Annotation-free glioma grading from pathological images using ensemble deep learning.

Glioma grading is critical for treatment selection, and the fine classification between glioma grades II and III is still a pathological challenge. Traditional systems based on a single deep learning (DL) model can only show relatively low accuracy in distinguishing glioma grades II and III. Introducing ensemble DL models by combining DL and ensemble learning techniques, we achieved annotation-free glioma grading (grade II or III) from pathological images. We established multiple tile-level DL models using residual network ResNet-18 architecture and then used DL models as component classifiers to develop ensemble DL models to achieve patient-level glioma grading. Whole-slide images of 507 subjects with low-grade glioma (LGG) from the Cancer Genome Atlas (TCGA) were included. The 30 DL models exhibited an average area under the curve (AUC) of 0.7991 in patient-level glioma grading. Single DL models showed large variation, and the median between-model cosine similarity was 0.9524, significantly smaller than the threshold of 1.0. The ensemble model based on logistic regression (LR) methods with a 14-component DL classifier (LR-14) demonstrated a mean patient-level accuracy and AUC of 0.8011 and 0.8945, respectively. Our proposed LR-14 ensemble DL model achieved state-of-the-art performance in glioma grade II and III classifications based on unannotated pathological images.

Noninvasive Tracking of Every Individual in Unmarked Mouse Groups Using Multi-Camera Fusion and Deep Learning.

Accurate and efficient methods for identifying and tracking each animal in a group are needed to study complex behaviors and social interactions. Traditional tracking methods (e.g., marking each animal with dye or surgically implanting microchips) can be invasive and may have an impact on the social behavior being measured. To overcome these shortcomings, video-based methods for tracking unmarked animals, such as fruit flies and zebrafish, have been developed. However, tracking individual mice in a group remains a challenging problem because of their flexible body and complicated interaction patterns. In this study, we report the development of a multi-object tracker for mice that uses the Faster region-based convolutional neural network (R-CNN) deep learning algorithm with geometric transformations in combination with multi-camera/multi-image fusion technology. The system successfully tracked every individual in groups of unmarked mice and was applied to investigate chasing behavior. The proposed system constitutes a step forward in the noninvasive tracking of individual mice engaged in social behavior.

Restoration of FMRP expression in adult V1 neurons rescues visual deficits in a mouse model of fragile X syndrome.

Many people affected by fragile X syndrome (FXS) and autism spectrum disorders have sensory processing deficits, such as hypersensitivity to auditory, tactile, and visual stimuli. Like FXS in humans, loss of Fmr1 in rodents also cause sensory, behavioral, and cognitive deficits. However, the neural mechanisms underlying sensory impairment, especially vision impairment, remain unclear. It remains elusive whether the visual processing deficits originate from corrupted inputs, impaired perception in the primary sensory cortex, or altered integration in the higher cortex, and there is no effective treatment. In this study, we used a genetic knockout mouse model (Fmr1KO), in vivo imaging, and behavioral measurements to show that the loss of Fmr1 impaired signal processing in the primary visual cortex (V1). Specifically, Fmr1KO mice showed enhanced responses to low-intensity stimuli but normal responses to high-intensity stimuli. This abnormality was accompanied by enhancements in local network connectivity in V1 microcircuits and increased dendritic complexity of V1 neurons. These effects were ameliorated by the acute application of GABAA receptor activators, which enhanced the activity of inhibitory neurons, or by reintroducing Fmr1 gene expression in knockout V1 neurons in both juvenile and young-adult mice. Overall, V1 plays an important role in the visual abnormalities of Fmr1KO mice and it could be possible to rescue the sensory disturbances in developed FXS and autism patients.

Development and validation of a deep learning system for ascites cytopathology interpretation.

BACKGROUND: Early diagnosis of Peritoneal metastasis (PM) is clinically significant regarding optimal treatment selection and avoidance of unnecessary surgical procedures. Cytopathology plays an important role in early screening of PM. We aimed to develop a deep learning (DL) system to achieve intelligent cytopathology interpretation, especially in ascites cytopathology. METHODS: The original ascites cytopathology image dataset consists of 139 patients' original hematoxylin-eosin (HE) and Papanicolaou (PAP) Staining images. DL system was developed using transfer learning (TL) to achieve cell detection and classification. Pre-trained alexnet, vgg16, goolenet, resnet18 and resnet50 models were studied. Cell detection dataset consists of 176 cropped images with 6573 annotated cell bounding boxes. Cell classification data set consists of 487 cropped images with 18,558 and 6089 annotated malignant and benign cells in total, respectively. RESULTS: We established a novel ascites cytopathology image dataset and achieved automatically cell detection and classification. DetectionNet based on Faster R-CNN using pre-trained resnet18 achieved cell detection with 87.22% of cells' Intersection of Union (IoU) bigger than the threshold of 0.5. The mean average precision (mAP) was 0.8316. The ClassificationNet based on resnet50 achieved the greatest performance in cell classification with AUC = 0.8851, Precision = 96.80%, FNR = 4.73%. The DL system integrating the separately trained DetectionNet and Classificationnet showed great performance in the cytopathology image interpretation. CONCLUSIONS: We demonstrate that the integration of DL can improve the efficiency of healthcare. The DL system we developed using TL techniques achieved accurate cytopathology interpretation, and had great potential to be integrated into clinician workflow.

Efficient implementation of convolutional neural networks in the data processing of two-photon in vivo imaging.

MOTIVATION: Functional imaging at single-neuron resolution offers a highly efficient tool for studying the functional connectomics in the brain. However, mainstream neuron-detection methods focus on either the morphologies or activities of neurons, which may lead to the extraction of incomplete information and which may heavily rely on the experience of the experimenters. RESULTS: We developed a convolutional neural networks and fluctuation method-based toolbox (ImageCN) to increase the processing power of calcium imaging data. To evaluate the performance of ImageCN, nine different imaging datasets were recorded from awake mouse brains. ImageCN demonstrated superior neuron-detection performance when compared with other algorithms. Furthermore, ImageCN does not require sophisticated training for users. AVAILABILITY AND IMPLEMENTATION: ImageCN is implemented in MATLAB. The source code and documentation are available at https://github.com/ZhangChenLab/ImageCN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A Normal Sensor Calibration Method Based on an Extended Kalman Filter for Robotic Drilling.

To enhance the perpendicularity accuracy in the robotic drilling system, a normal sensor calibration method is proposed to identify the errors of the zero point and laser beam direction of laser displacement sensors simultaneously. The procedure of normal adjustment of the robotic drilling system is introduced firstly. Next the measurement model of the zero point and laser beam direction on a datum plane is constructed based on the principle of the distance measurement for laser displacement sensors. An extended Kalman filter algorithm is used to identify the sensor errors. Then the surface normal measurement and attitude adjustments are presented to ensure that the axis of the drill bit coincides with the normal at drilling point. Finally, simulations are conducted to study the performance of the proposed calibration method and experiments are carried out on a robotic drilling system. The simulation and experimental results show that the perpendicularity of the hole is within 0.2°. They also demonstrate that the proposed calibration method has high accuracy of parameter identification and lays a basis for high-precision perpendicularity accuracy of drilling in the robotic drilling system.

An Excitatory Neural Assembly Encodes Short-Term Memory in the Prefrontal Cortex.

Short-term memory (STM) is crucial for animals to hold information for a small period of time. Persistent or recurrent neural activity, together with neural oscillations, is known to encode the STM at the cellular level. However, the coding mechanisms at the microcircuitry level remain a mystery. Here, we performed two-photon imaging on behaving mice to monitor the activity of neuronal microcircuitry. We discovered a neuronal subpopulation in the medial prefrontal cortex (mPFC) that exhibited emergent properties in a context-dependent manner underlying a STM-like behavior paradigm. These neuronal subpopulations exclusively comprise excitatory neurons and mainly represent a group of neurons with stronger functional connections. Microcircuitry plasticity was maintained for minutes and was absent in an animal model of Alzheimer's disease (AD). Thus, these results point to a functional coding mechanism that relies on the emergent behavior of a functionally defined neuronal assembly to encode STM.

The superior fault tolerance of artificial neural network training with a fault/noise injection-based genetic algorithm.

Artificial neural networks (ANNs) are powerful computational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance (FT), an important property of ANNs, ensures their reliability when significant portions of a network are lost. In this paper, a fault/noise injection-based (FIB) genetic algorithm (GA) is proposed to construct fault-tolerant ANNs. The FT performance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algorithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR (XOR) problem and the overlapping classification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.