Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists' assessment

PURPOSE

Ultrasonography is the most common imaging modality used to diagnose carpal tunnel syndrome (CTS). Recently artificial intelligence algorithms have been used to diagnose musculoskeletal diseases accurately without human errors using medical images. In this work, a computer-aided diagnosis (CAD) system is developed using radiomics features extracted from median nerves (MN) to diagnose CTS accurately.

METHOD

This study is performed on 228 wrists from 65 patients and 57 controls, with an equal number of control and CTS wrists. Nerve conduction study (NCS) is considered as the gold standard in this study. Two radiologists used two guides to evaluate and categorize the pattern and echogenicity of MNs. Radiomics features are extracted from B-mode ultrasound images (Ultrasomics), and the robust features are fed into support vector machine classifier for automated classification. The diagnostic performances of two radiologists and the CAD system are evaluated using ROC analysis.

RESULTS

The agreement of two radiologists was excellent for both guide 1 and 2. The honey-comb pattern clearly appeared in control wrists (based on guide 1). In addition, CTS wrists indicated significantly lower number of fascicles in MNs (based on guide 2). The area under ROC curve (AUC) of the radiologist 1 and 2 are 0.658 and 0.667 based on guide 1 and 0.736 and 0.721 based on guide 2, respectively. The CAD system indicated higher performance than two radiologists with AUC of 0.926.

CONCLUSION

The proposed CAD system shows the benefit of using ultrasomics features and can assist radiologists to diagnose CTS accurately.

Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks

Fast diagnostic methods can control and prevent the spread of pandemic diseases like coronavirus disease 2019 (COVID-19) and assist physicians to better manage patients in high workload conditions. Although a laboratory test is the current routine diagnostic tool, it is time-consuming, imposing a high cost and requiring a well-equipped laboratory for analysis. Computed tomography (CT) has thus far become a fast method to diagnose patients with COVID-19. However, the performance of radiologists in diagnosis of COVID-19 was moderate. Accordingly, additional investigations are needed to improve the performance in diagnosing COVID-19. In this study is suggested a rapid and valid method for COVID-19 diagnosis using an artificial intelligence technique based. 1020 CT slices from 108 patients with laboratory proven COVID-19 (the COVID-19 group) and 86 patients with other atypical and viral pneumonia diseases (the non-COVID-19 group) were included. Ten well-known convolutional neural networks were used to distinguish infection of COVID-19 from non-COVID-19 groups: AlexNet, VGG-16, VGG-19, SqueezeNet, GoogleNet, MobileNet-V2, ResNet-18, ResNet-50, ResNet-101, and Xception. Among all networks, the best performance was achieved by ResNet-101 and Xception. ResNet-101 could distinguish COVID-19 from non-COVID-19 cases with an AUC of 0.994 (sensitivity, 100%; specificity, 99.02%; accuracy, 99.51%). Xception achieved an AUC of 0.994 (sensitivity, 98.04%; specificity, 100%; accuracy, 99.02%). However, the performance of the radiologist was moderate with an AUC of 0.873 (sensitivity, 89.21%; specificity, 83.33%; accuracy, 86.27%). ResNet-101 can be considered as a high sensitivity model to characterize and diagnose COVID-19 infections, and can be used as an adjuvant tool in radiology departments.

•

Ten CNNs were used to distinguish infection of COVID-19 from non-COVID-19 groups.

•

ResNet-101 and Xception represented the best performance with an AUC of 0.994.

•

Deep learning technique can be used as an adjuvant tool in diagnosing COVID-19.

Magneto-plasmonic nanoparticle mediated thermo-radiotherapy significantly affects the nonlinear optical properties of treated cancer cells

In order to determine the level of cell damage in cancerous cells, current cytogenetic tests have limitations such as time consumption and high cost. The aim of this study was to demonstrate the ability of nonlinear refractive (NLR) index as a predictor of breast cell damage caused by magneto-plasmonic nanoparticle based thermo-radiotherapy treatments. MCF-7 breast cancer cells were subjected individually to the treatment of radiation, radio-frequency (RF) hyperthermia, and radiation + RF hyperthermia. These treatments were repeated in the presence of magneto-plasmonic nanoparticle (Au@IONP). The MTT and nonlinear optical assays were used to evaluate the damage induced by different treatment modalities. The results of MTT were correlated with Z-scan, as the magnitude of nonlinear refraction increased with higher intensity of induced cell damages. In this regard, the lowest cell viability (38 %,) and highest magnitude of NLR index (+28.12) were obtained from combination of radiation (at 4 Gy dose) and hyperthermia treatment in the presence of nanoparticles. The proposed optical index (NLR) indicated high capability and can be used as an auxiliary tool to monitor induced cell damage during different treatment strategies. This technique is fast, noninvasive, does not impose cost, and finally does not waste materials.

Evaluation of nonlinear optical behavior of mouse colon cancer cell line CT26 in hyperthermia treatment

Hyperthermia treatment can induce component changes on cell. This study explored the potential of Z-scan to improve accuracy in the identification of subtle differences in mouse colon cancer cell line CT26 during hyperthermia treatment. Twenty-one samples were subjected individually to treatment of hyperthermia at 41, 43, and 45 °C. Each hyperthermia treatment was done in six different time (15, 30, 45, 60, 75, and 90 min). Two optical setups were used to investigate the linear and nonlinear optical behavior of samples. Prior to the Z-scan technique, all samples were fixed with 1 mL of 5% paraformaldehyde. The linear optical setup indicated that extinction coefficient cannot monitor cell changes at different treatment regimes. But the nonlinear behavior of CT26 in all hyperthermia treatment regimens was different. By increasing the time and/or temperature of hyperthermia treatments, change in the sign of nonlinear refractive index from negative to positive occurred in earlier time intervals. This phenomenon was seen for 41, 43, and 45 °C in 75, 60, and 45 min, respectively. The results showed that the Z-scan technique is a reliable method with the potential to characterize cell changes during hyperthermia treatment regimes. Nonlinear refractive index can be used as a new index for evaluation of cell damage.

Radioprotective effects of selenium and vitamin-E against 6MV X-rays in human blood lymphocytes by micronucleus assay

BACKGROUND

Critical macromolecules of cells such as DNA are in exposure to damage of free radicals that induced from the interaction of ionizing radiation with biological systems. Selenium and vitamin-E are natural compounds that have been shown to be a direct free radical scavenger. The aim of this study was to investigate the radioprotective effect of selenium and vitamin-E separately and synergistically against genotoxicity induced by 6MV x-rays irradiation in blood lymphocytes.

METHODS

Fifteen volunteers were divided into three groups include A, B and C. These groups were given selenium (800IU), vitamin-E (100mg) and selenium (400IU) + vitamin-E (50mg), respectively. Peripheral blood samples were collected from each group before (0hr) and 1, 2 and 3hr after selenium and vitamin-E administration (separately and synergistically). Then the blood samples were irradiated to 200cGy of 6MV x-rays. After that lymphocyte samples were cultured with mitogenic stimulation to determine the chromosomal aberrations with micronucleus assay in cytokinesis-blocked binucleated cells.

RESULTS

The lymphocytes in the blood samples collected at one hr after ingestion selenium and vitamin-E, exposed in vitro to x-rays exhibited a significant decrease in the incidence of micronuclei, compared with control group at 0hr. The maximum protection and decrease in frequency of micronuclei (50%) were observed at one hr after administration of selenium and vitamin-E synergistically.

CONCLUSION

The data suggest that ingestion of selenium and vitamin-E as a radioprotector substance before exposures may reduce genetic damage caused by x-rays irradiation.