Machine learning-assisted image label-free smartphone platform for rapid segmentation and robust multi-urinalysis.

This study presents a groundbreaking approach for the early detection of chronic kidney disease (CKD) and other urological disorders through an image-label-free, multi-dipstick identification method, eliminating the need for complex machinery, label libraries, or preset coordinates. Our research successfully identified reaction pads on 187 multi-dipsticks, each with 11 pads, leveraging machine learning algorithms trained on human urine data. This technique aims to surpass traditional colourimetric methods and concentration-colour curve fitting, offering more robust and precise community screening and home monitoring capabilities. The developed algorithms enhance the generalizability of machine learning models by extracting primary colours and correcting urine colours on each reaction pad. This method's cost-effectiveness and portability are significant, as it requires no additional equipment beyond a standard smartphone. The system's performance rivals professional medical equipment without auxiliary lighting or flash under regular indoor light conditions, effectively managing false positives and negatives across various categories with remarkable accuracy. In a controlled experimental setting, we found that random forest algorithms, based on a Bagging strategy and applied in the HSV colour space, showed optimal results in smartphone-assisted urinalysis. This study also introduces a novel urine colour correction method, significantly improving machine learning model performance. Additionally, ISO parameters were identified as crucial factors influencing the accuracy of smartphone-based urinalysis in the absence of additional lighting or optical configurations, highlighting the potential of this technology in low-resource settings.

[Design of training system for foot ulcer patients based on three axis accelerometer].

The paper introduces a training system for foot ulcer patients based on three axis accelerometer, which uses three axis accelerometer and Apple mobile phone platform to guide foot ulcer patients to carry out a variety of lower limb muscle tissues training. The acceleration values of three directions for the foot training is obtained by analog-to-digital conversion and transmitted to the Apple mobile phone via its Bluetooth low energy. The Apple mobile phone accomplishes acceleration data preprocessing, numerical filtering and adaptive dual-threshold processing by our developed application program, so as to achieve the purpose of foot gesture recognition. The experimental result shows that the design can effectively present the training situation and effect of patients, encourage patients to adhere to the training, and provide some reference data for doctors and patients.

[System Design of a Medical Constnt Temperature Flushing Pump].

The flushing pump which is applied to clean operative wound has no temperature controlling function up to now, and doctors have to prepare the flushing fluid that has previously been warmed. The flushing pump system with medical constant temperature designed in our laboratory can absorb flushing fluid at the room temperature, and then eject flushing fluid with the temperature in accordance with the requirements of operations at a controlled constant flow rate. The system combines flow rate control with temperature control functions. The flushing pump system includes flushing part, temperature controlling part, key inputting part, liquid crystal displaying part and exceptional situation monitoring part. The present paper introduces the design method and principle of each part of the system at first, and then gives the debug method of all the system parameters. Finally the paper discusses the performance of the system according to the result of the experiment.

[Research on data acquisition of portable uroflowmeter and accuracy of measurement].

This paper presents the preliminary design of data acquisition system of a portable uroflowmeter. The system uses double-hole cantilever pressure sensor. The signal is transferred to ATmega644PA microprogrammed control unit (MCU), converted by A/D (analog to digital) convertor. Then the further data are processed and get the corresponding relationship of weight-time and two curves of urine flow and urinary flow rate. In the measurement accuracy of the device about urine flow, two factors about the placement and height of the data acquisition are analyzed to show the accuracy of the equipment through the Origin 8.0 data analysis software. The design is characterized by low cost and high speed of data collection, real-time, high accuracy.

[Design of the temperature control system for the thermostatic medical infusion pump].

In surgery operations, wound should be cleaned with warm sterilized saline solution. In order to reach rapidly warming the washing solution from the room temperature during the surgery, we designed a thermostatic medical infusion pump. The present paper mainly presents researches on the two temperature control methods in the standby mode and in the flushing mode of the system. In the standby mode, the traditional proportional-integral-derivative (PID) control algorithm was adopted. In the flushing mode, dynamic characteristics of the system was changed in real time, which made the thermostatic control process more complex, and the fitted control function combined with the PID control algorithm was adopted in this mode. The temperature control parameters were adjusted in real time according to the initial temperature and the flow rate of the washing solution to obtain a constant temperature of the washing solution, no matter how the initial temperature and the flow rate are changed. The experiment results showed that this kind of control system performed well with a high accuracy.

A ToF-based system for recording human sagittal back shape.

BACKGROUND: The sagittal back shape (SBS) of the human body, which should be highly consistent with the spinal morphology along the internal spine line, also presents an s-shaped curve. OBJECTIVE: We propose a novel time-of-flight (ToF) based system to record the s-shaped SBS of the human body, which was simple, inexpensive, and non-invasive. RESULTS: The system was composed of a bottom plate, an upright post, a vertical rod, dozens of horizontal measuring rods, and a ToF sensor. The experimental results showed that the system supported to obtain the s-shaped SBS of the human body with satisfactory accuracy. CONCLUSIONS: The ToF-based system for recording human sagittal back shape will be useful for routine screening of spinal physiological conditions in schools, as well as for e.g. digital garment design, and special seat-back design.

Research on a physical activity tracking system based upon three-axis accelerometer for patients with leg ulcers.

Venous leg ulcerations are a common problem, with high prevalence in the middle-aged and elderly population, and more attention on research of their physical activities has been paid, as they have great effects on the blood circulation of the lower limb. With enough, appropriate training, the chronic venous ulcerations in the lower limb can be avoided and alleviated, and venous hypertension can be reduced effectively. The study deals with a physical activity tracking system for the patients based on a three-axis accelerometer. The system uses a three-axis accelerometer, a microcontroller, and a wireless Bluetooth module to form a data acquisition platform to acquire accelerations of the lower limb movement, and sends it to a smart mobile phone via the wireless Bluetooth module. The system takes advantages of the smart mobile phone to guide the chronic venous leg ulcers to do prescribed rehabilitation exercises for the lower limb muscles, perform acceleration data preprocessing, wavelet transform and reconstruction, denoising and feature extraction, obtain the results of the rehabilitation exercises, and then give reasonable evaluation and judgment. It is helpful to treat underlying venous reflux, create such an environment that allows skin to grow across an ulcer, and accelerate ulcer healing process consequently.

Adaptive subject-based feature extraction in brain-computer interfaces using wavelet packet best basis decomposition.

In this paper we discuss a subject-based feature extraction method using wavelet packet best basis decomposition (WPBBD) in brain-computer interfaces (BCIs). The idea is to employ the wavelet packet best basis algorithm to adapt to each subject separately. Firstly, original electroencephalogram (EEG) signals are decomposed to a given level by wavelet packet transform. Secondly, for each subject, the best basis algorithm is used to find the best-adapted basis for that particular subject. Finally, subband energies contained in the best basis are used as effective features. Adaptive and specific features of a subject are so obtained. Three different motor imagery tasks of six subjects are discriminated using the above features. Experiment results show that the subject-based adaptation method yields significantly higher classification performance than the non-subject-based adaptation and non-adaptive approaches.

[Long-range correlations in human colonic pressure activity].

Using the method of detrended fluctuation analysis (DFA) and power spectral analysis (PSA), the paper deals with the characteristics of long-range correlations of colonic pressure activities and their surrogate data of healthy subjects. The DFA is a period representation of such correlations, whereas the PSA is a frequency representation. The analysis of the two methods consistently shows that there are long memories in colonic pressure activities and there exist long-range correlations, whereas there are no such long memories and long-range correlations in the surrogate data, whose sequential orders are randomly shuffled. The results to some extent indicate that human colonic pressure activities with normal motilities do have long memories, but these memories may be weaker or may even be destroyed with dysmotilities.

Feature extraction for EEG-based brain-computer interfaces by wavelet packet best basis decomposition.

A method based on wavelet packet best basis decomposition (WPBBD) is investigated for the purpose of extracting features of electroencephalogram signals produced during motor imagery tasks in brain-computer interfaces. The method includes the following three steps. (1) Original signals are decomposed by wavelet packet transform (WPT) and a wavelet packet library can be formed. (2) The best basis for classification is selected from the library. (3) Subband energies included in the best basis are used as effective features. Three different motor imagery tasks are discriminated using the features. The WPBBD produces a 70.3% classification accuracy, which is 4.2% higher than that of the existing wavelet packet method.

Phase coupling analysis of gastric pressure activity via wavelet packet based diagonal slice spectra.

We propose a new analysis method to detect quadratic phase coupling (QPC) behavior of human gastric interdigestive pressure activity that has been acquired by a telemetric capsule-like mini-robot. The method is referred to as diagonal slice spectra. They are the Fourier transforms of the diagonal slices of the triple correlations, and can actually detect the phase coupling and coupled components respectively by expanding the real process into the complex counterpart through Hilbert transform. In order to learn more about the QPC structure in a certain frequency band that we are mostly interested in and obtain a higher frequency resolution, the method, named the wavelet packet based diagonal slice spectrum, is introduced. It shows that the nonlinear QPC behavior occurs during gastric contractions (phase II), whereas no distinct phase coupling occurs during gastric motor quiescence (phase I). It is the nonlinear cell-to-cell coupling mechanisms, existence of fast and slow waves and their interactions that nonlinear QPC structure of the gastric pressure activity occurs.

[A review of brain-computer interfaces (BCIs)].

This paper introduces the general constitutions and principle of BCI systems. In addition, some characteristics and limitations of different research methods are discussed and compared. Finally, this paper points out the existing problems and future trends of BCIs. brain-computer interface (BCI), human-computer Interface (HCI), electroencephalography (EEG).

Nonlinear fractal dynamics of human colonic pressure activity based upon the box-counting method.

The computational fractal dimension of human colonic pressure activity acquired by a telemetric capsule robot under normal physiological conditions was studied using the box-counting method. The fractal dimension is a numeric value that quantifies to measure how rough the signal is from nonlinear dynamics, rather than its amplitude or other linear statistical features. The colonic pressure activities from the healthy subject during three typical periods were analysed. The results showed that the activity might be fractal with a non-integer fractal dimension after it being integrated over time using the cumsum method, which was never revealed before. Moreover, the activity (after it being integrated) acquired soon after wakening up was the roughest (also the most complex one) with the largest fractal dimension, closely followed by that acquired during sleep with that acquired long time after awakening up (in the daytime) ranking third with the smallest fractal dimension. Fractal estimation might provide a new method to learn the nonlinear dynamics of human gastrointestinal pressure recordings.

Correction method for wireless electromagnetic localization of microcapsule devices.

BACKGROUND: In the development of a telemetry localization system for wireless tracking of a microcapsule medical device based on alternating current magnetic fields, further improvements are required in terms of localization accuracy and reductions in systematic error. METHODS: A new correction method is proposed based on an improved neural network algorithm for wireless localization. Based on the wireless localization model and its prototype, a single neural network with five input and five output neurons was designed for correction. Because the position and attitude angle are defined on different domains, both the input and output variables were normalized to improve network convergence. To prevent overfitting, the Levenberg-Marquardt Bayesian regularization algorithm was used as an effective learning algorithm for the neural network. RESULTS: Through experimental testing, the tracked and true locations were obtained, and the effects of neural network correction on improving localization accuracy were assessed. The experiments demonstrated reductions in localization errors when using the improved neural network correction algorithm. After correction, average errors of the X, Y, Z, α, and ß components reduced to 8.1 mm, 9.3 mm, 7.2 mm, 0.075 rad, and 0.071 rad, respectively. CONCLUSIONS: Compared with the basic back propagation algorithm, the Levenberg-Marquardt Bayesian regularization algorithm effectively improves the generalizability and convergence accuracy of neural networks in wireless localization correction. In addition, this method provides a feasible solution for improving the accuracy when wirelessly tracking a microcapsule device.

Reconstruction and visualization of human gastrointestinal tract.

BACKGROUND: Converting the two-dimensional (2D) cross-sectional photographs into an intuitive three-dimensional (3D) model is a basic task for medical imaging data for auxiliary disease-linked diagnosis purpose. METHODS: Reconstruction and visualization process of gastrointestinal cross-sectional photographs includes image preparation, image registration, image segmentation, 3D surface-rendering reconstruction, and implementation of 3D digital visualization. RESULTS: Using the visualization toolkit (VTK), we implemented 3D digital reconstruction and visualization of gastrointestinal tract, whose visualized model can be zoomed, paned, and rotated, including the stomach, the small intestine, and the large intestine.

Detecting Phase Coupling of Gastric Interdigestive Pressure Activity via Diagonal Slice Spectra.

We propose a new analysis method to detect phase coupling behaviour of the human gastric interdigestive pressure wave that has been acquired by a telemetric capsule-like mini-robot. The method is referred to as diagonal slice spectra, which are the Fourier transforms of the diagonal slices of the triple correlation and can detect the phase coupling and coupled components respectively. It is shown that nonlinear quadratic phase coupling occurs during gastric contraction (phase II), whereas no distinct phase coupling occurs during gastric motor quiescence (phase I).