their performances were evaluated compared with SUV images. Results: 2T4K had the lowest Akaike information criterion value, and its fitting curves matched excellently with the origin time-activity curves. Visual assessment revealed that the [Formula: see text](2T4K) images and [Formula: see text](Logan with spatial constraint [SC]) images both showed less image noise and higher lesion conspicuity compared with SUV images. Objective image quality assessment demonstrated that parametric [Formula: see text](2T4K) images and parametric [Formula: see text](Logan with SC) images had a 5.0-fold and 5.0-fold higher average signal-to-noise ratio and 3.6-fold and 4.1-fold higher average contrast-to-noise ratio compared with conventional SUV images, respectively. In addition, no significant differences in signal-to-noise ratio and contrast-to-noise of pathologic lesions were observed between parametric [Formula: see text](2T4K) images and parametric [Formula: see text](Logan with SC) images (all P > 0.05). Conclusions: The 2T4K model was the preferred compartment model. Total-body parametric imaging of 68Ga-FAPI-04 PET yielded superior quantification beyond SUV with enhanced lesion contrast, which may serve as a promising imaging method to make an early diagnosis, to better reflect tumor characterization, or to allow evaluation of treatment response. [Formula: see text](2T4K) images are comparable in image quality and consistent to [Formula: see text](Logan with SC) images in lesions conspicuity; however, [Formula: see text](Logan with SC) images presented an appealing alternative to [Formula: see text](2T4K) images because of their simplicity.

Assessing dynamic metabolic heterogeneity in non-small cell lung cancer patients via ultra-high sensitivity total-body [18F]FDG PET/CT imaging: quantitative analysis of [18F]FDG uptake in primary tumors and metastatic lymph nodes.

PURPOSE: This study aimed to quantitatively assess [18F]FDG uptake in primary tumor (PT) and metastatic lymph node (mLN) in newly diagnosed non-small cell lung cancer (NSCLC) using the total-body [18F]FDG PET/CT and to characterize the dynamic metabolic heterogeneity of NSCLC. METHODS: The 60-min dynamic total-body [18F]FDG PET/CT was performed before treatment. The PTs and mLNs were manually delineated. An unsupervised K-means classification method was used to cluster patients based on the imaging features of PTs. The metabolic features, including Patlak-Ki, Patlak-Intercept, SUVmean, metabolic tumor volume (MTV), total lesion glycolysis (TLG), and textural features, were extracted from PTs and mLNs. The targeted next-generation sequencing of tumor-associated genes was performed. The expression of Ki67, CD3, CD8, CD34, CD68, and CD163 in PTs was determined by immunohistochemistry. RESULTS: A total of 30 patients with stage IIIA-IV NSCLC were enrolled. Patients were divided into fast dynamic FDG metabolic group (F-DFM) and slow dynamic FDG metabolic group (S-DFM) by the unsupervised K-means classification of PTs. The F-DFM group showed significantly higher Patlak-Ki (P < 0.001) and SUVmean (P < 0.001) of PTs compared with the S-DFM group, while no significant difference was observed in Patlak-Ki and SUVmean of mLNs between the two groups. The texture analysis indicated that PTs in the S-DFM group were more heterogeneous in FDG uptake than those in the F-DFM group. Higher T cells (CD3+/CD8+) and macrophages (CD68+/CD163+) infiltration in the PTs were observed in the F-DFM group. No significant difference was observed in tumor mutational burden between the two groups. CONCLUSION: The dynamic total-body [18F]FDG PET/CT stratified NSCLC patients into the F-DFM and S-DFM groups, based on Patlak-Ki and SUVmean of PTs. PTs in the F-DFM group seemed to be more homogenous in terms of [18F]FDG uptake than those in the S-DFM group. The higher infiltrations of T cells and macrophages were observed in the F-DFM group, which suggested a potential benefit from immunotherapy.

Machine Learning-Based Noninvasive Quantification of Single-Imaging Session Dual-Tracer 18F-FDG and 68Ga-DOTATATE Dynamic PET-CT in Oncology.

68Ga-DOTATATE PET-CT is routinely used for imaging neuroendocrine tumor (NET) somatostatin receptor subtype 2 (SSTR2) density in patients, and is complementary to FDG PET-CT for improving the accuracy of NET detection, characterization, grading, staging, and predicting/monitoring NET responses to treatment. Performing sequential 18F-FDG and 68Ga-DOTATATE PET scans would require 2 or more days and can delay patient care. To align temporal and spatial measurements of 18F-FDG and 68Ga-DOTATATE PET, and to reduce scan time and CT radiation exposure to patients, we propose a single-imaging session dual-tracer dynamic PET acquisition protocol in the study. A recurrent extreme gradient boosting (rXGBoost) machine learning algorithm was proposed to separate the mixed 18F-FDG and 68Ga-DOTATATE time activity curves (TACs) for the region of interest (ROI) based quantification with tracer kinetic modeling. A conventional parallel multi-tracer compartment modeling method was also implemented for reference. Single-scan dual-tracer dynamic PET was simulated from 12 NET patient studies with 18F-FDG and 68Ga-DOTATATE 45-min dynamic PET scans separately obtained within 2 days. Our experimental results suggested an 18F-FDG injection first followed by 68Ga-DOTATATE with a minimum 5 min delayed injection protocol for the separation of mixed 18F-FDG and 68Ga-DOTATATE TACs using rXGBoost algorithm followed by tracer kinetic modeling is highly feasible.

Dynamic topology analysis for spatial patterns of multifocal lesions on MRI.

Quantitatively analysing the spatial patterns of multifocal lesions on clinical MRI is an important step towards a better understanding of the disease and for precision medicine, which is yet to be properly explored by feature engineering and deep learning methods. Network science addresses this issue by explicitly modeling the inter-lesion topology. However, the construction of the informative graph with optimal edge sparsity and quantification of community graph structures are the current challenges in network science. In this paper, we address these challenges with a novel Dynamic Topology Analysis framework on the basis of persistent homology, aiming to investigate the predictive values of global geometry and local clusters of multifocal lesions. Firstly, Dynamic Hierarchical Network is proposed to construct informative global and community-level topology over multi-scale networks from sparse to dense. Multi-scale global topology is constructed with a nested sequence of Rips complexes, from which a new K-simplex Filtration is designed to generate a higher-level topological abstraction for community identification based on the connectivity of k-simplices in the Rips Complex. Secondly, to quantify multi-scale community structures, we design a new Decomposed Community Persistence algorithm to track the dynamic evolution of communities, and then summarise the evolutionary communities incorporated with a customisable descriptor. The quantified community features are encapsulated with global geometric invariants for topological pattern analysis. The proposed framework was evaluated on both diagnostic differentiation and prognostic prediction for multiple sclerosis that is a typical multifocal disease, and achieved ROC_AUC 0.875 and 0.767, respectively, outperforming seven state-of-the-art persistent homology methods and the reported performance of six feature engineering and deep learning methods.

Association between long-term donepezil treatment and brain regional amyloid and tau burden among individuals with mild cognitive impairment assessed using 18 F-AV-45 and 18 F-AV-1451 PET.

This study aims to investigate the association between long-term donepezil treatment and brain neuropathological burden and cognitive function in mild cognitive impairment (MCI) patients. Preprocessed 18 F-AV-45 amyloid and 18 F-AV-1451 tau positron emission tomography (PET) images, magnetic resonance imaging images (MRIs), demographic information, and donepezil use status were downloaded from 255 MCI participants enrolled in the Alzheimer's Disease Neuroimaging Initiative database. Partial volume correction was applied to all PET images. Structural MRIs were used for PET spatial normalization. Regions of interest (ROIs) were defined in standard space, and standardized uptake value ratio (SUVR) images relative to the cerebellum were computed. Multiple linear regression with the least absolute shrinkage selector operator was performed to analyze the effect of long-term donepezil treatment on (a) the SUVR of each 18 F-AV-45 or 18 F-AV-1451 brain PET ROI after adjusting for age, sex, education, ApoE ε4 status, and AD-associated disease risk factors; and (b) cognitive performance after adjusting for age, sex education, ApoE ε4 status, AD-associated disease risk factors, and regional amyloid or tau burden. In adjusted models, long-term donepezil treatment was associated with greater amyloid load in the orbital frontal, superior frontal, parietal, posterior precuneus, posterior cingulate, lateral temporal, inferior temporal and fusiform regions, and tau burden in the posterior cingulate, entorhinal and parahippocampal gyrus. Long-term donepezil treatment was also associated with worse performance on the 13-item Alzheimer's Disease Assessment Scale-Cognitive subscale after adjusting for AD-related risk factors and regional brain amyloid or tau load. These results indicate that long-term donepezil treatment is associated with increased regional amyloid and tau burden and worse cognitive performance among individuals with MCI. Our study highlights the importance of using noninvasive and quantitative 18 F-AV-45 and 18 F-AV-1451 PET to elucidate the consequences of drug administration in AD studies.

Sex modifies APOE ε4 dose effect on brain tau deposition in cognitively impaired individuals.

Recent studies in cognitively unimpaired elderly individuals suggest that the APOE ε4 allele exerts a dosage-dependent effect on brain tau deposition. The aim of this study was to investigate sex differences in APOE ε4 gene dosage effects on brain tau deposition in cognitively impaired individuals using quantitative 18F-flortaucipir PET. Preprocessed 18F-flortaucipir tau PET images, T1-weighted structural MRI, demographic information, global cortical amyloid-ß burden measured by 18F-florbetapir PET, CSF total tau and phosphorylated tau measurements were obtained from the Alzheimer's Disease Neuroimaging Initiative database. Two hundred and sixty-eight cognitively impaired individuals with 146 APOE ε4 non-carriers and 122 carriers (85 heterozygotes and 37 homozygotes) were included in the study. An iterative reblurred Van Cittert iteration partial volume correction method was applied to all downloaded PET images. Magnetic resonance images were used for PET spatial normalization. Twelve regional standardized uptake value ratios relative to the cerebellum were computed in standard space. APOE ε4 dosage × sex interaction effect on 18F-flortaucipir standardized uptake value ratios was assessed using generalized linear models and sex-stratified analysis. We observed a significant APOE ε4 dosage × sex interaction effect on tau deposition in the lateral temporal, posterior cingulate, medial temporal, inferior temporal, entorhinal cortex, amygdala, parahippocampal gyrus regions after adjusting for age and education level (P < 0.05). The medial temporal, entorhinal cortex, amygdala and parahippocampal gyrus regions retained a significant APOE ε4 dosage × sex interaction effect on tau deposition after adjusting for global cortical amyloid-ß (P < 0.05). In sex-stratified analysis, there was no significant difference in tau deposition between female homozygotes and heterozygotes (P > 0.05). In contrast, male homozygotes standardized uptake value ratios were significantly greater than heterozygotes or non-carriers throughout all 12 regions of interest (P < 0.05). Female heterozygotes exhibited significantly increased tau deposition compared to male heterozygotes in the orbitofrontal, posterior cingulate, lateral temporal, inferior temporal, entorhinal cortex, amygdala and parahippocampal gyrus (P < 0.05). Results from voxel-wise analysis were similar to the ones obtained from regions of interest analysis. Our findings indicate that an APOE ε4 dosage effect on brain region-specific tau deposition exists in males, but not females. These results have important clinical implications towards developing sex and genotype-guided therapeutics in Alzheimer's disease and uncovers a potential explanation underlying differential APOE ε4-associated Alzheimer's risk in males and females.

Association of sex and APOE ε4 with brain tau deposition and atrophy in older adults with Alzheimer's disease.

The objective of this study was to assess the association of sex and the apolipoprotein E (APOE) ε4 allele with brain tau deposition and atrophy in older adults with Alzheimer's disease (AD) using quantitative 18F-AV-1451 positron emission tomography (PET) and magnetic resonance imaging (MRI). Methods: Preprocessed 18F-AV-1451 tau PET, raw T1-weighted structural MR images, demographic information, cerebrospinal fluid (CSF) total tau (t-tau) and phosphorylated tau (p-tau) measurements from 57 elderly individuals with AD were downloaded from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. An iteratively reblurred Van Cittert partial volume correction (PVC) method was applied to all preprocessed PET images. MRI images were used for PET spatial normalization and gray matter volume calculation. 18F-AV-1451 PET standardized uptake value ratio (SUVR) was calculated relative to the cerebellum gray matter. The effect of sex and APOE ε4 status on SUVR and gray matter volume were assessed at both region of interest (ROI) and voxelwise levels. Results: Female APOE ε4 carriers (FACs) had significant higher 18F-AV-1451 SUVRs in the lateral temporal, parietal, posterior cingulate, medial temporal, inferior temporal, entorhinal cortex, amygdala and parahippocampal gyrus regions, and exhibited smaller gray matter volumes in the posterior cingulate, medial temporal, inferior temporal and amygdala regions, as compared to the non-FACs (NFACs) comprised of female APOE ε4 non-carriers, male APOE ε4 carriers and male APOE ε4 non-carriers. Voxelwise analysis revealed forebrain and limbic clusters with greater 18F-AV-1451 SUVRs and lower gray matter volume between FACs compared to the NFACs. Negative correlations between ROI 18F-AV-1451 SUVRs and gray matter volumes were significant after adjusting for age and years of education. Conclusions: Among elderly individuals with AD, sex modified the effects of the APOE ε4 allele on region-specific tau deposition and gray matter volume. FACs had elevated brain region-specific tau PET SUVR and decreased gray matter volume in comparison to NFACs. The study provides a basis for the use of precision medicine in the diagnosis of AD and evaluation of therapeutics using 18F-AV-1451 PET and structural MRI.

Multiparametric imaging hippocampal neurodegeneration and functional connectivity with simultaneous PET/MRI in Alzheimer's disease.

PURPOSE: The objective of this study is to investigate the hippocampal neurodegeneration and its associated aberrant functions in mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients using simultaneous PET/MRI. METHODS: Forty-two cognitively normal controls (NC), 38 MCI, and 22 AD patients were enrolled in this study. All subjects underwent 18F-FDG PET/functional MRI (fMRI) and high-resolution T1-weighted MRI scans on a hybrid GE Signa PET/MRI scanner. Neurodegeneration in hippocampus and its subregions was quantified by regional gray matter volume and 18F-FDG standardized uptake value ratio (SUVR) relative to cerebellum. An iterative reblurred Van Cittert iteration method was used for voxelwise partial volume correction on 18F-FDG PET images. Regional gray matter volume was estimated from voxel-based morphometric analysis with MRI. fMRI data were analyzed after slice time correction and head motion correction using statistical parametric mapping (SPM12) with DPARSF toolbox. The regions of interest including hippocampus, cornu ammonis (CA1), CA2/3/dentate gyrus (DG), and subiculum were defined in the standard MNI space. RESULTS: Patient groups had reduced SUVR, gray matter volume, and functional connectivity compared to NC in CA1, CA2/3/DG, and subiculum (AD < MCI < NC). There was a linear correlation between the left CA2/3DG gray matter volume and 18F-FDG SUVR in AD patients (P < 0.001, r = 0.737). Significant correlation was also found between left CA2/3/DG-superior medial frontal gyrus functional connectivity and left CA2/3/DG hypometabolism in patients with AD. The functional connectivity of right CA1-precuneus in patients with MCI and right subiculum-superior frontal gyrus in patients with AD was positively correlated with mini mental status examination scores (P < 0.05). CONCLUSION: Our findings demonstrate that the associations existed at subregional hippocampal level between the functional connectivity measured by fMRI and neurodegeneration measured by structural MRI and 18F-FDG PET. Our results may provide a basis for precision neuroimaging of hippocampus in AD.

18F-FDG PET/CT radiomic predictors of pathologic complete response (pCR) to neoadjuvant chemotherapy in breast cancer patients.

PURPOSE: Pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) is commonly accepted as the gold standard to assess outcome after NAC in breast cancer patients. 18F-Fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) has unique value in tumor staging, predicting prognosis, and evaluating treatment response. Our aim was to determine if we could identify radiomic predictors from PET/CT in breast cancer patient therapeutic efficacy prior to NAC. METHODS: This retrospective study included 100 breast cancer patients who received NAC; there were 2210 PET/CT radiomic features extracted. Unsupervised and supervised machine learning models were used to identify the prognostic radiomic predictors through the following: (1) selection of the significant (p < 0.05) imaging features from consensus clustering and the Wilcoxon signed-rank test; (2) selection of the most discriminative features via univariate random forest (Uni-RF) and the Pearson correlation matrix (PCM); and (3) determination of the most predictive features from a traversal feature selection (TFS) based on a multivariate random forest (RF). The prediction model was constructed with RF and then validated with 10-fold cross-validation for 30 times and then independently validated. The performance of the radiomic predictors was measured in terms of area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: The PET/CT radiomic predictors achieved a prediction accuracy of 0.857 (AUC = 0.844) on the training split set and 0.767 (AUC = 0.722) on the independent validation set. When age was incorporated, the accuracy for the split set increased to 0.857 (AUC = 0.958) and 0.8 (AUC = 0.73) for the independent validation set and both outperformed the clinical prediction model. We also found a close association between the radiomic features, receptor expression, and tumor T stage. CONCLUSION: Radiomic predictors from pre-treatment PET/CT scans when combined with patient age were able to predict pCR after NAC. We suggest that these data will be valuable for patient management.

18F-FDG PET/CT Radiomic Analysis with Machine Learning for Identifying Bone Marrow Involvement in the Patients with Suspected Relapsed Acute Leukemia.

18F-FDG PET / CT is used clinically for the detection of extramedullary lesions in patients with relapsed acute leukemia (AL). However, the visual analysis of 18F-FDG diffuse bone marrow uptake in detecting bone marrow involvement (BMI) in routine clinical practice is still challenging. This study aims to improve the diagnostic performance of 18F-FDG PET/CT in detecting BMI for patients with suspected relapsed AL. Methods: Forty-one patients (35 in training group and 6 in independent validation group) with suspected relapsed AL were retrospectively included in this study. All patients underwent both bone marrow biopsy (BMB) and 18F-FDG PET/CT within one week. The BMB results were used as the gold standard or real "truth" for BMI. The bone marrow 18F-FDG uptake was visually diagnosed as positive and negative by three nuclear medicine physicians. The skeletal volumes of interest were manually drawn on PET/CT images. A total of 781 PET and 1045 CT radiomic features were automatically extracted to provide a more comprehensive understanding of the embedded pattern. To select the most important and predictive features, an unsupervised consensus clustering method was first performed to analyze the feature correlations and then used to guide a random forest supervised machine learning model for feature importance analysis. Cross-validation and independent validation were conducted to justify the performance of our model. Results: The training group involved 16 BMB positive and 19 BMB negative patients. Based on the visual analysis of 18F-FDG PET, 3 patients had focal uptake, 8 patients had normal uptake, and 24 patients had diffuse uptake. The sensitivity, specificity, and accuracy of visual analysis for BMI diagnosis were 62.5%, 73.7%, and 68.6%, respectively. With the cross-validation on the training group, the machine learning model correctly predicted 31 patients in BMI. The sensitivity, specificity, and accuracy of the machine learning model in BMI detection were 87.5%, 89.5%, and 88.6%, respectively, significantly higher than the ones in visual analysis (P < 0.05). The evaluation on the independent validation group showed that the machine learning model could achieve 83.3% accuracy. Conclusions:18F-FDG PET/CT radiomic analysis with machine learning model provided a quantitative, objective and efficient mechanism for identifying BMI in the patients with suspected relapsed AL. It is suggested in particular for the diagnosis of BMI in the patients with 18F-FDG diffuse uptake patterns.

Topology-guided deformable registration with local importance preservation for biomedical images.

The demons registration (DR) model is well recognized for its deformation capability. However, it might lead to misregistration due to erroneous diffusion direction when there are no overlaps between corresponding regions. We propose a novel registration energy function, introducing topology energy, and incorporating a local energy function into the DR in a progressive registration scheme, to address these shortcomings. The topology energy that is derived from the topological information of the images serves as a direction inference to guide diffusion transformation to retain the merits of DR. The local energy constrains the deformation disparity of neighbouring pixels to maintain important local texture and density features. The energy function is minimized in a progressive scheme steered by a topology tree graph and we refer to it as topology-guided deformable registration (TDR). We validated our TDR on 20 pairs of synthetic images with Gaussian noise, 20 phantom PET images with artificial deformations and 12 pairs of clinical PET-CT studies. We compared it to three methods: (1) free-form deformation registration method, (2) energy-based DR and (3) multi-resolution DR. The experimental results show that our TDR outperformed the other three methods in regard to structural correspondence and preservation of the local important information including texture and density, while retaining global correspondence.

A statistical method for lung tumor segmentation uncertainty in PET images based on user inference.

PET has been widely accepted as an effective imaging modality for lung tumor diagnosis and treatment. However, standard criteria for delineating tumor boundary from PET are yet to develop largely due to relatively low quality of PET images, uncertain tumor boundary definition, and variety of tumor characteristics. In this paper, we propose a statistical solution to segmentation uncertainty on the basis of user inference. We firstly define the uncertainty segmentation band on the basis of segmentation probability map constructed from Random Walks (RW) algorithm; and then based on the extracted features of the user inference, we use Principle Component Analysis (PCA) to formulate the statistical model for labeling the uncertainty band. We validated our method on 10 lung PET-CT phantom studies from the public RIDER collections [1] and 16 clinical PET studies where tumors were manually delineated by two experienced radiologists. The methods were validated using Dice similarity coefficient (DSC) to measure the spatial volume overlap. Our method achieved an average DSC of 0.878 ± 0.078 on phantom studies and 0.835 ± 0.039 on clinical studies.

Automated CT liver segmentation using improved Chan-Vese model with global shape constrained energy.

In this paper, we propose an automated liver segmentation method to overcome the challenging issues of high degree of variations in liver shape / size and similar density distribution shared by the liver and its surrounding structures. To improve the performance of conventional statistical shape model for liver segmentation, in our method, the signed distance function is utilized so that the landmarks correspondence is not required when performing the principle component analysis. We improve the Chan-Vese model to bind the shape energy and local intensity feature to evolve the surface both globally and locally toward the closest shape driven by the PCA. In our experiments, 20 clinical CT studies were used for training and 25 clinical CT studies were used for validation. Our experimental results demonstrate that our method can achieve accurate and robust liver segmentation from both of low-contrast and high-contrast CT images.