DPAM-PSPNet: ultrasonic image segmentation of thyroid nodule based on dual-path attention mechanism.

Objective.Deep learning has demonstrated its versatility in the medical field, particularly in medical image segmentation, image classification, and other forms of automated diagnostics. The clinical diagnosis of thyroid nodules requires radiologists to locate nodules, diagnose conditions based on nodule boundaries, textures and their experience. This task is labor-intensive and tiring; therefore, an automated system for accurate thyroid nodule segmentation is essential. In this study, a model named DPAM-PSPNet was proposed, which automatically segments nodules in thyroid ultrasound images and enables to segment malignant nodules precisely.Approach.In this paper, accurate segmentation of nodule edges is achieved by introducing the dual path attention mechanism (DPAM) in PSPNet. In one channel, it captures global information with a lightweight cross-channel interaction mechanism. In other channel, it focus on nodal margins and surrounding information through the residual bridge network. We also updated the integrated loss function to accommodate the DPAM-PSPNet.Main results.The DPAM-PSPNet was tested against the classical segmentation model. Ablation experiments were designed for the two-path attention mechanism and the new loss function, and generalization experiments were designed on the public dataset. Our experimental results demonstrate that DPAM-PSPNet outperforms other existing methods in various evaluation metrics. In the model comparison experiments, it achieved performance with an mIOU of 0.8675, mPA of 0.9357, mPrecision of 0.9202, and Dice coefficient of 0.9213.Significance.The DPAM-PSPNet model can segment thyroid nodules in ultrasound images with little training data and generate accurate boundary regions for these nodules.

Preparation of a Low-Protein-Fouling and High-Protein-Retention Membrane via Novel Pre-Hydrolysis Treatment of Polyacrylonitrile (PAN).

The attainment of high-protein-retention and low-protein-fouling membranes is crucial for industries that necessitate protein production or separation process. The present study aimed to develop a novel method for preparing polyacrylonitrile (PAN) membranes possessing a highly hydrophilic and negatively charged surface as well as interior structure. The method involved a pre-hydrolysis treatment during the preparation of the PAN dope solution, followed by phase inversion in an alkaline solution. Chemical and material characterization of the dopes and membranes uncovered that the cyclized PAN structure served as a reaction intermediate that facilitated strong hydrolysis effect during phase inversion and homogeneously formed carboxyl groups in the membrane's interior structure. The resulting membrane showed a highly hydrophilic surface with a contact angle of 12.4° and demonstrated less than 21% flux decay and more than 95% flux recovery during multi-cycle filtration of bovine serum albumin (BSA) solution, with a high protein rejection rate of 96%. This study offers a facile and effective alternative for preparing PAN membranes with enhanced antifouling and protein-retention properties.

Rh(II)/Brønsted Acid Catalyzed General and Highly Diastereo- and Enantioselective Propargylation of in Situ Generated Oxonium Ylides and C-Alkynyl N-Boc N,O-Acetals: Synthesis of Polyfunctional Propargylamines.

The first metal/organo cooperatively catalyzed asymmetric reaction of C-alkynyl N-Boc-protected N,O-acetals with in situ generated oxonium ylides has been developed. This new type of propargylation allows for the efficient synthesis of structurally diverse unreported chiral propargylamines bearing oxa-quaternary stereocenters. The reaction features unprecedented substrate scope and high diastereo- and enantioselectivity. Theoretical studies suggest a novel cooperative catalysis model and the unique transfer of R2OH.