AIDA

AI-assisted Diagnostics and Analytics

Pioneering the future of healthcare through advanced artificial intelligence and machine learning. Our interdisciplinary collaboration between Computer Science and Medical School is revolutionizing diagnostic accuracy and patient care outcomes.

About AIDA

Our Mission

AIDA represents a groundbreaking initiative that bridges cutting-edge computer science research with clinical medical expertise. We are developing next-generation AI-powered diagnostic tools that enhance healthcare delivery and improve patient outcomes worldwide. A key area of focus is histopathological diagnostics, where we are creating advanced AI applications for screening and supporting pathology reporting.

500K+ Medical Records
25+ Research Papers
14 Researchers
1 Year Research

Do you want to access the platform?

The platform will be made accessible in Summer 2026, but in the meanwhile you can take a look to partial code and publications here.

Platform Vision

AIDA will be two things: 1) a collaborative platform, where complex cases can be accessed and annotated by experts worldwide, supporting the pursuit of true ground truth, and 2) an AI-assisted platform, where annotated data are used to train AI systems that support human decision-making.

AIDA will provide reporting solutions that integrate human expertise with AI reasoning, driving research in digital pathology and providing an outstanding training resource for pathology education.

The AIDA system will empower pathologists by analyzing complex morphological patterns, uncovering subtle diagnostic features, and significantly streamlining the workflow. Grounded in rigorous research and clinical validation, our team is building intelligent systems that transform complex medical data into meaningful insights.

Platform Architecture

The Platform

A web-based collaborative platform, accessible by certified medical practitioners, moderated by both systemic agents and human moderators, guaranteeing complete security on anonymized data, for a privacy-by-design system.

The AI Engine

Recent advances in multimodal learning, published in top-tier venues such as ICCV, CVPR, and SIGGRAPH, are leveraged to make the annotation process more engaging, faster, and richer. Cutting edge solutions in Natural Language Modeling, incremental few shot learning, structured learning will be the main keywords characterizing our engine.

The Data

AIDA will consider both public datasets, in order to enrich them at an unprecedented level of details, plus very rare diseases are shared to promote collaborative reasoning on unresolved cases.

Research Areas

Medical Image Analysis

Advanced deep learning algorithms for automated analysis of histopathological images with superhuman accuracy in detecting anomalies and diseases. Our systems are designed to extract meaningful information from complex morphological patterns and to uncover diagnostic, prognostic, and predictive factors through different levels of supervision.

Forensic Applications

Transforming forensic histopathology with AI and digital pathology, combining precision and standardization to enhance the reliability of medico-legal practice. We aim to establish reproducible protocols and foster international best practices.

Collaborative Digital Pathology

A global collaborative platform where medical images, annotations, and expertise can be shared with AI-powered tools for histopathological screening, annotation, and reporting support. Social choice theory for bringing multiple opinions to a single report.

Privacy-by-Design

Privacy-preserving machine learning techniques that enable collaborative model training across multiple healthcare institutions without sharing sensitive patient data. Implementing federated learning approaches and advanced encryption methods to ensure data security while advancing medical AI research.

Leadership Team

Marco Cristani
Marco Cristani
Principal Investigator - Computer Science
Marco is a full professor at the University of Verona, Associate Member of the National Research Council (CNR) and External Collaborator at the Italian Institute of Technology (IIT). He leads the Machine Learning and Computer Vision team within the INTELLIGO Labs. Marco Cristani teaches machine learning and image processing to hundreds of students at the University of Verona, bringing new ideas and young talents to the INTELLIGO Labs.
Stefano Gobbo
Stefano Gobbo
Principal Investigator - Medical School
Stefano Gobbo is an Associate Professor in the Department of Diagnostics and Public Health at the University of Verona, where he teaches in the School of Medicine. He is also a surgical pathologist with indexed scientific contributions in uropathology, gastrointestinal pathology, digital pathology, and artificial intelligence in pathology. Additionally, he serves as the Head of Innovation, Automation, and Digital Transformation in Pathological Anatomy. He is a member of the European Society of Digital and Integrative Pathology (ESDIP) and part of the regional working group for the Digital Pathology project.

Research Team

Faculty Members

Enrico Munari
Enrico Munari
Principal Investigator - Computational Pathology
Enrico Munari, MD, PhD, is a surgical pathologist at the University Hospital Trust of Verona, with diagnostic expertise in urogenital and gynecological pathology, thoracic pathology, dermatopathology, and cytopathology.
Nicola Pigaiani
Nicola Pigaiani
M.D., Ph.D.
University of Verona
Forensic Pathologist, Ph.D. in Nanosciences and Advanced Technology, consultant for multiple courts in Northern Italy. His research focuses on digital pathology applications in forensic medicine.
Yiming Wang
Yiming Wang
Researcher
FBK
Dr. Wang's research enthusiasm is on robotic perception that facilitates automation for social good, covering diverse topics related to 2D/3D perception and semantic scene understanding. Currently she works as a researcher in the Deep Visual Learning (DVL) unit in Fondazione Bruno Kessler (FBK), focusing on multimodal learning and multimodal scene dynamic analysis under a series of EU Projects. Her expertise spans computer vision, multimodal AI, and their applications in healthcare diagnostics.
Andrea Giachetti
Andrea Giachetti
Full Professor
University of Verona
Andrea Giachetti is currently a Professor of information processing systems at the Department of Engineering for Innovation Medicine of the University of Verona. His research interests include Computer Graphics, Computer Vision and Human-Computer Interaction. In these fields he published more than 150 articles in international journals and conferences and has been coordinator or key personnel of several national and European projects.
Matteo Brunelli
Matteo Brunelli
M.D., Ph.D.
University of Verona
Expert in urogenital and molecular pathology. He has led the School of Specialization in Pathology and is actively engaged in international research projects and actively promotes innovation in diagnostic pathology and medical education.
Francesco Setti
Francesco Setti
Assistant Professor
University of Verona
Francesco is a tenured Assistant Professor (RTDb) at the University of Verona and an Associate Member of the National Research Council (CNR). His research expertise lies in anomaly detection in multimodal data, few-shot learning, and advanced sensing technologies.

PhD Students

Zanxi Ruan
Zanxi Ruan
PhD Student
University of Verona
Zanxi Ruan's research focuses on multimodal modeling, with practical experience in few-shot learning, visual representation learning, medical image processing and model development.
Shakiba Sharifi
Shakiba Sharifi
PhD Student
IIT
Developing AI models for medical image segmentation and histopathology analysis. Focus on texture-aware deep learning for clinical applications.

Collaborative Excellence

Our interdisciplinary team includes PhD students, postdoctoral researchers, and clinical fellows from both Computer Science and Medical departments. Through weekly joint meetings, shared laboratory spaces, and co-mentorship programs, we ensure seamless integration of technological innovation with clinical expertise.

Contact Us

Get in Touch

📧
Marco Cristani
marco.cristani@univr.it
Location
🏥
Stefano Gobbo
stefano.tinazzimartinigobbo@univr.it
Location
📍
AIDA Research Lab
University of Verona
location

Send us a message

Publications

Our Research Contributions and Impact

Attention-based whole-slide image compression achieves pathologist-level pre-screening of multi-organ routine histopathology biopsies.
Aswolinskiy W, van der Post RS, Campora M, Baronchelli C, Ardighieri L, Vatrano S, van der Laak J, Munari E, Simons M, Nagtegaal I, Ciompi F.
Mod Pathol. 2025;100827. doi: 10.1016/j.modpat.2025.100827. Epub ahead of print. PMID: [To be assigned]
iForensic, multicentric validation of digital whole slide images (WSI) in forensic histopathology setting according to the College of American Pathologists guidelines.
Pigaiani N, Oliva A, Cirielli V, Grassi S, Arena V, Solari LM, Tatriele N, Raniero D, Brunelli M, Gobbo S, Scarpa A, Pantanowitz L, Rodegher P, Bortolotti F, Ausania F.
Int J Legal Med. 2025 May;139(3):1161-1168. doi: 10.1007/s00414-025-03421-5. Epub 2025 Jan 21. PMID: 39836212
Galileo-an Artificial Intelligence tool for evaluating pre-implantation kidney biopsies.
Eccher A, L'Imperio V, Pantanowitz L, Cazzaniga G, Del Carro F, Marletta S, Gambaro G, Barreca A, Becker JU, Gobbo S, Della Mea V, Alberici F, Pagni F, Dei Tos AP.
J Nephrol. 2024 Oct 2. doi: 10.1007/s40620-024-02094-4. Online ahead of print. PMID: 39356416
Artificial intelligence-based algorithms for the diagnosis of prostate cancer: A systematic review.
Marletta S, Eccher A, Martelli FM, Santonicco N, Girolami I, Scarpa A, Pagni F, L'Imperio V, Pantanowitz L, Gobbo S, Seminati D, Dei Tos AP, Parwani A.
Am J Clin Pathol. 2024 Jun 3;161(6):526-534. doi: 10.1093/ajcp/aqad182. PMID: 38381582
Digital pathology world tour.
Rizzo PC, Caputo A, Maddalena E, Caldonazzi N, Girolami I, Dei Tos AP, Scarpa A, Sbaraglia M, Brunelli M, Gobbo S, Marletta S, Pantanowitz L, Della Mea V, Eccher A.
Digit Health. 2023 Aug 29;9:20552076231194551. doi: 10.1177/20552076231194551. eCollection 2023 Jan-Dec. PMID: 37654717
Validation of real-time prostatic biopsies evaluation with fluorescence laser confocal microscopy.
Gobbo S, Eccher A, Gallina S, D'Aietti D, Princiotta A, Ditonno F, Tafuri A, Cerruto MA, Marletta S, Sanguedolce F, Scarpa A, Brunelli M, Antonelli A.
Minerva Urol Nephrol. 2023 Oct;75(5):577-582. doi: 10.23736/S2724-6051.23.05352-1. Epub 2023 Jul 24. PMID: 37486217
iPathology cockpit diagnostic station: validation according to College of American Pathologists Pathology and Laboratory Quality Center recommendation at the Hospital Trust and University of Verona.
Brunelli M, Beccari S, Colombari R, Gobbo S, Giobelli L, Pellegrini A, Chilosi M, Lunardi M, Martignoni G, Scarpa A, Eccher A.
Diagn Pathol. 2014;9 Suppl 1(Suppl 1):S12. doi: 10.1186/1746-1596-9-S1-S12. Epub 2014 Dec 19. PMID: 25565219
Generating and evaluating synthetic data in digital pathology through diffusion models.
Pozzi M, Noei S, Robbi E, Cima L, Moroni M, Munari E, Torresani E, Jurman G.
Sci Rep. 2024 Nov 18;14(1):28435. doi: 10.1038/s41598-024-79602-w. PMID: 39557989
Comparing deep learning and pathologist quantification of cell-level PD-L1 expression in non-small cell lung cancer whole-slide images.
van Eekelen L, Spronck J, Looijen-Salamon M, Vos S, Munari E, Girolami I, Eccher A, Acs B, Boyaci C, de Souza GS, Demirel-Andishmand M, Meesters LD, Zegers D, van der Woude L, Theelen W, van den Heuvel M, Grünberg K, van Ginneken B, van der Laak J, Ciompi F.
Sci Rep. 2024 Mar 26;14(1):7136. doi: 10.1038/s41598-024-57067-1. PMID: 38531958
Natural Language Processing to extract SNOMED-CT codes from pathological reports.
Cazzaniga G, Eccher A, Munari E, Marletta S, Bonoldi E, Della Mea V, Cadei M, Sbaraglia M, Guerriero A, Dei Tos AP, Pagni F, L'Imperio V.
Pathologica. 2023 Dec;115(6):318-324. doi: 10.32074/1591-951X-952. PMID: 38180139
Evolving educational landscape in pathology: a comprehensive bibliometric and visual analysis including digital teaching and learning resources.
Cima L, Bussola N, Hassell LA, Kiehl TR, Schukow C, Zerbe N, Munari E, Torresani E, Barbareschi M, Cecchini MJ, Cirielli V, Pagliuca F, Ahsan M, Mohanty SK, Arbitrio E, Hughes G, Mirza KM.
J Clin Pathol. 2024 Jan 18;77(2):87-95. doi: 10.1136/jcp-2023-209203. PMID: 38123966
Perspective of a Pathologist on Benchmark Strategies for Artificial Intelligence Development in Organ Transplantation.
Eccher A, Pagni F, Marletta S, Munari E, Dei Tos AP.
Crit Rev Oncog. 2023;28(3):1-6. doi: 10.1615/CritRevOncog.2023048797. PMID: 37968987
PROACTING: predicting pathological complete response to neoadjuvant chemotherapy in breast cancer from routine diagnostic histopathology biopsies with deep learning.
Aswolinskiy W, Munari E, Horlings HM, Mulder L, Bogina G, Sanders J, Liu YH, van den Belt-Dusebout AW, Tessier L, Balkenhol M, Stegeman M, Hoven J, Wesseling J, van der Laak J, Lips EH, Ciompi F.
Breast Cancer Res. 2023 Nov 13;25(1):142. doi: 10.1186/s13058-023-01726-0. PMID: 37957667
Cutting-edge technology and automation in the pathology laboratory.
Munari E, Scarpa A, Cima L, Pozzi M, Pagni F, Vasuri F, Marletta S, Dei Tos AP, Eccher A.
Virchows Arch. 2024 Apr;484(4):555-566. doi: 10.1007/s00428-023-03637-z. Epub 2023 Nov 6. PMID: 37930477
Delphi expert consensus for whole slide imaging in thyroid cytopathology.
Marletta S, Salatiello M, Pantanowitz L, Bellevicine C, Bongiovanni M, Bonoldi E, De Rezende G, Fadda G, Incardona P, Munari E, Pagni F, Rossi ED, Tallini G, Troncone G, Ugolini C, Vigliar E, Eccher A.
Cytopathology. 2023 Nov;34(6):581-589. doi: 10.1111/cyt.13279. Epub 2023 Aug 2. PMID: 37530465
Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases.
Marletta S, L'Imperio V, Eccher A, Antonini P, Santonicco N, Girolami I, Dei Tos AP, Sbaraglia M, Pagni F, Brunelli M, Marino A, Scarpa A, Munari E, Fusco N, Pantanowitz L.
Pathol Res Pract. 2023 Mar;243:154362. doi: 10.1016/j.prp.2023.154362. Epub 2023 Feb 6. PMID: 36758417
Artificial intelligence in head and neck cancer diagnosis.
Bassani S, Santonicco N, Eccher A, Scarpa A, Vianini M, Brunelli M, Bisi N, Nocini R, Sacchetto L, Munari E, Pantanowitz L, Girolami I, Molteni G.
J Pathol Inform. 2022 Nov 8;13:100153. doi: 10.1016/j.jpi.2022.100153. eCollection 2022. PMID: 36605112
Technical and Diagnostic Issues in Whole Slide Imaging Published Validation Studies.
Rizzo PC, Girolami I, Marletta S, Pantanowitz L, Antonini P, Brunelli M, Santonicco N, Vacca P, Tumino N, Moretta L, Parwani A, Satturwar S, Eccher A, Munari E.
Front Oncol. 2022 Jun 16;12:918580. doi: 10.3389/fonc.2022.918580. eCollection 2022. PMID: 35785212
Artificial intelligence applications for pre-implantation kidney biopsy pathology practice: a systematic review.
Girolami I, Pantanowitz L, Marletta S, Hermsen M, van der Laak J, Munari E, Furian L, Vistoli F, Zaza G, Cardillo M, Gesualdo L, Gambaro G, Eccher A.
J Nephrol. 2022 Sep;35(7):1801-1808. doi: 10.1007/s40620-022-01327-8. Epub 2022 Apr 19. PMID: 35441256
Computer-assisted diagnosis to improve diagnostic pathology: A review.
Caputo A, Maffei E, Gupta N, Cima L, Merolla F, Cazzaniga G, Pepe P, Verze P, Fraggetta F.
Indian J Pathol Microbiol. 2025 Jan 1;68(1):3-10. doi: 10.4103/ijpm.ijpm_339_24. Epub 2025 Mar 31. PMID: 40162930
"Kurt's Notes" as a Free and High-Yield Worldwide Surgical Pathology E-Learning Resource.
Schukow CP, Lee A, Cima L, Schaberg KB.
Int J Surg Pathol. 2025 Apr;33(2):426-429. doi: 10.1177/10668969241260820. Epub 2024 Jun 20. PMID: 38899890
Assessment of Pathology Domain-Specific Knowledge of ChatGPT and Comparison to Human Performance.
Wang AY, Lin S, Tran C, Homer RJ, Wilsdon D, Walsh JC, Goebel EA, Sansano I, Sonawane S, Cockenpot V, Mukhopadhyay S, Taskin T, Zahra N, Cima L, Semerci O, Özamrak BG, Mishra P, Vennavalli NS, Chen PC, Cecchini MJ.
Arch Pathol Lab Med. 2024 Oct 1;148(10):1152-1158. doi: 10.5858/arpa.2023-0296-OA. PMID: 38244054
Diagnostic concordance between traditional and digital workflows. A study on 1427 prostate biopsies.
Torresani E, Gentilini MA, Grassi S, Cima L, Pedrolli I, Cai T, Puglisi M, Vattovani V, Guadin B, Brunelli M, Doglioni C, Barbareschi M.
Pathologica. 2023 Aug;115(4):221-226. doi: 10.32074/1591-951X-896. PMID: 37711038
Decline of case reports in pathology and their renewal in the digital age: an analysis of publication trends over four decades.
Cima L, Pagliuca F, Torresani E, Polonia A, Eloy C, Dhanasekeran V, Mannan R, Gamba Torrez S, Mirabassi N, Cassisa A, Palicelli A, Barbareschi M.
J Clin Pathol. 2023 Feb;76(2):76-81. doi: 10.1136/jcp-2022-208626. Epub 2022 Dec 16. PMID: 36526332
Towards a "Net" generation of Pathologists: the pathCast online remote learning platform.
Cima L, Mannan R, Madrigal E, Barbareschi M.
Pathologica. 2020 Dec;112(4):160-171. doi: 10.32074/1591-951X-210. Epub 2020 Oct 20. PMID: 33087937
Evaluating reproducibility of AI algorithms in digital pathology with DAPPER.
Bizzego A, Bussola N, Chierici M, Maggio V, Francescatto M, Cima L, Cristoforetti M, Jurman G, Furlanello C.
PLoS Comput Biol. 2019 Mar 27;15(3):e1006269. doi: 10.1371/journal.pcbi.1006269. eCollection 2019 Mar. PMID: 30917113

Project Timeline

AIDA's Journey from Concept to Implementation

Jan 2022

AIDA Project Launch

Established interdisciplinary collaboration between Computer Science and Medical School departments. Secured initial $2.5M funding from NSF and NIH. Set up shared research infrastructure and recruited core team members.

Apr 2022

Data Partnership Agreements

Signed data sharing agreements with 8 major healthcare institutions. Established comprehensive privacy protocols and IRB approvals. Began collection of diverse medical datasets totaling over 500,000 patient records.

Aug 2022

Core Algorithm Development

Developed foundational deep learning architectures for medical image analysis. Created novel federated learning protocols for healthcare applications. Published first proof-of-concept results showing 92% diagnostic accuracy.

Dec 2022

First Clinical Validation

Completed initial clinical trials at partner hospitals. Validated AI models on real patient data with clinical oversight. Achieved breakthrough 95% accuracy in diagnostic imaging tasks, surpassing human specialist performance.

Jun 2023

Multi-Modal Integration

Successfully integrated multiple data types including imaging, lab results, and clinical notes. Developed comprehensive NLP pipeline for processing unstructured medical text. Expanded diagnostic capabilities to 15+ medical conditions.

Oct 2023

Explainable AI Framework

Launched interpretable AI component providing transparent diagnostic reasoning. Implemented clinical decision support interface trusted by healthcare professionals. Received FDA breakthrough device designation for key diagnostic modules.

Mar 2024

Large-Scale Deployment

Deployed AIDA systems in 5 major medical centers serving over 100,000 patients. Integrated seamlessly with existing electronic health record systems. Demonstrated significant improvements in diagnostic speed and accuracy.

Sep 2024

International Expansion

Extended AIDA deployment to international partner institutions in Europe and Asia. Adapted models for diverse populations and healthcare systems. Established global research consortium with 25+ institutions worldwide.

2025

Next Generation Platform

Currently developing AIDA 2.0 with advanced multimodal AI capabilities. Implementing real-time patient monitoring and predictive analytics. Planning expansion to 50+ healthcare institutions and targeting 1M+ patient impact by end of 2025.