Keywords:
Publications of Mara Graziani
2023
Concept discovery and Dataset exploration with Singular Value Decomposition, ICLR Workshop on Trustworthy ML, 2023 | , , , and ,
|
Deep learning interpretability: measuring the relevance of clinical concepts in convolutional neural networks features, Elsevier, volume 157-192, 2023 | , and ,
|
Deep learning uncertainty quantification of cortical lesions in MP2RAGE for missed lesions discovery, European Committee for Treatment and Research in Multiple Sclerosis (ECTRIMS) Conference 2023, 2023 | , , , , , , , and ,
|
Disentangling Neuron Representations with Concept Vectors, in: Proceedings of the 2nd Explainable AI for Computer Vision (XAI4CV) Workshop at CVPR 2023, 2023 | , , and ,
|
FLAIR vs MPRAGE contribution to white matter lesion automatic segmentation in MS using localized saliency maps, in: Bern Interpretable AI Symposium (BIAS), 2023 | , , , , , , , and ,
|
Learning Interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs To Improve Generalization (2023), in: Machine Learning for Biomedical Imaging (MELBA), 2 | , , , and ,
[DOI] |
NOVEL STRUCTURAL-SCALE UNCERTAINTY MEASURES AND ERROR RETENTION CURVES: APPLICATION TO MULTIPLE SCLEROSIS (2023), in: Proceedings of International Symposium of Biomedical Imaging 2023 | , , , , , , , and ,
|
Tackling Bias in the Dice Similarity Coefficient: Introducing nDSC for White Matter Lesion Segmentation, in: IEEE International Symposium on Biomedical Imaging, 2023 | , , , , , and ,
|
The Normalised Dice Similarity Coefficient for MS: tackling lesion load biases in white matter and cortical lesion segmentation, European Committee for Treatment and Research in Multiple Sclerosis (ECTRIMS) Conference 2023, 2023 | , , , , , , , , and ,
|
Towards Informative Uncertainty Measures for MRI Segmentation in Clinical Practice: Application to Multiple Sclerosis, in: Bern Interpretable Symposium (BIAS) 2023, 2023 | , , , , , , , and ,
|
Towards Informative Uncertainty Measures for MRI Segmentation in Clinical Practice: Application to Multiple Sclerosis, ISMRM & ISMRT 2023 Annual Meeting & Exhibition, 2023 | , , , , , , , and ,
|
2022
A Global Taxonomy of Interpretable AI: Unifying the Terminology for the Technical and Social Sciences (2022), in: Artificial Intelligence Review, 56(3473–3504) | , , , , , , , , , , , , , , and ,
|
Attention-based Interpretable Regression of Gene Expression in Histology, in: Proceedings of the The Workshop on Interpretability of Machine Intelligence in Medical Image Computing (iMIMIC) at MICCAI 2022, 2022 | , , , , and ,
|
Deep Learning Interpretability: Measureing the relevance of clinical concepts in CNN features, in: State of the art in neural networks, Elsevier, 2022 | , and ,
Shifts 2.0: Extending The Dataset of Real Distributional Shifts, arXiv, 2022 | , , , , , , , , , , , , , , , , and ,
[DOI] [URL] |
2021
Evaluation and Comparison of CNN Visual Explanations for Histopathology, in: XAI-AAAI-21, 2021 | , , and ,
|
On the Scale Invariance in State of the Art CNNs Trained on ImageNet (2021), in: Special Issue "Interpretable and Annotation-Efficient Learning for Medical Image Computing" in Machine Learning and Knowledge Extraction:3(374–391) | , , , and ,
|
Sharpening Local Interpretable Model-agnostic Explanations for Histopathology: Improved Understandability and Reliability, in: MICCAI 2021, Springer, 2021 | , , , , and ,
|
2020
Breast Histopathology with High-Performance Computing and Deep Learning (2020), in: Computer and Informatics | , , , , and ,
|
Concept attribution: Explaining CNN decisions to physicians (2020), in: Computers in Biology and Medicine | , and ,
[DOI] |
Consistency of Scale Covariance in Internal Representations of CNNs, in: Irish Machine Vision and Image Processing Conference, 2020 | , , and ,
|
Guiding CNNs towards Relevant Concepts by Multi-task and Adversarial Learning, arxiv, 2020 | , , and ,
[URL] |
Interpretable CNN Pruning for Preserving Scale-Covariant Features in Medical Imaging, in: Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2020, 2020 | , , , and ,
|
PROCESS Data Infrastructure and Data Service (2020), in: Computing and Informatics | , , , , , , , , , and ,
|
Reference Exascale Architecture - Extended Version (2020), in: Computer And Informatics | , , , , , , , , , and ,
|
2019
Heterogeneous exascale computing, in: INES 2018 conference, Springer, 2019 | , , , , , , , , , , , , , , , , , , , , , , and ,
|
Improved interpretability for computer-aided severity assessment of retinopathy of prematurity, in: SPIE Medical Imaging, San Diego, CA, USA, 2019 | , , , , , , , , and ,
|
Interpreting intentionally flawed models with linear probes, in: ICCV workshop on statistical deep learning in computer vision, Seoul, Korea, 2019 | , and ,
|
Machine Learning in Medical Imaging, Radenci, Slovenia, 2019 | , , and ,
|
Visualizing and interpreting feature reuse of pretrained CNNs for histopathology, in: IMVIP 2019, Dublin, Ireland, 2019 | , and ,
|
2018
Myo-electricity and gaze tracking data to improve hand prosthetics and neuro-cognitive examination, in: FESSH 2018, Copenhagen, Denmark, 2018 | , , , , , , , , , , , , and ,
|
Regression Concept Vectors for Bidirectional Explanations in Histopathology (2018), in: Lecture Notes in Computer Science, Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2018(8)
|
, and ,
|
2017
Megane Pro: myo-electricity, visual and gaze tracking integration as a resource for dexterous hand prosthetics, in: IEEE International Conference on Rehabilitation Robotics, London, UK, 2017 | , , , , , , , , , , , and ,
|
Semi-automatic training of an object recognition system in scene camera data using gaze tracking and accelerometers, in: International Conference on Computer Vision Systems (ICVS), Shenzhen (China), 2017 | , , , , , , , and ,
|
Regression-based Deep-Learning predicts molecular biomarkers from pathology slides | , , , , , , , , , , , , , , , and ,
|