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.

Fabrication of porous polyimide as cathode for high performance lithium-ion battery.

Herein, we report the preparation of porous polyimide (PI) with a cost-effective synthesis process by polycondensation between melamine and dianhydride monomers. The prepared porous PI served as a cathode for lithium-ion batteries (LIBs), and delivers a high discharge platform of 2.1 V and satisfactory electrochemical performance. Thus, the porous PI cathode provides another choice for LIBs.

Sequential therapy with combined trans-papillary endoscopic naso-pancreatic and endoscopic retrograde pancreatic drainage for pancreatic pseudocysts.

BACKGROUND: Endoscopic retrograde pancreatic drainage (ERPD) and stent implantation has become the major treatment method for pancreatic pseudocysts. However, it is associated with a high recurrence rate and infection. AIM: To manage pancreatic pseudocysts by sequential therapy with endoscopic naso-pancreatic drainage (ENPD) combined with ERPD and evaluate the treatment outcome. METHODS: One hundred and sixty-two cases of pancreatic pseudocyst confirmed by endoscopic examination at our hospital between January 2014 and January 2020 were retrospectively analyzed. There were 152 cases of intubation via the duodenal papilla, of which 92 involved pancreatic duct stent implantation and 60 involved sequential therapy with combined ENPD and ERPD (two-step procedure). The success rate of the procedure, incidence of complications (infection, bleeding, etc.), recurrence, and length and cost of hospitalization were compared between the two groups. RESULTS: The incidence of infection was significantly higher in the ERPD group (12 cases) than in the two-step procedure group (2 cases). Twelve patients developed infection in the ERPD group, and anti-infection therapy was effective in five cases but not in the remaining seven cases. Infection presented as fever and chills in the two-step procedure group. The reoperation rate was significantly higher in the ERPD group with seven cases compared with zero cases in the two-step procedure group (P < 0.05). Similarly, the recurrence rate was significantly higher in the ERPD group (19 cases) than in the two-step procedure group (0 cases). CONCLUSION: Sequential therapy with combined ENPD and ERPD is safe and effective in patients with pancreatic pseudocysts.