BACKGROUND Gastric cancer is a common gastrointestinal tumor. The incidence and mortality of gastric cancer are very high. Therefore, it is important to study targeted drugs. Recent studies found long chain non-coding RNA (lncRNAs) and microRNAs (miRNAs) were abnormal in gastric cancer. MATERIAL AND METHODS We collected adjacent normal and cancer tissues of gastric cancer patients and measured HOTAIR, miR-454-3p, STAT3, and Cyclin D1 expression and analyzed the correlation with clinical status. We also measured AGS and SGC7901 cells proliferation rate of different groups by MTT assay, and we evaluated AGS and SGC7901 cell apoptosis and cell cycle by flow cytometry. In addition, we assessed the relative proteins expressions by WB assay. Finally, we explored the correlation between miR-454-3p and STAT3 by use of double luciferase reporter. RESULTS lncRNA HOTAIR was negatively correlated with miR-454-3p expression in gastric cancer tissues. lncRNA HOTAIR knockdown suppressed AGS and SGC7901, which are gastric cancer cell lines that promote cell proliferation by increasing cell apoptosis and keeping the cell cycle in G1 phase. In further mechanism research, we found that the STAT3 and Cyclin D1 proteins expressions were suppressed by lncRNA HOTAIR down-regulation in AGS and SGC7901 cells. CONCLUSIONS Our results suggest that lncRNA HOTAIR knockdown stimulates miR-454-3p expression to inhibit gastric cancer growth by depressing STAT3/Cyclin D1 activity.

BACKGROUND The number of studies on deep learning in artificial intelligence (AI)-assisted diagnosis of thyroid nodules is increasing. However, it is difficult to explain what the models actually learn in artificial intelligence-assisted medical research. Our aim is to investigate the visual interpretability of the computer-assisted diagnosis of malignant and benign thyroid nodules using ultrasound images. MATERIAL AND METHODS We designed and implemented 2 experiments to test whether our proposed model learned to interpret the ultrasound features used by ultrasound experts to diagnose thyroid nodules. First, in an anteroposterior/transverse (A/T) ratio experiment, multiple models were trained by changing the A/T ratio of the original nodules, and their classification, accuracy, sensitivity, and specificity were tested. Second, in a visualization experiment, class activation mapping used global average pooling and a fully connected layer to visualize the neural network to show the most important features. We also examined the importance of data preprocessing. RESULTS The A/T ratio experiment showed that after changing the A/T ratio of the nodules, the accuracy of the neural network model was reduced by 9.24-30.45%, indicating that our neural network model learned the A/T ratio information of the nodules. The visual experiment results showed that the nodule margins had a strong influence on the prediction of the neural network. CONCLUSIONS This study was an active exploration of interpretability in the deep learning classification of thyroid nodules. It demonstrated the neural network-visualized model focused on irregular nodule margins and the A/T ratio to classify thyroid nodules.

BACKGROUND Thyroid nodules are extremely common and typically diagnosed with ultrasound whether benign or malignant. Imaging diagnosis assisted by Artificial Intelligence has attracted much attention in recent years. The aim of our study was to build an ensemble deep learning classification model to accurately differentiate benign and malignant thyroid nodules. MATERIAL AND METHODS Based on current advanced methods of image segmentation and classification algorithms, we proposed an ensemble deep learning classification model for thyroid nodules (EDLC-TN) after precise localization. We compared diagnostic performance with four other state-of-the-art deep learning algorithms and three ultrasound radiologists according to ACR TI-RADS criteria. Finally, we demonstrated the general applicability of EDLC-TN for diagnosing thyroid cancer using ultrasound images from multi medical centers. RESULTS The method proposed in this paper has been trained and tested on a thyroid ultrasound image dataset containing 26 541 images and the accuracy of this method could reach 98.51%. EDLC-TN demonstrated the highest value for area under the curve, sensitivity, specificity, and accuracy among five state-of-the-art algorithms. Combining EDLC-TN with models and radiologists could improve diagnostic accuracy. EDLC-TN achieved excellent diagnostic performance when applied to ultrasound images from another independent hospital. CONCLUSIONS Based on ensemble deep learning, the proposed approach in this paper is superior to other similar existing methods of thyroid classification, as well as ultrasound radiologists. Moreover, our network represents a generalized platform that potentially can be applied to medical images from multiple medical centers.