Marco Cristani

Digital pathology has transformed anatomic pathology by enabling whole-slide imaging, remote review, reproducible annotation, image analysis, and the development of artificial intelligence-based decision-support tools. In forensic pathology, however, the transition from glass slides to digital forensic histopathology remains in its early stages, despite recent evidence supporting the feasibility and diagnostic reliability of whole-slide imaging in medico-legal practice. The subsequent crucial step involves not merely digitizing forensic slides but also developing curated, multicentric, legally governed, and controlled-access datasets comprising forensic histopathological images. Such datasets are essential for education, interobserver harmonization, external quality assessment, and the development of reproducible quantitative tools suitable for forensic applications. This perspective paper argues that forensic pathology should regard datasets as scientific infrastructure rather than as passive image collections. An artificial intelligence-ready forensic histopathology dataset should include whole-slide images, standardized annotations, technical acquisition parameters, histological processing information, forensic metadata, quality-control records, reference standards, uncertainty labels, and explicit governance rules. Although important lessons can be drawn from anatomic pathology datasets, forensic pathology presents specific challenges, including low case numbers, post-mortem artifacts, heterogeneous sampling, variable fixation and preservation conditions, judicial and privacy concerns, and differences in national regulation of post-mortem data. We therefore propose a literature-informed conceptual framework for the development of forensic histopathology datasets, intended for forensic pathologists, researchers, institutional stakeholders, and AI tools developers. The framework is intended to support the development of shared resources for education, research, and AI development and validation, thereby providing a foundation for trustworthy and scientifically defensible computational applications in forensic pathology.

Cardiovascular disease is a leading cause of mortality, with coronary artery disease accounting for over 60% of cases in adults. Accurate quantification of coronary stenosis in forensic autopsies is crucial for determining causality between pathological findings and death, but is hindered by subjective visual assessments and inter-observer variability. This study aimed to develop an AI-driven tool using whole-slide images for objective stenosis measurement in forensic investigations. From 98 anonymized H&E-stained autopsy slides (234 coronary sections), 103 high-quality regions of interest were selected and split into training (n = 82), validation (n = 14), and test (n = 7) datasets. Annotations delineated lumen, internal elastic lamina, and external elastic lamina using QuPath. A SegFormer-B0 transformer model was trained with data augmentation, weighted cross-entropy loss, and AdamW optimization. Post-processing enforced anatomical structural hierarchy and generated hybrid confidence maps. On validation dataset, agreement with ground truth was excellent (MAE 3.22% points; RMSE 4.00; MAPE 6.07%; r = 0.986; ICC = 0.986), with slight underestimation. Bland–Altman bias was − 1.36 pp (95% LoA − 9.01 to 6.28 pp), indicating performance across severities. On the test set, accuracy improved (MAE 1.01 pp; RMSE 1.50; MAPE 2.11%; r = 0.998; ICC = 0.995) and outperformed three pathologists’ visual estimates (MAE 16.11, 8.18, 4.79 pp). Bland–Altman bias for the model was − 0.82 pp with tight limits of agreement (− 3.48 to 1.83 pp). Total inference time was 199.08 s for seven cases (28.44 s/image). WSI-based transformer pipeline enables rapid, auditable, and reproducible coronary stenosis measurement, reducing inter-observer variability and supporting standardized interpretation in forensic investigations. The online version contains supplementary material available at 10.1007/s00414-026-03800-6.

With the advent of Industrial 4.0 and the push toward Industry 5.0, the data generated by the industries have become surprisingly large. This abundance of data significantly boosts machine and deep learning models for Predictive Maintenance (PdM). The PdM plays a vital role in extending the lifespan of industrial equipment and machines while also helping to reduce the risk of unscheduled downtime. Given its multidisciplinary nature, the field of PdM has been approached from many different angles: this comprehensive survey aims at providing an up-to-date overview focused on all the learning-based industrial PdM strategies, discussing weaknesses and strengths. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing a systematic and complete review of the literature. In particular, firstly, we explore the main learning models used for PdM, mainly Convolutional Neural Networks (ConvNets), Autoencoders (AEs), Generative Adversarial Networks (GANs), and Transformers, also giving an overview of the newest models such as diffusion models and foundation models. Then, we discuss the main learning paradigms applied to PdM, i.e., supervised, unsupervised, ensemble, transfer, federated, and reinforcement learning. Furthermore, this work discusses the pipeline of the data-driven PdM and its benefits, practical applications, datasets, and benchmarks. In addition, the evaluation metrics for each PdM stage and the state-of-the-art hardware devices used are discussed. Finally, the challenges and future work are presented.

Sketches offer designers a concise yet expressive medium for early-stage fashion ideation by specifying structure, silhouette, and spatial relationships, while textual descriptions complement sketches to convey material, color, and stylistic details. Effectively combining textual and visual modalities requires adherence to the sketch visual structure when leveraging the guidance of localized attributes from text. We present LOcalized Text and Sketch with multi-level guidance (LOTS), a framework that enhances fashion image generation by combining global sketch guidance with multiple localized sketch-text pairs. LOTS employs a Multi-level Conditioning Stage to independently encode local features within a shared latent space while maintaining global structural coordination. Then, the Diffusion Pair Guidance stage integrates both local and global conditioning via attention-based guidance within the diffusion model's multi-step denoising process. To validate our method, we develop Sketchy, the first fashion dataset where multiple text-sketch pairs are provided per image. Sketchy provides high-quality, clean sketches with a professional look and consistent structure. To assess robustness beyond this setting, we also include an "in the wild" split with non-expert sketches, featuring higher variability and imperfections. Experiments demonstrate that our method strengthens global structural adherence while leveraging richer localized semantic guidance, achieving improvement over state-of-the-art. The dataset, platform, and code are publicly available.

Language-driven object navigation requires agents to interpret natural language descriptions of target objects, which combine intrinsic and extrinsic attributes for instance recognition and commonsense navigation. Existing methods either (i) use end-to-end trained models with vision-language embeddings, which struggle to generalize beyond training data and lack action-level explainability, or (ii) rely on modular zero-shot pipelines with large language models (LLMs) and open-set object detectors, which suffer from error propagation, high computational cost, and difficulty integrating their reasoning back into the navigation policy. To this end, we propose a compact 3B-parameter Vision-Language-Action (VLA) agent that performs human-like embodied reasoning for both object recognition and action selection, removing the need for stitched multi-model pipelines. Instead of raw embedding matching, our agent employs explicit image-grounded reasoning to directly answer "Is this the target object?" and "Why should I take this action?" The reasoning process unfolds in three stages: "think", "think summary", and "action", yielding improved explainability, stronger generalization, and more efficient navigation. Code and dataset available upon acceptance.

Industrial and medical anomaly detection faces critical challenges from data scarcity and prohibitive annotation costs, particularly in evolving manufacturing and healthcare settings. To address this, we propose CoZAD, a novel zero-shot anomaly detection framework that integrates soft confident learning with meta-learning and contrastive feature representation. Unlike traditional confident learning that discards uncertain samples, our method assigns confidence-based weights to all training data, preserving boundary information while emphasizing prototypical normal patterns. The framework quantifies data uncertainty through IQR-based thresholding and model uncertainty via covariance-based regularization within a Model-Agnostic Meta-Learning. Contrastive learning creates discriminative feature spaces where normal patterns form compact clusters, enabling rapid domain adaptation. Comprehensive evaluation across 10 datasets spanning industrial and medical domains demonstrates state-of-the-art performance, outperforming existing methods on 6 out of 7 industrial benchmarks with notable improvements on texture-rich datasets (99.2% I-AUROC on DTD-Synthetic, 97.2% on BTAD) and pixel-level localization (96.3% P-AUROC on MVTec-AD). The framework eliminates dependence on vision-language alignments or model ensembles, making it valuable for resource-constrained environments requiring rapid deployment.

To enable flexible, high-throughput automation in settings where people and robots share workspaces, collaborative robotic cells must reconcile stringent safety guarantees with the need for responsive and effective behavior. A dynamic obstacle is the stochastic, task-dependent variability of human motion: when robots fall back on purely reactive or worst-case envelopes, they brake unnecessarily, stall task progress, and tamper with the fluidity that true Human-Robot Interaction demands. In recent years, learning-based human-motion prediction has rapidly advanced, although most approaches produce worst-case scenario forecasts that often do not treat prediction uncertainty in a well-structured way, resulting in over-conservative planning algorithms, limiting their flexibility. We introduce Uncertainty-Aware Predictive Control Barrier Functions (UA-PCBFs), a unified framework that fuses probabilistic human hand motion forecasting with the formal safety guarantees of Control Barrier Functions. In contrast to other variants, our framework allows for dynamic adjustment of the safety margin thanks to the human motion uncertainty estimation provided by a forecasting module. Thanks to uncertainty estimation, UA-PCBFs empower collaborative robots with a deeper understanding of future human states, facilitating more fluid and intelligent interactions through informed motion planning. We validate UA-PCBFs through comprehensive real-world experiments with an increasing level of realism, including automated setups (to perform exactly repeatable motions) with a robotic hand and direct human-robot interactions (to validate promptness, usability, and human confidence). Relative to state-of-the-art HRI architectures, UA-PCBFs show better performance in task-critical metrics, significantly reducing the number of violations of the robot's safe space during interaction with respect to the state-of-the-art.

Industrial and medical anomaly detection faces critical challenges from data scarcity and prohibitive annotation costs, particularly in evolving manufacturing and healthcare settings. To address this, we propose CoZAD, a novel zero-shot anomaly detection framework that integrates soft confident learning with meta-learning and contrastive feature representation. Unlike traditional confident learning that discards uncertain samples, our method assigns confidence-based weights to all training data, preserving boundary information while emphasizing prototypical normal patterns. The framework quantifies data uncertainty through IQR-based thresholding and model uncertainty via covariance based regularization within a Model-Agnostic Meta-Learning. Contrastive learning creates discriminative feature spaces where normal patterns form compact clusters, enabling rapid domain adaptation. Comprehensive evaluation across 10 datasets spanning industrial and medical domains demonstrates state-of-the-art performance, outperforming existing methods on 6 out of 7 industrial benchmarks with notable improvements on texture-rich datasets (99.2% I-AUROC on DTD-Synthetic, 97.2% on BTAD) and pixellevel localization (96.3% P-AUROC on MVTec-AD). The framework eliminates dependence on vision-language alignments or model ensembles, making it valuable for resourceconstrained environments requiring rapid deployment.

Anomaly detection is fundamental for ensuring quality control and operational efficiency in industrial environments, yet conventional approaches face significant challenges when training data contains mislabeled samples-a common occurrence in real-world scenarios. This paper presents RAD, a robust anomaly detection framework that integrates Normalizing Flows with Model-Agnostic Meta-Learning to address the critical challenge of label noise in industrial settings. Our approach employs a bi-level optimization strategy where meta-learning enables rapid adaptation to varying noise conditions, while uncertainty quantification guides adaptive L2 regularization to maintain model stability. The framework incorporates multiscale feature processing through pretrained feature extractors and leverages the precise likelihood estimation capabilities of Normalizing Flows for robust anomaly scoring. Comprehensive evaluation on MVTec-AD and KSDD2 datasets demonstrates superior performance, achieving I-AUROC scores of 95.4% and 94.6% respectively under clean conditions, while maintaining robust detection capabilities above 86.8% and 92.1% even when 50% of training samples are mislabeled. The results highlight RAD's exceptional resilience to noisy training conditions and its ability to detect subtle anomalies across diverse industrial scenarios, making it a practical solution for real-world anomaly detection applications where perfect data curation is challenging.