A deep-learning-based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest X-ray.

Accurate identification and localization of multiple abnormalities are crucial steps in the interpretation of chest X-rays (CXRs); however, the lack of a large CXR dataset with bounding boxes severely constrains accurate localization research based on deep learning. We created a large CXR dataset named CXR-AL14, containing 165,988 CXRs and 253,844 bounding boxes. On the basis of this dataset, a deep-learning-based framework was developed to identify and localize 14 common abnormalities and calculate the cardiothoracic ratio (CTR) simultaneously. The mean average precision values obtained by the model for 14 abnormalities reached 0.572-0.631 with an intersection-over-union threshold of 0.5, and the intraclass correlation coefficient of the CTR algorithm exceeded 0.95 on the held-out, multicentre and prospective test datasets. This framework shows an excellent performance, good generalization ability and strong clinical applicability, which is superior to senior radiologists and suitable for routine clinical settings.

High lymphatic vessel density and presence of lymphovascular invasion both predict poor prognosis in breast cancer.

BACKGROUND: Lymphatic vessel density and lymphovascular invasion are commonly assessed to identify the clinicopathological outcomes in breast cancer. However, the prognostic values of them on patients' survival are still uncertain. METHODS: Databases of PubMed, Embase, and Web of Science were searched from inception up to 30 June 2016. The hazard ratio with its 95% confidence interval was used to determine the prognostic effects of lymphatic vessel density and lymphovascular invasion on disease-free survival and overall survival in breast cancer. RESULTS: Nineteen studies, involving 4215 participants, were included in this study. With the combination of the results of lymphatic vessel density, the pooled hazard ratios and 95% confidence intervals were 2.02 (1.69-2.40) for disease-free survival and 2.88 (2.07-4.01) for overall survival, respectively. For lymphovascular invasion study, the pooled hazard ratios and 95% confidence intervals were 1.81 (1.57-2.08) for disease-free survival and 1.64 (1.43-1.87) for overall survival, respectively. In addition, 29.56% (827/2798) of participants presented with lymphovascular invasion in total. CONCLUSIONS: Our study demonstrates that lymphatic vessel density and lymphovascular invasion can predict poor prognosis in breast cancer. Standardized assessments of lymphatic vessel density and lymphovascular invasion are needed.

Sensitization of breast cancer cells to paclitaxel by dichloroacetate through inhibiting autophagy.

Chemotherapy is still the main adjuvant strategy in the treatment of cancer, however, chemoresistance is also frequently encountered. Autophagy inhibition has been widely accepted as a promising therapeutic strategy in cancer, while the lack of effective and specific autophagy inhibitors hinders its application. Here we found that dichloroacetate (DCA), a small molecule compound, could significantly inhibit the autophagy induced by Doxorubicin in breast cancer cells. And DCA markedly enhances Doxorubicin-induced breast cancer cell death and anti-proliferation in vitro. But the sensitization to Dox of DCA was significantly reduced through induction of autophagy by rapamycin. Moreover, the combined therapy of Dox and DCA could significantly inhibit tumor growth in vivo and prolong mouse survival time. Taken together, we demonstrate that DCA could inhibit doxorubicin-inducing autophagy and provide a novel strategy for improving the anti-cancer efficacy of chemotherapy.