Search

Medical image segmentation methods based on deep learning show good performance advantages and application prospects, but such methods require experienced medical experts to spend a lot of time labeling data. To address this problem in gland segmentation research, a model named ILECGJL based on incomplete label error correction and group joint learning is proposed, which significantly reduces the dependence on labeled data while ensuring segmentation performance. ILECGJL employs the proposed incomplete label error correction method to capture semantic relationships between labeled and unlabeled images, enhancing the quality of pseudo labels and improving the accuracy of gland segmentation. At the same time, ILECGJL harnesses the proposed group joint learning strategy to enhance the model's robustness on pseudo label noise, further boosting segmentation performance. Experimental results on the CRAG dataset confirm that our proposed label error correction method yields substantial improvements based on initial segmentation predictions. The performance of the ILECGJL model demonstrates significant enhancements compared to fully supervised methods that solely rely on labeled data and outperforms other mainstream semi-supervised approaches. Results and comparisons on the GlaS dataset showcase good generalization ability of the ILECGJL model. Moreover, due to its modular design and customizability, ILECGJL offers high flexibility and can be conveniently integrated into different segmentation models. • Incomplete Label Error Correction and Group Joint Learning model. • A group joint learning strategy for the label error correction. • Gland segmentation on GlaS and CRAG datasets achieves SOTA performance. [ABSTRACT FROM AUTHOR]

The electrochemical sensing of dopamine is of great significance for studying and treating neurochemical diseases due to its potential feasibility for in vivo diagnostics. The commonly used sensors suffer from low sensitivity, the interference of ascorbic acid, and poor flexibility. In this paper, the function of electrode substrates including polyolefin, polystyrene, and polyethylene terephthalate films were investigated for their ability to improve electrochemical performances and provide favorable flexibility. The interference from ascorbic acid was cut down to a minimum by reducing the electrochemical resistance and the ascorbic acid diffusion current. The results demonstrate that gold electrodes prepared on polyolefin films exhibit a low charge transfer resistance of about 20 Ω, high sensitivity of dopamine detection (7.8 μA/μM), which is about 312 folds that of silicon electrode (0.025 μA/μM) and excellent flexibility. Having regulated the fabrication process of graphene by altering self-assembly layers and modification area, the sensor shows a dopamine detection limit of 0.11 μM in the presence of 500 μM ascorbic acid, and a sensitivity of 0.33 μA/μM. This work is valuable for the further improvement of the sensitivity and selectivity of the electrochemical sensor. • This paper presents a flexible micro sensor on a polyolefin substrate exhibits a high sensitivity of dopamine detection (7.8 μA/μM), about 312 folds of silicon-based sensor (0.025 μA/μM). • This proposed sensor shows a considerably low detection limit of dopamine (0.11 μM) in the existence of 500 μM ascorbic acid, compared with the most pure graphene-modified dopamine sensor. • A simple model of voltammetry curve simulation is reported to identify the interference mechanism of ascorbic acid for enhancing performance of the proposed microsensors. • Layer-by-layer self-assembly of graphene minimizes the interference from ascorbic acid by reducing electrochemical resistance and enhancing ascorbic acid diffusion. This is a new discovery in this paper. [ABSTRACT FROM AUTHOR]