We investigate partially identifiable queries in a class of causal models. We focus on acyclic Structural Causal Models that are quasi-Markovian (that is, each endogenous variable is connected with at most one exogenous confounder). We look into scenarios where endogenous variables are observed (and a distribution over them is known), while exogenous variables are not fully specified. This leads to a representation that is in essence a Bayesian network where the distribution of root variables is not uniquely determined. In such circumstances, it may not be possible to precisely compute a probability value of interest. We thus study the computation of tight probability bounds, a problem that has been solved by multilinear programming in general, and by linear programming when a single confounded component is intervened upon. We present a new algorithm to simplify the construction of such programs by exploiting input probabilities over endogenous variables. For scenarios with a single intervention, we apply column generation to compute a probability bound through a sequence of auxiliary linear integer programs, thus showing that a representation with polynomial cardinality for exogenous variables is possible. Experiments show column generation techniques to be superior to existing methods.

Poisoning attacks pose an increasing threat to the security and robustness of Artificial Intelligence systems in the military domain. The widespread use of open-source datasets and pretrained models exacerbates this risk. Despite the severity of this threat, there is limited research on the application and detection of poisoning attacks on object detection systems. This is especially problematic in the military domain, where attacks can have grave consequences. In this work, we both investigate the effect of poisoning attacks on military object detectors in practice, and the best approach to detect these attacks. To support this research, we create a small, custom dataset featuring military vehicles: MilCivVeh. We explore the vulnerability of military object detectors for poisoning attacks by implementing a modified version of the BadDet attack: a patch-based poisoning attack. We then assess its impact, finding that while a positive attack success rate is achievable, it requires a substantial portion of the data to be poisoned -- raising questions about its practical applicability. To address the detection challenge, we test both specialized poisoning detection methods and anomaly detection methods from the visual industrial inspection domain. Since our research shows that both classes of methods are lacking, we introduce our own patch detection method: AutoDetect, a simple, fast, and lightweight autoencoder-based method. Our method shows promising results in separating clean from poisoned samples using the reconstruction error of image slices, outperforming existing methods, while being less time- and memory-intensive. We urge that the availability of large, representative datasets in the military domain is a prerequisite to further evaluate risks of poisoning attacks and opportunities patch detection.

Mitotic figure detection is a crucial task in computational pathology, as mitotic activity serves as a strong prognostic marker for tumor aggressiveness. However, domain variability that arises from differences in scanners, tissue types, and staining protocols poses a major challenge to the robustness of automated detection methods. In this study, we introduce SDF-YOLO (Single Detect Focused YOLO), a lightweight yet domain-robust detection framework designed specifically for small, rare targets such as mitotic figures. The model builds on YOLOv11 with task-specific modifications, including a single detection head aligned with mitotic figure scale, coordinate attention to enhance positional sensitivity, and improved cross-channel feature mixing. Experiments were conducted on three datasets that span human and canine tumors: MIDOG ++, canine cutaneous mast cell tumor (CCMCT), and canine mammary carcinoma (CMC). When submitted to the preliminary test set for the MIDOG2025 challenge, SDF-YOLO achieved an average precision (AP) of 0.799, with a precision of 0.758, a recall of 0.775, an F1 score of 0.766, and an FROC-AUC of 5.793, demonstrating both competitive accuracy and computational efficiency. These results indicate that SDF-YOLO provides a reliable and efficient framework for robust mitotic figure detection across diverse domains.

We introduce a Partial Functional Dynamic Backdoor Diffusion-based Causal Model (PFD-BDCM), specifically designed for causal inference in the presence of unmeasured confounders with spatial heterogeneity and temporal dependency. The proposed PFD-BDCM framework addresses the restrictions of the existing approaches by uniquely integrating models for complex spatio-temporal dynamics with the analysis of multi-resolution variables. Specifically, the framework systematically mitigates confounding bias by integrating valid backdoor adjustment sets into a diffusion-based sampling mechanism. Moreover, it accounts for the intricate dynamics of unmeasured confounders through the deployment of region-specific structural equations and conditional autoregressive processes, and accommodates variables observed at heterogeneous resolutions via basis expansions for functional data. Our theoretical analysis establishes error bounds for counterfactual estimates of PFD-BDCM, formally linking reconstruction accuracy to counterfactual fidelity under monotonicity assumptions of structural equation and invertibility assumptions of encoding function. Empirical evaluations on synthetic datasets and real-world air pollution data demonstrate PFD-BDCM's superiority over existing methods.

Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs. Modern methods for bearing fault diagnosis rely heavily on vibration analysis and machine learning techniques, which often require extensive labeled data and may not adapt well to dynamic environments. This study explores the feasibility of reinforcement learning (RL), specifically Deep Q-Networks (DQNs), for bearing fault classification tasks in machine condition monitoring to enhance the accuracy and adaptability of bearing fault diagnosis. The results demonstrate that while RL models developed in this study can match the performance of traditional supervised learning models under controlled conditions, they excel in adaptability when equipped with optimized reward structures. However, their computational demands highlight areas for further improvement. These findings demonstrate RL's potential to complement traditional methods, paving the way for adaptive diagnostic frameworks.

--We investigate fine-tuning Vision-Language Models (VLMs) for multi-task medical image understanding, focusing on detection, localization, and counting of findings in medical images. Our objective is to evaluate whether instruction-tuned VLMs can simultaneously improve these tasks, with the goal of enhancing diagnostic accuracy and efficiency. Using MedMulti-Points, a multimodal dataset with annotations from endoscopy (polyps and instruments) and microscopy (sperm cells), we reformulate each task into instruction-based prompts suitable for vision-language reasoning. Results show that multi-task training improves robustness and accuracy. For example, it reduces the Count Mean Absolute Error (MAE) and increases Matching Accuracy in the Counting + Pointing task. However, trade-offs emerge, such as more zero-case point predictions, indicating reduced reliability in edge cases despite overall performance gains. Our study highlights the potential of adapting general-purpose VLMs to specialized medical tasks via prompt-driven fine-tuning. This approach mirrors clinical workflows, where radiologists simultaneously localize, count, and describe findings - demonstrating how VLMs can learn composite diagnostic reasoning patterns. The model produces interpretable, structured outputs, offering a promising step toward explainable and versatile medical AI. Medical imaging comes with numerous challenges, such as detecting subtle abnormalities, processing images captured under varied conditions, and managing high data volumes, all of which complicate automated analysis [1].

Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination. However, human reasoning inherently incorporates biases shaped by education, culture, and experience, suggesting their presence may be inevitable and potent ially valuable. We propose MEDLEY (Medical Ensemble Diagnostic system with Leveraged diversit Y), a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs rather than collapsing them into a consensus. Unlike traditional approaches that suppress disagreement, MEDLEY documents model - specific biases as potential strengths and treats hallucinations as provisional hypotheses for clinician verification. A proof - of - concept demonstrator was developed using over 30 large language models, creating a minimum viable product that preserved both consensus and minority views in synthetic cases, making diagnostic uncertainty and latent biases transparent for clinical oversight. While not yet a validated clini cal tool, the demonstration illustrates how structured diversity can enhance medical reasoning under clinician supervision. By reframing AI imperfection as a resource, MEDLEY offers a paradigm shift that opens new regulatory, ethical, and innovation pathwa ys for developing trustworthy medical AI systems.

Accurate sarcopenia diagnosis via ultrasound remains challenging due to subtle imaging cues, limited labeled data, and the absence of clinical context in most models. We propose MedVQA-TREE, a multimodal framework that integrates a hierarchical image interpretation module, a gated feature-level fusion mechanism, and a novel multi-hop, multi-query retrieval strategy. The vision module includes anatomical classification, region segmentation, and graph-based spatial reasoning to capture coarse, mid-level, and fine-grained structures. A gated fusion mechanism selectively integrates visual features with textual queries, while clinical knowledge is retrieved through a UMLS-guided pipeline accessing PubMed and a sarcopenia-specific external knowledge base. MedVQA-TREE was trained and evaluated on two public MedVQA datasets (VQA-RAD and PathVQA) and a custom sarcopenia ultrasound dataset. The model achieved up to 99% diagnostic accuracy and outperformed previous state-of-the-art methods by over 10%. These results underscore the benefit of combining structured visual understanding with guided knowledge retrieval for effective AI-assisted diagnosis in sarcopenia.

--Dermatological care via telemedicine often lacks the rich context of in-person visits. Clinicians must make diagnoses based on a handful of images and brief descriptions, without the benefit of physical exams, second opinions, or reference materials. While many medical AI systems attempt to bridge these gaps with domain-specific fine-tuning, this work hypothesized that mimicking clinical reasoning processes could offer a more effective path forward. This study tested seven vision-language models on medical visual question answering across six configurations: baseline models, fine-tuned variants, and both augmented with either reasoning layers that combine multiple model perspectives, analogous to peer consultation, or retrieval-augmented generation that incorporates medical literature at inference time, serving a role similar to reference-checking. While fine-tuning degraded performance in four of seven models with an average 30% decrease, baseline models collapsed on test data. Clinical-inspired architectures, meanwhile, achieved up to 70% accuracy, maintaining performance on unseen data while generating explainable, literature-grounded outputs critical for clinical adoption. These findings demonstrate that medical AI succeeds by reconstructing the collaborative and evidence-based practices fundamental to clinical diagnosis. Fine-tuning large models on medical data, the standard approach to medical AI, assumes domain exposure produces clinical competence [1]. Y et dermatology models show 15% performance drops in real-world settings [2], and catastrophic forgetting causes models to generate outputs exclusively from their training data [3]. This brittleness suggests a fundamental mismatch between current approaches and clinical reasoning. Additionally, physician groups achieve 85.6% diagnostic accuracy versus 62.5% for individuals [4], as collaboration reduces cognitive load and bias [5]. However, logistical constraints force physicians to work alone, a problem telemedicine intensifies by eliminating physical exams, peer consultation, and immediate reference access [6].

Rare diseases collectively affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains a pervasive challenge. This is largely due to their clinical heterogeneity, low individual prevalence, and the limited familiarity most clinicians have with rare conditions. Here, we introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM), capable of processing heterogeneous clinical inputs. The system generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning that links intermediate analytic steps to verifiable medical evidence. DeepRare comprises three key components: a central host with a long-term memory module; specialized agent servers responsible for domain-specific analytical tasks integrating over 40 specialized tools and web-scale, up-to-date medical knowledge sources, ensuring access to the most current clinical information. This modular and scalable design enables complex diagnostic reasoning while maintaining traceability and adaptability. We evaluate DeepRare on eight datasets. The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases. In HPO-based evaluations, DeepRare significantly outperforms other 15 methods, like traditional bioinformatics diagnostic tools, LLMs, and other agentic systems, achieving an average Recall@1 score of 57.18% and surpassing the second-best method (Reasoning LLM) by a substantial margin of 23.79 percentage points. For multi-modal input scenarios, DeepRare achieves 70.60% at Recall@1 compared to Exomiser's 53.20% in 109 cases. Manual verification of reasoning chains by clinical experts achieves 95.40% agreements. Furthermore, the DeepRare system has been implemented as a user-friendly web application http://raredx.cn/doctor.