Phosphatase and tensin homolog deleted on chromosome ten (PTEN) is a lipid and protein phosphatase and possesses an antitumor effect in lung cancers. miRNAs are reportedly abnormally expressed in human lung cancers. However, whether miRNA contributes to PTEN expression in non-small cell lung cancers (NSCLCs) has not been clearly clarified. In the present study, we found that miR-1297 probably binds with 3'UTR sequence of PTEN and negatively regulated the levels of PTEN in NSCLC cells. First, the expression levels of PTEN and Skp2 were detected by western blotting in NSCLC specimens and paired normal tissue specimens. The results showed that decreased levels of PTEN were detected in NSCLC tissues, compared with paired control tissues (**p < 0.01). The expression levels of PTEN were conversely correlated with the levels of Skp2 in clinical NSCLC specimens and NSCLC cell line. Transfection with miR-1297 mimic significantly promoted cell viability of A549 cells and NCI-H460 cells by downregulating the level of PTEN and upregulating the expression of Skp2. Interestingly, knockdown of Skp2 did not affect the expression of PTEN in A549 cells. Thus, miR-1297 might work as an oncogene by regulating PTEN/Akt/Skp2 signaling pathway in NSCLC cells. PTEN and Skp2 might be the potential targets in the clinical therapy of lung cancers.
Abstract The incidence of thyroid nodules is increasing year by year. Accurate determination of benign and malignant nodules is an important basis for formulating treatment plans. Ultrasonography is the most widely used methodology in the diagnosis of benign and malignant nodules, but diagnosis by doctors is highly subjective, and the rates of missed diagnosis and misdiagnosis are high. To improve the accuracy of clinical diagnosis, this paper proposes a new diagnostic model based on deep learning. The diagnostic model adopts the diagnostic strategy of localization-classification. First, the distribution laws of the nodule size and nodule aspect ratio are obtained through data statistics, a multiscale localization network structure is a priori designed, and the nodule aspect ratio is obtained from the positioning results. Then, uncropped ultrasound images and nodule area image are correspondingly input into a two-way classification network, and an improved attention mechanism is used to enhance the feature extraction performance. Finally, the deep features, the shallow features, and the nodule aspect ratio are fused, and a fully connected layer is used to complete the classification of benign and malignant nodules. The experimental dataset consists of 4021 ultrasound images, where each image has been labeled under the guidance of doctors, and the ratio of the training set, validation set, and test set sizes is close to 3:1:1. The experimental results show that the accuracy of the multiscale localization network reaches 93.74%, and that the accuracy, specificity, and sensitivity of the classification network reach 86.34%, 81.29%, and 90.48%, respectively. Compared with the champion model of the TNSCUI 2020 classification competition, the accuracy rate is 1.52 points higher. Therefore, the network model proposed in this paper can effectively diagnose benign and malignant thyroid nodules.
Abstract The incidence of thyroid nodules is increasing year by year. Accurate determination of benign and malignant nodules is an important basis for formulating treatment plans. Ultrasonography is the most widely used in the diagnosis of benign and malignant nodules, but manual diagnosis is highly subjective, and the rate of missed diagnosis and misdiagnosis is high. To improve the accuracy of clinical diagnosis, this paper proposes a new diagnostic model based on deep learning. The diagnostic model adopts the diagnosis strategy of Localization-Classification. First, the distribution law of nodule size and nodule aspect ratio is obtained through data statistics, the multi-scale localization network structure is a priori designed, and the nodule aspect ratio is obtained from the positioning results. Then, the uncropped ultrasound image and the nodule area image are correspondingly input into the two-way classification network, and the improved attention mechanism is used to enhance the feature extraction, and finally, the deep features, the shallow features, and the nodule aspect ratio are fused, input the fully connected layer to complete the classification of benign and malignant nodules. The experimental data set is 4021 ultrasound images, each image is marked under the guidance of doctors, and the ratio of the training set, validation set, and test set is close to 3:1:1. The experimental results show that the accuracy of the multi-scale localization network reaches 93.74%, and the accuracy, specificity, and sensitivity of the classification network reach 86.34%, 81.29%, and 90.48%, respectively. Compared with the champion model of the TNSCUI 2020 classification competition, the accuracy rate is 1.52 points higher. Therefore, the network model proposed in this paper can effectively diagnose benign and malignant thyroid nodules.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23c4272f' d='M0 0h960v480H0z'/%3e%3cpath fill='%23015197' d='M320 0h320v480H320z'/%3e%3ccircle cx='160' cy='164' r='44'/%3e%3ccircle cx='160' cy='144' r='48' fill='%23c4272f'/%3e%3ccircle cx='160' cy='152' r='32'/%3e%3cpath d='M140 92a20 20 0 0 0 40 0c0-8-5-9-5-12s3-7-3-12c3 5-2 6-2 11s2 5 2 9a4 4 0 0 1-8 0c0-4 4-8 4-14s-1-8-4-13-8-9-4-13c-6 2-3 10-3 15s-4 8-4 14 3 7 3 11a4 4 0 0 1-8 0c0-4 2-4 2-9s-5-6-2-11c-6 5-3 9-3 12s-5 4-5 12ZM72 216v192h40V216Zm136 0v192h40V216Zm-88 32v16h80v-16Zm0 112v16h80v-16Zm0-144h80l-40 24Zm0 168h80l-40 24Z'/%3e%3c/g%3e%3cg stroke='%23c4272f' stroke-width='24'%3e%3ccircle cx='800' cy='1560' r='212'/%3e%3cpath fill='none' d='M800 1348a106 106 0 0 1 0 212 106 106 0 0 0 0 212'/%3e%3c/g%3e%3c/g%3e%3cg fill='%23c4272f'%3e%3ccircle cx='800' cy='1454' r='40'/%3e%3ccircle cx='800' cy='1666' r='40'/%3e%3c/g%3e%3c/svg%3e)