Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait.

Diabetic neuropathy (DN) is one of the prevalent forms of neuropathy that involves alterations in biomechanical changes in the human gait. Diabetic foot ulceration (DFU) is one of the pervasive types of complications that arise due to DN. In the literature, for the last 50 years, researchers have been trying to observe the biomechanical changes due to DN and DFU by studying muscle electromyography (EMG) and ground reaction forces (GRF). However, the literature is contradictory. In such a scenario, we propose using Machine learning techniques to identify DN and DFU patients by using EMG and GRF data. We collected a dataset from the literature which involves three patient groups: Control (n = 6), DN (n = 6), and previous history of DFU (n = 9) and collected three lower limb muscles EMG (tibialis anterior (TA), vastus lateralis (VL), gastrocnemius lateralis (GL)), and three GRF components (GRFx, GRFy, and GRFz). Raw EMG and GRF signals were preprocessed, and different feature extraction techniques were applied to extract the best features from the signals. The extracted feature list was ranked using four different feature ranking techniques, and highly correlated features were removed. In this study, we considered different combinations of muscles and GRF components to find the best performing feature list for the identification of DN and DFU. We trained eight different conventional ML models: Discriminant analysis classifier (DAC), Ensemble classification model (ECM), Kernel classification model (KCM), k-nearest neighbor model (KNN), Linear classification model (LCM), Naive Bayes classifier (NBC), Support vector machine classifier (SVM), and Binary decision classification tree (BDC), to find the best-performing algorithm and optimized that model. We trained the optimized the ML algorithm for different combinations of muscles and GRF component features, and the performance matrix was evaluated. Our study found the KNN algorithm performed well in identifying DN and DFU, and we optimized it before training. We found the best accuracy of 96.18% for EMG analysis using the top 22 features from the chi-square feature ranking technique for features from GL and VL muscles combined. In the GRF analysis, the model showed 98.68% accuracy using the top 7 features from the Feature selection using neighborhood component analysis for the feature combinations from the GRFx-GRFz signal. In conclusion, our study has shown a potential solution for ML application in DN and DFU patient identification using EMG and GRF parameters. With careful signal preprocessing with strategic feature extraction from the biomechanical parameters, optimization of the ML model can provide a potential solution in the diagnosis and stratification of DN and DFU patients from the EMG and GRF signals.

Custom Hardware Architectures for Deep Learning on Portable Devices: A Review.

The staggering innovations and emergence of numerous deep learning (DL) applications have forced researchers to reconsider hardware architecture to accommodate fast and efficient application-specific computations. Applications, such as object detection, image recognition, speech translation, as well as music synthesis and image generation, can be performed with high accuracy at the expense of substantial computational resources using DL. Furthermore, the desire to adopt Industry 4.0 and smart technologies within the Internet of Things infrastructure has initiated several studies to enable on-chip DL capabilities for resource-constrained devices. Specialized DL processors reduce dependence on cloud servers, improve privacy, lessen latency, and mitigate bandwidth congestion. As we reach the limits of shrinking transistors, researchers are exploring various application-specific hardware architectures to meet the performance and efficiency requirements for DL tasks. Over the past few years, several software optimizations and hardware innovations have been proposed to efficiently perform these computations. In this article, we review several DL accelerators, as well as technologies with emerging devices, to highlight their architectural features in application-specific integrated circuit (IC) and field-programmable gate array (FPGA) platforms. Finally, the design considerations for DL hardware in portable applications have been discussed, along with some deductions about the future trends and potential research directions to innovate DL accelerator architectures further. By compiling this review, we expect to help aspiring researchers widen their knowledge in custom hardware architectures for DL.

Brain MR Image Enhancement for Tumor Segmentation Using 3D U-Net.

MRI images are visually inspected by domain experts for the analysis and quantification of the tumorous tissues. Due to the large volumetric data, manual reporting on the images is subjective, cumbersome, and error prone. To address these problems, automatic image analysis tools are employed for tumor segmentation and other subsequent statistical analysis. However, prior to the tumor analysis and quantification, an important challenge lies in the pre-processing. In the present study, permutations of different pre-processing methods are comprehensively investigated. In particular, the study focused on Gibbs ringing artifact removal, bias field correction, intensity normalization, and adaptive histogram equalization (AHE). The pre-processed MRI data is then passed onto 3D U-Net for automatic segmentation of brain tumors. The segmentation results demonstrated the best performance with the combination of two techniques, i.e., Gibbs ringing artifact removal and bias-field correction. The proposed technique achieved mean dice score metrics of 0.91, 0.86, and 0.70 for the whole tumor, tumor core, and enhancing tumor, respectively. The testing mean dice scores achieved by the system are 0.90, 0.83, and 0.71 for the whole tumor, core tumor, and enhancing tumor, respectively. The novelty of this work concerns a robust pre-processing sequence for improving the segmentation accuracy of MR images. The proposed method overcame the testing dice scores of the state-of-the-art methods. The results are benchmarked with the existing techniques used in the Brain Tumor Segmentation Challenge (BraTS) 2018 challenge.

Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification.

BACKGROUND: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature. METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms. RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs. CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.

Performance analysis of noninvasive electrophysiological methods for the assessment of diabetic sensorimotor polyneuropathy in clinical research: a systematic review and meta-analysis with trial sequential analysis.

Despite the availability of various clinical trials that used different diagnostic methods to identify diabetic sensorimotor polyneuropathy (DSPN), no reliable studies that prove the associations among diagnostic parameters from two different methods are available. Statistically significant diagnostic parameters from various methods can help determine if two different methods can be incorporated together for diagnosing DSPN. In this study, a systematic review, meta-analysis, and trial sequential analysis (TSA) were performed to determine the associations among the different parameters from the most commonly used electrophysiological screening methods in clinical research for DSPN, namely, nerve conduction study (NCS), corneal confocal microscopy (CCM), and electromyography (EMG), for different experimental groups. Electronic databases (e.g., Web of Science, PubMed, and Google Scholar) were searched systematically for articles reporting different screening tools for diabetic peripheral neuropathy. A total of 22 studies involving 2394 participants (801 patients with DSPN, 702 controls, and 891 non-DSPN patients) were reviewed systematically. Meta-analysis was performed to determine statistical significance of difference among four NCS parameters, i.e., peroneal motor nerve conduction velocity, peroneal motor nerve amplitude, sural sensory nerve conduction velocity, and sural sensory nerve amplitude (all p < 0.001); among three CCM parameters, including nerve fiber density, nerve branch density, and nerve fiber length (all p < 0.001); and among four EMG parameters, namely, time to peak occurrence (from 0 to 100% of the stance phase) of four lower limb muscles, including the vastus lateralis (p < 0.001), tibialis anterior (p = 0.63), lateral gastrocnemius (p = 0.01), and gastrocnemius medialis (p = 0.004), and the vibration perception threshold (p < 0.001). Moreover, TSA was conducted to estimate the robustness of the meta-analysis. Most of the parameters showed statistical significance between each other, whereas some were statistically nonsignificant. This meta-analysis and TSA concluded that studies including NCS and CCM parameters were conclusive and robust. However, the included studies on EMG were inconclusive, and additional clinical trials are required.

Characterization of capacitive electromyography biomedical sensor insulated with porous medical bandages.

A capacitive electromyography (cEMG) biomedical sensor measures the EMG signal from human body through capacitive coupling methodology. It has the flexibility to be insulated by different types of materials. Each type of insulator will yield a unique skin-electrode capacitance which determine the performance of a cEMG biomedical sensor. Most of the insulator being explored are solid and non-breathable which cause perspiration in a long-term EMG measurement process. This research aims to explore the porous medical bandages such as micropore, gauze, and crepe bandage to be used as an insulator of a cEMG biomedical sensor. These materials are breathable and hypoallergenic. Their unique properties and characteristics have been reviewed respectively. A 50 Hz digital notch filter was developed and implemented in the EMG measurement system design to further enhance the performance of these porous medical bandage insulated cEMG biomedical sensors. A series of experimental verifications such as noise floor characterization, EMG signals measurement, and performance correlation were done on all these sensors. The micropore insulated cEMG biomedical sensor yielded the lowest noise floor amplitude of 2.44 mV and achieved the highest correlation coefficient result in comparison with the EMG signals captured by the conventional wet contact electrode.