Quantitative characterization of the colorectal cancer in a rabbit model using high-frequency endoscopic ultrasound

Evaluating the effect of tissue stimulation at different frequencies on breast lesion classification based on nonlinear features using a novel radio frequency time series approach

Objective

Radio Frequency Time Series (RF TS) is a cutting-edge ultrasound approach in tissue typing. The RF TS does not provide dynamic insights into the propagation medium; when the tissue and probe are fixed. We previously proposed the innovative RFTSDP method in which the RF data are recorded while stimulating the tissue. Applying stimulation can unveil the mechanical characteristics of the tissue in RF echo.

Materials and methods

In this study, an apparatus was developed to induce vibrations at different frequencies to the medium. Data were collected from four PVA phantoms simulating the nonlinear behaviors of healthy, fibroadenoma, cyst, and cancerous breast tissues. Raw focused, raw, and beamformed ultrafast data were collected under conditions of no stimulation, constant force, and various vibrational stimulations using the Supersonic Imagine Aixplorer clinical/research ultrasound imaging system. Time domain (TD), spectral, and nonlinear features were extracted from each RF TS. Support Vector Machine (SVM), Random Forest, and Decision Tree algorithms were employed for classification.

Results

The optimal outcome was achieved using the SVM classifier considering 19 features extracted from beamformed ultrafast data recorded while applying vibration at the frequency of 65 Hz. The classification accuracy, specificity, and precision were 98.44 ± 0.20 %, 99.49 ± 0.01 %, and 98.53 ± 0.04 %, respectively. Applying RFTSDP, a notable 24.45 % improvement in accuracy was observed compared to the case of fixed probe assessing the recorded raw focused data.

Conclusions

External vibration at an appropriate frequency, as applied in RFTSDP, incorporates beneficial information about the medium and its dynamic characteristics into the RF TS, which can improve tissue characterization.

Clinical Value and Imaging Features of Bedside High-Frequency Ultrasound Imaging in the Diagnosis of Neonatal Pneumonia

The aim is to solve the problem of the urgent need of a nonradiation, noninvasive, and simple-to-operate diagnostic method for neonatal pneumonia that can indicate the severity of the disease and dynamically monitor the outcome of the disease. The authors propose a bedside high-frequency ultrasound technique based on methods for evaluation in the detection and treatment of neonatal pneumonia. The results obtained are as follows: the sensitivity of neonatal lung ultrasound in the diagnosis of neonatal pneumonia was 96.6%, the specificity was 93.3%, the positive predictive value was 93.5%, and the negative predictive value was 96.5%. The sensitivity of chest X-ray in the diagnosis of neonatal pneumonia was 93.3%. Compared with the lung ultrasound and chest X-ray in the diagnosis of neonatal pneumonia, the two had a good correlation. The neonatal respiratory score was positively correlated with the lung ultrasound score, and the higher the lung ultrasound score, the more severe the disease. The score decreased by 35% after 3 days of treatment and 68% after 7 days of treatment, indicating that the lung high-frequency ultrasound score can be very effective in characterizing the treatment situation. It has been demonstrated that the lung ultrasound can be used as an imaging method for the diagnosis of neonatal pneumonia. The higher the lung ultrasound score, the more severe the disease, and the lung ultrasound score was positively correlated with the disease severity. With dynamic monitoring of the lung ultrasound and the gradual improvement of clinical symptoms after treatment, the lung ultrasound score gradually decreased; therefore, the lung ultrasound can be used for re-examination of neonatal pneumonia to evaluate the treatment effect and guidance.

A high frequency endoscopic ultrasound imaging method combining chirp coded excitation and compressed sensing

Insufficient imaging penetration and large data acquisition are two of the major challenges of high-frequency ultrasound imaging. Based on the good autocorrelation properties of chirp signal and the feasibility of using compressed sensing theory to reconstruct high-quality ultrasound images with low sampling requirements, this paper proposed a chirp coded excitation combined with compressed sensing (CCE-CS) technique for high-frequency endoscopic ultrasound (HFEUS) imaging. The feasibility of the method was verified by a brief theoretical analysis, and the relevant parameters were selected and analyzed according to the actual engineering situation. Simulated phantoms and in-vitro tissue experiments were used to evaluate the performance of the CCE-CS. Simulation results demonstrate that CCE-CS is capable of reducing the impact of reconstruction errors and improving imaging quality through comparison with conventional methods. The reduction of reconstruction data had less impact on penetration depth, resolution and general contrast general contrast-to-noise ratio (gCNR), and the reconstructed image was closer to the original image with a maximum improvement of 37% in peak signal-to-noise ratio (PSNR). Moreover, comparisons were conducted on the digestive tract of swine, and the results show that CCE-CS is also feasible in the in-vitro environment. These results demonstrated that CCE-CS method has good potential for application to improve the imaging quality of HFEUS while reducing the sampling rate.