Francisco Maria Calisto

Francisco Maria Calisto

Lisboa, Lisboa, Portugal
8 mil seguidores + de 500 conexões

Sobre

Francisco's primary research areas are in the fields of Human-Computer Interaction (HCI),…

Artigos de Francisco Maria

Contribuições

Atividades

Cadastre-se agora para visualizar todas as atividades

Experiência

  • Gráfico BreastScreening-AI

    BreastScreening-AI

    Coimbra, Portugal

  • -

    Lisbon, Portugal

  • -

    Lisbon, Portugal

  • -

    Pittsburgh, Pennsylvania, United States

  • -

    Lisbon Area, Portugal

  • -

    Lisbon Area, Portugal

  • -

    Elsevier Limited (Corporate Office), 125 London Wall - London, EC2Y 5AS

  • -

    Rua Alves Redol, 9 1000-029 Lisboa Portugal

  • -

    Avenida Rovisco Pais 1, 1049-001 Lisboa - Portugal

  • -

    Rua Alves Redol, 9 1000-029 Lisboa Portugal

  • -

    Rua Alves Redol, 9 1000-029 Lisboa Portugal

Formação acadêmica

  • Gráfico Instituto Superior Técnico

    Instituto Superior Técnico

    The PhD program in Computer Science and Engineering at Técnico (ULisboa) provides the opportunity for outstanding students with a Master’s (or equivalent) degree in areas that are related to the broad field of computing to conduct highly specialized training in Computer Science and Engineering, geared towards scientific research, technological development and innovation.

  • Atividades e grupos:College Tennis Team

    The experts holding an MSc degree in Engineering Systems and Computer Engineering obtained at the IST campus in Alameda (MEIC-Alameda) will be able to analyse, develop and implement complex information systems, in distributed and heterogeneous environments, in permanent technological mutation, which characterize the current information-based society. Through the training acquired in this programme, students will also be able to confidently develop their activity in the Areas of software…

    The experts holding an MSc degree in Engineering Systems and Computer Engineering obtained at the IST campus in Alameda (MEIC-Alameda) will be able to analyse, develop and implement complex information systems, in distributed and heterogeneous environments, in permanent technological mutation, which characterize the current information-based society. Through the training acquired in this programme, students will also be able to confidently develop their activity in the Areas of software engineering, in its multiple aspects, ranging from the conception of information systems for all types of companies to the implementation of complex distributed systems, based on the Internet technologies.

  • Atividades e grupos:College Tennis Team

    In spite of being a new area comparatively to other more traditional engineering branches, information systems and computer engineering has been growing quickly. One of the reasons is the concentration of economic resources on the activities related with information technologies and telecommunications.

  • -

    Atividades e grupos:At the European Innovation Academy 2023, we developed an AI for breast cancer imaging that interprets images across expertise levels and integrates them into clinical workflows. We addressed data scarcity and clarified AI decisions for doctors. Emphasizing transparency, our solution aimed to enhance medical processes, mitigate bias, and foster trust. Validated by top journals, our system empowers clinicians with improved decision-making and control.

    At the European Innovation Academy 2023, I contributed to an AI-driven breast cancer imaging diagnosis system. We aimed for an AI that interprets medical images across expertise levels and fits various clinical workflows. We tackled: (i) the challenge of limited curated medical data for AI, and (ii) professionals' uncertainty about AI's decision-making. Our approach focused on AI's clear communication with doctors. The goal was a transformative platform where AI significantly benefits medical…

    At the European Innovation Academy 2023, I contributed to an AI-driven breast cancer imaging diagnosis system. We aimed for an AI that interprets medical images across expertise levels and fits various clinical workflows. We tackled: (i) the challenge of limited curated medical data for AI, and (ii) professionals' uncertainty about AI's decision-making. Our approach focused on AI's clear communication with doctors. The goal was a transformative platform where AI significantly benefits medical processes.

    Key considerations were bias reduction, trust-building, and real-world clinical effectiveness. We incorporated explainability methods for AI transparency, endorsed by leading scientific journals. Our system combined control features with visual clarity techniques, bolstering clinicians' decisions and autonomy.

  • -

    Atividades e grupos:While participating in the Santander X Launch 5.0 program by Babson Academy in 2023 (Remote), I collaborated with a diverse group of entrepreneurs and innovators to bring a groundbreaking fintech solution to the market. Our primary objective was to design a platform that simplifies financial transactions for small businesses, addressing the challenges of accessibility, security, and user experience.

    The project tackled two main issues: (i) the complexity of financial systems for small business owners, and (ii) the need for a secure yet user-friendly interface. Our solution focused on leveraging cutting-edge technology to create an intuitive platform, ensuring businesses of all sizes could easily navigate and benefit from our services.

    Key considerations during development were user trust, data security, and adaptability to various financial landscapes. Specifically, we are…

    The project tackled two main issues: (i) the complexity of financial systems for small business owners, and (ii) the need for a secure yet user-friendly interface. Our solution focused on leveraging cutting-edge technology to create an intuitive platform, ensuring businesses of all sizes could easily navigate and benefit from our services.

    Key considerations during development were user trust, data security, and adaptability to various financial landscapes. Specifically, we are incorporating advanced encryption methods and multifactor authentication to ensure the utmost safety. Feedback from potential users played a crucial role in refining our platform, ensuring it met the needs of our target audience. Our efforts culminated in a revolutionary fintech tool that simplifies transactions and empowers businesses to manage their finances confidently.

Licenças e certificados

Experiência de voluntariado

  • Gráfico Web Summit

    Operations Team - Survey

    Web Summit

    - o momento 8 anos 1 mês

    Empoderamento econômico

    Working as Operations Team - Survey Volunteer at Web Summit 2016.

    Certificate:

    http://franciscocalisto.me/downloads/WS16+Volunteer+Certificates+814.pdf

Publicações

  • Assertiveness-based Agent Communication for a Personalized Medicine on Medical Imaging Diagnosis

    CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

    Intelligent agents are showing increasing promise for clinical decision-making in a variety of healthcare settings. While a substantial body of work has contributed to the best strategies to convey these agents’ decisions to clinicians, few have considered the impact of personalizing and customizing these communications on the clinicians’ performance and receptiveness. This raises the question of how intelligent agents should adapt their tone in accordance with their target audience. We…

    Intelligent agents are showing increasing promise for clinical decision-making in a variety of healthcare settings. While a substantial body of work has contributed to the best strategies to convey these agents’ decisions to clinicians, few have considered the impact of personalizing and customizing these communications on the clinicians’ performance and receptiveness. This raises the question of how intelligent agents should adapt their tone in accordance with their target audience. We designed two approaches to communicate the decisions of an intelligent agent for breast cancer diagnosis with different tones: a suggestive (non-assertive) tone and an imposing (assertive) one. We used an intelligent agent to inform about: (1) number of detected findings; (2) cancer severity on each breast and per medical imaging modality; (3) visual scale representing severity estimates; (4) the sensitivity and specificity of the agent; and (5) clinical arguments of the patient, such as pathological co-variables. Our results demonstrate that assertiveness plays an important role in how this communication is perceived and its benefits. We show that personalizing assertiveness according to the professional experience of each clinician can reduce medical errors and increase satisfaction, bringing a novel perspective to the design of adaptive communication between intelligent agents and clinicians.

    Outros autores
    Ver publicação
  • Modeling Adoption of Intelligent Agents in Medical Imaging

    International Journal of Human-Computer Studies

    Artificial intelligence has the potential to transform many application domains fundamentally. One notable example is clinical radiology. A growing number of decision-making support systems are available for lesion detection and segmentation, two fundamental steps to accomplish diagnosis and treatment planning. This paper proposes a model based on the unified theory of acceptance and use of technology to study the determinants for the adoption of intelligent agents across the medical imaging…

    Artificial intelligence has the potential to transform many application domains fundamentally. One notable example is clinical radiology. A growing number of decision-making support systems are available for lesion detection and segmentation, two fundamental steps to accomplish diagnosis and treatment planning. This paper proposes a model based on the unified theory of acceptance and use of technology to study the determinants for the adoption of intelligent agents across the medical imaging workflow. We tested the model via confirmatory factor analysis and structural equation modeling using clinicians’ data from an international evaluation of healthcare practitioners. Results show an increased understanding of the vital role of security, risk, and trust in the usage intention of intelligent agents. These empirical findings provide valuable theoretical contributions to researchers by explaining the reasons behind the adoption and usage of intelligent agents in the medical imaging workflow.

    Outros autores
    Ver publicação
  • BreastScreening-AI: Evaluating Medical Intelligent Agents for Human-AI Interactions

    Artificial Intelligence in Medicine

    In this paper, we developed BreastScreening-AI within two scenarios for the classification of multimodal beast images: (1) Clinician-Only; and (2) Clinician-AI. The novelty relies on the introduction of a deep learning method into a real clinical workflow for medical imaging diagnosis. We attempt to address three high-level goals in the two above scenarios. Concretely, how clinicians: i) accept and interact with these systems, revealing whether are explanations and functionalities required; ii)…

    In this paper, we developed BreastScreening-AI within two scenarios for the classification of multimodal beast images: (1) Clinician-Only; and (2) Clinician-AI. The novelty relies on the introduction of a deep learning method into a real clinical workflow for medical imaging diagnosis. We attempt to address three high-level goals in the two above scenarios. Concretely, how clinicians: i) accept and interact with these systems, revealing whether are explanations and functionalities required; ii) are receptive to the introduction of AI-assisted systems, by providing benefits from mitigating the clinical error; and iii) are affected by the AI assistance. We conduct an extensive evaluation embracing the following experimental stages: (a) patient selection with different severities, (b) qualitative and quantitative analysis for the chosen patients under the two different scenarios. We address the high-level goals through a real-world case study of 45 clinicians from nine institutions. We compare the diagnostic and observe the superiority of the Clinician-AI scenario, as we obtained a decrease of 27% for False-Positives and 4% for False-Negatives. Through an extensive experimental study, we conclude that the proposed design techniques positively impact the expectations and perceptive satisfaction of 91% clinicians, while decreasing the time-to-diagnose by 3 min per patient.

    Outros autores
    Ver publicação
  • Introduction of Human-Centric AI Assistant to Aid Radiologists for Multimodal Breast Image Classification

    International Journal of Human-Computer Studies

    In this research, we take an HCI perspective on the opportunities provided by AI techniques in medical imaging, focusing on workflow efficiency and quality, preventing errors and variability of diagnosis in Breast Cancer. Starting from a holistic understanding of the clinical context, we developed BreastScreening to support Multimodality and integrate AI techniques (using a deep neural network to support automatic and reliable classification) in the medical diagnosis workflow. This was assessed…

    In this research, we take an HCI perspective on the opportunities provided by AI techniques in medical imaging, focusing on workflow efficiency and quality, preventing errors and variability of diagnosis in Breast Cancer. Starting from a holistic understanding of the clinical context, we developed BreastScreening to support Multimodality and integrate AI techniques (using a deep neural network to support automatic and reliable classification) in the medical diagnosis workflow. This was assessed by using a significant number of clinical settings and radiologists. Here we present: i) user study findings of 45 physicians comprising nine clinical institutions; ii) list of design recommendations for visualization to support breast screening radiomics; iii) evaluation results of a proof-of-concept BreastScreening prototype for two conditions Current (without AI assistant) and AI-Assisted; and iv) evidence from the impact of a Multimodality and AI-Assisted strategy in diagnosing and severity classification of lesions. The above strategies will allow us to conclude about the behavior of clinicians when an AI module is present in a diagnostic system. This behavior will have a direct impact on the clinicians' workflow that is thoroughly addressed herein. Our results show a high level of acceptance of AI techniques from radiologists and point to a significant reduction of cognitive workload and improvement in diagnosis execution.

    Outros autores
    Ver publicação
  • BreastScreening: A Multimodality Diagnostic Assistant

    Fundação para a Ciência e a Tecnologia (FCT)

    All over the world, breast cancer remains a significant issue for women healthcare. In worldwide countries, we observe increasing numbers of new cases and deaths, due to the population age, but also to other factors such as family records or environmental issues. In Europe, each year, we have more than 300,000 new breast cancer cases resulting in more than 90,000 deaths. We present an assistant for a fully automated breast cancer detection and segmentation from multi-modal medical images…

    All over the world, breast cancer remains a significant issue for women healthcare. In worldwide countries, we observe increasing numbers of new cases and deaths, due to the population age, but also to other factors such as family records or environmental issues. In Europe, each year, we have more than 300,000 new breast cancer cases resulting in more than 90,000 deaths. We present an assistant for a fully automated breast cancer detection and segmentation from multi-modal medical images introducing clinical covariates. The Assistant will be crucial for developing new machine learning methodologies (e.g., Deep Convolutional Neural Networks) that will be able to provide a reliable automatic classification of the whole exam, based on the data above mentioned.

    Outros autores
    Ver publicação
  • BreastScreening: A Multimodality Diagnostic Assistant

    Laboratory for Robotics and Engineering Systems (LARSyS)

    We present an assistant for a fully automated breast cancer detection and segmentation from Multi-Modal medical images introducing, also, clinical covariates. The key features of this poster are as follows. First of all, the collection of a huge amount of data, within the ground truth (annotations), concerning two types of lesions (i.e., masses and calcifications) in all image modalities. Secondly, provide both classification of the lesion severity (BI-RADS), as well as the clinical covariates,…

    We present an assistant for a fully automated breast cancer detection and segmentation from Multi-Modal medical images introducing, also, clinical covariates. The key features of this poster are as follows. First of all, the collection of a huge amount of data, within the ground truth (annotations), concerning two types of lesions (i.e., masses and calcifications) in all image modalities. Secondly, provide both classification of the lesion severity (BI-RADS), as well as the clinical covariates, including the person and familiar records. Finally, categorization of the tissue and visualizations of the mentioned lesions, available for a proper diagnosis to perform patients follow-up.

    Outros autores
    Ver publicação
  • Towards Touch-Based Medical Image Diagnosis Annotation

    ACM International Conference on Interactive Surfaces and Spaces

    A fundamental step in medical diagnosis for patient follow-up relies on the ability of radiologists to perform a trusty diagnostic from acquired images. Basically, the diagnosis strongly depends on the visual inspection over the shape of the lesions. As datasets increase in size, such visual evaluation becomes harder. For this reason, it is crucial to introduce easy-to-use interfaces that help the radiologists to perform a reliable visual inspection and allow the efficient delineation of the…

    A fundamental step in medical diagnosis for patient follow-up relies on the ability of radiologists to perform a trusty diagnostic from acquired images. Basically, the diagnosis strongly depends on the visual inspection over the shape of the lesions. As datasets increase in size, such visual evaluation becomes harder. For this reason, it is crucial to introduce easy-to-use interfaces that help the radiologists to perform a reliable visual inspection and allow the efficient delineation of the lesions. We will explore the radiologist's receptivity to the current touch environment solution. The advantages of touch are threefold: (i) the time performance is superior regarding the traditional use, (ii) it has more intuitive control and, (iii) for less time, the user interface delivers more information per action, concerning annotations. From our studies, we conclude that the radiologists still exhibit a resistance to change from traditional to touch based interfaces in current clinical setups.

    Outros autores
    Ver publicação
  • Adaptive Q-Sort Matrix Generation: A Simplified Approach

    INESC-ID

    This paper aims to use the previous work related to the DELPHI method, and, in particular, the Q-Sort method for information retrieval of a panel of experts, to provide a new and simple algorithm to generate Q-Sort matrices that adjust to the size of a given survey to have more questions whose weight is null for the outcome of the round, giving experts the need to prioritise some questions above others in order to reach a consensus in a more direct way.

    Outros autores
    Ver publicação

Patentes

  • Computational Method and System for Improved Identification of Breast Lesions

    Expedidas em WO2022071818A1

    The present invention falls within the field of medical imaging, specifically imaging aimed at identifying breast lesions, specifically, identifying potential breast cancer lesion masses or potential cancer lesion calcifications of the breast. The object of the present invention is a computational method for the improved identification of breast lesions that involves obtaining digital images of a breast section, with at least two digital images obtained by different imaging technologies, their…

    The present invention falls within the field of medical imaging, specifically imaging aimed at identifying breast lesions, specifically, identifying potential breast cancer lesion masses or potential cancer lesion calcifications of the breast. The object of the present invention is a computational method for the improved identification of breast lesions that involves obtaining digital images of a breast section, with at least two digital images obtained by different imaging technologies, their segmentation and consequent correlations, to identify one or more cancer lesions. This allows for improved automation of the identification of breast lesions.

    Outros inventores
    Ver patente

Cursos

  • Analysis and Synthesis of Algorithms

    6.0

  • Artificial Intelligence

    7.5

  • Compilers

    6.0

  • Complex Analysis and Differential Equations

    7.5

  • Computer Architecture

    6.0

  • Computer Graphics

    4.5

  • Computer Networks

    6.0

  • Computer Organization

    6.0

  • Computing and Society

    3.0

  • Databases

    6.0

  • Differential and Integral Calculus I

    6.0

  • Differential and Integral Calculus II

    7.5

  • Digital Systems

    6.0

  • Discrete Mathematics

    7.5

  • Distributed Systems

    7.5

  • Electromagnetism and Optics

    6.0

  • Enterprise Architecture

    7.5

  • Entrepreneurship and Innovation

    6.0

  • Foundations of Information Systems

    7.5

  • Foundations of Programming

    7.5

  • Human-Computer Interaction

    7.5

  • IT Governance and Management

    7.5

  • Independent Studies I

    1.5

  • Independent Studies II

    1.5

  • Independent Studies III

    1.5

  • Independent Studies IV

    1.5

  • Information Systems Project Management

    7.5

  • Information Visualization

    7.5

  • Interactive Visual Communication

    7.5

  • Introduction to Algorithms and Data Structures

    7.5

  • Introduction to Computer Architecture

    7.5

  • Introduction to Information Systems and Computer Engineering

    3.0

  • Linear Algebra

    6.0

  • Logic for Programming

    7.5

  • Management

    4.5

  • Master Project in Information and Software Engineering

    12.0

  • Master Thesis in Information and Software Engineering

    30.0

  • Mechanics and Waves

    6.0

  • Multimedia Content Production

    7.5

  • Object-Oriented Programming

    6.0

  • Operating Systems

    6.0

  • Probabilistic and Statistics

    6.0

  • Professional and Social Aspects of Computer Science & Engineering

    3.0

  • Software Engineering

    7.5

  • Systems Analysis and Modeling

    6.0

  • Technology Based Entrepreneurship

    7.5

  • Theory of Computation

    4.5

  • Usability and Information Systems

    7.5

  • User Centered Design

    7.5

Projetos

  • BreastScreening-AI

    BreastScreening-AI is an innovative project developed at the European Innovation Academy (EIA) 2023. The project aimed to develop a system supported by intelligent agents to assist in diagnosing breast cancer using medical images. Our team sought to address two primary challenges: the scarcity of ready-to-use, curated medical data for AI algorithms, and the lack of transparency in how AI systems arrive at their decisions. We focused on creating an AI solution capable of interpreting medical…

    BreastScreening-AI is an innovative project developed at the European Innovation Academy (EIA) 2023. The project aimed to develop a system supported by intelligent agents to assist in diagnosing breast cancer using medical images. Our team sought to address two primary challenges: the scarcity of ready-to-use, curated medical data for AI algorithms, and the lack of transparency in how AI systems arrive at their decisions. We focused on creating an AI solution capable of interpreting medical images at various levels of medical expertise, integrating them into different clinical workflows, and communicating with physicians in an interpretable and interactive manner. The project emphasized transparency and trust in AI, introducing various explainability techniques to ensure clarity in the AI's decision-making process. These techniques were validated by top scientific publications, demonstrating effectiveness and efficiency. We designed the solution to empower clinicians by pairing control functionalities with visual explainability techniques, fostering a greater sense of control over the AI outputs.

  • Computers & Graphics Journal Web Dissemination

    Developing, analysing and researching propaganda, as well as content dissemination strategies using the web and social networks as a tool.

    Outros criadores
    Ver projeto
  • Medical Imaging Multimodality Breast Cancer Diagnosis User Interface (MIMBCD-UI)

    - o momento

    The project is being developed by the Associated Laboratory - Institute for Systems and Robotics (ISR). This project proposes the development of a methodology for breast detection and cancer targeting using multi-modality of medical imaging and textual information.

    More Specifically, this project deals with the use of a recently proposed technique in literature: Deep Convolutional Neural Networks (CNNs). These deep networks will incorporate information from several different modes:…

    The project is being developed by the Associated Laboratory - Institute for Systems and Robotics (ISR). This project proposes the development of a methodology for breast detection and cancer targeting using multi-modality of medical imaging and textual information.

    More Specifically, this project deals with the use of a recently proposed technique in literature: Deep Convolutional Neural Networks (CNNs). These deep networks will incorporate information from several different modes: magnetic resonance imaging volumes (MRI), ultrasound images, mammographic images (both views CC and MLO) and text. The proposed algorithm, called for multimodality CNNs (MMCNNs) will have the ability to process multimodal information at an unified and sustained manner. This methodology needs to "learn" what are the masses and calcifications.

    So that is necessary to collect the ground truth, or notes of the masses and calcifications provided by medical experts. For the collection of these notes, the design and development of an interface is necessary allows the user (in this case, the medical specialist) to display various types of image (i.e., ultrasound, MRI and mammography), and that also allows for user interaction, particularly in providing the notes of the masses and calcifications. For these reasons, it is crucial for the development of this project, cooperation with experts providing the above notes.

    Outros criadores
    Ver projeto
  • Bubble Docs

    The application BUBBLE DOCS enables the creation, management and editing of various document types: spreadsheets, text and presentation.

    Users of the developed application can interact with each other through the alteration of documents shared between them.

    The developed project consists in the design and partial implementation of BUBBLE DOCS and associated services in order to provide a subset of the functionality expected in a system of this kind.

    In the developed…

    The application BUBBLE DOCS enables the creation, management and editing of various document types: spreadsheets, text and presentation.

    Users of the developed application can interact with each other through the alteration of documents shared between them.

    The developed project consists in the design and partial implementation of BUBBLE DOCS and associated services in order to provide a subset of the functionality expected in a system of this kind.

    In the developed application is only consider a single document type, the calculation sheet.

    The BUBBLE DOCS is integrated with two external services:

    - A service identity and authentication (SD-ID);

    - A reliable storage service (SD-STORE);

    Outros criadores
    Ver projeto
  • The My Internet of Things (TMIT) - Systems Analysis and Modeling

    This Project was developed under the Systems Analysis and Modeling class course.

    It aims to Develop and Modulate the Business Process, Architecture and System Modeling of an Internet of Things Project.

    Outros criadores
    Ver projeto
  • FUNNY SUGAR Website Development

    The aim of this project was to successfully Develop a Website Platform to advertise the cake brand called FUNNY SUGAR.

    It was made in PHP, Javascript, HTML 5 ans CSS technologies implementation, developed from the beginning structurally the layout and the code from this technologies.

    Outros criadores
    Ver projeto
  • Academic Webpage

    Academic Webpage with Academic Projects.

    Ver projeto
  • KITT

    The car brand BAM is developing a new car model which will have a smart system to integrate various types of information: Information supplied by car, traffic information, status of passengers, safety, etc..

    The information will be displayed on the car window using augmented reality. The driver can control the system via 4 buttons on the steering wheel.

    Outros criadores
    Ver projeto
  • Support System Delphi Studies

    -

    This Project aims to implement a DELPHI method variation, and, in particular using the the Q-Sort technique for information retrieval of a panel of experts, to provide a new and simple algorithm to generate Q-Sort matrixes.

    Outros criadores
    Ver projeto
  • New VIMMI Webpage Prototype

    -

    The New VIMMI Webpage Prototype (NVWP) Project aims to develop and deploy the future VIMMI Webpage, a group from INESC-ID. It was develop using Wordpress CMS Platform integrating new Plugins develop by us and for us.

    Outros criadores
    Ver projeto

Recomendações recebidas

Mais atividade de Francisco Maria

Veja o perfil completo de Francisco Maria

  • Saiba quem vocês conhecem em comum
  • Apresente-se
  • Entre em contato direto com Francisco Maria
Cadastre-se para ver o perfil completo

Outros perfis semelhantes

Adicione novas competências com estes cursos