Publications

The exponential growth of healthcare data, driven by advancements in medical research and digital health technologies, has underscored the critical need for interoperability and standardization. However, the heterogeneous nature of real-world clinical data poses significant challenges to ensuring seamless data exchange and secondary use for research purposes. These challenges include syntactic inconsistencies (e.g., variable use of terminologies like ICD-10 vs SNOMED CT), semantic mismatches (e.g., differing conceptualizations of disease staging across institutions), and structural fragmentation (e.g., laboratory results encoded in free text rather than structured fields). Fast Healthcare Interoperability Resources (FHIR) has emerged as a leading standard for structuring and harmonizing healthcare data, enabling integration across diverse systems. This work presents a FHIR-based transformation pipeline that leverages Resource Description Framework (RDF) to convert raw, conceptually heterogeneous oncology data into research-ready, semantically enriched datasets. By representing FHIR resources as RDF graphs, our approach enables semantic interoperability, enhances data linkage across heterogeneous sources, and supports automated reasoning through ontology-based queries and inference mechanisms. The pipeline employs a templated conversion strategy, allowing for the declarative definition of mappings that enable domain experts to focus on the data model. In Cancer Virtual Lab, we applied this methodology to a real-world oncology dataset comprising 36,335 anonymized patient records, successfully converting 1,093,705 clinical records into 1,151,559 distinct RDF-based FHIR resource types. The process incorporated syntactic and semantic validation, along with expert review, to ensure technical correctness and clinical relevance. Our results demonstrate the feasibility of semantically integrating oncology data using FHIR and RDF, fostering machine-readable, interoperable knowledge representation. This enriched representation supports data quality monitoring and improvement, data harmonization, longitudinal analysis, advanced analytics, and AI-driven decision support, promoting large-scale secondary use.

Since their invention in 1949, barcodes have remained the preferred method for automatic data capture, playing a crucial role in supply chain management. To detect a barcode in an image, multiple algorithms have been proposed in the literature, with a significant increase of interest in the topic since the rise of deep learning. However, research in the field suffers from many limitations, including the scarcity of public datasets and code implementations, which hampers the reproducibility and reliability of published results. For this reason, we developed "BarBeR" (Barcode Benchmark Repository), a benchmark designed for testing and comparing barcode detection algorithms. This benchmark includes the code implementation of various detection algorithms for barcodes, along with a suite of useful metrics. It offers a range of test setups and can be expanded to include any localization algorithm. In addition, we provide a large, annotated dataset of 8748 barcode images, combining multiple public barcode datasets with standardized annotation formats for both detection and segmentation tasks. Finally, we share the results obtained from running the benchmark on our dataset, offering valuable insights into the performance of different algorithms.

This paper addresses the challenges of deploying deep learning models, specifically Binary Neural Networks (BNNs), on resource-constrained embedded devices within the Internet of Things context. As deep learning continues to gain traction in IoT applications, the need for efficient models that can learn continuously from incremental data streams without requiring extensive computational resources has become more pressing. We propose a solution that integrates Continual Learning with BNNs, utilizing replay memory to prevent catastrophic forgetting. Our method focuses on quantized neural networks, introducing the quantization also for the backpropagation step, significantly reducing memory and computational requirements. Furthermore, we enhance the replay memory mechanism by storing intermediate feature maps (i.e. latent replay) with 1bit precision instead of raw data, enabling efficient memory usage. In addition to well-known benchmarks, we introduce the DL-Hazmat dataset, which consists of over 140k high-resolution grayscale images of 64 hazardous material symbols. Experimental results show a significant improvement in model accuracy and a substantial reduction in memory requirements, demonstrating the effectiveness of our method in enabling deep learning applications on embedded devices in real-world scenarios. Our work expands the application of Continual Learning and BNNs for efficient on-device training, offering a promising solution for IoT and other resource-constrained environments.

Creating high-quality and realistic images is now possible thanks to the impressive advancements in image generation. A description in natural language of your desired output is all you need to obtain breathtaking results. However, as the use of generative models grows, so do concerns about the propagation of malicious content and misinformation. Consequently, the research community is actively working on the development of novel fake detection techniques, primarily focusing on low-level features and possible fingerprints left by generative models during the image generation process. In a different vein, in our work, we leverage human semantic knowledge to investigate the possibility of being included in frameworks of fake image detection. To achieve this, we collect a novel dataset of partially manipulated images using diffusion models and conduct an eye-tracking experiment to record the eye movements of different observers while viewing real and fake stimuli. A preliminary statistical analysis is conducted to explore the distinctive patterns in how humans perceive genuine and altered images. Statistical findings reveal that, when perceiving counterfeit samples, humans tend to focus on more confined regions of the image, in contrast to the more dispersed observational pattern observed when viewing genuine images. Our dataset is publicly available at: https://github.com/aimagelab/unveiling-the-truth.

Eye stimulation research plays a critical role in advancing our understanding of visual processing and developing new therapies for visual impairments. Despite its importance, researchers and clinicians still face challenges with the availability of cost-effective, precise, and versatile tools for conducting these studies. Therefore, this study introduces a high-resolution, compact, and budget-friendly multi-wavelength LED light source tailored for precise and versatile eye stimulation, addressing the aforementioned needs in medical research and visual science. Accommodating standard 3 mm or 5 mm package LEDs, the system boasts broad compatibility, while its integration with any microcontroller capable of PWM generation and supporting SPI and UART communication ensures adaptability across diverse applications. Operating at high resolution (18 bits or more) with great linearity, the LED light source offers nuanced control for sophisticated eye stimulation protocols. The simple 3D printable optical design allows the coupling of up to seven different wavelengths while ensuring the cost-effectiveness of the device. The system’s output has been designed to be fiber-coupled with standard SMA connectors to be compatible with most solutions. The proposed implementation significantly undercuts the cost of commercially available solutions, providing a viable, budget-friendly option for advancing eye stimulation research.

While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution. Rehearsal-based Continual Learning (CL) approaches have been established as a versatile and reliable solution to overcome this limitation; however, sudden input disruptions and memory constraints are known to alter the consistency of their predictions. We study this phenomenon by investigating the geometric characteristics of the learner’s latent space and find that replayed data points of different classes increasingly mix up, interfering with classification. Hence, we propose a geometric regularizer that enforces weak requirements on the Laplacian spectrum of the latent space, promoting a partitioning behavior. Our proposal, called Continual Spectral Regularizer for Incremental Learning (CaSpeR-IL), can be easily combined with any rehearsal-based CL approach and improves the performance of SOTA methods on standard benchmarks.

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability in sensitive and trustworthy contexts and could raise significant concerns in their adoption. Our research introduces a novel approach to enhancing the safety of vision-and-language models by diminishing their sensitivity to NSFW (not safe for work) inputs. In particular, our methodology seeks to sever "toxic" linguistic and visual concepts, unlearning the linkage between unsafe linguistic or visual items and unsafe regions of the embedding space. We show how this can be done by fine-tuning a CLIP model on synthetic data obtained from a large language model trained to convert between safe and unsafe sentences, and a text-to-image generator. We conduct extensive experiments on the resulting embedding space for cross-modal retrieval, text-to-image, and image-to-text generation, where we show that our model can be remarkably employed with pre-trained generative models. Our source code and trained models are available at: https://github.com/aimagelab/safe-clip.

Multimodal LLMs are the natural evolution of LLMs and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach termed Wiki-LLaVA aims at integrating an external knowledge source of multimodal documents which is accessed through a hierarchical retrieval pipeline. Relevant passages using this approach are retrieved from the external knowledge source and employed as additional context for the LLM augmenting the effectiveness and precision of generated dialogues. We conduct extensive experiments on datasets tailored for visual question answering with external data and demonstrate the appropriateness of our approach.