Deep learning-based automatic pipeline system for predicting lateral cervical lymph node metastasis in patients with papillary thyroid carcinoma using computed tomography:A multi-center study

Objective:The assessment of lateral lymph node metastasis(LLNM)in patients with papillary thyroid carcinoma(PTC)holds great significance.This study aims to develop and evaluate a deep learning-based automatic pipeline system(DLAPS)for diagnosing LLNM in PTC using computed tomography(CT).Methods:A total of 1,266 lateral lymph nodes(LLNs)from 519 PTC patients who underwent CT examinations from January 2019 to November 2022 were included and divided into training and validation set,internal test set,pooled external test set,and prospective test set.The DLAPS consists of an auto-segmentation network based on RefineNet model and a classification network based on ensemble model(ResNet,Xception,and DenseNet).The performance of the DLAPS was compared with that of manually segmented DL models,the clinical model,and Node Reporting and Data System(Node-RADS).The improvement of radiologists’diagnostic performance under the DLAPS-assisted strategy was explored.In addition,bulk RNA-sequencing was conducted based on 12 LLNs to reveal the underlying biological basis of the DLAPS.Results:The DLAPS yielded good performance with area under the receiver operating characteristic curve(AUC)of 0.872,0.910,and 0.822 in the internal,pooled external,and prospective test sets,respectively.The DLAPS significantly outperformed clinical models(AUC 0.731,P<0.001)and Node-RADS(AUC 0.602,P<0.001)in the internal test set.Moreover,the performance of the DLAPS was comparable to that of the manually segmented deep learning(DL)model with AUCs ranging 0.814−0.901 in three test sets.Furthermore,the DLAPSassisted strategy improved the performance of radiologists and enhanced inter-observer consistency.In clinical situations,the rate of unnecessary LLN dissection decreased from 33.33%to 7.32%.Furthermore,the DLAPS was associated with the cell-cell conjunction in the microenvironment.Conclusions:Using CT images from PTC patients,the DLAPS could effectively segment and classify LLNs non-invasively,and this system had a good generalization ability and clinical applicability.

Tim-3 promotes cell aggressiveness and paclitaxel resistance through NF-κB/STAT3 signalling pathway in breast cancer cells

Objective:Although T-cell immunoglobulin and mucin-domain containing molecule-3(Tim-3)has been recognized as a promising target for cancer immunotherapy,its exact role in breast cancer has not been fully elucidated.Methods:Tim-3 gene expression in breast cancer and its prognostic significance were analyzed.Associated mechanisms were then explored in vitro by establishing Tim-3-overexpressing breast cancer cells.Results:In a pooled analysis of The Cancer Genome Atlas(TCGA)database,Tim-3 gene expression levels were significantly higher(P<0.001)in breast cancer tissue,compared with normal tissues.Tim-3 was a prognosis indicator in breast cancer patients[relapse-free survival(RFS),P=0.004;overall survival(OS),P=0.099].Tim-3 overexpression in Tim-3 low breast cancer cells promoted aggressiveness of breast cancer cells,as evidenced by enhanced proliferation,migration,invasion,tight junction deterioration and tumor-associated tubal formation.Tim-3 also enhanced cellular resistance to paclitaxel.Furthermore,Tim-3 exerted its function by activating the NF-κB/STAT3 signalling pathway and by regulating gene expression[cyclin D1(CCND1),C-Myc,matrix metalloproteinase-1(MMP1),TWIST,vascular endothelial growth factor(VEGF)upregulation,concomitant with Ecadherin downregulation).Lastly,Tim-3 downregulated tight junction-associated molecules zona occludens(ZO)-2,ZO-1 and occludin,which may further facilitate tumor progression.Conclusions:Tim-3 plays an oncogenic role in breast cancer and may represent a potential target for antitumor therapy.

Striatins and STRIPAK complex partners in clinical outcomes of patients with breast cancer and responses to drug treatment

Objective: Striatins(STRNs) family, which contains three multi-domain scaffolding proteins, are cornerstones of the striatins interacting phosphatase and kinase(STRIPAK) complex. Although the role of the STRIPAK complex in cancer has become recognized in recent years, its clinical significance in breast cancer has not been fully established.Methods: Using a freshly frozen breast cancer tissue cohort containing both cancerous and adjacent normal mammary tissues, we quantitatively evaluated the transcript-level expression of all members within the STRIPAK complex along with some key interacting and regulatory proteins of STRNs. The expression profile of each molecule and the integrated pattern of the complex members were assessed against the clinical-pathological factors of the patients. The Cancer Genome Atlas(TCGA) dataset was used to evaluate the breast cancer patients’ response to chemotherapies. Four human breast cancer cell lines, MDA-MB-231, MDA-MB-361, MCF-7, and SKBR-3, were subsequently adopted for in vitro work.Results: Here we found that high-level expressions of STRIP2, calmodulin, CCM3, MINK1 and SLMAP were respectively associated with shorter overall survival(OS) of patients. Although the similar pattern observed for STRN3, STRN4 and a contrary pattern observed for PPP2CA, PPP2CB and PPPR1A were not significant, the integrated expression profile of STRNs group and PPP2 group members constitutes a highly significant prognostic indicator for OS [P<0.001, hazard ratio(HR)=2.04, 95% confidence interval(95% CI), 1.36-3.07] and disease-free survival(DFS)(P=0.003, HR=1.40, 95% CI, 1.12-1.75). Reduced expression of STRN3 has an influence on the biological functions including adhesiveness and migration. In line with our clinical findings, the breast cancer cells responded to STRN3 knockdown with changes in their chemo-sensitivity, of which the response is also breast cancer subtype dependent.Conclusions: Our results suggest a possible role of the STRIPAK complex in breast cancer development and prognosis. Among the members, the expression profile of STRN3 presents a valuable factor for assessing patients’ responses to drug treatment.