In utilizing deep learning techniques for medical image segmentation, two types of imbalance issues are observed: inter-class imbalance between majority and minority classes and intra-class imbalance between easy and hard samples. However, existing loss functions typically confuse these issues, leading to enhancements that cater to only one aspect. Moreover, loss functions optimized for specific tasks often exhibit limited generalizability. To address these issues, we propose Inter-class and Intra-class Balance loss, as well as a unified loss termed Balance loss. The Inter-class Balance loss controls the extent of hard sample mining for majority class samples by considering the frequency of minority classes present in each input image. This approach requires no manual adjustment weights and adapts automatically to different datasets. The Intra-class Balance loss enhances the network's ability to learn from hard samples by performing mining on hard samples within each class. We evaluate our loss functions on five segmentation tasks with varying degrees of class imbalance. The experimental results show that our proposed Balance loss enhances segmentation performance compared with the current loss functions and exhibits superior robustness.

Radiology report generation (RRG), intended to automatically generate a coherent free-text report describing the clinical observations of a radiograph, has been attracting increasing attention from researchers. In recent years, the Transformer-based encoder-decoder architecture has been adopted by most existing methods. However, they neglect the structural rationality issue when applying this single-modal architecture to the multi-modal RRG task, where information can only flow from visual features to textual features, but not in the opposite direction. This information asymmetry results in visual features having no knowledge of the textual features, sending out all visual information, including a large amount of heterogeneous noise. Consequently, this introduces significant resistance to the downstream decoder, which substantially limits or even harms the generation process. To tackle this problem, we present a method where a cross-counter-repeat attention is developed to integrate useful information from two separate modalities, and a memory-driven visual semantics enhancing module is designed to reinforce the visual features with strong time-ordered semantic information. Experimental results on the widely-used IU-Xray dataset show that our approach achieves the state-of-the-art performance, with a remarkable 6.9% improvement in BLEU-4 score. Further analyses also demonstrate that our method can generate sufficiently comprehensive reports to assist radiologists in their clinical decision-making.

Semi-supervised Camouflaged Object Detection (SSCOD) aims to reduce reliance on costly pixel-level annotations by leveraging limited annotated data and abundant unlabeled data. However, existing SSCOD methods based on Teacher-Student frameworks suffer from severe prediction bias and error propagation under scarce supervision, while their multi-network architectures incur high computational overhead and limited scalability. To overcome these limitations, we propose ST-SAM, a highly annotation-efficient yet concise framework that breaks away from conventional SSCOD constraints. Specifically, ST-SAM employs Self-Training strategy that dynamically filters and expands high-confidence pseudo-labels to enhance a single-model architecture, thereby fundamentally circumventing inter-model prediction bias. Furthermore, by transforming pseudo-labels into hybrid prompts containing domain-specific knowledge, ST-SAM effectively harnesses the Segment Anything Model's potential for specialized tasks to mitigate error accumulation in self-training. Experiments on COD benchmark datasets demonstrate that ST-SAM achieves state-of-the-art performance with only 1% labeled data, outperforming existing SSCOD methods and even matching fully supervised methods. Remarkably, ST-SAM requires training only a single network, without relying on specific models or loss functions. This work establishes a new paradigm for annotation-efficient SSCOD. Codes will be available at https://github.com/hu-xh/ST-SAM.

Medical image segmentation is a critical task for clinical diagnosis and research. However, dealing with highly imbalanced data remains a significant challenge in this domain, where the region of interest (ROI) may exhibit substantial variations across different slices. This presents a significant hurdle to medical image segmentation, as conventional segmentation methods may either overlook the minority class or overly emphasize the majority class, ultimately leading to a decrease in the overall generalization ability of the segmentation results. To overcome this, we propose a novel approach based on multi-step reinforcement learning, which integrates prior knowledge of medical images and pixel-wise segmentation difficulty into the reward function. Our method treats each pixel as an individual agent, utilizing diverse actions to evaluate its relevance for segmentation. To validate the effectiveness of our approach, we conduct experiments on four imbalanced medical datasets, and the results show that our approach surpasses other state-of-the-art methods in highly imbalanced scenarios. These findings hold substantial implications for clinical diagnosis and research.

The next generation IP networks will provide differentiated services to the applications. There is a strong need to design new bandwidth constraint (BC) models to meet the new requirements. A desirable BC model takes both bandwidth isolation and bandwidth utilization into account. Conventional BC models have their limits due to their static nature. In this paper, we propose a new BC model, called the self-adaptive bandwidth constraint model (SAM), in which the priorities of different application classes are adaptively updated. The performance of the SAM is compared with three representative conventional BC models. The simulation results suggest that the SAM has certain advantages over others.

Abstract ANIX is a multiprocessor operating system to be used in the backbone Asynchronous Transfer Mode (ATM) switches. In ANIX, memory contention by processes running on different CPUs is managed with a protocol called WWWH (when to sleep, who to sleep, where to sleep, and how to sleep). Tools are needed to test, debug, and tune the system running WWWH. This paper describes the experience and practice in design of SHMON, a performance tool that monitors the dynamic behavior of the running system. Copyright © 2004 John Wiley & Sons, Ltd.