Objectives/Hypothesis: To develop a deep-learning-based computer-aided diagnosis system for distinguishing laryngeal neoplasms (benign, precancerous lesions, and cancer) and improve the clinician-based accuracy of diagnostic assessments of laryngoscopy findings. Study Design: Retrospective study. Methods: A total of 24,667 laryngoscopy images (normal, vocal nodule, polyps, leukoplakia and malignancy) were collected to develop and test a convolutional neural network (CNN)-based classifier. A comparison between the proposed CNNbased classifier and the clinical visual assessments (CVAs) by 12 otolaryngologists was conducted. Results: In the independent testing dataset, an overall accuracy of 96.24% was achieved; for leukoplakia, benign, malignancy, normal, and vocal nodule, the sensitivity and specificity were 92.8% vs. 98.9%, 97% vs. 99.7%, 89% vs. 99.3%, 99.0% vs. 99.4%, and 97.2% vs. 99.1%, respectively. Furthermore, when compared with CVAs on the randomly selected test dataset, the CNN-based classifier outperformed physicians for most laryngeal conditions, with striking improvements in the ability to distinguish nodules (98% vs. 45%, P < .001), polyps (91% vs. 86%, P < .001), leukoplakia (91% vs. 65%, P < .001), and malignancy (90% vs. 54%, P < .001). Conclusions: The CNN-based classifier can provide a valuable reference for the diagnosis of laryngeal neoplasms during laryngoscopy, especially for distinguishing benign, precancerous, and cancer lesions.

Since there are not many studies on the application of polymeric surfactants in viscosity reduction emulsification of heavy oil, a series of polyether carboxylic acid–sulfonate polymeric surfactants were synthesized. The viscosity reduction performance and the effect of different chain lengths on the viscosity reduction effect were also investigated. The viscosity reduction, emulsification, wetting, and foaming performance tests showed that the viscosity reduction performance of this series of polymeric surfactants was excellent, with the viscosity reduction rate exceeding 95%, and the viscosity was reduced to 97 mPa·s by the polymeric surfactant with a molecular weight of 600 polyethers. It was also concluded that among the three surfactants with different side chains, the polymeric surfactant with a polyether molecular weight of 600, which is the medium side-chain length, had the best viscosity reduction performance. The study showed that the polyether carboxylic acid–sulfonate polymer surfactant had a promising application in the viscosity reduction of heavy oil.

Heavy oil exploitation needs efficient viscosity reducers to reduce viscosity, and polyether carboxylate viscosity reducers have a significant viscosity reduction effect on heavy oil. Previous work has studied the effect of different side chain lengths on this viscosity reducer, and now a series of polyether carboxylate viscosity reducers, including APAD, APASD, APAS, APA, and AP5AD (the name of the viscosity reducer is determined by the name of the desired monomer), with different electrical properties have been synthesized to investigate the effect of their different electrical properties on viscosity reduction performance. Through the performance tests of surface tension, contact angle, emulsification, viscosity reduction, and foaming, it was found that APAD viscosity reducers had the best viscosity reduction performance, reducing the viscosity of heavy oil to 81 mPa·s with a viscosity reduction rate of 98.34%, and the worst viscosity reduction rate of other viscosity reducers also reached 97%. Additionally, APAD viscosity reducers have the highest emulsification rate, and the emulsion formed with heavy oil is also the most stable. The net charge of APAD was calculated from the molar ratio of the monomers and the total mass to minimize the net charge. While the net charge of other surfactants was higher. It shows that the amount of the surfactant’s net charge affects the surfactant’s viscosity reduction effect, and the smaller the net charge of the surfactant itself, the better the viscosity reduction effect.