Background-The incidence of thyroid cancer is rising steadily because of overdiagnosis and overtreatment conferred by widespread use of sensitive imaging techniques for screening. This overall incidence growth is especially driven by increased diagnosis of indolent and welldifferentiated papillary subtype and early-stage thyroid cancer, whereas the incidence of advancedstage thyroid cancer has increased marginally. Thyroid ultrasound is frequently used to diagnose thyroid cancer. The aim of this study was to use deep convolutional neural network (DCNN) models to improve the diagnostic accuracy of thyroid cancer by analysing sonographic imaging data from clinical ultrasounds.Methods-We did a retrospective, multicohort, diagnostic study using ultrasound images sets from three hospitals in China. We developed and trained the DCNN model on the training set, 131 731 ultrasound images from 17 627 patients with thyroid cancer and 180 668 images from 25 325 controls from the thyroid imaging database at Tianjin Cancer Hospital. Clinical diagnosis of the training set was made by 16 radiologists from Tianjin Cancer Hospital. Images from anatomical sites that were judged as not having cancer were excluded from the training set and only individuals with suspected thyroid cancer underwent pathological examination to confirm diagnosis. The model's diagnostic performance was validated in an internal validation set from Tianjin Cancer Hospital (8606 images from 1118 patients) and two external datasets in China (the

Nicotinamide phosphoribosyltransferase (NAMPT) possesses various functions in human cells, and altered NAMPT expression is associated with human carcinogenesis. The present study detected the expression of NAMPT in normal and cancerous breast tissues from 83 patients using immunohistochemistry, and analyzed its association with the clinicopathological and survival data of the patients. NAMPT was significantly overexpressed in the breast invasive ductal carcinoma tissues compared with adjacent normal mammary gland tissues. Upregulated NAMPT expression was associated with a larger tumor size, lymph node metastasis, advanced clinical tumor-node-metastasis stages, and estrogen receptor and progesterone receptor expression. Furthermore, NAMPT expression was associated with poor overall and disease-free survival in patients with breast cancer. In conclusion, NAMPT increased protein expression in tumor cells may contribute to the development and progression of breast invasive ductal carcinoma. Thus, detection of NAMPT expression might be useful as a biomarker for the early detection and prognosis prediction of breast cancer.

BackgroundThe different expression level of Dickkopf-1 (DKK-1) in different cancers shows that the function of DKK-1 depends on the histological type of the cancer cells and the tissue microenvironment. To our knowledge, the serum expression level of DKK-1 in breast cancer is little known.MethodsBlood samples from 125 consecutive patients diagnosed with breast cancer and 53 control subjects from March 2008 to August 2013 were investigated. Serum DKK-1 expression levels were measured by enzyme-linked immunosorbent assay (ELISA). The overall survival (OS) and relapse-free survival (RFS) analyzed by log-rank test, and survival curves were plotted according to Kaplan–Meier.ResultsThe mean serum level of DKK-1 in patients with breast cancer was 4.99 ± 1.50 ng/mL, and was significantly higher than that in healthy individuals (1.88 ± 0.81 ng/mL, P < 0.001). DKK-1 level correlated significantly with TNM stage (P = 0.009), tumor grade (P = 0.02), lymph node metastasis (P = 0.001), and expression of HER2 (P = 0.002). The DKK-1 expression level was classified as high or low in relation to the median value, and patients with breast cancer (n = 125) were divided into a high expression group (n = 63) and a low expression group (n = 62). The Kaplan-Meier method for survival analysis showed that the patients with a high serum DKK-1 level had a poorer OS (48.7% vs. 81.3%, p = 0.01) and RFS (24.3% vs. 71.6%, p = 0.003) than those with a low expression level. The multivariate Cox regression analysis indicated that serum DKK-1 level was independent prognostic factors for OS and RFS.ConclusionsSerum DKK-1 level can be used as a noninvasive biomarker for the prognosis of breast cancer.Virtual slidesThe virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/13000_2014_161

Hashimoto’s thyroiditis (HT) is the main cause of hypothyroidism. We develop a deep learning model called HTNet for diagnosis of HT by training on 106,513 thyroid ultrasound images from 17,934 patients and test its performance on 5051 patients from 2 datasets of static images and 1 dataset of video data. HTNet achieves an area under the receiver operating curve (AUC) of 0.905 (95% CI: 0.894 to 0.915), 0.888 (0.836–0.939) and 0.895 (0.862–0.927). HTNet exceeds radiologists’ performance on accuracy (83.2% versus 79.8%; binomial test, p < 0.001) and sensitivity (82.6% versus 68.1%; p < 0.001). By integrating serologic markers with imaging data, the performance of HTNet was significantly and marginally improved on the video (AUC, 0.949 versus 0.888; DeLong’s test, p = 0.004) and static-image (AUC, 0.914 versus 0.901; p = 0.08) testing sets, respectively. HTNet may be helpful as a tool for the management of HT.

The incidence of granulomatous mastitis (GLM) in multiparae as seriously affected the quality of life and breastfeeding of pregnant women after delivery, but the treatment is rarely reported. In this article, the development, healing, and lactation of 13 cases were reported and a retrospective analysis was performed. 10 cases of GLM were treated at the Breast Disease Prevention and Treatment Center of Haidian Maternal & Child Health Hospital of Beijing and 3 cases of GLM were treated in the Breast Department of Weihai Municipal Hospital of Shandong province from February 2017 to May 2019. Among the 13 patients, conservative symptomatic treatment was adopted during pregnancy and lactation: anti-infective therapy consisting of oral cephalosporin antibiotic for patients; ultrasound-guided puncture and drainage of pus or incision and drainage after abscess formation. Observation continued during the sinus tract phase. Postpartum breastfeeding was encouraged, especially on the affected side. In this study, the median healing time was 20 months and the average healing time was 30.4 months in 5 healthy breast lactation cases. In 8 cases of bilateral breast lactation, the median healing time was 30 months and the average healing time was 26.5 months. Linear regression test analysis: whether the affected breast was breast-fed after delivery had no effect on the postpartum wound healing time, P = .792. The wounds of 13 patients healed well after lactation, and none of them recurred since the last follow-up visit. There were no adverse events in all infants. Conservative symptomatic treatment for GLM of multiparous women during pregnancy and lactation and encouraging breastfeeding after delivery have no effect on infant health and the recovery time of patients.