Publications (17)
Generative Feature-driven Image Replay for Continual Learning
Kevin Thandiackal, Tiziano Portenier, Andrea Giovannini +2
Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a sub…
HACT-Net: A Hierarchical Cell-to-Tissue Graph Neural Network for Histopathological Image Classification
Pushpak Pati, Guillaume Jaume, Lauren Alisha Fernandes +13
Cancer diagnosis, prognosis, and therapeutic response prediction are heavily influenced by the relationship between the histopathological structures and the function of the tissue.…
Mitosis Detection Under Limited Annotation: A Joint Learning Approach
Pushpak Pati, Antonio Foncubierta-Rodriguez, Orcun Goksel +1
Mitotic counting is a vital prognostic marker of tumor proliferation in breast cancer. Deep learning-based mitotic detection is on par with pathologists, but it requires large labe…
Revisiting Few-Shot Learning for Facial Expression Recognition
Anca-Nicoleta Ciubotaru, Arnout Devos, Behzad Bozorgtabar +2
Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest imp…
Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images
Kevin Thandiackal, Boqi Chen, Pushpak Pati +4
Multiple Instance Learning (MIL) methods have become increasingly popular for classifying giga-pixel sized Whole-Slide Images (WSIs) in digital pathology. Most MIL methods operate…
edGNN: a Simple and Powerful GNN for Directed Labeled Graphs
Guillaume Jaume, An-phi Nguyen, MarÃa RodrÃguez MartÃnez +2
The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on pr…
HistoCartography: A Toolkit for Graph Analytics in Digital Pathology
Guillaume Jaume, Pushpak Pati, Valentin Anklin +2
Advances in entity-graph based analysis of histopathology images have brought in a new paradigm to describe tissue composition, and learn the tissue structure-to-function relations…
Quantifying Explainers of Graph Neural Networks in Computational Pathology
Guillaume Jaume, Pushpak Pati, Behzad Bozorgtabar +7
Explainability of deep learning methods is imperative to facilitate their clinical adoption in digital pathology. However, popular deep learning methods and explainability techniqu…
Hierarchical Graph Representations in Digital Pathology
Pushpak Pati, Guillaume Jaume, Antonio Foncubierta +14
Cancer diagnosis, prognosis, and therapy response predictions from tissue specimens highly depend on the phenotype and topological distribution of constituting histological entitie…
Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training
M. Emre Sahin, Benjamin C. B. Symons, Pushpak Pati +5
Quantum machine learning with quantum kernels for classification problems is a growing area of research. Recently, quantum kernel alignment techniques that parameterise the kernel…
AI Age Discrepancy: A Novel Parameter for Frailty Assessment in Kidney Tumor Patients
Rikhil Seshadri, Jayant Siva, Angelica Bartholomew +20
Kidney cancer is a global health concern, and accurate assessment of patient frailty is crucial for optimizing surgical outcomes. This paper introduces AI Age Discrepancy, a novel…
Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs
Valentin Anklin, Pushpak Pati, Guillaume Jaume +6
Segmenting histology images into diagnostically relevant regions is imperative to support timely and reliable decisions by pathologists. To this end, computer-aided techniques have…
Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks
Guillaume Jaume, Behzad Bozorgtabar, Hazim Kemal Ekenel +2
We introduce a new scene graph generation method called image-level attentional context modeling (ILAC). Our model includes an attentional graph network that effectively propagates…
NINEPINS: Nuclei Instance Segmentation with Point Annotations
Ting-An Yen, Hung-Chun Hsu, Pushpak Pati +3
Deep learning-based methods are gaining traction in digital pathology, with an increasing number of publications and challenges that aim at easing the work of systematically and ex…
Weakly Supervised Joint Whole-Slide Segmentation and Classification in Prostate Cancer
Pushpak Pati, Guillaume Jaume, Zeineb Ayadi +4
The segmentation and automatic identification of histological regions of diagnostic interest offer a valuable aid to pathologists. However, segmentation methods are hampered by the…
Towards Explainable Graph Representations in Digital Pathology
Guillaume Jaume, Pushpak Pati, Antonio Foncubierta-Rodriguez +6
Explainability of machine learning (ML) techniques in digital pathology (DP) is of great significance to facilitate their wide adoption in clinics. Recently, graph techniques encod…
BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images
Nadia Brancati, Anna Maria Anniciello, Pushpak Pati +10
Breast cancer is the most commonly diagnosed cancer and registers the highest number of deaths for women with cancer. Recent advancements in diagnostic activities combined with lar…