REC-NN: A reconstruction error compensation neural network for Magnetic Resonance Electrical Property Tomography (MREPT).

Electrical properties (EPs) are expected as biomarkers for early cancer detection. Magnetic resonance electrical properties tomography (MREPT) is a technique to non-invasively estimate the EPs of tissues from MRI measurements. While noise sensitivity and artifact problems of MREPT are being solved progressively through recent efforts, the loss of tissue contrast emerges as an obstacle to the clinical applications of MREPT. To solve the problem, we propose a reconstruction error compensation neural network scheme (REC-NN) for a typical analytic MREPT method, Stab-EPT. Two NN structures: one with only ResNet blocks, and the other hybridizing ResNet blocks with an encoder-decoder structure. Results of experiments with digital brain phantoms show that, compared with Stab-EPT, and conventional NN based reconstruction, REC-NN improves both reconstruction accuracy and tissue contrast. It is found that, the encoder-decoder structure could improve the compensation accuracy of EPs in homogeneous region but showed worse reconstruction than only ResNet structure for tumorous tissues unseen in the training samples. Future research is required to address overcompensation problems, optimization of NN structure and application to clinical data.

Physics Informed Neural Networks (PINN) for Low Snr Magnetic Resonance Electrical Properties Tomography (MREPT).

Electrical properties (EPs) of tissues facilitate early detection of cancerous tissues. Magnetic resonance electrical properties tomography (MREPT) is a technique to non-invasively probe the EPs of tissues from MRI measurements. Most MREPT methods rely on numerical differentiation (ND) to solve partial differential Equations (PDEs) to reconstruct the EPs. However, they are not practical for clinical data because ND is noise sensitive and the MRI measurements for MREPT are noisy in nature. Recently, Physics informed neural networks (PINNs) have been introduced to solve PDEs by substituting ND with automatic differentiation (AD). To the best of our knowledge, it has not been applied to MREPT due to the challenges in using PINN on MREPT as (i) a PINN requires part of ground-truth EPs as collocation points to optimize the network's AD, (ii) the noisy input data disrupts the optimization of PINNs despite the noise-filtering nature of NNs and additional denoising processes. In this work, we propose a PINN-MREPT model based on a canonical analytic MREPT model. A reference padding layer with known EPs was added to surround the region of interest for providing additive collocation points. Moreover, an optimizable diffusion coefficient was embedded in the analytic MREPT model used in the PINN-MREPT. The noise robustness of the proposed PINN-MREPT for single-sample reconstruction was tested by using numerical phantoms of human brain with extra tumor-like tissues at different noise levels. The results of numerical experiments show that PINN-MREPT outperforms two typical numerical MREPT methods in terms of reconstruction accuracy, sensitivity to the extra tissues, and the correlations of line profiles in the regions of interest. The advantage of the PINN-MREPT is shown by the results of an experiment on phantom measurement, too. Moreover, it is found that the diffusion term plays an important role to achieve a noise-robust PINN-MREPT. This is an important step moving forward to a clinical application of MREPT.

Physics-Coupled Neural Network Magnetic Resonance Electrical Property Tomography (MREPT) for Conductivity Reconstruction.

The electrical property (EP) of human tissues is a quantitative biomarker that facilitates early diagnosis of cancerous tissues. Magnetic resonance electrical properties tomography (MREPT) is an imaging modality that reconstructs EPs by the radio-frequency field in an MRI system. MREPT reconstructs EPs by solving analytic models numerically based on Maxwell's equations. Most MREPT methods suffer from artifacts caused by inaccuracy of the hypotheses behind the models, and/or numerical errors. These artifacts can be mitigated by adding coefficients to stabilize the models, however, the selection of such coefficient has been empirical, which limit its medical application. Alternatively, end-to-end Neural networks-based MREPT (NN-MREPT) learns to reconstruct the EPs from training samples, circumventing Maxwell's equations. However, due to its pattern-matching nature, it is difficult for NN-MREPT to produce accurate reconstructions for new samples. In this work, we proposed a physics-coupled NN for MREPT (PCNN-MREPT), in which an analytic model, cr-MREPT, works with diffusion and convection coefficients, learned by NNs from the difference between the reconstructed and ground-truth EPs to reduce artifacts. With two simulated datasets, three generalization experiments in which test samples deviate gradually from the training samples, and one noise-robustness experiment were conducted. The results show that the proposed PCNN-MREPT achieves higher accuracy than two representative analytic methods. Moreover, compared with an end-to-end NN-MREPT, the proposed method attained higher accuracy in two critical generalization tests. This is an important step to practical MREPT medical diagnoses.

Investigation on Perceptron Learning for Water Region Estimation Using Large-Scale Multispectral Images.

Land cover classification and investigation of temporal changes are considered to be common applications of remote sensing. Water/non-water region estimation is one of the most fundamental classification tasks, analyzing the occurrence of water on the Earth's surface. However, common remote sensing practices such as thresholding, spectral analysis, and statistical approaches are not sufficient to produce a globally adaptable water classification. The aim of this study is to develop a formula with automatically derived tuning parameters using perceptron neural networks for water/non-water region estimation, which we call the Perceptron-Derived Water Formula (PDWF), using Landsat-8 images. Water/non-water region estimates derived from PDWF were compared with three different approaches-Modified Normalized Difference Water Index (MNDWI), Automatic Water Extraction Index (AWEI), and Deep Convolutional Neural Network-using various case studies. Our proposed method outperforms all three approaches, showing a significant improvement in water/non-water region estimation. PDWF performance is consistently better even in cases of challenging conditions such as low reflectance due to hill shadows, building-shadows, and dark soils. Moreover, our study implemented a sunglint correction to adapt water/non-water region estimation over sunglint-affected pixels.

Evaluation of a Home Biomonitoring Autonomous Mobile Robot.

Increasing population age demands more services in healthcare domain. It has been shown that mobile robots could be a potential solution to home biomonitoring for the elderly. Through our previous studies, a mobile robot system that is able to track a subject and identify his daily living activities has been developed. However, the system has not been tested in any home living scenarios. In this study we did a series of experiments to investigate the accuracy of activity recognition of the mobile robot in a home living scenario. The daily activities tested in the evaluation experiment include watching TV and sleeping. A dataset recorded by a distributed distance-measuring sensor network was used as a reference to the activity recognition results. It was shown that the accuracy is not consistent for all the activities; that is, mobile robot could achieve a high success rate in some activities but a poor success rate in others. It was found that the observation position of the mobile robot and subject surroundings have high impact on the accuracy of the activity recognition, due to the variability of the home living daily activities and their transitional process. The possibility of improvement of recognition accuracy has been shown too.

Development of robust behaviour recognition for an at-home biomonitoring robot with assistance of subject localization and enhanced visual tracking.

Our research is focused on the development of an at-home health care biomonitoring mobile robot for the people in demand. Main task of the robot is to detect and track a designated subject while recognizing his/her activity for analysis and to provide warning in an emergency. In order to push forward the system towards its real application, in this study, we tested the robustness of the robot system with several major environment changes, control parameter changes, and subject variation. First, an improved color tracker was analyzed to find out the limitations and constraints of the robot visual tracking considering the suitable illumination values and tracking distance intervals. Then, regarding subject safety and continuous robot based subject tracking, various control parameters were tested on different layouts in a room. Finally, the main objective of the system is to find out walking activities for different patterns for further analysis. Therefore, we proposed a fast, simple, and person specific new activity recognition model by making full use of localization information, which is robust to partial occlusion. The proposed activity recognition algorithm was tested on different walking patterns with different subjects, and the results showed high recognition accuracy.

Ultrasound imaging and semi-automatic analysis of active muscle features in electrical stimulation by optical flow.

Ultrasound imaging is an effective way to measure the muscle activity in electrical stimulation studies. However, it is a time consuming task to manually measure pennation angle and muscle thickness, which are the benchmark features to analyze muscle activity from the ultrasound imaging. In previous studies, the muscle features were measured by calculating optical flow of the pennation angle by using only fibers of a muscle from the ultrasound, without carefully considering moving muscle edges during active and passive contraction. Therefore, this study aimed to measure the pennation angle and muscle thickness by using the edges and fibers of a muscle in a quantitative way in a semi-automatic optical flow based approach. The results of the semi-automatic analysis were compared to that of manual measurement. Through the comparison, it is clear that the proposed algorithm could achieve higher accuracy in tracking the thickness and pennation angle for a sequence of ultrasound images.

Human body contour data based activity recognition.

This research work is aimed to develop autonomous bio-monitoring mobile robots, which are capable of tracking and measuring patients' motions, recognizing the patients' behavior based on observation data, and providing calling for medical personnel in emergency situations in home environment. The robots to be developed will bring about cost-effective, safe and easier at-home rehabilitation to most motor-function impaired patients (MIPs). In our previous research, a full framework was established towards this research goal. In this research, we aimed at improving the human activity recognition by using contour data of the tracked human subject extracted from the depth images as the signal source, instead of the lower limb joint angle data used in the previous research, which are more likely to be affected by the motion of the robot and human subjects. Several geometric parameters, such as, the ratio of height to weight of the tracked human subject, and distance (pixels) between centroid points of upper and lower parts of human body, were calculated from the contour data, and used as the features for the activity recognition. A Hidden Markov Model (HMM) is employed to classify different human activities from the features. Experimental results showed that the human activity recognition could be achieved with a high correct rate.