Search

Your search keyword '"Tsiknakis, Nikos"' showing total 18 results
Start Over Author "Tsiknakis, Nikos"
18 results on '"Tsiknakis, Nikos"'

5. Using Commercial and Open-Source Tools for Artificial Intelligence: A Case Demonstration on a Complete Radiomics Pipeline

Author

Stamoulou, Elisavet, Spanakis, Constantinos, Nikiforaki, Katerina, Karantanas, Apostolos H., Tsiknakis, Nikos, Matikas, Alexios, Foukakis, Theodoros, Manikis, Georgios C., van Ooijen, Peter M. A., Series Editor, Ranschaert, Erik R., Series Editor, Trianni, Annalisa, Series Editor, Klontzas, Michail E., Series Editor, Fanni, Salvatore Claudio, editor, and Neri, Emanuele, editor

Published
2023
Full Text
View/download PDF

7. Unveiling the Power of Model-Agnostic Multiscale Analysis for Enhancing Artificial Intelligence Models in Breast Cancer Histopathology Images

Author

Tsiknakis, Nikos, Manikis, Georgios, Tzoras, Evangelos, Salgkamis, Dimitrios, Vidal, Joan Martinez, Wang, Kang, Zaridis, Dimitris, Sifakis, Emmanouil, Zerdes, Ioannis, Bergh, Jonas, Hartman, Johan, Acs, Balazs, Marias, Kostas, and Foukakis, Theodoros

Abstract

Developing AI models for digital pathology has traditionally relied on single-scale analysis of histopathology slides. However, a whole slide image is a rich digital representation of the tissue, captured at various magnification levels. Limiting our analysis to a single scale overlooks critical information, spanning from intricate high-resolution cellular details to broad low-resolution tissue structures. In this study, we propose a model-agnostic multiresolution feature aggregation framework tailored for the analysis of histopathology slides in the context of breast cancer, on a multicohort dataset of 2038 patient samples. We have adapted 9 state-of-the-art multiple instance learning models on our multi-scale methodology and evaluated their performance on grade prediction, TP53 mutation status prediction and survival prediction. The results prove the dominance of the multiresolution methodology, and specifically, concatenating or linearly transforming via a learnable layer the feature vectors of image patches from a high (20x) and low (10x) magnification factors achieve improved performance for all prediction tasks across domain-specific and imagenet-based features. On the contrary, the performance of uniresolution baseline models was not consistent across domain-specific and imagenet-based features. Moreover, we shed light on the inherent inconsistencies observed in models trained on whole-tissue-sections when validated against biopsy-based datasets. Despite these challenges, our findings underscore the superiority of multiresolution analysis over uniresolution methods. Finally, cross-scale analysis also benefits the explainability aspects of attention-based architectures, since one can extract attention maps at the tissue- and cell-levels, improving the interpretation of the model's decision.

Published
2024
Full Text
View/download PDF

12. OCT Sequence Registration Before and after Percutaneous Coronary Intervention (Stent Implantation)

Author

Tsiknakis, Nikos, primary, Spanakis, Constantinos, additional, Tsoumpou, Panagiota, additional, Karanasiou, Georgia, additional, Karanasiou, Gianna, additional, Sakellarios, Antonis, additional, Rigas, George, additional, Kyriakidis, Savvas, additional, Papafaklis, Michail I., additional, Nikopoulos, Sotirios, additional, Michalis, Lampros, additional, Fotiadis, Dimitrios I., additional, and Marias, Kostas, additional

Published
2022
Full Text
View/download PDF

13. IVUS Longitudinal and Axial Registration for Atherosclerosis Progression Evaluation

Author

Tsiknakis, Nikos, primary, Spanakis, Constantinos, additional, Tsompou, Panagiota, additional, Karanasiou, Georgia, additional, Karanasiou, Gianna, additional, Sakellarios, Antonis, additional, Rigas, George, additional, Kyriakidis, Savvas, additional, Papafaklis, Michael, additional, Nikopoulos, Sotirios, additional, Gijsen, Frank, additional, Michalis, Lampros, additional, Fotiadis, Dimitrios I., additional, and Marias, Kostas, additional

Published
2021
Full Text
View/download PDF

16. Advancing Covid‑19 differentiation with a robust preprocessing and integration of multi‑institutional open‑repository computer tomography datasets for deep learning analysis

Author

Trivizakis, Eleftherios, primary, Tsiknakis, Nikos, additional, Vassalou, Evangelia, additional, Papadakis, Georgios, additional, Spandidos, Demetrios, additional, Sarigiannis, Dimosthenis, additional, Tsatsakis, Aristidis, additional, Papanikolaou, Nikolaos, additional, Karantanas, Apostolos, additional, and Marias, Kostas, additional

Published
2020
Full Text
View/download PDF

17. Interpretable artificial intelligence framework for COVID‑19 screening on chest X‑rays

Author

Tsiknakis, Nikos, primary, Trivizakis, Eleftherios, additional, Vassalou, Evangelia, additional, Papadakis, Georgios, additional, Spandidos, Demetrios, additional, Tsatsakis, Aristidis, additional, Sánchez‑García, Jose, additional, López‑González, Rafael, additional, Papanikolaou, Nikolaos, additional, Karantanas, Apostolos, additional, and Marias, Kostas, additional

Published
2020
Full Text
View/download PDF

18. Multiresolution Self-Supervised Feature Integration via Attention Multiple Instance Learning for Histopathology Analysis.

Author

Tsiknakis N, Tzoras E, Zerdes I, Manikis GC, Acs B, Hartman J, Hatschek T, Foukakis T, and Marias K

Subjects
Humans, Female, Diagnostic Imaging, Image Processing, Computer-Assisted methods, Breast Neoplasms diagnosis, Breast Neoplasms pathology
Abstract

Digital histopathology image analysis of tumor tissue sections has seen great research interest for automating standard diagnostic tasks, but also for developing novel prognostic biomarkers. However, research has mainly been focused on developing uniresolution models, capturing either high-resolution cellular features or low-resolution tissue architectural features. In addition, in the patch-based weakly-supervised training of deep learning models, the features which represent the intratumoral heterogeneity are lost. In this study, we propose a multiresolution attention-based multiple instance learning framework that can capture cellular and contextual features from the whole tissue for predicting patient-level outcomes. Several basic mathematical operations were examined for integrating multiresolution features, i.e. addition, mean, multiplication and concatenation. The proposed multiplication-based multiresolution model performed the best (AUC=0.864), while all multiresolution models outperformed the uniresolution baseline models (AUC=0.669, 0.713) for breast-cancer grading. (Implementation: https://github.com/tsikup/multiresolution-clam).

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results