Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma.

Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of glioblastoma (GBM). This heterogeneity is further exacerbated during GBM recurrence, as treatment-induced reactive changes produce additional intratumoral heterogeneity that is ambiguous to differentiate on clinical imaging. There is an urgent need to develop non-invasive approaches to map the heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We propose to predictively fuse Magnetic Resonance Imaging (MRI) with the underlying intratumoral heterogeneity in recurrent GBM using machine learning (ML) by leveraging image-localized biopsies with their associated locoregional MRI features. To this end, we develop BioNet, a biologically-informed neural network model, to predict regional distributions of three tissue-specific gene modules: proliferating tumor, reactive/inflammatory cells, and infiltrated brain tissue. BioNet offers valuable insights into the integration of multiple implicit and qualitative biological domain knowledge, which are challenging to describe in mathematical formulations. BioNet performs significantly better than a range of existing methods on cross-validation and blind test datasets. Voxel-level prediction maps of the gene modules by BioNet help reveal intratumoral heterogeneity, which can improve surgical targeting of confirmatory biopsies and evaluation of neuro-oncological treatment effectiveness. The non-invasive nature of the approach can potentially facilitate regular monitoring of the gene modules over time, and making timely therapeutic adjustment. These results also highlight the emerging role of ML in precision medicine.

Correlation enhanced distribution adaptation for prediction of fall risk.

With technological advancements in diagnostic imaging, smart sensing, and wearables, a multitude of heterogeneous sources or modalities are available to proactively monitor the health of the elderly. Due to the increasing risks of falls among older adults, an early diagnosis tool is crucial to prevent future falls. However, during the early stage of diagnosis, there is often limited or no labeled data (expert-confirmed diagnostic information) available in the target domain (new cohort) to determine the proper treatment for older adults. Instead, there are multiple related but non-identical domain data with labels from the existing cohort or different institutions. Integrating different data sources with labeled and unlabeled samples to predict a patient's condition poses a significant challenge. Traditional machine learning models assume that data for new patients follow a similar distribution. If the data does not satisfy this assumption, the trained models do not achieve the expected accuracy, leading to potential misdiagnosing risks. To address this issue, we utilize domain adaptation (DA) techniques, which employ labeled data from one or more related source domains. These DA techniques promise to tackle discrepancies in multiple data sources and achieve a robust diagnosis for new patients. In our research, we have developed an unsupervised DA model to align two domains by creating a domain-invariant feature representation. Subsequently, we have built a robust fall-risk prediction model based on these new feature representations. The results from simulation studies and real-world applications demonstrate that our proposed approach outperforms existing models.

Usability of the novel ankle training equipment with spring resistance-based plantar press exercises in the standing position: A focus on chronic stroke patients with hemiplegic gait.

BACKGROUND: To improve gait disability in patients with chronic stroke, ankle muscle strengthening and calf muscle stretching exercises are required. However, currently available ankle training equipment limit ankle exercises based on the position. Recently developed ankle training equipment enables spring resistance-based plantar press exercises to be performed in the standing position with weight support. OBJECTIVE: To conduct a usability test of the ankle training equipment in the standing position by stroke patients with hemiplegic gait and verify its effects on ankle movements. METHODS: The ankle training equipment was applied to five patients with chronic stroke and hemiplegic gait. In the standing position, the patients performed forefoot and rearfoot press exercises in the affected side with a day's interval at 20 repetitions maximum (RM). During the exercises, surface electromyography (sEMG) was used to measure the maximum voluntary isometric contraction (%MVIC) of the leg muscles. The System Usability Scale (SUS) was used to assess the ankle training equipment. Wilcoxon signed-rank test was used to evaluate the differences in muscle activity between the two exercises. RESULTS: Forefoot and rearfoot press exercises increased the %MVIC in the biceps femoris. Additionally, the tibialis anterior and medial gastrocnemius activity was significantly different between the two exercises. The SUS was 78.75% (SD 12.7). CONCLUSION: The usability test of the passive-control foot press trainer (PFPT) that with improvements in the structure and functions for convenience, it could be commercialized. PFPT could be an alternative to the ankle rehabilitation robot that necessitates a sitting position.

Harmonizing Healthy Cohorts to Support Multicenter Studies on Migraine Classification using Brain MRI Data.

Multicenter and multi-scanner imaging studies might be needed to provide sample sizes large enough for developing accurate predictive models. However, multicenter studies, which likely include confounding factors due to subtle differences in research participant characteristics, MRI scanners, and imaging acquisition protocols, might not yield generalizable machine learning models, that is, models developed using one dataset may not be applicable to a different dataset. The generalizability of classification models is key for multi-scanner and multicenter studies, and for providing reproducible results. This study developed a data harmonization strategy to identify healthy controls with similar (homogenous) characteristics from multicenter studies to validate the generalization of machine-learning techniques for classifying individual migraine patients and healthy controls using brain MRI data. The Maximum Mean Discrepancy (MMD) was used to compare the two datasets represented in Geodesic Flow Kernel (GFK) space, capturing the data variabilities for identifying a "healthy core". A set of homogeneous healthy controls can assist in overcoming some of the unwanted heterogeneity and allow for the development of classification models that have high accuracy when applied to new datasets. Extensive experimental results show the utilization of a healthy core. One dataset consists of 120 individuals (66 with migraine and 54 healthy controls) and another dataset consists of 76 (34 with migraine and 42 healthy controls) individuals. A homogeneous dataset derived from a cohort of healthy controls improves the performance of classification models by about 25% accuracy improvements for both episodic and chronic migraineurs.

Prediction of fall risk among community-dwelling older adults using a wearable system.

Falls are among the most common cause of decreased mobility and independence in older adults and rank as one of the most severe public health problems with frequent fatal consequences. In the present study, gait characteristics from 171 community-dwelling older adults were evaluated to determine their predictive ability for future falls using a wearable system. Participants wore a wearable sensor (inertial measurement unit, IMU) affixed to the sternum and performed a 10-m walking test. Measures of gait variability, complexity, and smoothness were extracted from each participant, and prospective fall incidence was evaluated over the following 6-months. Gait parameters were refined to better represent features for a random forest classifier for the fall-risk classification utilizing three experiments. The results show that the best-trained model for faller classification used both linear and nonlinear gait parameters and achieved an overall 81.6 ± 0.7% accuracy, 86.7 ± 0.5% sensitivity, 80.3 ± 0.2% specificity in the blind test. These findings augment the wearable sensor's potential as an ambulatory fall risk identification tool in community-dwelling settings. Furthermore, they highlight the importance of gait features that rely less on event detection methods, and more on time series analysis techniques. Fall prevention is a critical component in older individuals' healthcare, and simple models based on gait-related tasks and a wearable IMU sensor can determine the risk of future falls.

AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction.

The prediction of Mild Cognitive Impairment (MCI) patients who are at higher risk converting to Alzheimer's Disease (AD) is critical for effective intervention and patient selection in clinical trials. Different biomarkers including neuroimaging have been developed to serve the purpose. With extensive methodology development efforts on neuroimaging, an emerging field is deep learning research. One great challenge facing deep learning is the limited medical imaging data available. To address the issue, researchers explore the use of transfer learning to extend the applicability of deep models on neuroimaging research for AD diagnosis and prognosis. Existing transfer learning models mostly focus on transferring the features from the pre-training into the fine-tuning stage. Recognizing the advantages of the knowledge gained during the pre-training, we propose an AD-NET (Age-adjust neural network) with the pre-training model serving two purposes: extracting and transferring features; and obtaining and transferring knowledge. Specifically, the knowledge being transferred in this research is an age-related surrogate biomarker. To evaluate the effectiveness of the proposed approach, AD-NET is compared with 8 classification models from literature using the same public neuroimaging dataset. Experimental results show that the proposed AD-NET outperforms the competing models in predicting the MCI patients at risk for conversion to the AD stage.

Artificial Intelligence for the Computer-aided Detection of Periapical Lesions in Cone-beam Computed Tomographic Images.

INTRODUCTION: The aim of this study was to use a Deep Learning (DL) algorithm for the automated segmentation of cone-beam computed tomographic (CBCT) images and the detection of periapical lesions. METHODS: Limited field of view CBCT volumes (n = 20) containing 61 roots with and without lesions were segmented clinician dependent versus using the DL approach based on a U-Net architecture. Segmentation labeled each voxel as 1 of 5 categories: "lesion" (periapical lesion), "tooth structure," "bone," "restorative materials," and "background." Repeated splits of all images into a training set and a validation set based on 5-fold cross validation were performed using Deep Learning segmentation (DLS), and the results were averaged. DLS versus clinical-dependent segmentation was assessed by dichotomized lesion detection accuracy evaluating sensitivity, specificity, positive predictive value, negative predictive value, and voxel-matching accuracy using the DICE index for each of the 5 labels. RESULTS: DLS lesion detection accuracy was 0.93 with specificity of 0.88, positive predictive value of 0.87, and negative predictive value of 0.93. The overall cumulative DICE indexes for the individual labels were lesion = 0.52, tooth structure = 0.74, bone = 0.78, restorative materials = 0.58, and background = 0.95. The cumulative DICE index for all actual true lesions was 0.67. CONCLUSIONS: This DL algorithm trained in a limited CBCT environment showed excellent results in lesion detection accuracy. Overall voxel-matching accuracy may be benefited by enhanced versions of artificial intelligence.

CAPTCHA Image Generation: Two-Step Style-Transfer Learning in Deep Neural Networks.

Mobile devices such as sensors are used to connect to the Internet and provide services to users. Web services are vulnerable to automated attacks, which can restrict mobile devices from accessing websites. To prevent such automated attacks, CAPTCHAs are widely used as a security solution. However, when a high level of distortion has been applied to a CAPTCHA to make it resistant to automated attacks, the CAPTCHA becomes difficult for a human to recognize. In this work, we propose a method for generating a CAPTCHA image that will resist recognition by machines while maintaining its recognizability to humans. The method utilizes the style transfer method, and creates a new image, called a style-plugged-CAPTCHA image, by incorporating the styles of other images while keeping the content of the original CAPTCHA. In our experiment, we used the TensorFlow machine learning library and six CAPTCHA datasets in use on actual websites. The experimental results show that the proposed scheme reduces the rate of recognition by the DeCAPTCHA system to 3.5% and 3.2% using one style image and two style images, respectively, while maintaining recognizability by humans.

Deep Residual Inception Encoder-Decoder Network for Medical Imaging Synthesis.

Image synthesis is a novel solution in precision medicine for scenarios where important medical imaging is not otherwise available. The convolutional neural network (CNN) is an ideal model for this task because of its powerful learning capabilities through the large number of layers and trainable parameters. In this research, we propose a new architecture of residual inception encoder-decoder neural network (RIED-Net) to learn the nonlinear mapping between the input images and targeting output images. To evaluate the validity of the proposed approach, it is compared with two models from the literature: synthetic CT deep convolutional neural network (sCT-DCNN) and shallow CNN, using both an institutional mammogram dataset from Mayo Clinic Arizona and a public neuroimaging dataset from the Alzheimer's Disease Neuroimaging Initiative. Experimental results show that the proposed RIED-Net outperforms the two models on both datasets significantly in terms of structural similarity index, mean absolute percent error, and peak signal-to-noise ratio.

Integration of machine learning and mechanistic models accurately predicts variation in cell density of glioblastoma using multiparametric MRI.

Glioblastoma (GBM) is a heterogeneous and lethal brain cancer. These tumors are followed using magnetic resonance imaging (MRI), which is unable to precisely identify tumor cell invasion, impairing effective surgery and radiation planning. We present a novel hybrid model, based on multiparametric intensities, which combines machine learning (ML) with a mechanistic model of tumor growth to provide spatially resolved tumor cell density predictions. The ML component is an imaging data-driven graph-based semi-supervised learning model and we use the Proliferation-Invasion (PI) mechanistic tumor growth model. We thus refer to the hybrid model as the ML-PI model. The hybrid model was trained using 82 image-localized biopsies from 18 primary GBM patients with pre-operative MRI using a leave-one-patient-out cross validation framework. A Relief algorithm was developed to quantify relative contributions from the data sources. The ML-PI model statistically significantly outperformed (p < 0.001) both individual models, ML and PI, achieving a mean absolute predicted error (MAPE) of 0.106 ± 0.125 versus 0.199 ± 0.186 (ML) and 0.227 ± 0.215 (PI), respectively. Associated Pearson correlation coefficients for ML-PI, ML, and PI were 0.838, 0.518, and 0.437, respectively. The Relief algorithm showed the PI model had the greatest contribution to the result, emphasizing the importance of the hybrid model in achieving the high accuracy.

A secure and efficient audit mechanism for dynamic shared data in cloud storage.

With popularization of cloud services, multiple users easily share and update their data through cloud storage. For data integrity and consistency in the cloud storage, the audit mechanisms were proposed. However, existing approaches have some security vulnerabilities and require a lot of computational overheads. This paper proposes a secure and efficient audit mechanism for dynamic shared data in cloud storage. The proposed scheme prevents a malicious cloud service provider from deceiving an auditor. Moreover, it devises a new index table management method and reduces the auditing cost by employing less complex operations. We prove the resistance against some attacks and show less computation cost and shorter time for auditing when compared with conventional approaches. The results present that the proposed scheme is secure and efficient for cloud storage services managing dynamic shared data.

Immunomodulatory effects of Aureobasidium pullulans SM-2001 exopolymers on the cyclophosphamide-treated mice.

The immunomodulatory effects of exopolymers of Aureobasidium pullulans SM-2001 containing beta-1,3/1,6-glucan were evaluated on the cyclophosphamide (CPA)-treated mice. To induce immunosuppress, 150 and 110 mg/kg of CPA were intraperitoneally injected at 1 and 3 days before start of test material administrations, respectively. Exopolymers were subcutaneously or orally administered in a volume of 10 ml/kg, 4 times; 12-hr intervals from 24 hrs after second treatment of CPA. After treatment of exopolymers, the changes of thymus and spleen weights, splenic amounts of tumor necrosis factor (TNF)-alpha, interleukin (IL)-1beta and IL-10, thymic and splenic CD3+, CD4+, CD8+ and TNF-alpha+ cells were monitored in CPA-treated mice. As results of CPA treatment, dramatical decreases of the CD3+, CD4+, CD8+ and TNF-alpha+ cells were detected in thymus and spleen with decreases of thymus and spleen weights. In addition, decreases of splenic TNF-alpha, IL-1beta and IL-10 contents were also detected at flow cytometrical observations. However, oral and subcutaneous treatment of exopolymers effectively reduced the immunosuppressive changes induced by CPA. Therefore, it is concluded that exopolymers of A. pullulans can be effectively prevent the immunosuppress mediated, at least partially, recruitment of T cells and TNF-alpha+ cells or enhancement of their activity, and can provide effective prevention or treat regimes for the immunosuppress and related diseases such as cancer, sepsis and high-dose chemotherapy or radiotherapy.

High efficient white organic light-emitting diodes using BCzVBi as blue fluorescent dopant.

Efficiency improvement and color optimization of white organic light-emitting diodes (WOLEDs) were achieved via employing blue host DPVBi doped with blue fluorescent, BCzVBi. The structure of high efficient WOLED device was composed of ITO/NPB/DPVBi:BCzVBi-6%/MADN:DCM2-0.5%/Bphen/Liq/Al. WOLED doped by blue fluorescent BCzVBi exhibits 6.19 cd/A of luminous efficiency and 15400 cd/m2 of maximum luminescence. It also performs 480 cd/m2 of luminance at 5.7 V and 15400 cd/m2 at 12.9 V with CIE(x,y) coordinates of (0.33, 0.32) and (0.32, 0.32), respectively. Hole carrier and energy transfer from DPVBi to BCzVBi are proposed to explain the observed phenomena.

Transcriptional profiling of the developmentally important signalling pathways in human embryonic stem cells.

BACKGROUND: Embryonic stem cells (ESC) maintain their 'stemness' by self-renewal. However, the molecular mechanisms underlying self-renewal of human embryonic stem cells (hESC) remain to be elucidated. In this study, expression profiles of the molecules of developmentally important signalling pathways were investigated to better understand the relationships of the signalling pathways for self-renewal in hESC. METHODS: Two human ESC lines were cultured on mouse embryonic fibroblast (MEF) feeder cells. Gene expression was analysed by RT-PCR, real-time RT-PCR and Western blotting. RESULTS: In the bone morphogenetic protein (BMP4), transforming growth factor (TGF-beta) and fibroblast growth factor (FGF4) signalling pathways, ligands and antagonists were highly expressed in hESC compared with human embryoid body (hEB). Human ESC showed abundant transcripts of intracellular molecules in the Wnt, Hh and Notch signalling pathways. No difference was detected in the expression level of the JAK/STAT signalling molecules between hESC and hEB. Western blot analysis showed that the transcriptional levels of the signalling molecules in hESC were consistent with translational levels. From the real-time PCR analysis, expression levels of some genes, such as Oct3/4, Nodal and beta-catenin, were different between two hESC lines. CONCLUSION: The self-renewal of hESC is probably maintained by coordinated regulation of signalling-specific molecules and in a signalling-specific manner.