Adversarial Confidence Learning for Medical Image Segmentation and Synthesis.

Generative adversarial networks (GAN) are widely used in medical image analysis tasks, such as medical image segmentation and synthesis. In these works, adversarial learning is directly applied to the original supervised segmentation (synthesis) networks. The usage of adversarial learning is effective in improving visual perception performance since adversarial learning works as realistic regularization for supervised generators. However, the quantitative performance often cannot improve as much as the qualitative performance, and it can even become worse in some cases. In this paper, we explore how we can take better advantage of adversarial learning in supervised segmentation (synthesis) models and propose an adversarial confidence learning framework to better model these problems. We analyze the roles of discriminator in the classic GANs and compare them with those in supervised adversarial systems. Based on this analysis, we propose adversarial confidence learning, i.e., besides the adversarial learning for emphasizing visual perception, we use the confidence information provided by the adversarial network to enhance the design of supervised segmentation (synthesis) network. In particular, we propose using a fully convolutional adversarial network for confidence learning to provide voxel-wise and region-wise confidence information for the segmentation (synthesis) network. With these settings, we propose a difficulty-aware attention mechanism to properly handle hard samples or regions by taking structural information into consideration so that we can better deal with the irregular distribution of medical data. Furthermore, we investigate the loss functions of various GANs and propose using the binary cross entropy loss to train the proposed adversarial system so that we can retain the unlimited modeling capacity of the discriminator. Experimental results on clinical and challenge datasets show that our proposed network can achieve state-of-the-art segmentation (synthesis) accuracy. Further analysis also indicates that adversarial confidence learning can both improve the visual perception performance and the quantitative performance.

Stress-Induced Hyperglycemia and Remote Diffusion-Weighted Imaging Lesions in Primary Intracerebral Hemorrhage.

BACKGROUND AND PURPOSE: Stress-induced hyperglycemia (SIH) is the relative transient increase in glucose during a critical illness such as intracerebral hemorrhage (ICH) and is likely to play an important role in the pathogenesis of remote diffusion-weighted imaging (DWI) lesion (R-DWIL) in primary ICH. We sought to determine the association between SIH and the occurrence of R-DWILs. METHODS: We prospectively enrolled primary ICH patients within 14 days after onset from November 2016 to May 2018. In these patients, cerebral magnetic resonance imaging was performed within 14 days after ICH onset. R-DWIL was defined as a hyperintensity signal in DWI with corresponding hypointensity in apparent diffusion coefficient, and at least 20 mm apart from the hematoma. SIH was measured by stress-induced hyperglycemia ratio (SHR). SHR was calculated by fasting blood glucose (FBG) divided by estimated average glucose derived from glycosylated hemoglobin. The included patients were dichotomized into two groups by the 50th percentile of SHR, and named as SHR (-P50) group and SHR (P50+) group, respectively. We evaluated the association between SHR and R-DWIL occurrence using multivariable logistic regression modeling adjusted for potential confounders. RESULTS: Among the 288 patients enrolled, forty-six (16.0%) of them had one or more R-DWILs. Compared with the patients in the lower 50% of SHR (SHR [-P50]), the odds ratio (OR) [95% confidence interval (CI)] for the higher 50% of SHR (SHR [P50+]) group for R-DWIL occurrence was 3.13 (1.39-7.07) in the total population and 6.33 (2.19-18.30) in population absent of background hyperglycemia after adjusting for potential covariates. Similar results were observed after further adjusted for FBG. CONCLUSIONS: Our study demonstrated that SIH was associated with the occurrence of R-DWILs in patients with primary ICH within 14 days of symptom onset.

Multi-task diagnosis for autism spectrum disorders using multi-modality features: A multi-center study.

Autism spectrum disorder (ASD) is a neurodevelopment disease characterized by impairment of social interaction, language, behavior, and cognitive functions. Up to now, many imaging-based methods for ASD diagnosis have been developed. For example, one may extract abundant features from multi-modality images and then derive a discriminant function to map the selected features toward the disease label. A lot of recent works, however, are limited to single imaging centers. To this end, we propose a novel multi-modality multi-center classification (M3CC) method for ASD diagnosis. We treat the classification of each imaging center as one task. By introducing the task-task and modality-modality regularizations, we solve the classification for all imaging centers simultaneously. Meanwhile, the optimal feature selection and the modeling of the discriminant functions can be jointly conducted for highly accurate diagnosis. Besides, we also present an efficient iterative optimization solution to our formulated problem and further investigate its convergence. Our comprehensive experiments on the ABIDE database show that our proposed method can significantly improve the performance of ASD diagnosis, compared to the existing methods. Hum Brain Mapp 38:3081-3097, 2017. © 2017 Wiley Periodicals, Inc.

Deep Auto-context Convolutional Neural Networks for Standard-Dose PET Image Estimation from Low-Dose PET/MRI.

Positron emission tomography (PET) is an essential technique in many clinical applications such as tumor detection and brain disorder diagnosis. In order to obtain high-quality PET images, a standard-dose radioactive tracer is needed, which inevitably causes the risk of radiation exposure damage. For reducing the patient's exposure to radiation and maintaining the high quality of PET images, in this paper, we propose a deep learning architecture to estimate the high-quality standard-dose PET (SPET) image from the combination of the low-quality low-dose PET (LPET) image and the accompanying T1-weighted acquisition from magnetic resonance imaging (MRI). Specifically, we adapt the convolutional neural network (CNN) to account for the two channel inputs of LPET and T1, and directly learn the end-to-end mapping between the inputs and the SPET output. Then, we integrate multiple CNN modules following the auto-context strategy, such that the tentatively estimated SPET of an early CNN can be iteratively refined by subsequent CNNs. Validations on real human brain PET/MRI data show that our proposed method can provide competitive estimation quality of the PET images, compared to the state-of-the-art methods. Meanwhile, our method is highly efficient to test on a new subject, e.g., spending ~2 seconds for estimating an entire SPET image in contrast to ~16 minutes by the state-of-the-art method. The results above demonstrate the potential of our method in real clinical applications.

Multimodal Brain Tumor Segmentation Boosted by Monomodal Normal Brain Images.

Many deep learning based methods have been proposed for brain tumor segmentation. Most studies focus on deep network internal structure to improve the segmentation accuracy, while valuable external information, such as normal brain appearance, is often ignored. Inspired by the fact that radiologists often screen lesion regions with normal appearance as reference in mind, in this paper, we propose a novel deep framework for brain tumor segmentation, where normal brain images are adopted as reference to compare with tumor brain images in a learned feature space. In this way, features at tumor regions, i.e., tumor-related features, can be highlighted and enhanced for accurate tumor segmentation. It is known that routine tumor brain images are multimodal, while normal brain images are often monomodal. This causes the feature comparison a big issue, i.e., multimodal vs. monomodal. To this end, we present a new feature alignment module (FAM) to make the feature distribution of monomodal normal brain images consistent/inconsistent with multimodal tumor brain images at normal/tumor regions, making the feature comparison effective. Both public (BraTS2022) and in-house tumor brain image datasets are used to evaluate our framework. Experimental results demonstrate that for both datasets, our framework can effectively improve the segmentation accuracy and outperforms the state-of-the-art segmentation methods. Codes are available at https://github.com/hb-liu/Normal-Brain-Boost-Tumor-Segmentation.

A New Multi-Atlas Based Deep Learning Segmentation Framework With Differentiable Atlas Feature Warping.

Deep learning based multi-atlas segmentation (DL-MA) has achieved the state-of-the-art performance in many medical image segmentation tasks, e.g., brain parcellation. In DL-MA methods, atlas-target correspondence is the key for accurate segmentation. In most existing DL-MA methods, such correspondence is usually established using traditional or deep learning based registration methods at image level with no further feature level adaption. This could cause possible atlas-target feature inconsistency. As a result, the information from atlases often has limited positive and even counteractive impact on the final segmentation results. To tackle this issue, in this paper, we propose a new DL-MA framework, where a novel differentiable atlas feature warping module with a new smooth regularization term is presented to establish feature level atlas-target correspondence. Comparing with the existing DL-MA methods, in our framework, atlas features containing anatomical prior knowledge are more relevant to the target image feature, leading the final segmentation results to a high accuracy level. We evaluate our framework in the context of brain parcellation using two public MR brain image datasets: LPBA40 and NIREP-NA0. The experimental results demonstrate that our framework outperforms both traditional multi-atlas segmentation (MAS) and state-of-the-art DL-MA methods with statistical significance. Further ablation studies confirm the effectiveness of the proposed differentiable atlas feature warping module.

Overexpression of human SPATA17 protein induces germ cell apoptosis in transgenic male mice.

SPATA17 is a new testis-specific-expressed gene that is involved in Spermatogenesis process. Previous studies show that SPATA17 was involved in acceleration of cell apoptosis in GC-1 cell lines. To further investigate specific roles of SPATA17 in Spermatogenesis in vivo, we generated transgenic mice in which the human SPATA17 gene was expressed specifically in spermatocytes using the human phosphoglycerate kinase 2 (PGK2) promoter. The SPATA17 transgenic mice did not show any significant defect in gross testicular anatomy as well as in fertility. However, a significant increase was observed in defective spermatogenic cells, such as apoptotic cells in the SPATA17 transgenic mice. These results revealed that elevated production of the SPATA17 protein disturbed the normal development of male germ cells.

[Long-term results of personalized treatment in 72 breast cancer patients who failed chemotherapy].

OBJECTIVE: To evaluate the efficacy and prognostic factors of personalized treatment for breast cancer patients who failed chemotherapy. METHODS: Seventy-two patients with breast cancer who failed chemotherapy were treated at the Tumor Hospital of Harbin Medical University from January 2001 to January 2012. Among them, 42 cases received 5.6 cycles (range, 4-8 cycles) of postoperative adjuvant chemotherapy, and 30 cases received 12.2 cycles (range, 6-22 cycles), both postoperative adjuvant and salvage chemotherapy. All of the 72 patients of stage IV were given personalized treatment. Under guidance of the principle that multidisciplinary treatment improves control rate but does not or less damage the normal tissues and host immune function, precise radiotherapy combined with Chinese herbal medicine (CHM), biological agent and others were chosen for the patients. RESULTS: The median survival time was 20 months. Univariate analysis showed that non-invasive ductal carcinoma, less metastasized organs, without brain, liver and lung metastasis, Karnofsky performance scores ≥ 80, not combined with chemotherapy, and multiple courses of Chinese herbal medicine and biolojical agent treatment had significant impact on survival (P < 0.05). Multivariate analysis showed that no brain metastasis, non-invasive ductal carcinoma, and Chinese herbal medicine and biological agent treatment ≥ 7 courses and not combined with chemotherapy had obvious significance (P < 0.05). The rate of grade 3 and 4 treatment-related hematological toxicity was 8.3% (6/72) and 5.6% (4/72), respectively. All the patients with grade 4 hematological toxicity were the cases of grade 3 at hospital admission. No grade 3 and 4 acute radiation damages of the lung and liver were noticed. CONCLUSION: Chinese herbal medicine combined with biological agents and others prolongs survival time in breast cancer patients who failed chemotherapy, and provides an alternative treatment modality for them.

The Devil is in the Upsampling: Architectural Decisions Made Simpler for Denoising with Deep Image Prior.

Deep Image Prior (DIP) shows that some network architectures inherently tend towards generating smooth images while resisting noise, a phenomenon known as spectral bias. Image denoising is a natural application of this property. Although denoising with DIP mitigates the need for large training sets, two often intertwined practical challenges need to be overcome: architectural design and noise fitting. Existing methods either handcraft or search for suitable architectures from a vast design space, due to the limited understanding of how architectural choices affect the denoising outcome. In this study, we demonstrate from a frequency perspective that unlearnt upsampling is the main driving force behind the denoising phenomenon with DIP. This finding leads to straightforward strategies for identifying a suitable architecture for every image without laborious search. Extensive experiments show that the estimated architectures achieve superior denoising results than existing methods with up to 95% fewer parameters. Thanks to this under-parameterization, the resulting architectures are less prone to noise-fitting.

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.

Fast Multi-Contrast MRI Acquisition by Optimal Sampling of Information Complementary to Pre-Acquired MRI Contrast.

Recent studies on multi-contrast MRI reconstruction have demonstrated the potential of further accelerating MRI acquisition by exploiting correlation between contrasts. Most of the state-of-the-art approaches have achieved improvement through the development of network architectures for fixed under-sampling patterns, without considering inter-contrast correlation in the under-sampling pattern design. On the other hand, sampling pattern learning methods have shown better reconstruction performance than those with fixed under-sampling patterns. However, most under-sampling pattern learning algorithms are designed for single contrast MRI without exploiting complementary information between contrasts. To this end, we propose a framework to optimize the under-sampling pattern of a target MRI contrast which complements the acquired fully-sampled reference contrast. Specifically, a novel image synthesis network is introduced to extract the redundant information contained in the reference contrast, which is exploited in the subsequent joint pattern optimization and reconstruction network. We have demonstrated superior performance of our learned under-sampling patterns on both public and in-house datasets, compared to the commonly used under-sampling patterns and state-of-the-art methods that jointly optimize the reconstruction network and the under-sampling patterns, up to 8-fold under-sampling factor.

Efficacy of concurrent chemoradiotherapy with thalidomide and S-1 for esophageal carcinoma and its influence on serum tumor markers.

BACKGROUND: Although the current conventional treatment strategies for esophageal carcinoma (EC) have been proven effective, they are often accompanied by serious adverse events. Therefore, it is still necessary to continue to explore new therapeutic strategies for EC to improve the clinical outcome of patients. AIM: To elucidate the clinical efficacy of concurrent chemoradiotherapy (CCRT) with thalidomide (THAL) and S-1 (tegafur, gimeracil, and oteracil potassium capsules) in the treatment of EC as well as its influence on serum tumor markers (STMs). METHODS: First, 62 patients with EC treated at the Zibo 148 Hospital between November 2019 and November 2022 were selected and grouped according to the received treatment. Among these, 30 patients undergoing CCRT with cis-platinum and 5-fluorouracil were assigned to the control group (Con), and 32 patients receiving CCRT with THAL and S-1 were assigned to the research group (Res). Second, inter-group comparisons were carried out with respect to curative efficacy, incidence of drug toxicities, STMs [carbohydrate antigen 125 (CA125) and macrophage inflammatory protein-3α (MIP-3α)], angiogenesis-related indicators [vascular endothelial growth factor (VEGF); VEGF receptor-1 (VEGFR-1); basic fibroblast growth factor (bFGF); angiogenin-2 (Ang-2)], and quality of life (QoL) [QoL core 30 (QLQ-C30)] after one month of treatment. RESULTS: The analysis showed no statistical difference in the overall response rate and disease control rate between the two patient cohorts; however, the incidences of grade I-II myelosuppression and gastrointestinal reactions were significantly lower in the Res than in the Con. Besides, the post-treatment CA125, MIP-3α, VEGF, VEGFR-1, bFGF, and Ang-2 Levels in the Res were markedly lower compared with the pre-treatment levels and the corresponding post-treatment levels in the Con. Furthermore, more evident improvements in QLQ-C30 scores from the dimensions of physical, role, emotional, and social functions were determined in the Res. CONCLUSION: The above results demonstrate the effectiveness of THAL + S-1 CCRT for EC, which contributes to mild side effects and significant reduction of CA125, MIP-3α, VEGF, VEGFR-1, bFGF, and Ang-2 Levels, thus inhibiting tumors from malignant progression and enhancing patients' QoL.

[Simultaneous determination of 36 mycotoxins in fruits by QuEChERS coupled with ultra performance liquid chromatography-tandem mass spectrometry].

Mycotoxins are secondary metabolites produced by toxigenic fungi under specific environmental conditions. Fruits, owing to their high moisture content, rich nutrition, and improper harvest or storage conditions, are highly susceptible to various mycotoxins, such as ochratoxin A (OTA), zearalenone (ZEN), patulin (PAT), Alternaria toxins, etc. These mycotoxins can cause acute and chronic toxic effects (teratogenicity, mutagenicity, and carcinogenicity, etc) in animals and humans. Given the high toxicity and wide prevalence of mycotoxins, establishing an efficient analytical method to detect multiple mycotoxins simultaneously in different types of fruits is of great importance. Conventional mycotoxin detection methods rely on high performance liquid chromatography (HPLC) coupled with mass spectrometry (MS). However, fruit sample matrices contain large amounts of pigments, cellulose, and minerals, all of which dramatically impede the detection of trace mycotoxins in fruits. Therefore, the efficient enrichment and purification of multiple mycotoxins in fruit samples is crucial before instrumental analysis. In this study, a reliable method based on a QuEChERs sample preparation approach coupled with ultra performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS) was established to determine 36 mycotoxins in fruits. In the optimal extraction method, 2.0 g of a sample was extracted with 10 mL of acetic acid-acetonitrile-water (1∶79∶20, v/v/v) in a 50 mL centrifuge tube, vortexed for 30 s, and ultrasonicated for 40 min. The mixture was then salted out with 2.0 g of anhydrous MgSO4 and 0.5 g of NaCl and centrifuged for 5 min. Next, 6 mL of the supernatant was purified using 85 mg of octadecylsilane-bonded silica gel (C18) and 15 mg of N-propylethylenediamine (PSA). After vigorous shaking and centrifugation, the supernatant was collected and dried with nitrogen at 40 ℃. Finally, the residues were redissolved in 1 mL of 5 mmol/L ammonium acetate aqueous solution-acetonitrile (50∶50, v/v) and passed through a 0.22 µm nylon filter before analysis. The mycotoxins were separated on a Waters XBridge BEH C18 column using a binary gradient mixture of ammonium acetate aqueous solution and methanol. The injection volume was 3 µL. The mycotoxins were analyzed in multiple reaction monitoring (MRM) mode under both positive and negative electrospray ionization. Quantitative analysis was performed using an external standard method with matrix-matched calibration curves. Under optimal conditions, good linear relationships were obtained in the respective linear ranges, with correlation coefficients (R2) no less than 0.990. The limits of detection (LODs) and quantification (LOQs) were 0.02-5 and 0.1-10 µg/kg, respectively. The recoveries of the 36 mycotoxins in fruits ranged from 77.0% to 118.9% at low, medium, and high spiked levels, with intra- and inter-day precisions in the range of 1.3%-14.9% and 0.2%-17.3%, respectively. The validated approach was employed to investigate mycotoxin contamination in actual fruit samples, including strawberry, grape, pear, and peach (15 samples of each type). Eleven mycotoxins, namely, altenuene (ALT), altenusin (ALS), alternariol-methyl ether (AME), tenuazonic acid (TeA), tentoxin (Ten), OTA, beauvericin (BEA), PAT, zearalanone (ZAN), T-2 toxin (T2), and mycophenolic acid (MPA), were found in the samples; three samples were contaminated with multiple mycotoxins. The incidence rates of mycotoxins in strawberry, grape, pear, and peach were 27%, 40%, 40%, and 33%, respectively. In particular, Alternaria toxins were the most frequently found mycotoxins in these fruits, with an incidence of 15%. The proposed method is simple, rapid, accurate, sensitive, reproducible, and stable; thus, it is suitable for the simultaneous detection of the 36 mycotoxins in different fruits.

TransDose: Transformer-based radiotherapy dose prediction from CT images guided by super-pixel-level GCN classification.

Radiotherapy is a mainstay treatment for cancer in clinic. An excellent radiotherapy treatment plan is always based on a high-quality dose distribution map which is produced by repeated manual trial-and-errors of experienced experts. To accelerate the radiotherapy planning process, many automatic dose distribution prediction methods have been proposed recently and achieved considerable fruits. Nevertheless, these methods require certain auxiliary inputs besides CT images, such as segmentation masks of the tumor and organs at risk (OARs), which limits their prediction efficiency and application potential. To address this issue, we design a novel approach named as TransDose for dose distribution prediction that treats CT images as the unique input in this paper. Specifically, instead of inputting the segmentation masks to provide the prior anatomical information, we utilize a super-pixel-based graph convolutional network (GCN) to extract category-specific features, thereby compensating the network for the necessary anatomical knowledge. Besides, considering the strong continuous dependency between adjacent CT slices as well as adjacent dose maps, we embed the Transformer into the backbone, and make use of its superior ability of long-range sequence modeling to endow input features with inter-slice continuity message. To our knowledge, this is the first network that specially designed for the task of dose prediction from only CT images without ignoring necessary anatomical structure. Finally, we evaluate our model on two real datasets, and extensive experiments demonstrate the generalizability and advantages of our method.

Changes on brief cognitive instruments over time in Parkinson's disease.

Two hundred and twenty-one subjects with Parkinson's disease (PD) were examined using the Mini-Mental Status Examination (MMSE) and Montreal Cognitive Assessment (MoCA), with a subset of these (n = 98) examined on repeat testing up to 3 years. The MoCA was more sensitive in identifying cognitive deficit, specifically in the domains of visuospatial abilities, language, and memory. In longitudinal study, the MMSE changed significantly over time, particularly in patients with disease duration of >10 years. The MoCA, however, did not change significantly, even when subjects were stratified by age, MMSE score, and disease duration. This suggests that the MoCA may be more sensitive for detecting early cognitive change in PD, but that the MMSE, and not the MoCA, may be better for tracking cognitive decline.

Semantic instance segmentation with discriminative deep supervision for medical images.

Semantic instance segmentation is crucial for many medical image analysis applications, including computational pathology and automated radiation therapy. Existing methods for this task can be roughly classified into two categories: (1) proposal-based methods and (2) proposal-free methods. However, in medical images, the irregular shape-variations and crowding instances (e.g., nuclei and cells) make it hard for the proposal-based methods to achieve robust instance localization. On the other hand, ambiguous boundaries caused by the low-contrast nature of medical images (e.g., CT images) challenge the accuracy of the proposal-free methods. To tackle these issues, we propose a proposal-free segmentation network with discriminative deep supervision (DDS), which at the same time allows us to gain the power of the proposal-based method. The DDS module is interleaved with a carefully designed proposal-free segmentation backbone in our network. Consequently, the features learned by the backbone network become more sensitive to instance localization. Also, with the proposed DDS module, robust pixel-wise instance-level cues (especially structural information) are introduced for semantic segmentation. Extensive experiments on three datasets, i.e., a nuclei dataset, a pelvic CT image dataset, and a synthetic dataset, demonstrate the superior performance of the proposed algorithm compared to the previous works.

An Efficient Semi-Supervised Framework with Multi-Task and Curriculum Learning for Medical Image Segmentation.

A practical problem in supervised deep learning for medical image segmentation is the lack of labeled data which is expensive and time-consuming to acquire. In contrast, there is a considerable amount of unlabeled data available in the clinic. To make better use of the unlabeled data and improve the generalization on limited labeled data, in this paper, a novel semi-supervised segmentation method via multi-task curriculum learning is presented. Here, curriculum learning means that when training the network, simpler knowledge is preferentially learned to assist the learning of more difficult knowledge. Concretely, our framework consists of a main segmentation task and two auxiliary tasks, i.e. the feature regression task and target detection task. The two auxiliary tasks predict some relatively simpler image-level attributes and bounding boxes as the pseudo labels for the main segmentation task, enforcing the pixel-level segmentation result to match the distribution of these pseudo labels. In addition, to solve the problem of class imbalance in the images, a bounding-box-based attention (BBA) module is embedded, enabling the segmentation network to concern more about the target region rather than the background. Furthermore, to alleviate the adverse effects caused by the possible deviation of pseudo labels, error tolerance mechanisms are also adopted in the auxiliary tasks, including inequality constraint and bounding-box amplification. Our method is validated on ACDC2017 and PROMISE12 datasets. Experimental results demonstrate that compared with the full supervision method and state-of-the-art semi-supervised methods, our method yields a much better segmentation performance on a small labeled dataset. Code is available at https://github.com/DeepMedLab/MTCL.

Fentanyl enhances HIV infection in vitro.

Acquired immunodeficiency syndrome (AIDS) caused by Human immunodeficiency virus type 1 (HIV-1) has a high tendency among illicit drug abusers. Recently, it is reported that abuse of fentanyl, a potent synthetic µ receptor-stimulating opioid, is an independent risk factor for HIV-1 infection. However, the mechanism of action in augmenting HIV-1 infection still remains elusive. In this study, we found that fentanyl enhanced infection of HIV-1 in MT2 cells, primary macrophages and Jurkat C11 cells. Fentanyl up-regulated CXCR4 and CCR5 receptor expression, which facilitated the entry of virion into host cells. In addition, it down-regulated interferon-ß (IFN-ß) and interferon-stimulated genes (APOBEC3F, APOBEC3G and MxB) expression in MT2 cells. Our findings identify an essential role of fentanyl in the positive regulation of HIV-1 infection via the upregulation of co-receptors (CXCR4/CCR5) and downregulation of IFN-ß and ISGs, and it may have an important role in HIV-1 immunopathogenesis.

Synthetic digital reconstructed radiographs for MR-only robotic stereotactic radiation therapy: A proof of concept.

PURPOSE: To create synthetic CTs and digital reconstructed radiographs (DRRs) from MR images that allow for fiducial visualization and accurate dose calculation for MR-only radiosurgery. METHODS: We developed a machine learning model to create synthetic CTs from pelvic MRs for prostate treatments. This model has been previously proven to generate synthetic CTs with accuracy on par or better than alternate methods, such as atlas-based registration. Our dataset consisted of 11 paired CT and conventional MR (T2) images used for previous CyberKnife (Accuray, Inc) radiotherapy treatments. The MR images were pre-processed to mimic the appearance of fiducial-enhancing images. Two models were trained for each parameter case, using a sub-set of the available image pairs, with the remaining images set aside for testing and validation of the model to identify the optimal patch size and number of image pairs used for training. Four models were then trained using the identified parameters and used to generate synthetic CTs, which in turn were used to generate DRRs at angles 45° and 315°, as would be used for a CyberKnife treatment. The synthetic CTs and DRRs were compared visually and using the mean squared error and peak signal-to-noise ratio against the ground-truth images to evaluate their similarity. RESULTS: The synthetic CTs, as well as the DRRs generated from them, gave similar visualization of the fiducial markers in the prostate as the true counterparts. There was no significant difference found for the fiducial localization for the CTs and DRRs. Across the 8 DRRs analyzed, the mean MSE between the normalized true and synthetic DRRs was 0.66 ± 0.42% and the mean PSNR for this region was 22.9 ± 3.7 dB. For the full CTs, the mean MAE was 72.9 ± 88.1 HU and the mean PSNR was 31.2 ± 2.2 dB. CONCLUSIONS: Our machine learning-based method provides a proof of concept of a way to generate synthetic CTs and DRRs for accurate dose calculation and fiducial localization for use in radiation treatment of the prostate.

HF-UNet: Learning Hierarchically Inter-Task Relevance in Multi-Task U-Net for Accurate Prostate Segmentation in CT Images.

Accurate segmentation of the prostate is a key step in external beam radiation therapy treatments. In this paper, we tackle the challenging task of prostate segmentation in CT images by a two-stage network with 1) the first stage to fast localize, and 2) the second stage to accurately segment the prostate. To precisely segment the prostate in the second stage, we formulate prostate segmentation into a multi-task learning framework, which includes a main task to segment the prostate, and an auxiliary task to delineate the prostate boundary. Here, the second task is applied to provide additional guidance of unclear prostate boundary in CT images. Besides, the conventional multi-task deep networks typically share most of the parameters (i.e., feature representations) across all tasks, which may limit their data fitting ability, as the specificity of different tasks are inevitably ignored. By contrast, we solve them by a hierarchically-fused U-Net structure, namely HF-UNet. The HF-UNet has two complementary branches for two tasks, with the novel proposed attention-based task consistency learning block to communicate at each level between the two decoding branches. Therefore, HF-UNet endows the ability to learn hierarchically the shared representations for different tasks, and preserve the specificity of learned representations for different tasks simultaneously. We did extensive evaluations of the proposed method on a large planning CT image dataset and a benchmark prostate zonal dataset. The experimental results show HF-UNet outperforms the conventional multi-task network architectures and the state-of-the-art methods.