Skip to content
View gianlucarloni's full-sized avatar

Highlights

  • Pro

Block or report gianlucarloni

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
gianlucarloni/README.md

πŸš€ About Me

Hi there! I'm Gianluca, a passionate Research Scientist involved in conquering cancer through AI


πŸ’Ό Career Highlights

Applied Research Scientist at Lunit Inc. πŸ”΅ πŸ”΅

Nov 2024 - Present
Berlin, Germany

In the Model-Centric AI research team of the Oncology group, I have been:

  • 🩻 Developing AI models to advance the suit of LunitΒ΄s products and the SOTA in medical image analysis.
  • πŸ’» Contributing to the internal research codebases with high-quality code and development standards.
  • 🀝 Collaborating with research engineers and medical doctors for practical medical applications.
  • πŸ“° Pushing Lunit's technological advancement and publishing in top-tier journals and conferences

Research Fellow and PhD Student at National Research Council of Italy

Sep 2021 - Oct 2024
Pisa, Italy

In the Signals and Images Laboratory, I have:

  • ⏫ Proposed bias-mitigation frameworks for robust DL image classification in out-of-distribution settings under domain shift. Based on causal inference, feature disentanglement, contrastive learning, and injection of prior knowledge. Applied to large RWD CXR datasets.
  • πŸ” Investigated techniques to discover causal disposition signals in images via Attention-inspired CNNs for cancer prediction from medical imaging (prostate MRI and HE digital pathology).
  • 🧠 Proposed biologically inspired context-aware image classifiers akin to human vision.
  • πŸ€– Experienced with DDPMs (generative AI) to synthesize MRI images of prostate cancer.
  • πŸ“š Led a systematic literature review to study the intersection of causality and Explainable AI.
  • 🀱 Explored the applicability of prototypical part learning in medical imaging by experimenting with ProtoPNet on a breast mass classification from mammogram images.

Visiting researcher at The University of Edinburgh

Apr - Jun 2023
Edinburgh, UK

At the VIOS Collaboratory led by Prof. Tsaftaris, I have:

  • πŸ”­ Experimented with representation learning, causal reasoning in neural networks, and diffusion models.
  • ↔️ Collaborated in international research groups
  • πŸ–₯️ Group-coded with four other PhD students for a MICCAI 2023 challenge.

πŸ‘¨β€πŸŽ“ Education

PhD in Information Engineering

Pisa, Italy (Nov 2021 - Nov 2024)
Thesis: β€œHuman-aligned Deep Learning: Explainability, Causality, and Biological Inspiration.”

MSc in Biomedical Engineering

Pisa, Italy (Oct 2018 - Jul 2021)
Thesis: β€œStudy and development of advanced models integrating radiomic features and clinical data for outcome prediction in non-small cell lung cancer patients treated for brain metastases with stereotactic radiotherapy.”

BSc in Biomedical Engineering

Bologna, Italy (Sep 2015 - Oct 2018)
Thesis: β€œDevelopment of a Graphical User Interface in MATLAB for the visualization and spectral analysis of EEG and ECG signals.”


πŸ› οΈ Technologies & Tools

Programming Languages:

Python Libraries:

Tools & Technologies:


🌟 Notable Projects during my PhD on AI for Medical Imaging

to do

  1. [Project Name 1](Link to GitHub Repo)
    Short description of the project and technologies used.
    πŸš€ Features: [Key Features]
    πŸ’» Built with: [Tech Stack]

  2. [Project Name 2](Link to GitHub Repo)
    Short description of the project and technologies used.
    πŸš€ Features: [Key Features]
    πŸ’» Built with: [Tech Stack]


πŸ“ˆ GitHub Stats

My GitHub stats


πŸ“ž Connect With Me

LinkedIn


🎨 Fun Fact

When I’m not coding, I’m into photography, cooking, rock music, and exploring the outdoors. Here’s a peek at my stuff:

Pinned Loading

  1. crocodile crocodile Public

    Carloni, G., Tsaftaris, S. A., & Colantonio, S. (2024). CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning @ MICCAI 2024 UNSURE Workshop

    Python 7 1

  2. causality_conv_nets causality_conv_nets Public

    Experiment with our attention-inspired framework for causality-driven CNNs: learn how to model causal dispositions within image datasets and enhance your image classifier's performance and XAI robu…

    Python 4 1

  3. CoCoReco CoCoReco Public

    Code base for our paper "Connectivity-Inspired Network for Context-Aware Recognition" (ECCV 2024, Human-inspired Computer Vision workshop)

    Python 3 1