Enhanced accuracy with Segmentation of Colorectal Polyp using NanoNetB, and Conditional Random Field Test-Time Augmentation.

Colonoscopy is a reliable diagnostic method to detect colorectal polyps early on and prevent colorectal cancer. The current examination techniques face a significant challenge of high missed rates, resulting in numerous undetected polyps and irregularities. Automated and real-time segmentation methods can help endoscopists to segment the shape and location of polyps from colonoscopy images in order to facilitate clinician's timely diagnosis and interventions. Different parameters like shapes, small sizes of polyps, and their close resemblance to surrounding tissues make this task challenging. Furthermore, high-definition image quality and reliance on the operator make real-time and accurate endoscopic image segmentation more challenging. Deep learning models utilized for segmenting polyps, designed to capture diverse patterns, are becoming progressively complex. This complexity poses challenges for real-time medical operations. In clinical settings, utilizing automated methods requires the development of accurate, lightweight models with minimal latency, ensuring seamless integration with endoscopic hardware devices. To address these challenges, in this study a novel lightweight and more generalized Enhanced Nanonet model, an improved version of Nanonet using NanonetB for real-time and precise colonoscopy image segmentation, is proposed. The proposed model enhances the performance of Nanonet using Nanonet B on the overall prediction scheme by applying data augmentation, Conditional Random Field (CRF), and Test-Time Augmentation (TTA). Six publicly available datasets are utilized to perform thorough evaluations, assess generalizability, and validate the improvements: Kvasir-SEG, Endotect Challenge 2020, Kvasir-instrument, CVC-ClinicDB, CVC-ColonDB, and CVC-300. Through extensive experimentation, using the Kvasir-SEG dataset, our model achieves a mIoU score of 0.8188 and a Dice coefficient of 0.8060 with only 132,049 parameters and employing minimal computational resources. A thorough cross-dataset evaluation was performed to assess the generalization capability of the proposed Enhanced Nanonet model across various publicly available polyp datasets for potential real-world applications. The result of this study shows that using CRF (Conditional Random Fields) and TTA (Test-Time Augmentation) enhances performance within the same dataset and also across diverse datasets with a model size of just 132,049 parameters. Also, the proposed method indicates improved results in detecting smaller and sessile polyps (flats) that are significant contributors to the high miss rates.

Detection of organic dyes by surface-enhanced Raman spectroscopy using plasmonic NiAg nanocavity films.

This work presents the NiAg nanocavity film for the detection of organic dyes by surface-enhanced Raman spectroscopy (SERS). Nanocavity films were prepared by colloidal lithography using 518-nm polystyrene spheres combined with the electrochemical deposition of Ni supporting layer and Ag nanoparticles homogeneous SERS-active layer. The theoretical study was modelled by finite-difference time-domain (FDTD) simulation of electromagnetic field enhancement near the nanostructured surface and experimentally proven by SERS measurement of selected organic dyes (rhodamine 6G, crystal violet, methylene blue, and malachite green oxalate) in micromolar concentration. Furthermore, the concentration dependence was investigated to prove the suitability of NiAg nanocavity films to detect ultra-low concentrations of samples. The detection limit was 1.3 × 10-12, 1.5 × 10-10, 1.4 × 10-10, 7.5 × 10-11 mol·dm-3, and the standard deviation was 20.1%, 13.8%, 16.7%, and 19.3% for R6G, CV, MB, and MGO, respectively. The analytical enhancement factor was 3.4 × 105 using R6G as a probe molecule. The principal component analysis (PCA) was performed to extract the differences in complex spectra of the dyes where the first and second PCs carry 42.43% and 31.39% of the sample variation, respectively. The achieved results demonstrated the suitability of AgNi nanocavity films for the SERS-based detection of organic dyes, with a potential in other sensing applications.

Objectivization of vacuum-compression therapy effects on micro- and macrovascular perfusion in type 2 diabetic patients.

The present study aimed to evaluate the characteristic influence of physical therapeutic procedures of vacuum-compression therapy (VCT) on microvascular perfusion (MiP) and macrovascular perfusion (MaP) of the lower limb in diabetic patients. A sample of nine patients with a medical history of type 2 diabetes was used for the purpose of this study. Most of the subjects' medical conditions included venous and neurological complications of the lower limb, whereas the rest of the subjects entered the treatment due to injury recovery or their phlebological disease. The PeriFlux System 5000 (Perimed, Sweden) diagnostic device was used to measure MiP. The MaP was evaluated based on the perfusion index (PI) using the Extremiter monitoring device (Embitron, Czech Republic) designed to perform VCT procedures. The study found that MiP and MaP increase as an effect of VCT procedures and at the same time PI clearly reflects the effect of the applied vacuum and compression phases, verifying the method's vital influence on peripheral perfusion disorders.

Effect of High-Induction Magnetic Stimulation on Elasticity of the Patellar Tendon.

Nowadays, a high-induction magnetic stimulation is starting to be increasingly applied as a biophysical stimulation in the conservative treatment of the degenerative locomotor system diseases. These are mainly in correlation with the changes in soft tissue elasticity, which should be positively influenced by the flow-induced electrical currents of high current density during high-induction magnetic stimulation. This assumption was verified within the interventional and prospective study using the ultrasound elastography. The group consisted of 6 volunteers, whose elasticity of the patellar tendons was measured using the 2D shear-wave ultrasound elastography. The volunteers were then exposed to a 20-minute high-induction magnetic stimulation session with a frequency of 20 Hz, in 2 s package intervals, with a 5 s pause, and a induced electric current density of 100 Am-2 in the tendons area. A tendon tension was measured five times for all volunteers, where mean tension at the marked area of the tendon, as well as the highest point tension indicated by the Q-Box, was monitored. The measurement results show that high-induction magnetic stimulation has an influence on the patellar tendon tension change, which occurred in the case of all involved volunteers when the patellar tension was decreased.

Quantification of Trunk Postural Stability Using Convex Polyhedron of the Time-Series Accelerometer Data.

Techniques to quantify postural stability usually rely on the evaluation of only two variables, that is, two coordinates of COP. However, by using three variables, that is, three components of acceleration vector, it is possible to describe human movement more precisely. For this purpose, a single three-axis accelerometer was used, making it possible to evaluate 3D movement by use of a novel method, convex polyhedron (CP), together with a traditional method, based on area of the confidence ellipse (ACE). Ten patients (Pts) with cerebellar ataxia and eleven healthy individuals of control group (CG) participated in the study. The results show a significant increase of volume of the CP (CPV) in Pts or CG standing on foam surface with eyes open (EO) and eyes closed (EC) after the EC phase. Significant difference between Pts and CG was found in all cases as well. Correlation coefficient indicates strong correlation between the CPV and ACE in most cases of patient examinations, thus confirming the possibility of quantification of postural instability by the introduced method of CPV.

Assessment of postural stability in patients with cerebellar disease using gyroscope data.

This study examines a relatively new method of studying and quantifying human postural stability in patients with degenerative cerebellar disease. Trunk sway and feet sway were measured during quiet stance. To test the method, ten patients and eleven healthy subjects performed two different stance tasks: standing with eyes open on a firm surface and standing with eyes closed on a foam support surface. Data were recorded using three body-worn gyroscopes (Xsens Technologies B.V.) to measure roll and pitch angular movements of the lower trunk, and left and right foot. The pitch versus roll plots of the trunk and feet were created, and the areas of the convex hull shapes were calculated. It was found that the area of the convex hull of the pitch versus roll plots is suitable for the identification of postural instability disorders caused by degenerative cerebellar disease.

Volume of confidence ellipsoid: a technique for quantifying trunk sway during stance.

The position of the trunk can be negatively affected by many diseases. This work focuses on a noninvasive method of quantifying human postural stability and identifying defects in balance and coordination as a result of the nervous system pathology. We used a three-degree-of-freedom orientation tracker (Xsens MTx unit) placed on a patient's trunk and measured three-dimensional (3-D) data (pitch, roll, and yaw) during quiet stance. The principal component analysis was used to analyze the data and to determine the volume of 3-D 95% confidence ellipsoid. Using this method, we were able to model the distribution of the measured 3-D data (pitch, roll, and yaw). Eight patients with degenerative cerebellar disease and eight healthy subjects in this study were measured during stance, with eyes open and eyes closed, and statistical analysis was performed. The results of the new method based on the 3-D confidence ellipsoid show that the volumes related to the patients are significantly larger than the volumes related to the healthy subjects. The concept of confidence ellipsoid volume, although known to the biomechanics community, has not been used before to study the postural balance problems. The method can also be used to study, for example, head and pelvis movements or alignments during stance.

Differences in evaluation methods of trunk sway using different MoCap systems.

The position of the trunk can be negatively influenced by many diseases. Several methods can be used for identifying defects in balance and coordination as a result of pathology of the musculoskeletal or nervous system. The aim of this article is to examine the relationship between the three methods used for analysis of trunk sway and compare two fundamentally different MoCap systems. We used a camera system and a 3DOF orientation tracker placed on subject's trunk, and measured inclination (roll) and flexion (pitch) during quiet stance. Ten healthy participants in the study were measured with eyes open and closed. The pitch versus roll plots of trunk were formed, and the area of the convex hull, area of confidence ellipse and total length of the trajectory of the pitch versus roll plot were calculated. The statistical analysis was performed and strong correlation between the area of the convex hull and area of the confidence ellipse was found. Also, the results show moderate correlation between the area of the confidence ellipse and total length of the trace, and moderate correlation between the area of the convex hull and total length of the trace. In general, the different MoCap systems show different areas and lengths but lead to the same conclusions. Statistical analysis of the participants with eyes open and eye closed did not show significant difference in the areas and total lengths of the pitch versus roll plots.