Multi-class discrimination of lymphadenopathy by using dual-modal ultrasound radiomics with elastography and B-mode ultrasound / 生物医学工程学杂志

The purpose of our study is to evaluate the diagnostic performance of radiomics in multi-class discrimination of lymphadenopathy based on elastography and B-mode dual-modal ultrasound images. We retrospectively analyzed a total of 251 lymph nodes (89 benign lymph nodes, 70 lymphoma and 92 metastatic lymph nodes) from 248 patients, which were examined by both elastography and B-mode sonography. Firstly, radiomic features were extracted from multimodal ultrasound images, including shape features, intensity statistics features and gray-level co-occurrence matrix texture features. Secondly, three feature selection methods based on information theory were used on the radiomic features to select different subsets of radiomic features, consisting of conditional infomax feature extraction, conditional mutual information maximization, and double input symmetric relevance. Thirdly, the support vector machine classifier was performed for diagnosis of lymphadenopathy on each radiomic subsets. Finally, we fused the results from different modalities and different radiomic feature subsets with Adaboost to improve the performance of lymph node classification. The results showed that the accuracy and overall 1 score with five-fold cross-validation were 76.09%±1.41% and 75.88%±4.32%, respectively. Moreover, when considering on benign lymph nodes, lymphoma or metastatic lymph nodes respectively, the area under the receiver operating characteristic curve of multi-class classification were 0.77, 0.93 and 0.84, respectively. This study indicates that radiomic features derived from multimodal ultrasound images are benefit for diagnosis of lymphadenopathy. It is expected to be useful in clinical differentiation of lymph node diseases.

Application of magnetic iron oxide nanoparticles in magnetic resonance/photothermal dual-modal imaging / 药学学报

In this study, water-dispersible magnetic iron oxide (Fe3O4) nanoparticles were synthesized with solvothermal method. The nanoparticles were characterized with a transmission electron microscopy (TEM) and vibrating sample magnetometer (VSM). The in vitro magnetic resonance response and photothermal conversion characteristics of the nanoparticles were evaluated. In addition, the cellular uptake, cytotoxicity and biodistribution were studied. Finally, magnetic resonance/photothermal dual-modal imaging effect of the as-synthesized Fe3O4 nanoparticles was investigated in the tumor-bearing mice. The results showed that the obtained magnetic nanoparticles were uniform with a mean diameter of about 125 nm. Moreover, the superparamagnetic Fe3O4 nanoparticles showed remarkable magnetic resonance response and photothermal conversion properties. The results of cellular experiments showed that the cell viability was nearly 85% even the concentration of the nanoparticles was up to 1 000 μg·mL-1, an indicator of good biocompatibility. In addition, the nanoparticles could be taken up by the tumor cells and then located in the cytoplasm. After intravenous injection, the nanoparticles were tended to enrich in the tumor over time, which is helpful in achieving dual-modal magnetic resonance/photothermal imaging. In sum, the obtained Fe3O4 nanoparticles showed great potential to be applied for multi-modal bio-imaging which may play an important role in the diagnosis of tumors.