Multi-class biological tissue classification based on a multi-classifier: Preliminary study of an automatic output power control for ultrasonic surgical units

Electric impedance spectroscopy feature extraction for tissue classification with electrode embedded surgical needles through a modified forward stepwise method

There has been a growing interest in developing electric impedance sensing surgical tools for tissue identification during surgery. A key facet of this development is identifying distinct features that can be used to identify tissues from one another. This paper explores several feature extraction techniques and classification methods applied to electric impedance data. Furthermore, a modified forward stepwise method is proposed. The method introduces a scoring metric to help select features to add to the model, that is based off of the coefficient of variation and overlapping index from the feature's probability density functions for each of the classes. The proposed and existing methods were applied to spectral data measured at 23 frequencies, from 132 samples across 6 different tissues including ex-vivo bovine kidney, liver and muscle, poultry liver, as well as freshly excised canine testicle and ovary samples. These methods were able to successfully find impedance spectra features for the investigated biological tissues. The best predictive accuracy was with Boruta feature extraction and a Random Forest classifier but without significantly reducing the number of features in the classifier model. The proposed method was able to reduce the number of features in the model to an average of 5.8 features for all tested classifiers. These methods may have use in finding features to discriminate other tissue types, possibly to aid in targeting lesions in minimally invasive cancer treatment surgeries.

Depolarization metric spaces for biological tissues classification

Classification of tissues is an important problem in biomedicine. An efficient tissue classification protocol allows, for instance, the guided-recognition of structures through treated images or discriminating between healthy and unhealthy regions (e.g., early detection of cancer). In this framework, we study the potential of some polarimetric metrics, the so-called depolarization spaces, for the classification of biological tissues. The analysis is performed using 120 biological ex vivo samples of three different tissues types. Based on these data collection, we provide for the first time a comparison between these depolarization spaces, as well as with most commonly used depolarization metrics, in terms of biological samples discrimination. The results illustrate the way to determine the set of depolarization metrics which optimizes tissue classification efficiencies. In that sense, the results show the interest of the method which is general, and which can be applied to study multiple types of biological samples, including of course human tissues. The latter can be useful for instance, to improve and to boost applications related to optical biopsy.

Machine learning-based pre-impact fall detection model to discriminate various types of fall

Preimpact fall detection can send alarm service faster to reduce long-lie conditions and decrease the risk of hospitalization. Detecting various types of fall to determine the impact site or direction prior to impact is important because it increases the chance of decreasing the incidence or severity of fall-related injuries. In this study, a robust preimpact fall detection model was developed to classify various activities and falls as multi-class and its performance was compared with the performance of previous developed models. Twelve healthy subjects participated in this study. All subjects were asked to place an inertial measuring unit module by fixing on a belt near the left iliac crest to collect accelerometer data for each activity. Our novel proposed model consists of feature calculation and infinite latent feature selection algorithm, auto labeling of activities, application of machine learning classifiers for discrete and continuous time series data. Nine machine-learning classifiers were applied to detect falls prior to impact and derive final detection results by sorting the classifier. Our model showed the highest classification accuracy. Results for the proposed model that could classify as multi-class showed significantly higher average classification accuracy of 99.57 ± 0.01% for discrete data-based classifiers and 99.84 ± 0.02% for continuous time series-based classifiers than previous models (p < 0.01). In the future, multi-class preimpact fall detection models can be applied to fall protector devices by detecting various activities for sending alerts or immediate feedback reactions to prevent falls.

Improving the ground reaction force prediction accuracy using one-axis plantar pressure: Expansion of input variable for neural network

In this study, we describe a method to predict 6-axis ground reaction forces based solely on plantar pressure (PP) data obtained from insole type measurement devices free of space limitations. Because only vertical force is calculable from PP data, a wavelet neural network derived from a non-linear mapping function was used to obtain 3-axis ground reaction force in medial-lateral (GRF_ML), anterior-posterior (GRF_AP) and vertical (GRF_V) and 3-axis ground reaction moment in sagittal (GRF_S), frontal (GRF_F) and transverse (GRF_T) data for the remaining axes and planes. As the prediction performance of nonlinear models depends strongly on input variables, in this study, three input variables - accumulated PP with respect to time, center of pressure (COP) pattern, and measurements of the opposite foot, which are calculable only with a PP device - were considered in order to improve prediction performance. To conduct this study, the golf swing motions of 80 subjects were characterized as unilateral movement and GRF patterns as functions of individual characteristics. The prediction model was verified with 5-fold cross-validation utilizing the measured values of two force plates. As a result, prediction model (correlation coefficient, r=0.73-0.97) utilized accumulated PP and PP data of the opposite foot and showed the highest prediction accuracy in left-foot GRF_V, GRM_F, GRM_T and right-foot GRF_AP, GRF_ML, GRM_F, GRM_T. Likewise, another prediction model (r=0.83-0.98) utilized accumulated PP and COP patterns as input and showed the best accuracy in left-foot GRF_AP, GRF_ML, GRM_S and right-foot GRF_V, GRM_S. New methods based on the findings of the present study are expected to help resolve problems such as spatial limitation and limited analyzable motions in existing GRF measurement processes.