Deep learning for quantifying spatial patterning and formation process of early differentiated human-induced pluripotent stem cells with micropattern images.

Micropatterning is reliable method for quantifying pluripotency of human-induced pluripotent stem cells (hiPSCs) that differentiate to form a spatial pattern of sorted, ordered and nonoverlapped three germ layers on the micropattern. In this study, we propose a deep learning method to quantify spatial patterning of the germ layers in the early differentiation stage of hiPSCs using micropattern images. We propose decoding and encoding U-net structures learning labelled Hoechst (DNA-stained) hiPSC regions with corresponding Hoechst and bright-field micropattern images to segment hiPSCs on Hoechst or bright-field images. We also propose a U-net structure to extract extraembryonic regions on a micropattern, and an algorithm to compares intensities of the fluorescence images staining respective germ-layer cells and extract their regions. The proposed method thus can quantify the pluripotency of a hiPSC line with spatial patterning including cell numbers, areas and distributions of germ-layer and extraembryonic cells on a micropattern, and reveal the formation process of hiPSCs and germ layers in the early differentiation stage by segmenting live-cell bright-field images. In our assay, the cell-number accuracy achieved 86% and 85%, and the cell region accuracy 89% and 81% for segmenting Hoechst and bright-field micropattern images, respectively. Applications to micropattern images of multiple hiPSC lines, micropattern sizes, groups of markers, living and fixed cells show the proposed method can be expected to be a useful protocol and tool to quantify pluripotency of a new hiPSC line before providing it to the scientific community.

Nuclear condensation and cell cycle arrest induced by telomerase siRNA in neuroblastoma cells.

Neuroblastoma is a type of malignant extracranial tumor that occurs in children. Advanced neuroblastoma, and tumors with MYCN amplification in particular, have poor prognoses. Therefore, it is important to find an effective cure for this disease. Small interfering RNA (siRNA) disrupts gene function by specifically binding to target mRNA. In this study, we used siRNA against telomerase to treat neuroblastoma, to evaluate any anti-proliferative effect on these cells. We evaluated cell viability by WST-1 assay on neuroblastoma cells treated with or without telomerase siRNA. Nuclear condensation, an indicator for apoptotic cells, was determined by DAPI labeling following siRNA treatment. The effectiveness of telomerase siRNA on altering the neuroblastoma cell cycle was detected by flow cytometry. Our results indicated that telomerase siRNA reduces the viability of neuroblastoma cells and increases the percentage of cells in the cell cycle's sub-G1 phase. We found that telomerase siRNA increases the percentage of condensed DNA in neuroblastoma cells. In conclusion, using siRNA against telomerase could be further developed as a therapy for the treatment of neuroblastoma.

Quantitative Analyses for Early Tempo-spatial Patterning of Differentiated Human Induced Pluripotent Stem Cells on Micropatterns using Time-lapse Bright-field Microscopy Images.

Three germ layer formation on micropatterns are extremely useful for quantitative analysis of hiPSC (human induced pluripotent stem cells) pluripotency. Spatial patterns of stem cells differentiated on the micropatterns will be formed from about 24 hours after differentiation induction and usually quantitated near 48 hours. To delineate the germ layer formation process, temporal changes in spatial patterning of germ layers should be analyzed by noninvasive microscopy. This study proposed a series of image processing methods combined with a U-net automatic segmentation to segment differentiated hiPSCs captured by bright-field microscopy. High segmentation accuracy (83.3%) for the test bright-field images compared with their concurrent Hoechst images (85%) was achieved. Tempo-spatial patterning and formation process of germ layers on the micropatterns can be visualized and quantified by segmenting time-lapse bright-field microscopy images using our method.

Human induced pluripotent stem cell formation and morphology prediction during reprogramming with time-lapse bright-field microscopy images using deep learning methods.

BACKGROUND AND OBJECTIVE: Human induced pluripotent stem cells (hiPSCs) represent an ideal source for patient specific cell-based regenerative medicine; however, efficiency of hiPSC formation from reprogramming cells is low. We use several deep-learning results from time-lapse brightfield microscopy images during culture, to early detect the cells potentially reprogramming into hiPSCs and predict the colony morphology of these cells for improving efficiency of culturing a new hiPSC line. METHODS: Sets of time-lapse bright-field images are taken to track reprogramming process of CD34+ cells biologically identified as just beginning reprogramming. Prior the experiment, 9 classes of templates with distinct cell features clipped from microscopy images at various reprogramming stages are used to train a CNN model. The CNN is then used to classify a microscopy image as probability images of these classes. Probability images of some class are used to train a densely connected convolutional network for extracting regions of this class on a microscopy image. A U-net is trained to segment cells on the time-lapse images in early reprogramming stage during culture. The segmented cells are classified by the extracted regions to count various types of cells appearing in the early reprogramming stage for predicting the identified cells potentially forming hiPSCs. The probability images of hiPSC classes are also used to train a spatiotemporal RNN for predicting the future hiPSC colony morphology of the potential cells. RESULTS: Experimental results show the prediction (before 7 days after of beginning of the reprogramming) achieved 0.8 accuracy, and 66% of the identified cells under different culture conditions, predicted as forming, finally formed hiPSCs. The predicted hiPSC images and extracted colonies on the images show the prediction for future 1.5 days achieved high accuracy of hiPSC colony areas and image similarity. CONCLUSIONS: Our study proposes a method using several deep learning models to efficiently select the reprogramming cells possibly forming hiPSCs and to predict the shapes of growing hiPSC colonies. The proposed method is expected to improve the efficiency when establishing a new hiPSC line culture.

Quantitative Analysis of Differentiation Activity for Mouse Embryonic Stem Cells by Deep Learning for Cell Center Detection using Three-Dimensional Confocal Fluorescence Microscopy Images.

Accurate single cell segmentation provides means to monitor the behavior of single cell within a population of cells. Time-lapse fluorescence images are used to reveal heterogeneous nature of single mouse embryonic stem cell (ESC) colony and monitor fluctuations of the cell states. Automatic quantification of speed and status shifts of the ESCs depends on accurate single cell segmentation that is used to calculate the 3D center of every cell and track this cell for the quantification. This study proposes a new 3D U-net to accurately detect center of each single cell in 3D confocal images. The dimension of input 3D images to the U-net is flexible so that multiple center detections from different image directions can be implemented simultaneously to improve the center detection accuracy. This study showed that our method can improve accuracy for cell center detection and thus the quantification for ESC speeds and status shifts.

Involvement of Smac, p53, and caspase pathways in induction of apoptosis by gossypol in human retinoblastoma cells.

PURPOSE: Retinoblastoma is a malignant tumor of the retina usually occurring in young children. To date, the conventional treatments for retinoblastoma have been enucleation, cryotherapy, external beam radiotherapy, or chemotherapy. Most of these treatments, however, have possible side effects, including blindness, infections, fever, gastrointestinal toxicity, and neurotoxicity. More effective treatments are therefore imperative. Gossypol has been reported as a potential inhibitor of cell proliferation in various types of cancers, such as prostate cancer, breast cancer, leukemia, and lung cancer. This study investigates the possible antiproliferative effect of gossypol on retinoblastoma. METHODS: Human retinoblastoma cells were cultured with various concentrations of gossypol and checked for cell viability with a 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay. Nuclear condensation caused by cell apoptosis was detected by staining retinoblastoma cells with 4',6-diamidino-2-phenylindole (DAPI), counting those with condensed nuclei, and determining the percentage of apoptotic cells. In addition, the stages of apoptosis and phases in cell cycles were examined with flow cytometry. The possible signal transduction pathways involved were examined with a protein array assay and western blot analysis. RESULTS: After incubation, the cell survival rate was significantly lower after treatment with 5, 10, and 20 µM of gossypol. The maximum antisurvival effect of gossypol was observed at 20 µM, and the number of apoptotic cells was higher in the preparations cultured with 10 and 20 µM of gossypol. The results in flow cytometry indicated that at concentrations of 10 and 20 µM, gossypol increased the proportion of early- and late-apoptotic retinoblastoma cells and induced cell arrest of retinoblastoma cells at the same concentrations. This antiproliferative effect was later confirmed by upregulating the expression of death receptor 5 (DR5), caspase 8, caspase 9, caspase 3, cytochrome C, tumor protein 53 (p53), and second mitochondria-derived activator of caspases (Smac) in the signal transduction pathways. CONCLUSIONS: We concluded that gossypol has an antiproliferative effect on retinoblastoma cells.

Combination of nerve blockade and intravenous alfentanil is better than single treatment in relieving postoperative pain.

BACKGROUND/PURPOSE: Multimodal analgesia can improve perioperative analgesia but knowledge of combination protocols is still incomplete. This study was designed to evaluate whether the combination of sciatic nerve blockade (SNB) and intravenous alfentanil (IVA) is more effective than either single treatment in relieving postoperative pain in rats. METHODS: In a plantar incision model, withdrawal thresholds were evaluated by von Frey test before incision as baselines and for 7 days after incision. The animals were randomly allocated into various groups to receive SNB with 1% or 2% lidocaine, IVA of 50 or 150 µg/kg, or combined treatments (SNB 1% + 50 µg/kg IVA or SNB 2% + 150 µg/kg IVA) before incision. The results were compared with those of sham procedures--i.e., injections of peri-sciatic or intravenous saline, or a combination of both. RESULTS: Plantar incision caused postoperative allodynia for 3 days. SNB with 2% lidocaine reduced allodynia at 1 hour, 3 hours, day 1, and day 2, but not at postoperative 5 hours or days 3-7, whereas 150 µg/kg IVA produced short analgesia for only 3 hours after surgery. Neither low-dose SNB nor low-dose IVA had a significant effect. When high-dose SNB and high-dose IVA were combined, a strong antiallodynic effect was shown in an additive manner. No synergism was evidently displayed by the combination. CONCLUSION: Our results indicated that in an incisional pain model, multimodal analgesia is superior to single or no pretreatment; however, the combination of multimodal analgesic treatments should be individually discerned depending on nociceptive types and analgesic mechanisms.

U-net structures for segmentation of single mouse embryonic stem cells using three-dimensional confocal microscopy images.

Cell segmentation at a single cell resolution is required to provide insights for basic biology and application study. However, there are issues of low signal-to-noise ratio, weak fluorescence response, and insufficient resolution along the image stacking direction in 3D confocal images (volume). It has been difficult to segment out single cells from close or contacted cells in a cell volume using image processing methods or together with geometric processing methods. Recently, 3D deep learning methods have been used to avoid tedious parameter settings in the image and geometric processing, but still not easy to segment out close or contacted single cells. This paper proposes a 2D U-net to segment cell regions in high accuracy and computing performance. Better 3D cell images and single cell segmentation for close or contacted cells are achieved by combining a 3D U-net to detect the centers of single cells in the volume.

Prediction of Human Induced Pluripotent Stem Cell Formation Based on Deep Learning Analyses Using Time-lapse Brightfield Microscopy Images.

We use deep learning methods to predict human induced pluripotent stem cell (hiPSC) formation using time-lapse brightfield microscopy images taken from a cell identified as the beginning of entered into the reprogramming process. A U-net is used to segment cells and a CNN is used to classify the segmented cells into eight types of cells during the reprogramming and hiPSC formation based on cellular morphology on the microscopy images. The numbers of respective types of cells in cell clusters before the hiPSC formation stage are used to predict if hiPSC regions can be well formed lately. Experimental results show good prediction by the criteria using the numbers of different cells in the clusters. Time-series images with respective types of classified cells can be used to visualize and quantitatively analyze the growth and transition among dispersed cells not in cell clusters, various types of cells in the clusters before the hiPSC formation stage and hiPSC cells.

High Resolution U-Net for Quantitatively Analyzing Early Spatial Patterning of Human Induced Pluripotent Stem Cells on Micropatterns.

Human induced pluripotent stem cells (hiPSCs) can differentiate into three germ layer cells, i.e. ectoderm, mesoderm and endoderm, on micropatterned chips in highly synchronous and reproducible manners. The cells are confined within the chip, expanding two-dimensionally as almost in the form of monolayer, thus to be ideal for serving quantitative analysis of their pluripotency. We present a new U-Net (MP-UNet) structure for cell segmentation of early spatial patterning of hiPSCs on micropattern chips using Hoechst fluorescence images. In this structure, the encoding/decoding layers can be dynamically adjusted to extract sufficient image features and be flexible to image sizes. Dice and weight loss functions are designed to identify slight difference in low signal-to-noise ratio, high boundary-to-area ratio and compacted cell images. Several sizes of Hoechst images were tested to show MP-UNet can achieve high accuracy in cell regions and number counting for various sizes of micropattern chips, thus to be excellent quantitative tool for early spatial patterning of hiPSCs.

Visualization and quantitative analyses for mouse embryonic stem cell tracking by manipulating hierarchical data structures using time-lapse confocal microscopy images.

We present a cell tracking method for time-lapse confocal microscopy (3D) images that uses dynamic hierarchical data structures to assist cell and colony segmentation and tracking. During the segmentation, the cell and colony numbers and their geometric data are recorded for each 3D image set. In tracking, the colony correspondences between neighboring frames of time-lapse 3D images are first computed using the recorded colony centers. Then, cell correspondences in the correspondent colonies are computed using the recorded cell centers. The examples show the proposed cell tracking method can achieve high tracking accuracy for time-lapse 3D images of undifferentiated but self-renewing mouse embryonic stem (mES) cells where the number and mobility of ES cells in a cell colony may change suddenly by a colony merging or splitting, and cell proliferation or death. The geometric data in the hierarchical data structures also help the visualization and quantitation of the cell shapes and mobility.

Longitudinal changes in the health-related quality of life during the first year after traumatic brain injury.

OBJECTIVE: To track the health-related quality of life (HRQL) at discharge and at 6 and 12 months after a traumatic brain injury (TBI) and examine factors associated with changes in each HRQL domain. DESIGN: Longitudinal cohort study. SETTING: Using codes of the International Classification of Diseases, eligible participants who had a newly diagnosed TBI were identified from discharge records of 4 hospitals in northern Taiwan. Information on the HRQL and injury-related characteristics at the initial and 2 follow-up assessments was collected by extracting medical records and conducting telephone interviews. PARTICIPANTS: Subjects (N=158) participated in the initial assessment, and 147 and 146, respectively, completed the follow-up assessments at 6 and 12 months after injury. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURE: The brief version of the World Health Organization Quality of Life (WHOQOL-BREF) with 4 domains of physical capacity, psychologic well being, social relationships, and environment. RESULTS: Scores on all WHOQOL-BREF domains except social relationships greatly improved over the first 6 months and showed continued improvement at 12 months after injury. The domain scores of the WHOQOL-BREF at discharge were significantly associated with the preinjury HRQL level, marital status, alcohol consumption at the time of injury, Glasgow Outcome Scale (GOS) level, cognition, activities of daily living, social support, and depressive status. However, after adjusting for these baseline differences, only the GOS level and depressive status significantly influenced longitudinal changes in the psychologic and social domains over the 12-month period. Changes in the physical and environmental domains were not significantly associated with any characteristics of the study. CONCLUSIONS: During the first year after a TBI, the magnitude of HRQL recovery differed across different HRQL domains. Many factors may have significant associations with the initial domain scores of HRQL after TBI; however, only a few factors can significantly influence longitudinal changes in the HRQL.

Accurate visual and haptic burring surgery simulation based on a volumetric model.

Burring surgery is mainly implemented for fine or critical structures and widely used in orthopedic, oral and maxillofacial, ENT and neurosurgery departments to delicately cut or polish bones, joints or other tissues. This paper describes a volume manipulation method that extends a voxel with multiple values to represent accurate burred changes on tissue surfaces. Tissue surface reconstruction is implemented for the local burred surface to provide a real-time visual response. A burring force vector for a haptic response is calculated by detecting which parts of a bur contact tissue and summated from tissue removal loads on the contacted parts. A spine surgery example showed that rough surface features by gross cutting or smooth features by fine cutting can be clearly demonstrated and high haptic reality can be achieved by our simulations. The burring surgery simulator with the accurate visual and haptic responses can be an effective rehearsing and training tool.

Prediction for Morphology and States of Stem Cell Colonies using a LSTM Network with Progressive Training Microscopy Images.

We present a new LSTM (P-LSTM: Progressive LSTM) network, aiming to predict morphology and states of cell colonies from time-lapse microscopy images. Apparent short-term changes occur in some types of time-lapse cell images. Therefore, long-term-memory dependent LSTM networks may not predict accurately. The P-LSTM network incorporates the images newly generated from cell imaging progressively into LSTM training to emphasize the LSTM short-term memory and thus improve the prediction accuracy. The new images are input into a buffer to be selected for batch training. For real-time processing, parallel computation is introduced to implement concurrent training and prediction on partitioned images.Two types of stem cell images were used to show effectiveness of the P-LSTM network. One is for tracking of ES cell colonies. The actual and predicted ES cell images possess similar colony areas and the same transitions of colony states (moving, merging or morphology changing), although the predicted colony mergers may delay in several time-steps. The other is for prediction of iPS cell reprogramming from the CD34+ human cord blood cells. The actual and predicted iPS cell images possess high similarity evaluated by the PSNR and SSIM similarity evaluation metrics, indicating the reprogramming iPS cell colony features and morphology can be accurately predicted.

Human Induced Pluripotent Stem Cell Reprogramming Prediction in Microscopy Images using LSTM based RNN.

We present a LSTM (Long Short-Term Memory) based RNN (recurrent neural network) method for predicting human induced Pluripotent Stem (hiPS) cells in the reprogramming process. The method uses a trained LSTM network by time-lapse microscopy images to predict growth and transition of reprogramming processes of CD34+ human cord blood cells into hiPS cells. The prediction can be visualized by output time-series probability images. The growth and transition are thus analyzed quantitatively by region areas of distinct cells emerged during the iPS formation processes. The experimental results show that our LSTM network is a potentially powerful tool to predict the cells at the distinct phases of the reprogramming to hiPS cells. This method should be extremely useful not only for basic biology of iPS cells but also detection of the reprogramming cells that will become genuine hiPS cells even at early stages of hiPS formation. Such predictive power should greatly reduce cost, labor and time required for establishment of the genuine hiPS cells, thereby accelerating the practical use of hiPS cells in regenerative medicine.

Inflammatory mediators of cerebrospinal fluid from patients with spinal cord injury.

BACKGROUND: The guidelines of MP treatment for acute SCI are still under debate. We examined the inflammatory mediators of CSF in patients with SCI and assessed the effect of MP treatment. METHODS: We studied 7 patients with acute SCI at the cervical level and examined the mediators of CSF in patients by cytokine antibody array, ELISA and gelatin zymography. RESULTS: We found that levels of IL-6, IL-8, monocyte chemoattractant protein-1, neutrophil-activating peptide 2, intracellular adhesion molecule-1, soluble Fas, tissue inhibitors of metalloproteinase 1, and matrix metalloproteinases-2 and -9 were upregulated in patients with complete SCI without MP treatment as compared to patients with MP treatments, incomplete SCI, or controls. Nerve growth factor was upregulated in patients with MP treatment. CONCLUSIONS: We suggest that a neuroinflammatory CSF profile after complete SCI could be suppressed with MP treatment via downregulating the expression of various cytokines.

Fingerprint verification on medical image reporting system.

The healthcare industry is recently going through extensive changes, through adoption of robust, interoperable healthcare information technology by means of electronic medical records (EMR). However, a major concern of EMR is adequate confidentiality of the individual records being managed electronically. Multiple access points over an open network like the Internet increases possible patient data interception. The obligation is on healthcare providers to procure information security solutions that do not hamper patient care while still providing the confidentiality of patient information. Medical images are also part of the EMR which need to be protected from unauthorized users. This study integrates the techniques of fingerprint verification, DICOM object, digital signature and digital envelope in order to ensure that access to the hospital Picture Archiving and Communication System (PACS) or radiology information system (RIS) is only by certified parties.

Volume Manipulation Based on 3D Reconstructed Surfaces for Joint Function Evaluation and Surgery Simulation.

In joint surgery, evaluation of the relative positions and angles among joint structures (bones, ligaments, muscle, and cartilages, etc.) in range of motion, lifting and weight bearing of the joint is required. However, current volume visualization techniques provide only static 3D images of anatomic structures in volume data. We propose a method to manipulate (reposition, resize and bend) the joint structures in a volume, by which surgeons can visualize and evaluate the critical positions or angles of the joint structures, and thus plan surgery to correct the morphologic pathology of the joint structures. We also propose a system with a real-time cutting simulation function together with the proposed structure manipulation functions by which surgeons can rehearse and verify joint surgery.

Neuropathic Pain Experiences of Spinal Cord Injury Patients.

BACKGROUND: Neuropathic pain (NP) is a common, severe problem that affects spinal cord injury (SCI) patients. Only SCI patients truly understand the impact and extent of this type of pain. PURPOSE: The aim of this study was to understand the NP experienced by SCI patients and the influence of this type of pain on their daily life. METHOD: A qualitative design was used. An interview guide including a semistructured questionnaire and in-depth interviews was conducted with SCI patients with NP in a neurorehabilitation department at a medical center in northern Taiwan. The data were collected using a purposive sampling method. Content analysis was performed on the interview data, which were obtained from 13 SCI patients with NP. RESULTS: Three themes and eight subthemes were identified that described the NP experience of the participants and the influence of NP on their daily life. The three themes included elusive pain (changing and individual pain sensations, erratically haunting threat, and phantom limb sensations), complicated feelings about pain (converting depression into an active attitude toward life, having feelings of anticipation and anxiety about future pain relief, and facing and experiencing pain), and renewed hope (bravely fighting pain and seeking pain relief methods). CONCLUSIONS: This study revealed three important themes of NP experienced by SCI patients, including elusive pain, complicated feelings about pain, and renewed hope. Nurses should understand the nature of NP, provide a thorough pain assessment, and design a proper pain management plan to care effectively for patients with NP.

The Clinical Predictors of Shunt-Dependent Hydrocephalus Following Aneurysmal Subarachnoid Hemorrhage.

AIM: Shunt-dependent hydrocephalus (SDH) is a relatively common complication following aneurysmal subarachnoid hemorrhage (aSAH). Delay in diagnosis and treatment may worsen neurological outcome. This study was conducted to identify early clinical factors associated with SDH following aSAH. MATERIAL AND METHODS: Patients diagnosed with aSAH at our hospital from January 2010 through July 2014 were included. Patients aged ? 18 or ? 90 years, with concurrent arteriovenous malformation, treated with both clipping and coiling, or not receiving definitive treatment were excluded. Both clinical and radiological variables were analyzed by univariate and multivariate logistic model to identify factors independently associated with outcome of SDH following aSAH. RESULTS: Overall, 33 patients (36.2%) developed SDH following aSAH after definitive treatment. Univariate analysis revealed age, emergency department (ED) white blood cell (WBC) count, hypernatremia, Hunt & Hess Grade, modified Fisher"s Grade, presentation of acute hydrocephalus, initial placement of external ventriculostomy, and post-operative central nervous system infection were clinically significant factors. Multivariate logistic regression showed ED WBC count > 14,500/?L (OR 5.096, 95% CI 1.332 to 19.499, p=0.017), poor Hunt&Hess Grade (III, IV & V) (OR 3.562, 95% CI 1.081 to 11.737, p=0.037), and initial placement of external ventriculostomy (OR 4.294, 95% CI 1.125 to 16.393, p=0.033) were independent factors. < p < CONCLUSION: Three early independent predictors of SDH were identified including poor Hunt&Hess Grade, initial placement of external ventriculostomy and ED leukocytosis. Early placement of a ventricular-peritoneal shunt after aSAH may shorten length of stay in hospital and in intensive care unit.