Predicting clinically significant prostate cancer in elderly patients: A nomogram approach with shear wave elastography.

PURPOSE: This study was to construct a nomogram utilizing shear wave elastography and assess its efficacy in detecting clinically significant prostate cancer (csPCa). METHODS: 290 elderly people with suspected PCa who received prostate biopsy and shear wave elastography (SWE) imaging were respectively registered from April 2022 to December 2023. The elderly participants were stratified into two groups: those with csPCa and those without csPCa, which encompassed cases of clinically insignificant prostate cancer (cisPCa) and non-prostate cancer tissue, as determined by pathology findings. The LASSO algorithm, known as the least absolute shrinkage and selection operator, was utilized to identify features. Logistic regression analysis was utilized to establish models. Receiver operating characteristic (ROC) and calibration curves were utilized to evaluate the discriminatory ability of the nomogram. Bootstrap (1000 bootstrap iterations) was employed for internal validation and comparison with two models. A decision curve and a clinical impact curve were employed to assess the clinical usefulness. RESULTS: Our nomogram, which contained Emean, ΔEmean, prostate volume, prostate-specific antigen density (PSAD), and transrectal ultrasound (TRUS), showed better discrimination (AUC = 0.89; 95% CI: 0.83-0.94), compared to the clinical model without SWE parameters (p = 0.0007). Its accuracy, sensitivity and specificity were 0.83, 0.89 and 0.78, respectively. Based on the analysis of decision curve, the thresholds ranged from 5% to 90%. According to our nomogram, biopsying patients at a 20% probability threshold resulted in a 25% reduction in biopsies without missing any csPCa. The clinical impact curve demonstrated that the nomogram's predicted outcome is closer to the observed outcome when the probability threshold reaches 20% or greater. CONCLUSION: Our nomogram demonstrates efficacy in identifying elderly individuals with clinically significant prostate cancer, thereby facilitating informed clinical decision-making based on diagnostic outcomes and potential clinical benefits.

LncRNA GABPB1-AS1 is a potential target for the diagnosis of prostate cancer.

BACKGROUND: Prostate cancer is an adverse tumor that occurs in the male reproductive system. The symptoms of patients in the early stage are not obvious and are generally difficult to detect. AIM: The aim of this study was to determine the regulation of lncRNA GABPB1-AS1 (GABPB1-AS1) on prostate cancer progression and explore the diagnostic potential of GABPB1-AS1. METHODS: The contents of serum GABPB1-AS1 and miR-330-3p were examined by RT-qPCR assay. The functions of silencing GABPB1-AS1 and miR-330-3p inhibitor in prostate cancer cells were determined using transfection assay, CCK-8 assay and Transwell assay. The target of GABPB1-AS1 was predicted and verified at the molecular level by bioinformatics and luciferase reporter gene assay. The function of GABPB1-AS1 in prostate cancer diagnosis was evaluated via ROC method. RESULTS: GABPB1-AS1 was upregulated in prostate cancer serum, which was associated with patients' Gleason score and TNM stage. Mechanistically, GABPB1-AS1 directly targeted miR-330-3p, and there was a negative correlation between them. Reduced levels of GABPB1-AS1 in cells after knockdown of GABPB1-AS1 resulted in decreased prostate cancer cell growth and activity, and these inhibitory effects were repaired by miR-330-3p inhibitor. CONCLUSION: The present study confirmed that GABPB1-AS1 was overexpressed in prostate cancer, and its sponge miR-330-3p may be an effective target for timely diagnosis of prostate cancer.

Real-time diagnosis of intracerebral hemorrhage by generating dual-energy CT from single-energy CT.

Real-time diagnosis of intracerebral hemorrhage after thrombectomy is crucial for follow-up treatment. However, this is difficult to achieve with standard single-energy CT (SECT) due to similar CT values of blood and contrast agents under a single energy spectrum. In contrast, dual-energy CT (DECT) scanners employ two different energy spectra, which allows for real-time differentiation between hemorrhage and contrast extravasation based on energy-related attenuation characteristics. Unfortunately, DECT scanners are not as widely used as SECT scanners due to their high costs. To address this dilemma, in this paper, we generate pseudo DECT images from a SECT image for real-time diagnosis of hemorrhage. More specifically, we propose a SECT-to-DECT Transformer-based Generative Adversarial Network (SDTGAN), which is a 3D transformer-based multi-task learning framework equipped with a shared attention mechanism. In this way, SDTGAN can be guided to focus more on high-density areas (crucial for hemorrhage diagnosis) during the generation. Meanwhile, the introduced multi-task learning strategy and the shared attention mechanism also enable SDTGAN to model dependencies between interconnected generation tasks, improving generation performance while significantly reducing model parameters and computational complexity. In the experiments, we approximate real SECT images using mixed 120kV images from DECT data to address the issue of not being able to obtain the true paired DECT and SECT data. Extensive experiments demonstrate that SDTGAN can generate DECT images better than state-of-the-art methods. The code of our implementation is available at https://github.com/jiang-cw/SDTGAN.

TriLA: Triple-Level Alignment Based Unsupervised Domain Adaptation for Joint Segmentation of Optic Disc and Optic Cup.

Cross-domain joint segmentation of optic disc and optic cup on fundus images is essential, yet challenging, for effective glaucoma screening. Although many unsupervised domain adaptation (UDA) methods have been proposed, these methods can hardly achieve complete domain alignment, leading to suboptimal performance. In this paper, we propose a triple-level alignment (TriLA) model to address this issue by aligning the source and target domains at the input level, feature level, and output level simultaneously. At the input level, a learnable Fourier domain adaptation (LFDA) module is developed to learn the cut-off frequency adaptively for frequency-domain translation. At the feature level, we disentangle the style and content features and align them in the corresponding feature spaces using consistency constraints. At the output level, we design a segmentation consistency constraint to emphasize the segmentation consistency across domains. The proposed model is trained on the RIGA+ dataset and widely evaluated on six different UDA scenarios. Our comprehensive results not only demonstrate that the proposed TriLA substantially outperforms other state-of-the-art UDA methods in joint segmentation of optic disc and optic cup, but also suggest the effectiveness of the triple-level alignment strategy.

Multi-omics and immunogenomics analysis revealed PFKFB3 as a targetable hallmark and mediates sunitinib resistance in papillary renal cell carcinoma: in silico study with laboratory verification.

Glycolysis-related metabolic reprogramming is a central hallmark of human cancers, especially in renal cell carcinoma. However, the regulatory function of glycolytic signature in papillary RCC has not been well elucidated. In the present study, the glycolysis-immune predictive signature was constructed and validated using WGCNA, glycolysis-immune clustering analysis. PPI network of DEGs was constructed and visualized. Functional enrichments and patients' overall survival were analyzed. QRT-PCR experiments were performed to detect hub genes' expression and distribution, siRNA technology was used to silence targeted genes; cell proliferation and migration assays were applied to evaluate the biological function. Glucose concentration, lactate secretion, and ATP production were measured. Glycolysis-Immune Related Prognostic Index (GIRPI) was constructed and combined analyzed with single-cell RNA-seq. High-GIRPI signature predicted significantly poorer outcomes and relevant clinical features of pRCC patients. Moreover, GIRPI also participated in several pathways, which affected tumor immune microenvironment and provided potential therapeutic strategy. As a key glycolysis regulator, PFKFB3 could promote renal cancer cell proliferation and migration in vitro. Blocking of PFKFB3 by selective inhibitor PFK-015 or glycolytic inhibitor 2-DG significantly restrained renal cancer cells' neoplastic potential. PFK-015 and sunitinib could synergistically inhibit pRCC cells proliferation. Glycolysis-Immune Risk Signature is closely associated with pRCC prognosis, progression, immune infiltration, and therapeutic response. PFKFB3 may serve as a pivotal glycolysis regulator and mediates Sunitinib resistance in pRCC patients.

Deep learning-assisted preclinical MR fingerprinting for sub-millimeter T1 and T2 mapping of entire macaque brain.

PURPOSE: Preclinical MR fingerprinting (MRF) suffers from long acquisition time for organ-level coverage due to demanding image resolution and limited undersampling capacity. This study aims to develop a deep learning-assisted fast MRF framework for sub-millimeter T1 and T2 mapping of entire macaque brain on a preclinical 9.4 T MR system. METHODS: Three dimensional MRF images were reconstructed by singular value decomposition (SVD) compressed reconstruction. T1 and T2 mapping for each axial slice exploited a self-attention assisted residual U-Net to suppress aliasing-induced quantification errors, and the transmit-field (B1 + ) measurements for robustness against B1 + inhomogeneity. Supervised network training used MRF images simulated via virtual parametric maps and a desired undersampling scheme. This strategy bypassed the difficulties of acquiring fully sampled preclinical MRF data to guide network training. The proposed fast MRF framework was tested on experimental data acquired from ex vivo and in vivo macaque brains. RESULTS: The trained network showed reasonable adaptability to experimental MRF images, enabling robust delineation of various T1 and T2 distributions in the brain tissues. Further, the proposed MRF framework outperformed several existing fast MRF methods in handling the aliasing artifacts and capturing detailed cerebral structures in the mapping results. Parametric mapping of entire macaque brain at nominal resolution of 0.35 × $$ \times $$ 0.35 × $$ \times $$ 1 mm3 can be realized via a 20-min 3D MRF scan, which was sixfold faster than the baseline protocol. CONCLUSION: Introducing deep learning to MRF framework paves the way for efficient organ-level high-resolution quantitative MRI in preclinical applications.

Dynamic feature splicing for few-shot rare disease diagnosis.

Annotated images for rare disease diagnosis are extremely hard to collect. Therefore, identifying rare diseases under a few-shot learning (FSL) setting is significant. Existing FSL methods transfer useful and global knowledge from base classes with abundant training samples to enrich features of novel classes with few training samples, but still face difficulties when being applied to medical images due to the complex lesion characteristics and large intra-class variance. In this paper, we propose a dynamic feature splicing (DNFS) framework for few-shot rare disease diagnosis. Under DNFS, both low-level features (i.e., the output of three convolutional blocks) and high-level features (i.e., the output of the last fully connected layer) of novel classes are dynamically enriched. We construct the position coherent DNFS (P-DNFS) module to perform low-level feature splicing, where a lesion-oriented Transformer is designed to detect lesion regions. Thus, novel-class channels are replaced by similar base-class channels within the detected lesion regions to achieve disease-related feature enrichment. We also devise a semantic coherent DNFS (S-DNFS) module to perform high-level feature splicing. It explores cross-image channel relations and selects base-class channels with semantic consistency for explicit knowledge transfer. Both low-level and high-level feature splicings are performed dynamically and iteratively. Consequently, abundant spliced features are generated for disease diagnosis, leading to more accurate decision boundary and improved diagnosis performance. Extensive experiments have been conducted on three medical image classification datasets. Our results suggest that the proposed DNFS achieves superior performance against state-of-the-art approaches.

Quantitative Cerebral Blood Volume Image Synthesis from Standard MRI Using Image-to-Image Translation for Brain Tumors.

Background Cerebral blood volume (CBV) maps derived from dynamic susceptibility contrast-enhanced (DSC) MRI are useful but not commonly available in clinical scenarios. Purpose To test image-to-image translation techniques for generating CBV maps from standard MRI sequences of brain tumors using the bookend technique DSC MRI as ground-truth references. Materials and Methods A total of 756 MRI examinations, including quantitative CBV maps produced from bookend DSC MRI, were included in this retrospective study. Two algorithms, the feature-consistency generative adversarial network (GAN) and three-dimensional encoder-decoder network with only mean absolute error loss, were trained to synthesize CBV maps. The performance of the two algorithms was evaluated quantitatively using the structural similarity index (SSIM) and qualitatively by two neuroradiologists using a four-point Likert scale. The clinical value of combining synthetic CBV maps and standard MRI scans of brain tumors was assessed in several clinical scenarios (tumor grading, prognosis prediction, differential diagnosis) using multicenter data sets (four external and one internal). Differences in diagnostic and predictive accuracy were tested using the z test. Results The three-dimensional encoder-decoder network with T1-weighted images, contrast-enhanced T1-weighted images, and apparent diffusion coefficient maps as the input achieved the highest synthetic performance (SSIM, 86.29% ± 4.30). The mean qualitative score of the synthesized CBV maps by neuroradiologists was 2.63. Combining synthetic CBV with standard MRI improved the accuracy of grading gliomas (standard MRI scans area under the receiver operating characteristic curve [AUC], 0.707; standard MRI scans with CBV maps AUC, 0.857; z = 15.17; P < .001), prediction of prognosis in gliomas (standard MRI scans AUC, 0.654; standard MRI scans with CBV maps AUC, 0.793; z = 9.62; P < .001), and differential diagnosis between tumor recurrence and treatment response in gliomas (standard MRI scans AUC, 0.778; standard MRI scans with CBV maps AUC, 0.853; z = 4.86; P < .001) and brain metastases (standard MRI scans AUC, 0.749; standard MRI scans with CBV maps AUC, 0.857; z = 6.13; P < .001). Conclusion GAN image-to-image translation techniques produced accurate synthetic CBV maps from standard MRI scans, which could be used for improving the clinical evaluation of brain tumors. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Branstetter in this issue.

Disentangle First, Then Distill: A Unified Framework for Missing Modality Imputation and Alzheimer's Disease Diagnosis.

Multi-modality medical data provide complementary information, and hence have been widely explored for computer-aided AD diagnosis. However, the research is hindered by the unavoidable missing-data problem, i.e., one data modality was not acquired on some subjects due to various reasons. Although the missing data can be imputed using generative models, the imputation process may introduce unrealistic information to the classification process, leading to poor performance. In this paper, we propose the Disentangle First, Then Distill (DFTD) framework for AD diagnosis using incomplete multi-modality medical images. First, we design a region-aware disentanglement module to disentangle each image into inter-modality relevant representation and intra-modality specific representation with emphasis on disease-related regions. To progressively integrate multi-modality knowledge, we then construct an imputation-induced distillation module, in which a lateral inter-modality transition unit is created to impute representation of the missing modality. The proposed DFTD framework has been evaluated against six existing methods on an ADNI dataset with 1248 subjects. The results show that our method has superior performance in both AD-CN classification and MCI-to-AD prediction tasks, substantially over-performing all competing methods.

Semi-Supervised Standard-Dose PET Image Generation via Region-Adaptive Normalization and Structural Consistency Constraint.

Positron Emission Tomography (PET) is an important nuclear medical imaging technique, and has been widely used in clinical applications, e.g., tumor detection and brain disease diagnosis. As PET imaging could put patients at risk of radiation, the acquisition of high-quality PET images with standard-dose tracers should be cautious. However, if dose is reduced in PET acquisition, the imaging quality could become worse and thus may not meet clinical requirement. To safely reduce the tracer dose and also maintain high quality of PET imaging, we propose a novel and effective approach to estimate high-quality Standard-dose PET (SPET) images from Low-dose PET (LPET) images. Specifically, to fully utilize both the rare paired and the abundant unpaired LPET and SPET images, we propose a semi-supervised framework for network training. Meanwhile, based on this framework, we further design a Region-adaptive Normalization (RN) and a structural consistency constraint to track the task-specific challenges. RN performs region-specific normalization in different regions of each PET image to suppress negative impact of large intensity variation across different regions, while the structural consistency constraint maintains structural details during the generation of SPET images from LPET images. Experiments on real human chest-abdomen PET images demonstrate that our proposed approach achieves state-of-the-art performance quantitatively and qualitatively.

Reconstruction-Driven Dynamic Refinement Based Unsupervised Domain Adaptation for Joint Optic Disc and Cup Segmentation.

Glaucoma is one of the leading causes of irreversible blindness. Segmentation of optic disc (OD) and optic cup (OC) on fundus images is a crucial step in glaucoma screening. Although many deep learning models have been constructed for this task, it remains challenging to train an OD/OC segmentation model that could be deployed successfully to different healthcare centers. The difficulties mainly comes from the domain shift issue, i.e., the fundus images collected at these centers usually vary greatly in the tone, contrast, and brightness. To address this issue, in this paper, we propose a novel unsupervised domain adaptation (UDA) method called Reconstruction-driven Dynamic Refinement Network (RDR-Net), where we employ a due-path segmentation backbone for simultaneous edge detection and region prediction and design three modules to alleviate the domain gap. The reconstruction alignment (RA) module uses a variational auto-encoder (VAE) to reconstruct the input image and thus boosts the image representation ability of the network in a self-supervised way. It also uses a style-consistency constraint to force the network to retain more domain-invariant information. The low-level feature refinement (LFR) module employs input-specific dynamic convolutions to suppress the domain-variant information in the obtained low-level features. The prediction-map alignment (PMA) module elaborates the entropy-driven adversarial learning to encourage the network to generate source-like boundaries and regions. We evaluated our RDR-Net against state-of-the-art solutions on four public fundus image datasets. Our results indicate that RDR-Net is superior to competing models in both segmentation performance and generalization ability.

Effect of Radical Laparoscopic Surgery and Conventional Open Surgery on Surgical Outcomes, Complications, and Prognosis in Elderly Patients with Bladder Cancer.

Background: Bladder cancer is a common malignant tumor of the urinary system in the clinic. It has multiple lesions, easy recurrence, easy metastasis, poor prognosis, and high mortality. Objective: The aim of this study is to investigate the impact of laparoscopic radical cystectomy (LRC) and open radical cystectomy (ORC) on the surgical outcome, complications, and prognosis of elderly patients with bladder cancer. Materials and Methods: One hundred elderly bladder cancer patients who underwent surgery in our hospital from June 2019 to June 2021 were selected for the retrospective study and were divided into 50 cases each in the ORC group and the LRC group according to the different surgical methods. The ORC group was treated with ORC, and the LRC group implemented LRC treatment. The differences in surgery, immune function, recent clinical outcomes, and complications between the two groups were observed and compared. Results: The mean operative time, mean intraoperative bleeding, intraoperative and postoperative transfusion rate, and transfusion volume of patients in the LRC group were statistically significant when compared to the ORC group. The differences in the meantime to resume eating, time to get out of bed, mean number of days in hospital after surgery, and the amount of postoperative numbing analgesics used by patients in the LRC group after surgery were statistically significant compared to the ORC group (P < 0.05). There was no statistically significant difference in the comparison of immune function between the two groups before surgery (P > 0.05), while the comparison of CD8+ and B cells 1 week after surgery of the LRC group was significantly better than that of the ORC group (P < 0.05), and the operation time of the LRC group was longer than that of the ORC group (P < 0.05). Statistical analysis of postoperative complications showed that the overall incidence of postoperative complications in the LRC group was significantly lower than that in the ORC group (16.67% vs. 46.67%) (P < 0.05). Conclusion: LRC has less surgical trauma and intraoperative bleeding, faster postoperative recovery, and fewer postoperative complications, providing some reference for clinical surgery for elderly bladder cancer patients.

Demethylase FTO inhibits the development of prostate cancer by upregulating EGR2 expression in an m6A manner.

Fat mass and obesity-associated protein (FTO) is a demethylase and plays a vital role in various cancers. However, the regulation mechanism of FTO in prostate cancer (PCa) remains unclear. This study aimed to elucidate the mechanism of FTO in PCa. The function and mechanism of FTO-mediated in PCa were determined by gain-of-function assays and RNA-seq. We found that FTO expression in PCa tissues and two PCa cell lines were significantly lower than that in adjacent tissues and normal cell line. PCa cells after overexpression of FTO showed a significant lower in proliferation, migration, and invasion capabilities. RNA-seq displayed that FTO overexpression altered transcriptome landscape in Du145 and PC-3 cells, particularly upregulating EGR2 expression. FTO overexpression induced differential expression genes, including MYLK2, DNA2, CDK, and CDC (6, 7, 20, 25, and 45), which were mainly enriched in adjustment of cell cycle and growth pathways. Furthermore, FTO overexpression significantly reduced the EGR2 methylation level. Arresting the proliferation, migration, and invasion of Du145 cells induced by FTO overexpression was significantly rescued by EGR2 knockdown. FTO overexpression also significantly inhibited tumor growth and promoted EGR2 protein expression. Taken together, FTO suppresses PCa progression by regulating EGR2 methylation. We uncovered a novel regulatory mechanism of FTO in PCa and provide a new potential therapeutic target for PCa.

bpMRI and mpMRI for detecting prostate cancer: A retrospective cohort study.

Background: We aimed to compare the detection rates of prostate cancer (PCa) and clinically significant prostate cancer(csPCa) by biparametric (bp-) and multiparameter magnetic resonance imaging (mpMRI). Materials and Methods: A total of 699 patients who underwent transperineal prostate biopsy in the Department of Urology, the Second Affiliated Hospital of Nantong University from January 2018 to December 2021 were retrospectively reviewed. Multivariate analysis was used to explore the influencing factors associated with the detection rates of PCa and csPCa. According to MRI examination before biopsy, the patients were divided into bpMRI group and mpMRI group. The detection rates of PCa and csPCa by bpMRI and mpMRI were compared. Furthermore, stratified analysis was performed for patients in these two groups to compare the detection rates of PCa and csPCa at different tPSA intervals, different prostate volume (PV) intervals and different PI-RADS V2 scores. Results: A total of 571 patients were finally analyzed in this study after exclusion, and the overall detection rate of PCa was 54.5%. Multivariate analysis showed that patient age, tPSA level, prostate volume and PI-RADS V2 score were independent risk factors affecting the detection rates of PCa and csPCa. The detection rates of PCa and csPCa by bpMRI and mpMRI were comparable (51.3% vs. 57.9%, 44.0% vs. 48.0%, both P > 0.05), with no statistical significance. In the tPSA 10-20 ng/ml interval, the detection rates of PCa (59.72% vs. 40.35%, P = 0.011) and csPCa (51.39% vs. 28.82%, P = 0.005) by mpMRI were significantly higher than those by bpMRI, while in other tPSA interval (tPSA < 4 ng/ml, 4-10 ng/ml, 20-100 ng/ml), different PVs (≤30 ml, 30-60 ml, >60 ml) and different PI-RADS V2 scores (3, 4, and 5), the detection rates of PCa and csPCa were comparable between the two groups. Conclusion: For detecting PCa and csPCa, bpMRI and mpMRI had similar diagnostic efficacies, whereas mpMRI detected more PCa and csPCa in the tPSA interval of 10-20 ng/ml.

Attention-Guided Hybrid Network for Dementia Diagnosis With Structural MR Images.

Deep-learning methods (especially convolutional neural networks) using structural magnetic resonance imaging (sMRI) data have been successfully applied to computer-aided diagnosis (CAD) of Alzheimer's disease (AD) and its prodromal stage [i.e., mild cognitive impairment (MCI)]. As it is practically challenging to capture local and subtle disease-associated abnormalities directly from the whole-brain sMRI, most of those deep-learning approaches empirically preselect disease-associated sMRI brain regions for model construction. Considering that such isolated selection of potentially informative brain locations might be suboptimal, very few methods have been proposed to perform disease-associated discriminative region localization and disease diagnosis in a unified deep-learning framework. However, those methods based on task-oriented discriminative localization still suffer from two common limitations, that is: 1) identified brain locations are strictly consistent across all subjects, which ignores the unique anatomical characteristics of each brain and 2) only limited local regions/patches are used for model training, which does not fully utilize the global structural information provided by the whole-brain sMRI. In this article, we propose an attention-guided deep-learning framework to extract multilevel discriminative sMRI features for dementia diagnosis. Specifically, we first design a backbone fully convolutional network to automatically localize the discriminative brain regions in a weakly supervised manner. Using the identified disease-related regions as spatial attention guidance, we further develop a hybrid network to jointly learn and fuse multilevel sMRI features for CAD model construction. Our proposed method was evaluated on three public datasets (i.e., ADNI-1, ADNI-2, and AIBL), showing superior performance compared with several state-of-the-art methods in both tasks of AD diagnosis and MCI conversion prediction.

Disease-Image-Specific Learning for Diagnosis-Oriented Neuroimage Synthesis With Incomplete Multi-Modality Data.

Incomplete data problem is commonly existing in classification tasks with multi-source data, particularly the disease diagnosis with multi-modality neuroimages, to track which, some methods have been proposed to utilize all available subjects by imputing missing neuroimages. However, these methods usually treat image synthesis and disease diagnosis as two standalone tasks, thus ignoring the specificity conveyed in different modalities, i.e., different modalities may highlight different disease-relevant regions in the brain. To this end, we propose a disease-image-specific deep learning (DSDL) framework for joint neuroimage synthesis and disease diagnosis using incomplete multi-modality neuroimages. Specifically, with each whole-brain scan as input, we first design a Disease-image-Specific Network (DSNet) with a spatial cosine module to implicitly model the disease-image specificity. We then develop a Feature-consistency Generative Adversarial Network (FGAN) to impute missing neuroimages, where feature maps (generated by DSNet) of a synthetic image and its respective real image are encouraged to be consistent while preserving the disease-image-specific information. Since our FGAN is correlated with DSNet, missing neuroimages can be synthesized in a diagnosis-oriented manner. Experimental results on three datasets suggest that our method can not only generate reasonable neuroimages, but also achieve state-of-the-art performance in both tasks of Alzheimer's disease identification and mild cognitive impairment conversion prediction.

Identifying Type 2 Diabetic Brains by Investigating Disease-Related Structural Changes in Magnetic Resonance Imaging.

Diabetes with high blood glucose levels may damage the brain nerves and thus increase the risk of dementia. Previous studies have shown that dementia can be reflected in altered brain structure, facilitating computer-aided diagnosis of brain diseases based on structural magnetic resonance imaging (MRI). However, type 2 diabetes mellitus (T2DM)-mediated changes in the brain structures have not yet been studied, and only a few studies have focused on the use of brain MRI for automated diagnosis of T2DM. Hence, identifying MRI biomarkers is essential to evaluate the association between changes in brain structure and T2DM as well as cognitive impairment (CI). The present study aims to investigate four methods to extract features from MRI, characterize imaging biomarkers, as well as identify subjects with T2DM and CI.

Injectable hydrogel-loaded nano-hydroxyapatite that improves bone regeneration and alveolar ridge promotion.

In stomatology, the promotion of alveolar bone regeneration while preventing the reduction of ridge absorption remains a challenge. In this work, we designed and prepared bio-mimetic polysaccharide hydrogels that are multi-functional in terms of being injectable, promote self-healing, degradable, porous structure, et al. After introducing nano-hydroxyapatite particles, the composite scaffold of hydrogel/hydroxyapatite (GH) stent was obtained. When GH material was injected into the mandibular incisors of rats following tooth extraction, the new bone area was enhanced more than 50%, while the alveolar ridge was promoted in excess of 60% after 4 weeks. What's more, the wound soft tissue was healed within 1 week. Overall, our results indicate that this optimized GH stent has the potential to both maintain dimensional alveolar ridge, as well as to promote soft tissue healing. Moreover, using the hydroxyapatite-containing hydrogel platform has the potential to promote bone and soft tissue regeneration.

High-Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network.

BACKGROUND: A generative adversarial network could be used for high-resolution (HR) medical image synthesis with reduced scan time. PURPOSE: To evaluate the potential of using a deep convolutional generative adversarial network (DCGAN) for generating HRpre and HRpost images based on their corresponding low-resolution (LR) images (LRpre and LRpost ). STUDY TYPE: This was a retrospective analysis of a prospectively acquired cohort. POPULATION: In all, 224 subjects were randomly divided into 200 training subjects and an independent 24 subjects testing set. FIELD STRENGTH/SEQUENCE: Dynamic contrast-enhanced (DCE) MRI with a 1.5T scanner. ASSESSMENT: Three breast radiologists independently ranked the image datasets, using the DCE images as the ground truth, and reviewed the image quality of both the original LR images and the generated HR images. The BI-RADS category and conspicuity of lesions were also ranked. The inter/intracorrelation coefficients (ICCs) of mean image quality scores, lesion conspicuity scores, and Breast Imaging Reporting and Data System (BI-RADS) categories were calculated between the three readers. STATISTICAL TEST: Wilcoxon signed-rank tests evaluated differences among the multireader ranking scores. RESULTS: The mean overall image quality scores of the generated HRpre and HRpost were significantly higher than those of the original LRpre and LRpost (4.77 ± 0.41 vs. 3.27 ± 0.43 and 4.72 ± 0.44 vs. 3.23 ± 0.43, P < 0.0001, respectively, in the multireader study). The mean lesion conspicuity scores of the generated HRpre and HRpost were significantly higher than those of the original LRpre and LRpost (4.18 ± 0.70 vs. 3.49 ± 0.58 and 4.35 ± 0.59 vs. 3.48 ± 0.61, P < 0.001, respectively, in the multireader study). The ICCs of the image quality scores, lesion conspicuity scores, and BI-RADS categories had good agreements among the three readers (all ICCs >0.75). DATA CONCLUSION: DCGAN was capable of generating HR of the breast from fast pre- and postcontrast LR and achieved superior quantitative and qualitative performance in a multireader study. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2 J. MAGN. RESON. IMAGING 2020;52:1852-1858.

Spatially-Constrained Fisher Representation for Brain Disease Identification With Incomplete Multi-Modal Neuroimages.

Multi-modal neuroimages, such as magnetic resonance imaging (MRI) and positron emission tomography (PET), can provide complementary structural and functional information of the brain, thus facilitating automated brain disease identification. Incomplete data problem is unavoidable in multi-modal neuroimage studies due to patient dropouts and/or poor data quality. Conventional methods usually discard data-missing subjects, thus significantly reducing the number of training samples. Even though several deep learning methods have been proposed, they usually rely on pre-defined regions-of-interest in neuroimages, requiring disease-specific expert knowledge. To this end, we propose a spatially-constrained Fisher representation framework for brain disease diagnosis with incomplete multi-modal neuroimages. We first impute missing PET images based on their corresponding MRI scans using a hybrid generative adversarial network. With the complete (after imputation) MRI and PET data, we then develop a spatially-constrained Fisher representation network to extract statistical descriptors of neuroimages for disease diagnosis, assuming that these descriptors follow a Gaussian mixture model with a strong spatial constraint (i.e., images from different subjects have similar anatomical structures). Experimental results on three databases suggest that our method can synthesize reasonable neuroimages and achieve promising results in brain disease identification, compared with several state-of-the-art methods.