articles
publications by categories in reversed chronological order. generated by jekyll-scholar.
I have a total of 6 publications, of which 5 are journal articles and 1 are conference papers.
2021
- JournalDeep Learning for Diabetic Retinopathy Detection and Classification Based on Fundus Images: A ReviewN. Tsiknakis, D. Theodoropoulos, G. Manikis, E. Ktistakis, O. Boutsora, A. Berto, F. Scarpa, A. Scarpa, D. Fotiadis, and K. MariasComputers in Biology and Medicine 2021
Diabetic Retinopathy is a retina disease caused by diabetes mellitus and it is the leading cause of blindness globally. Early detection and treatment are necessary in order to delay or avoid vision deterioration and vision loss. To that end, many artificial-intelligence-powered methods have been proposed by the research community for the detection and classification of diabetic retinopathy on fundus retina images. This review article provides a thorough analysis of the use of deep learning methods at the various steps of the diabetic retinopathy detection pipeline based on fundus images. We discuss several aspects of that pipeline, ranging from the datasets that are widely used by the research community, the preprocessing techniques employed and how these accelerate and improve the modelsâ performance, to the development of such deep learning models for the diagnosis and grading of the disease as well as the localization of the diseaseâs lesions. We also discuss certain models that have been applied in real clinical settings. Finally, we conclude with some important insights and provide future research directions.
@article{deeptsiknakis2021, abbr = {Journal}, title = {Deep Learning for Diabetic Retinopathy Detection and Classification Based on Fundus Images: A Review}, journal = {Computers in Biology and Medicine}, publisher = {Elsevier}, pages = {104599}, year = {2021}, issn = {0010-4825}, pdf = {Tsiknakis - Deep learning for diabetic retinopathy detection and classification based on fundus images: A review.pdf}, doi = {https://doi.org/10.1016/j.compbiomed.2021.104599}, simple_doi = {10.1016/j.compbiomed.2021.104599}, url = {https://www.sciencedirect.com/science/article/pii/S0010482521003930}, author = {Tsiknakis, Nikos and Theodoropoulos, Dimitris and Manikis, Georgios and Ktistakis, Emmanouil and Boutsora, Ourania and Berto, Alexa and Scarpa, Fabio and Scarpa, Alberto and Fotiadis, Dimitrios I. and Marias, Kostas}, keywords = {artificial intelligence, classification, deep learning, detection, diabetic retinopathy, fundus, retina, review, segmentation}, selected = {true}, bibtex_show = {true} }
- JournalSegmenting 20 Types of Pollen Grains for the Cretan Pollen Dataset v1 (CPD-1)N. Tsiknakis, E. Savvidaki, S. Kafetzopoulos, G. Manikis, N. Vidakis, K. Marias, and E. AlissandrakisApplied Sciences 2021
Pollen analysis and the classification of several pollen species is an important task in melissopalynology. The development of machine learning or deep learning based classification models depends on available datasets of pollen grains from various plant species from around the globe. In this paper, Cretan Pollen Dataset v1 (CPD-1) is presented, which is a novel dataset of grains from 20 pollen species from plants gathered in Crete, Greece. The pollen grains were prepared and stained with fuchsin, in order to be captured by a camera attached to a microscope under a Ă400 magnification. In addition, a pollen grain segmentation method is presented, which segments and crops each unique pollen grain and achieved an overall detection accuracy of 92%. The final dataset comprises 4034 segmented pollen grains of 20 different pollen species, as well as the raw data and ground truth, as annotated by an expert. The developed dataset is publicly accessible, which we hope will accelerate research in melissopalynology.
@article{app11146657, abbr = {Journal}, author = {Tsiknakis, Nikos and Savvidaki, Elisavet and Kafetzopoulos, Sotiris and Manikis, Georgios and Vidakis, Nikolas and Marias, Kostas and Alissandrakis, Eleftherios}, title = {Segmenting 20 Types of Pollen Grains for the Cretan Pollen Dataset v1 (CPD-1)}, journal = {Applied Sciences}, publisher = {MDPI}, volume = {11}, year = {2021}, number = {14}, article-number = {6657}, url = {https://www.mdpi.com/2076-3417/11/14/6657}, issn = {2076-3417}, simple_doi = {10.3390/app11146657}, doi = {https://doi.org/10.3390/app11146657}, keywords = {dataset, honey, melissopalinology, pollen grain, segmentation}, pdf = {Tsiknakis - Segmenting 20 Types of Pollen Grains for the Cretan Pollen v1 (CPD-1).pdf}, selected = {false}, bibtex_show = {true} }
- JournalIVUS Longitudinal and Axial Registration for Atherosclerosis Progression EvaluationN. Tsiknakis, C. Spanakis, P. Tsompou, G. Karanasiou, G. Karanasiou, A. Sakellarios, G. Rigas, S. Kyriakidis, M. Papafaklis, S. Nikopoulos, F. Gijsen, L. Michalis, D. Fotiadis, and K. MariasDiagnostics 2021
@article{diagnostics11081513, abbr = {Journal}, author = {Tsiknakis, Nikos and Spanakis, Constantinos and Tsompou, Panagiota and Karanasiou, Georgia and Karanasiou, Gianna and Sakellarios, Antonis and Rigas, George and Kyriakidis, Savvas and Papafaklis, Michael and Nikopoulos, Sotirios and Gijsen, Frank and Michalis, Lampros and Fotiadis, Dimitrios I. and Marias, Kostas}, title = {IVUS Longitudinal and Axial Registration for Atherosclerosis Progression Evaluation}, journal = {Diagnostics}, volume = {11}, year = {2021}, number = {8}, article-number = {1513}, url = {https://www.mdpi.com/2075-4418/11/8/1513}, pubmedid = {34441447}, issn = {2075-4418}, doi = {https://doi.org/10.3390/diagnostics11081513}, simple_doi = {10.3390/diagnostics11081513}, keywords = {atherosclerosis, IVUS, stent, longitudinal registration, axial registration, image registration, 3D registration, ultrasound}, pdf = {Tsiknakis - IVUS Longitudinal and Axial Registration.pdf}, selected = {false}, bibtex_show = {true} }
2020
- JournalAdvancing COVID-19 differentiation with a robust preprocessing and integration of multi-institutional open-repository computer tomography datasets for deep learning analysisE. Trivizakis, N. Tsiknakis, E. Vassalou, G. Papadakis, D. Spandidos, D. Sarigiannis, A. Tsatsakis, N. Papanikolaou, A. Karantanas, and K. MariasExperimental and Therapeutic Medicine 2020
The coronavirus pandemic and its unprecedented consequences globally has spurred the interest of the artificial intelligence research community. A plethora of published studies have investigated the role of imaging such as chest Xârays and computer tomography in coronavirus disease 2019 (COVIDâ19) automated diagnosis. Îpen repositories of medical imaging data can play a significant role by promoting cooperation among institutes in a worldâwide scale. However, they may induce limitations related to variable data quality and intrinsic differences due to the wide variety of scanner vendors and imaging parameters. In this study, a stateâofâtheâart custom UâNet model is presented with a dice similarity coefficient performance of 99.6% along with a transfer learning VGGâ19 based model for COVIDâ19 versus pneumonia differentiation exhibiting an area under curve of 96.1%. The above was significantly improved over the baseline model trained with no segmentation in selected tomographic slices of the same dataset. The presented study highlights the importance of a robust preprocessing protocol for image analysis within a heterogeneous imaging dataset and assesses the potential diagnostic value of the presented COVIDâ19 model by comparing its performance to the state of the art.
@article{trivizakis2020advancing, abbr = {Journal}, title = {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 and Tsiknakis, Nikos and Vassalou, Evangelia E and Papadakis, Georgios Z and Spandidos, Demetrios A and Sarigiannis, Dimosthenis and Tsatsakis, Aristidis and Papanikolaou, Nikolaos and Karantanas, Apostolos H and Marias, Kostas}, journal = {Experimental and Therapeutic Medicine}, publisher = {Spandidos Publications}, volume = {20}, number = {5}, year = {2020}, days = {11}, month = sep, code = {https://github.com/trivizakis/ct-covid-analysis}, pdf = {Advancing_COVID_19_differentiation_with_a_robust_preprocessing_and_integration_of_multi_institutional_open_repository_computer_tomography_datasets_for_deep_learning_analysis.pdf}, doi = {https://doi.org/10.3892/etm.2020.9210}, simple_doi = {10.3892/etm.2020.9210}, selected = {false}, bibtex_show = {true} }
- JournalInterpretable artificial intelligence framework for COVIDâ19 screening on chest XâraysN. Tsiknakis, E. Trivizakis, E. Vassalou, G. Papadakis, D. Spandidos, A. Tsatsakis, J. SĂĄnchezâGarcĂa, R. LĂłpezâGonzĂĄlez, N. Papanikolaou, A. Karantanas, and K. MariasExperimental and Therapeutic Medicine 2020
COVID-19 has led to an unprecedented healthcare crisis with millions of infected people across the globe often pushing infrastructures, healthcare workers and entire economies beyond their limits. The scarcity of testing kits, even in developed countries, has led to extensive research efforts towards alternative solutions with high sensitivity. Chest radiological imaging paired with artificial intelligence (AI) can offer significant advantages in diagnosis of novel coronavirus infected patients. To this end, transfer learning techniques are used for overcoming the limitations emanating from the lack of relevant big datasets, enabling specialized models to converge on limited data, as in the case of Xârays of COVIDâ19 patients. In this study, we present an interpretable AI framework assessed by expert radiologists on the basis on how well the attention maps focus on the diagnosticallyârelevant image regions. The proposed transfer learning methodology achieves an overall area under the curve of 1 for a binary classification problem across a 5âfold training/testing dataset.
@article{tsiknakis2020covid, abbr = {Journal}, author = {Tsiknakis, Nikos and Trivizakis, Eleftherios and Vassalou, Evangelia E. and Papadakis, Georgios Z. and Spandidos, Demetrios A. and Tsatsakis, Aristidis and SĂĄnchezâGarcĂa, Jose and LĂłpezâGonzĂĄlez, Rafael and Papanikolaou, Nikolaos and Karantanas, Apostolos H. and Marias, Kostas}, title = {Interpretable artificial intelligence framework for COVIDâ19 screening on chest Xârays}, journal = {Experimental and Therapeutic Medicine}, publisher = {Spandidos Publications}, days = {27}, month = may, year = {2020}, doi = {https://doi.org/10.3892/etm.2020.8797}, simple_doi = {10.3892/etm.2020.8797}, code = {https://github.com/tsikup/covid19-xray-cnn}, pdf = {Interpretable_artificial_intelligence_framework_for_COVID_19_screening_on_chest_X_rays.pdf}, keywords = {COVIDâ19, chest Xârays, interpretable artificial intelligence, transfer learning}, selected = {true}, bibtex_show = {true} }
2019
- ConferenceRenyi divergence and non-deterministic subsampling in Rigid Image RegistrationC. Spanakis, E. Mathioudakis, N. Kampanis, N. Tsiknakis, and K. MariasIn IEEE International Conference on Imaging Systems and Techniques (IST) 2019
The successful application and reported robustness of Mutual Information both in rigid and nonrigid image registration over the last decades gave rise to an ongoing research on other information based similarity metrics emanating from Renyi Divergence. To the best of our knowledge however, this is the first paper studying the effects of Renyi parameter in combination with a subsampling factor in image registration accuracy. To this end, a series of experiments are presented with respect to the effect of Renyiâs parameter and the subsampling factor in registration accuracy. Our results show that the increase of the Renyi parameter and the percentage of the pixels used leads, on average, to the reduction of the registration error.
@inproceedings{Span1912:Renyi, abbr = {Conference}, author = {Spanakis, Constantinos and Mathioudakis, Emmanuel and Kampanis, Nikos and Tsiknakis, Nikos and Marias, Kostas}, title = {Renyi divergence and non-deterministic subsampling in Rigid Image Registration}, booktitle = {IEEE International Conference on Imaging Systems and Techniques (IST)}, address = {Abu Dhabi, United Arab Emirates}, days = {7}, month = dec, year = {2019}, doi = {https://doi.org/10.1109/IST48021.2019.9010237}, simple_doi = {10.1109/IST48021.2019.9010237}, keywords = {Renyi divergence; Renyi Entropy; Rigid Image Registration; Subsampling; Mutual Information}, selected = {false}, bibtex_show = {true} }