Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears

Technical advancements significantly improve earlier diagnosis of cervical cancer, but accurate diagnosis is still difficult due to various factors. We develop an artificial intelligence assistive diagnostic solution, AIATBS, to improve cervical liquid-based thin-layer cell smear diagnosis according to clinical TBS criteria. We train AIATBS with >81,000 retrospective samples. It integrates YOLOv3 for target detection, Xception and Patch-based models to boost target classification, and U-net for nucleus segmentation. We integrate XGBoost and a logical decision tree with these models to optimize the parameters given by the learning process, and we develop a complete cervical liquid-based cytology smear TBS diagnostic system which also includes a quality control solution. We validate the optimized system with >34,000 multicenter prospective samples and achieve better sensitivity compared to senior cytologists, yet retain high specificity while achieving a speed of <180s/slide. Our system is adaptive to sample preparation using different standards, staining protocols and scanners.

Development of a Membrane Liquid-Based Thin-Layer Cell Film Maker

Specimen production is a key step in cytological diagnosis. This paper proposes a membrane liquid-based thin-layer cell film maker based on the principle of liquid-based thin-layer cell production. To be specific, the designed maker mainly consists of two parts including the mechanical system and control system. For the mechanical part, a novel type of polar coordinate manipulator is developed with the corresponding working scheme. In order to handle cell breakage and collection, a dynamic sealing head system is designed, which saves cost and improves automation. For the control part, both hardware and software are designed to realize the functions including the motion feedback and control of mechanical components, the measurement and adjustment of the pressure system, and the real-time information interaction between human and machine interface. Experimental results demonstrate that the developed maker is capable of fully meeting the requirements of clinical pathology, clinical detection and diagnosis, owing to the advantages such as the compact structure, high cost performance, stable performance and high satisfaction rate.

Staircase voltammetry of dissolved redox couple in a thin layer twin electrode cell

A model of reversible and quasi-reversible electrode reaction of dissolved redox couple is developed for the staircase voltammetry and the twin electrode thin layer cell. It is assumed that the neutral molecule is oxidized to a monovalent cation. The calculations were performed for the absence of supporting electrolyte and for its various concentrations. The influence of migration of cations and of IRΩ drop on the peak currents and peak potentials was investigated. Also, the kinetically controlled electrode reactions were simulated. These reactions can be distinguished from the reactions influenced by the resistance in the solution.

(Invited) New Carbon Electrodes for Neurochemistry

Carbon-fiber microelectrodes are the standard for neurochemical measurements, but improvements can be made for both sensitivity and spatial resolution. In this talk, I will cover how principles of thin layer cell electrochemistry are driving the design of new carbon electrodes. Specifically, electrodes that have roughness on the micron scale or cavities that trap dopamine are useful for enhancing the sensitivity and selectivity of electrodes. Three examples will be discussed, CNT yarn electrodes, cavity carbon nanopipettes, and 3D printed electrodes. These examples show how new technology, combined with a fundamental understanding of electrochemistry, is pushing development of better electrodes for neurochemistry.

A new thin layer cell for battery related DEMS-experiments: the activity of redox mediators in the Li–O2 cell

The activity of four different redox mediators was investigated with DEMS. The paper provides information about the underlying mechanism of Li2O2 oxidation by a redox mediator as well as about the stability of the redox mediator.