Self-supervised learning (SSL) has emerged as a powerful paradigm for medical image representation learning, particularly in settings with limited labeled data. However, existing SSL methods often rely on complex architectures, anatomy-specific priors, or heavily tuned augmentations, which limit their scalability and generalizability. More critically, these models are prone to shortcut learning, especially in modalities like chest X-rays, where anatomical similarity is high and pathology is subtle. In this work, we introduce DiSSECT -- Discrete Self-Supervision for Efficient Clinical Transferable Representations, a framework that integrates multi-scale vector quantization into the SSL pipeline to impose a discrete representational bottleneck. This constrains the model to learn repeatable, structure-aware features while suppressing view-specific or low-utility patterns, improving representation transfer across tasks and domains. DiSSECT achieves strong performance on both classification and segmentation tasks, requiring minimal or no fine-tuning, and shows particularly high label efficiency in low-label regimes. We validate DiSSECT across multiple public medical imaging datasets, demonstrating its robustness and generalizability compared to existing state-of-the-art approaches.

The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample selection as an alternative efficient paradigm plays an important direction to accelerate the training process. However, recent advances on sample selection either mostly rely on an oracle model to offline select a high-quality coreset, which is limited in the cold-start scenarios, or focus on online selection based on real-time model predictions, which has not sufficiently or efficiently considered the noisy correspondence. To address this dilemma, we propose a novel Differential-Informed Sample Selection (DISSect) method, which accurately and efficiently discriminates the noisy correspondence for training acceleration. Specifically, we rethink the impact of noisy correspondence on contrastive learning and propose that the differential between the predicted correlation of the current model and that of a historical model is more informative to characterize sample quality. Based on this, we construct a robust differential-based sample selection and analyze its theoretical insights. Extensive experiments on three benchmark datasets and various downstream tasks demonstrate the consistent superiority of DISSect over current state-of-the-art methods. Source code is available at: https://github.com/MediaBrain-SJTU/DISSect.

Surgical procedures are inherently complex and dynamic, with intricate dependencies and various execution paths. Accurate identification of the intentions behind critical actions, referred to as Primary Intentions (PIs), is crucial to understanding and planning the procedure. This paper presents a novel framework that advances PI recognition in instructional videos by combining top-down grammatical structure with bottom-up visual cues. The grammatical structure is based on a rich corpus of surgical procedures, offering a hierarchical perspective on surgical activities. A grammar parser, utilizing the surgical activity grammar, processes visual data obtained from laparoscopic images through surgical action detectors, ensuring a more precise interpretation of the visual information. Experimental results on the benchmark dataset demonstrate that our method outperforms existing surgical activity detectors that rely solely on visual features. Our research provides a promising foundation for developing advanced robotic surgical systems with enhanced planning and automation capabilities.

Surgical triplet recognition is an essential building block to enable next-generation context-aware operating rooms. The goal is to identify the combinations of instruments, verbs, and targets presented in surgical video frames. In this paper, we propose DiffTriplet, a new generative framework for surgical triplet recognition employing the diffusion model, which predicts surgical triplets via iterative denoising. To handle the challenge of triplet association, two unique designs are proposed in our diffusion framework, i.e., association learning and association guidance. During training, we optimize the model in the joint space of triplets and individual components to capture the dependencies among them. At inference, we integrate association constraints into each update of the iterative denoising process, which refines the triplet prediction using the information of individual components. Experiments on the CholecT45 and CholecT50 datasets show the superiority of the proposed method in achieving a new state-of-the-art performance for surgical triplet recognition. Our codes will be released.

Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars. One of the principal benefits of counterfactual explanations is allowing users to explore "what-if" scenarios through what does not and cannot exist in the data, a quality that many other forms of explanation such as heatmaps and influence functions are inherently incapable of doing. However, most previous work on generative explainability cannot disentangle important concepts effectively, produces unrealistic examples, or fails to retain relevant information. We propose a novel approach, DISSECT, that jointly trains a generator, a discriminator, and a concept disentangler to overcome such challenges using little supervision. DISSECT generates Concept Traversals (CTs), defined as a sequence of generated examples with increasing degrees of concepts that influence a classifier's decision. By training a generative model from a classifier's signal, DISSECT offers a way to discover a classifier's inherent "notion" of distinct concepts automatically rather than rely on user-predefined concepts. We show that DISSECT produces CTs that (1) disentangle several concepts, (2) are influential to a classifier's decision and are coupled to its reasoning due to joint training (3), are realistic, (4) preserve relevant information, and (5) are stable across similar inputs. We validate DISSECT on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that it performs consistently well and better than existing methods.

In the 1930s and 40s, around the birth of the "automatic computer", mathematicians wanted to formalise what we mean when we say some result or some function is "effectively computable", whether by machine or human. A "computer", originally, was a person who performed arithmetic calculations. The "effectively" part is included to indicate that we are not concerned with the time any particular computer might take to produce the result, so long as it would get there eventually. They wanted to find the simplest possible system that could be said to compute. Several such systems were invented and for the most part looked entirely unlike each other. Remarkably, they were all eventually shown to be equivalent in the sense that any one could be made to behave like the others.

Artificial intelligence scans haystacks with tremendous precision. It will MATCH the combination of D. Smith, Doug Smith, and Douglas Smith on one side, with activity that sums to 1,000 with Douglas H. Smith on the other side, that also sums to 1,000. Intelligence that matches ACH transfers on a Friday with bank transactions that arrive on the following Monday. Intelligence that looks at every combination of every column to look for the best matches (meaning the ones with the most matching columns) and then methodically identifying matches of lesser quality. And enabling the user to identify each segment of the haystack. It matches data in smart ways.

After reading the press releases for this batch of 24 research reports, although they vary widely in their forecasts, they almost all agree that most segments of the robotics industry are expected to grow at a double-digit pace at least through 2022. Drone Identification System Market April 2017, Markets and Markets, $5,650 The drone identification market is estimated to grow from $801.8 Million in 2016 to $16 billion by 2022, at a CAGR 64.64% during the forecast period. Automated Guided Vehicle Market April 2017, Markets and Markets, $5,650 The automated guided vehicle market is expected to reach $2.68 billion by 2022, at a CAGR of 9.34% between 2017 and 2022. The growth of this market is propelled by advancements in automation, emphasis on workplace safety, and the growing need to cut down operational cost and increase productivity. Global smart robots market January 2017, 84 pages, TechNavio, $2,500 Forecasts the global smart robots market to grow at a CAGR of 20.65% during the period 2016-2020.