Purpose Clinically, the risk stratification of thyroid nodules is usually used to formulate the next treatment plan. The American College of Radiology (ACR) thyroid imaging reporting and data system (TI‐RADS) is a type of medical standard widely used in classification diagnosis. It divides the nodule’s ACR TI‐RADS level into five levels by quantitative scoring, from benign to high suspicion of malignancy. However, such assessment often relies on the radiologists’ experience and is time consuming. So computer‐aided diagnosis is necessary. But many deep learning (DL) models are difficult for doctors to understand, limiting their applicability in clinical practice. In this work, we mainly focus on how to achieve automatic thyroid nodules risk stratification based on deep integration of deep learning and clinical experience. Methods An automatic hierarchical method of thyroid nodules risk based on deep learning is proposed, called risk stratification network (RS‐Net). It incorporates medical experience based on ACR TI‐RADS. The convolutional neural network (CNN) is used to classify the five categories in ACR TI‐RADS and assign their points respectively. According to the point totals, the level of risk can be obtained. In addition, a dataset involving 13 984 thyroid ultrasound images is established to develop and evaluate the proposed method. Results We have extensively compared the results of this paper with the evaluation results of sonographers. The accuracy of the risk stratification (TR1 to TR5) of the proposed method is 65%, and the mean absolute error (MAE) is 0.54. The MAE of the point totals (0 to 13 points) is 1.67. The Pearson's correlation between our method evaluation and doctor evaluation reached 0.84. For the benign and malignant classification, the performance indices accuracy, sensitivity, specificity, PPV, and NPV were 88.0%, 98.1%, 79.1%, 80.5%, and 97.9%, respectively. Our method's level of thyroid nodules risk stratification is comparable to that of a senior doctor. Conclusions This work provides a way to automate the risk stratification of thyroid nodules. Our method can effectively avoid missed diagnosis and misdiagnosis caused by the difference of observers so as to assist doctors to improve efficiency and diagnosis rate. Compared with the previous benign and malignant classification, the proposed method incorporates clinical experience. So it can greatly increase the clinicians’ trust in the DL model, thereby improving the applicability of the model in clinical practice.

Alternative splicing (AS) provides the primary mechanism for producing protein diversity. There is growing evidence that AS is involved in the development and progression of cancers. The rapid accumulation of high‐throughput sequencing technologies and clinical data sets offers an opportunity to systematically profile the relationship between mRNA variants and clinical outcomes. However, there is a lack of systematic analysis of AS in prostate cancer: Download RNA‐seq data and clinical information from The Cancer Genome Atlas (TCGA) data portal. Evaluate RNA splicing patterns by SpliceSeq and calculate splicing percentage (PSI) values. Different expressions were identified as differently expressed AS events (DEAs) based on PSI values. Bioinformatics methods were used for further analysis of DEAs and their splicing networks. Kaplan‐Meier, Cox proportional regression, and unsupervised cluster analysis were used to assess the correlation between DEAs and clinical characteristics. In total, 43 834 AS events were identified, of which 1628 AS events were differentially expressed. The parental genes of these DEAs played a significant role in the regulation of prostate cancer‐related processes. In total, 226 DEAs events were found to be associated with disease‐free survival. Four clusters of molecules with different survival modes were revealed by unsupervised cluster analysis of DEAs. AS events may be important determinants of prognosis and bio‐modulation in prostate cancer. In this study, we established strong prognostic predictors, discovered a splicing network that may be a potential mechanism, and provided further validated therapeutic targets.

The use of the BRAF inhibitor vemurafenib exhibits drug resistance in the treatment of thyroid cancer (TC), and finding more effective multitarget combination therapies may be an important solution. In the present study, we found strong correlations between Ref-1 high expression and BRAF mutation, lymph node metastasis, and TNM stage. The oxidative stress environment induced by structural activation of BRAF upregulates the expression of Ref-1, which caused intrinsic resistance of PTC to vemurafenib. Combination inhibition of the Ref-1 redox function and BRAF could enhance the antitumor effects of vemurafenib, which was achieved by blocking the action of Ref-1 on BRAF proteins. Furthermore, combination treatment could cause an overload of autophagic flux via excessive AMPK protein activation, causing cell senescence and cell death in vitro. And combined administration of Ref-1 and vemurafenib in vivo suppressed PTC cell growth and metastasis in a cell-based lung metastatic tumor model and xenogeneic subcutaneous tumor model. Collectively, our study provides evidence that Ref-1 upregulation via constitutive activation of BRAF in PTC contributes to intrinsic resistance to vemurafenib. Combined treatment with a Ref-1 redox inhibitor and a BRAF inhibitor could make PTC more sensitive to vemurafenib and enhance the antitumor effects of vemurafenib by further inhibiting the MAPK pathway and activating the excessive autophagy and related senescence process.

ObjectiveCentral lymph node metastasis (CLNM) is a predictor of poor prognosis for papillary thyroid carcinoma (PTC) patients. The options for surgeon operation or follow-up depend on the state of CLNM while accurate prediction is a challenge for radiologists. The present study aimed to develop and validate an effective preoperative nomogram combining deep learning, clinical characteristics and ultrasound features for predicting CLNM.Materials and methodsIn this study, 3359 PTC patients who had undergone total thyroidectomy or thyroid lobectomy from two medical centers were enrolled. The patients were divided into three datasets for training, internal validation and external validation. We constructed an integrated nomogram combining deep learning, clinical characteristics and ultrasound features using multivariable logistic regression to predict CLNM in PTC patients.ResultsMultivariate analysis indicated that the AI model-predicted value, multiple, position, microcalcification, abutment/perimeter ratio and US-reported LN status were independent risk factors predicting CLNM. The area under the curve (AUC) for the nomogram to predict CLNM was 0.812 (95% CI, 0.794-0.830) in the training cohort, 0.809 (95% CI, 0.780-0.837) in the internal validation cohort and 0.829(95%CI, 0.785-0.872) in the external validation cohort. Based on the analysis of the decision curve, our integrated nomogram was superior to other models in terms of clinical predictive ability.ConclusionOur proposed thyroid cancer lymph node metastasis nomogram shows favorable predictive value to assist surgeons in making appropriate surgical decisions in PTC treatment.

Background: Hepatitis B virus X protein (HBx) is an indispensable progression factor in hepatocellular carcinoma (HCC). CCL15 could be a peculiar proteomic biomarker of HCC with tumorigenesis and tumor invasion. Objective: The aim of study was to explore the relationship between HBx and CCL15 expression in HCC. Methods: HBV–positive HCC pathological tissue samples and corresponding adjacent non-tumor liver tissues were clearly collected. The expression of HBx and CCL15 was analyzed by immunohistochemistry, real-time polymerase chain reaction (PCR) and western blot analysis in tissues or in vitro. Results: The levels of CCL15 mRNA and protein expression in HCC samples were observably higher than the ones of adjacent non-tumor liver tissues. The CCL15 was significantly associated with the expression of HBx in HBV-positive HCC samples. The up-regulation of HBx induced CCL15 expression in vitro. The high expression score of CCL15 was significant associated with the poor prognosis of HCC patients. Conclusions: The CCL15 expression was observably associated with HBx in HCC patients. The CCL15 may be considered as a indicator in clinical managment of HBV-associated HCC.