Lung cancer is one of the most common malignant tumors in human beings. It is highly fatal, as its early symptoms are not obvious. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the final diagnosis of many diseases. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far outpace the number of pathologists, especially for the treatment of lung cancer in less developed countries. To address this problem, we propose a plug-and-play visual activation function (AF), CroReLU, based on a priori knowledge of pathology, which makes it possible to use deep learning models for precision medicine. To the best of our knowledge, this work is the first to optimize deep learning models for pathology image diagnosis from the perspective of AFs. By adopting a unique crossover window design for the activation layer of the neural network, CroReLU is equipped with the ability to model spatial information and capture histological morphological features of lung cancer such as papillary, micropapillary, and tubular alveoli. To test the effectiveness of this design, 776 lung cancer pathology images were collected as experimental data. When CroReLU was inserted into the SeNet network (SeNet_CroReLU), the diagnostic accuracy reached 98.33%, which was significantly better than that of common neural network models at this stage. The generalization ability of the proposed method was validated on the LC25000 dataset with completely different data distribution and recognition tasks in the face of practical clinical needs. The experimental results show that CroReLU has the ability to recognize inter- and intra-class differences in cancer pathology images, and that the recognition accuracy exceeds the extant research work on the complex design of network layers.
24 April 2024 in Computers in Biology and Medicine
Remote sensing image segmentation is crucial for environmental monitoring, disaster assessment, and resource management, but its performance largely depends on the quality of the dataset. Although several high-quality datasets are broadly accessible, data scarcity remains for specialized tasks like marine oil spill segmentation. Such tasks still rely on manual annotation, which is both time-consuming and influenced by subjective human factors. The Segment Anything Model 2 (SAM2) has strong potential as an automatic annotation framework but struggles to perform effectively on heterogeneous, low-contrast remote sensing imagery. To address these challenges, we introduce a novel label enhancement and automatic annotation framework, termed SAM2-ELNet (Enhancement and Labeling Network). Specifically, we employ the frozen Hiera backbone from the pre-trained SAM2 as the encoder, while fine-tuning the adapter and decoder for different remote sensing tasks. Additionally, the proposed framework includes a label quality evaluator for filtering, ensuring the reliability of the generated labels. We design a series of experiments targeting resource-limited remote sensing tasks and evaluate our method on two datasets: the Deep-SAR Oil Spill (SOS) dataset with Synthetic Aperture Radar (SAR) imagery, and the CHN6-CUG Road dataset with Very High Resolution (VHR) optical imagery. The proposed framework can enhance coarse annotations and generate reliable training data under resource-limited conditions. Fine-tuned on only 30% of the training data, it generates automatically labeled data. A model trained solely on these achieves slightly lower performance than using the full original annotations, while greatly reducing labeling costs and offering a practical solution for large-scale remote sensing interpretation.
28 January 2026 in Expert Systems with Applications
Urban taxi serves as an irreplaceable tool in public transportation systems. The balancing of demand-and-supply can be of significant social benefit, for which the equilibrium method for urban taxis, especially with dynamic trip demands, is not well studied yet. In this paper, we formally define the equilibrium problem and propose a coarse-grained dynamic balancing algorithm. It efficiently evaluates the trip demand distribution pattern and schedules supplies to more unbalanced regions. We first propose a density-based blocking algorithm to detect regions that are with more travel demands. A trip demand merging strategy is then proposed, which checks the correlation of trip demands to merge the trips into ones. To reduce the computation load, a lazy trip correlation strategy is devised to speed up the merging process. By calculating the defined balance factor, a scheduling algorithm is proposed to realize the trip merge and supply translocation based balancing approach. We evaluated our approach using a month of global positioning system (GPS) trajectories generated by 13,000 taxis of Shanghai. By learning the spatiotemporal distribution of historical taxi demand-and-supplies, we simulated an inflated trip demand platform. Tested on this platform with extensive experiments, the proposed approach demonstrates its effectiveness and scalability.
The advancement of autonomous driving technology is becoming increasingly vital in the modern technological landscape, where it promises notable enhancements in safety, efficiency, traffic management, and energy use. Despite these benefits, conventional deep reinforcement learning algorithms often struggle to effectively navigate complex driving environments. To tackle this challenge, we propose a novel network called DynamicNoise, which was designed to significantly boost the algorithmic performance by introducing noise into the deep Q-network (DQN) and double deep Q-network (DDQN). Drawing inspiration from the NoiseNet architecture, DynamicNoise uses stochastic perturbations to improve the exploration capabilities of these models, thus leading to more robust learning outcomes. Our experiments demonstrated a 57.25% improvement in the navigation effectiveness within a 2D experimental setting. Moreover, by integrating noise into the action selection and fully connected layers of the soft actor–critic (SAC) model in the more complex 3D CARLA simulation environment, our approach achieved an 18.9% performance gain, which substantially surpassed the traditional methods. These results confirmed that the DynamicNoise network significantly enhanced the performance of autonomous driving systems across various simulated environments, regardless of their dimensionality and complexity, by improving their exploration capabilities rather than just their efficiency.