Recent developments underscore the potential of textual information in enhancing learning models for a deeper understanding of medical visual semantics. However, language-guided medical image segmentation still faces a challenging issue. Previous works employ implicit architectures to embed textual information. This leads to segmentation results that are inconsistent with the semantics represented by the language, sometimes even diverging significantly. To this end, we propose a novel cross-modal conditioned Reconstruction for Language-guided Medical Image Segmentation (RecLMIS) to explicitly capture cross-modal interactions, which assumes that well-aligned medical visual features and medical notes can effectively reconstruct each other. We introduce conditioned interaction to adaptively predict patches and words of interest. Subsequently, they are utilized as conditioning factors for mutual reconstruction to align with regions described in the medical notes. Extensive experiments demonstrate the superiority of our RecLMIS, surpassing LViT by 3.74% mIoU on the MosMedData+ dataset and 1.89% mIoU on the QATA-CoV19 dataset. More importantly, we achieve a relative reduction of 20.2% in parameter count and a 55.5% decrease in computational load. The code will be available at https://github.com/ShawnHuang497/RecLMIS.

Quality control in quantitative proteomics is a persistent challenge, particularly in identifying and managing outliers. Unsupervised learning models, which rely on data structure rather than predefined labels, offer potential solutions. However, without clear labels, their effectiveness might be compromised. Single models are susceptible to the randomness of parameters and initialization, which can result in a high rate of false positives. Ensemble models, on the other hand, have shown capabilities in effectively mitigating the impacts of such randomness and assisting in accurately detecting true outliers. Therefore, we introduced SEAOP, a Python toolbox that utilizes an ensemble mechanism by integrating multi-round data management and a statistics-based decision pipeline with multiple models. Specifically, SEAOP uses multi-round resampling to create diverse sub-data spaces and employs outlier detection methods to identify candidate outliers in each space. Candidates are then aggregated as confirmed outliers via a chi-square test, adhering to a 95% confidence level, to ensure the precision of the unsupervised approaches. Additionally, SEAOP introduces a visualization strategy, specifically designed to intuitively and effectively display the distribution of both outlier and non-outlier samples. Optimal hyperparameter models of SEAOP for outlier detection were identified by using a gradient-simulated standard dataset and Mann-Kendall trend test. The performance of the SEAOP toolbox was evaluated using three experimental datasets, confirming its reliability and accuracy in handling quantitative proteomics.

Polyp segmentation models have recently exhibited considerable success in computer-aided diagnostic systems. Despite the high performance demonstrated by numerous existing deep learning-based techniques on publicly available datasets, these methods still face challenges when it comes to accurate polyp recognition: (1) Undershoot and overshoot problems are frequent. (2) Robustness still needs to be improved in practical application scenarios. To tackle these challenges, we introduce a novel framework called Polyp2Former, which employs a decoupled mask feature strategy. Instead of optimizing the whole region, Polyp2Former divides the mask into the boundary and the body first and utilizes the boundary to refine the final result. It comprises three core components: the Query Embedding Module (QEM), the Mask Decoupling Module (MDM), and the Boundary Guided Module (BGM). These modules collectively contribute to achieving precise and resilient polyp segmentation. In QEM, the framework first embedded boundary and body information as input of MDM and BGM. In the MDM, we first warp the multiscale image features by learning a flow field to make the polyp more consistent, and the resulting body feature and the residual edge feature are further optimized under decoupled supervision by explicitly sampling different parts (polyp or boundary) pixels. In the BGM, we use the boundary map after mapping and the sigmoid function to guide the body feature to predict the final mask with better inner consistency and accurate boundary. Extensive experiments on four challenging polyp semantic segmentation benchmarks demonstrate that our proposed approach improves the segmentation accuracy and robustness significantly against the State-of-the-art methods through five-fold cross-validation and cross-datasets validation.

Underwater robots have been widely used in Marine environment monitoring, deep-sea resources exploration, underwater archaeology, and other fields. The underwater robot hovering is a very demanding technology, especially in a dynamic environment, the underwater multi-disturbance robot has a great influence, and accurate hovering of the underwater robot is the basic guarantee to complete the task. In this paper, a hybrid control strategy based on a neural network and PID is proposed to realize the perception and decision of complex environment states and realize the accurate hovering of the underwater robot. Experimental results show that the hybrid control based on neural network and PID can stably and accurately complete the hovering function, which proves the effectiveness of the algorithm. (Video: https://youtu.be/1GU4BKHeTB8t)

The precise positioning of underwater robots is the premise and foundation to complete other operations. Since a global positioning system (GPS) cannot be used underwater, and the positioning method of the underwater robot based on inertial navigation could cause significant errors, a multi-sensor information fusion method based on Elman neural network is proposed to solve these problems. The network is trained by taking data of doppler velocity log (DVL) and inertial measurement unit (IMU) as input and GPS as output. In the underwater area without GPS, the training network is used to predict the real-time position error of the acquired DVL and IMU data. The method can realize dynamic training and learning to improve the accuracy of the system. The experimental results show that the proposed method has lower positioning error than the traditional method, effectively inhibits the accumulation error of positioning, and improves underwater robots' positioning accuracy.

Breast cancer is a high-incidence type of cancer for women. Early diagnosis plays a crucial role in the successful treatment of the disease and the effective reduction of deaths. In this paper, deep learning technology combined with ultrasound imaging diagnosis was used to identify and determine whether the tumors were benign or malignant. First, the tumor regions were segmented from the breast ultrasound (BUS) images using the supervised block-based region segmentation algorithm. Then, a VGG-19 network pretrained on the ImageNet dataset was applied to the segmented BUS images to predict whether the breast tumor was benign or malignant. The benchmark data for bio-validation were obtained from 141 patients with 199 breast tumors, including 69 cases of malignancy and 130 cases of benign tumors. The experiment showed that the accuracy of the supervised block-based region segmentation algorithm was almost the same as that of manual segmentation; therefore, it can replace manual work. The diagnostic effect of the combination feature model established based on the depth feature of the B-mode ultrasonic imaging and strain elastography was better than that of the model established based on these two images alone. The correct recognition rate was 92.95%, and the AUC was 0.98 for the combination feature model.