Deep learning-based photodamage reduction on harmonic generation microscope at low-level optical power.

The trade-off between high-quality images and cellular health in optical bioimaging is a crucial problem. We demonstrated a deep-learning-based power-enhancement (PE) model in a harmonic generation microscope (HGM), including second harmonic generation (SHG) and third harmonic generation (THG). Our model can predict high-power HGM images from low-power images, greatly reducing the risk of phototoxicity and photodamage. Furthermore, the PE model trained only on normal skin data can also be used to predict abnormal skin data, enabling the dermatopathologist to successfully identify and label cancer cells. The PE model shows potential for in-vivo and ex-vivo HGM imaging.

RepE: unsupervised representation learning for image enhancement in nonlinear optical microscopy.

We present an unsupervised learning denoising method, RepE (representation and enhancement), designed for nonlinear optical microscopy images, such as second harmonic generation (SHG) and two-photon fluorescence (TPEF). Addressing the challenge of effectively denoising images with various noise types, RepE employs an encoder network to learn noise-free representations and a reconstruction network to generate denoised images. It offers several key advantages, including its ability to (i) operate without restrictive statistic assumptions, (ii) eliminate the need for clean-noisy pairs, and (iii) requires only a few training images. Comparative evaluations on real-world SHG and TPEF images from esophageal cancer tissue slides (ESCC) demonstrate that our method outperforms existing techniques in image quality metrics. The proposed method provides a practical, robust solution for denoising nonlinear optical microscopy images, and it has the potential to be extended to other nonlinear optical microscopy modalities.

Novel Record Replacement Algorithm and Architecture for QoS Management over Local Area Networks.

An effective System-on-Chip (SoC) for smart Quality-of-Service (QoS) management over a virtual local area network (LAN) is presented in this study. The SoC is implemented by field programmable gate array (FPGA) for accelerating the delivery quality prediction for a service. The quality prediction is carried out by the general regression neural network (GRNN) algorithm based on a time-varying profile consisting of the past delivery records of the service. A novel record replacement algorithm is presented to update the profile, so that the bandwidth usage of the service can be effectively tracked by GRNN. Experimental results show that the SoC provides self-aware QoS management with low computation costs for applications over virtual LAN.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework.

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R 2 = 0.88; support vector regression, MAE = 4.42 years, R 2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R 2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Continuous Finger Gesture Recognition Based on Flex Sensors.

The goal of this work is to present a novel continuous finger gesture recognition system based on flex sensors. The system is able to carry out accurate recognition of a sequence of gestures. Wireless smart gloves equipped with flex sensors were implemented for the collection of the training and testing sets. Given the sensory data acquired from the smart gloves, the gated recurrent unit (GRU) algorithm was then adopted for gesture spotting. During the training process for the GRU, the movements associated with different fingers and the transitions between two successive gestures were taken into consideration. On the basis of the gesture spotting results, the maximum a posteriori (MAP) estimation was carried out for the final gesture classification. Because of the effectiveness of the proposed spotting scheme, accurate gesture recognition was achieved even for complicated transitions between successive gestures. From the experimental results, it can be observed that the proposed system is an effective alternative for robust recognition of a sequence of finger gestures.