Where we introduce the one of the most simple machine learning models, and show how to obtain a numerical solution.
I am a Post-Doctoral Fellow at the École de Tecnologie Superieure, Montréal (Canada). I work at the Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle (LIVIA), under the supervision of Prof. Ismail ben Ayed and Prof. Hervé Lombaert. My current research is focused on Computer Vision for Medical Imaging applications. I am interested in Deep Learning methods that can be trained on scarce labeled data, with a focus on Weakly-Supervised and Self-Supervised approaches. The main areas of application are Retinal and Histopathological Image Analysis.
Previously I was a Post-Doctoral Fellow at INESC-TEC, INstituto de Engenharia de Sistemas e Computadores, in Porto (Portugal), working on Retinal Image Analysis under the supervision of Prof. Aurélio Campilho. Before this, during my PhD (Basque Country) I worked on the design of new Image Restoration algorithms adapted for problems on which there is an attenuating media in between the observer and the imaged scene.
PhD in Mathematical Image Processing, 2015
University of the Basque Country
MSc in Mathematical Modelization, Statistics and Computation, 2011
Basque Country University
MSc in Mathematical Investigation, 2009
University of Valencia/Polytechnical University of Valencia, Spain
Graduate on Mathematics, 2008
University of Valencia, Spain
CATARACTS: Challenge on Automatic Tool Annotation for cataRACT Surgery, H. Al Hajj, …, A. Galdran, …, G. Quellec, Medical Image Analysis (Q1), Feb/2019, [DOI], [PDF].
Uncertainty-Aware Artery/vein Classification on Retinal Images, A. Galdran, M. I. Meyer, P. Costa, A. M. Mendonça, A. Campilho, IEEE International Symposium on Biomedical Imaging (ISBI), Venice (Italy), Apr/2019, [PDF], [Code].
Real-Time Informative Laryngoscopic Frame Classification with Pre-Trained Convolutional Neural Networks, A. Galdran, P. Costa, A. Campilho, IEEE International Symposium on Biomedical Imaging (ISBI), Venice (Italy), Apr/2019, [PDF].
Learning to Segment the Lung Volume from Ct Scans Based on Semi-Automatic Ground-Truth, P. Sousa, A. Galdran, P. Costa, A. Campilho, IEEE International Symposium on Biomedical Imaging (ISBI), Venice (Italy), Apr/2019. [PDF].
Image Dehazing by Artificial Multi-Exposure Image Fusion, A. Galdran, Signal Processing (Q1), Aug/2018, [DOI], [PDF], [Code].
A fast image dehazing method that does not introduce color artifacts, J. Vazquez-Corral, A. Galdran, Praveen Cyriac, Marcelo Bertalmío, Journal of Real-Time Image Processing (Q3), Aug/2018, [DOI], [PDF].
End-to-end Adversarial Retinal Image Synthesis, P. Costa, A. Galdran, M. I. Meyer, M. Niemeijer, M. Àbramoff, A. M. Mendonça, A. Campilho, IEEE Transactions on Medical Imaging, Mar/2018, [DOI], [PDF], [Code].
A Weakly-Supervised Framework for Interpretable Diabetic Retinopathy Detection on Retinal Images, P. Costa, A. Galdran, A. Smailagic, A. Campilho, IEEE Access (Q1), Mar/2018, [DOI], [PDF].
Weakly-Supervised Fog Detection, A. Galdran, P. Costa, J. Vazquez-Corral, A. Campilho, IEEE International Conference on Image Processing (ICIP), Athens (Greece), Oct/2018, [DOI], [PDF].
A No-Reference Retinal Vessel Tree Segmentation Quality Metric, A. Galdran, P. Costa, A. Bria, T. Araújo, A. M. Mendonça, A. Campilho, 2018 Medical Image Computing and Computer Assisted Intervention (MICCAI), Granada (Spain), Sep/2018, [DOI], [PDF].
A Pixel-wise Distance Regression Approach for Joint Optical Disc and Fovea Detection, M.I. Meyer, A. Galdran, A. M. Mendonça, A. Campilho, 2018 Medical Image Computing and Computer Assisted Intervention (MICCAI), Granada (Spain), Sep/2018, [DOI], [PDF], [Code].
UOLO - automatic object detection and segmentation in biomedical images, T. Araújo, G. Aresta, A. Galdran, P. Costa, A. M. Mendonça, A. Campilho, 2018 Medical Image Computing and Computer Assisted Intervention Workshop (MICCAIw), Granada (Spain), Sep/2018, [DOI], [PDF].
End-to-End Supervised Lung Lobe Segmentation, F.T. Ferreira, P. Sousa, A. Galdran, M. R. Sousa, A. Campilho, 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro (Brazil), Jul/2018, [PDF], [DOI], [Code].
On the Duality Between Retinex and Image Dehazing, A. Galdran, A. Alvarez-Gila, A. Bria, J. Vazquez-Corral, M. Bertalmío, 2018 Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City (USA), Jun/2018, [PDF].
NTIRE 2018 Challenge on Image Dehazing: Methods and Results, C. Ancuti, …, A. Galdran, …, Z. Chen, 2018 Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W), Salt Lake City (USA), Jun/2018, [PDF].
NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images, B. Arad, …, A. Galdran, …, S. Sarkar, 2018 Conference on Computer Vision and Pattern Recognition Workshops (CVPR-W), Salt Lake City (USA), Jun/2018, [PDF].
Deep Convolutional Artery/Vein Classification of Retinal Vessels, M.I. Meyer, A. Galdran, P. Costa, A. M. Mendonça, A. Campilho, International Conference on Image Analysis and Recognition (ICIAR), Porto (Portugal), Jun/2018, [DOI], [PDF].
Fusion-Based Variational Image Dehazing, A. Galdran, J. Vazquez-Corral, D. Pardo, M. Bertalmio, IEEE Signal Processing Letters (Q2), Feb/2017, [DOI], [PDF], [Code].
Retinal Image Quality Assessment by Mean-Subtracted Contrast-Normalized Coefficients, A. Galdran, T. Araújo, A. M. Mendonça, A. Campilho, VI ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing (VIPIMAGE), Porto (Portugal), Oct/2017, [DOI], [PDF].
Spatial Enhancement by Dehazing for Detection of Microcalcifications with Convolutional Nets, A. Bria, C. Marrocco, A. Galdran, A. Campilho, A. Marchesi, J.J. Mordang, N. Karssemeijer, M. Molinara, F. Tortorella, International Conference on Image Analysis and Processing (ICIAP), Catania (Italy), Sep/2017, [DOI], [PDF].
Deflectometry setup definition for automatic chrome surface inspection, A. Isasi, E. Garrote, P. Iriondo, D. Aldama, A. Galdran, IEEE Emerging Technologies and Factory Automation (ETFA), Lymassol (Cyprus), Sep/2017, [DOI], [PDF].
An Efficient Non-uniformity Correction Technique for Side-Scan Sonar Imagery, A. Galdran, A. Isasi, M. Al-Rawi, J. Rodriguez, J. Bastos, F. Elmgren, M. Pinto, IEEE Oceans Conference, Aberdeen (Scotland), Jul/2017, [DOI], [PDF].
A Deep Neural Network for Vessel Segmentation of Scanning Laser Ophthalmoscopy Images, M.I. Meyer, P. Costa, A. Galdran, A. M. Mendonça, A. Campilho, International Conference on Image Analysis and Recognition (ICIAR), Montreal (Canada), Jul/2017, [DOI], [PDF].
Adversarial Synthesis of Retinal Images from Vessel Trees, P. Costa, A. Galdran, M.I. Meyer, A. M. Mendonça, A. Campilho, International Conference on Image Analysis and Recognition (ICIAR), Montreal (Canada), Jul/2017, [DOI], [PDF].
Illumination correction by dehazing for retinal vessel segmentation, B. Savelli, A. Bria, C. Marrocco, M. Molinara, F. Tortorella, A. Galdran, A. Campilho, IEEE 30th International Symposium on Computer-based Medical Systems (CBMS), Thessaloniki (Greece), [DOI], [PDF].
Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis, A. Galdran, A. Alvarez-Gila, M. I. Meyer, C. L. Saratxaga, T. Araújo, E. Garrote, G. Aresta, P. Costa, A. M. Mendonça, A. Campilho, Mar/2017. [Arxiv link].
Towards Adversarial Retinal Image Synthesis, P. Costa, A. Galdran, M. I. Meyer, M. D. Abràmoff, M. Niemeijer, A.M. Mendonça, A. Campilho, Jan/2017. [Arxiv link], [Code].
3D Active Surfaces for Liver Segmentation in Multisequence MRI Images, A. Bereciartua, A. Picon, A. Galdran, P. Iriondo, Computer Methods and Programs in Biomedicine (Q1), Aug/2016, [DOI].
Intensity normalization of sidescan sonar imagery, M. S. Al-Rawi, A. Galdran, X. Yuan, M. Eckert, J. F. Martinez, F. Elmgren, B. Cürüklü, J. Rodriguez, J. Bastos, M. Pinto, Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), Oulu (Finland), Dec/2016, [DOI], [PDF].
Image processing applications through a variational perceptually-based color correction related to Retinex, J. Vazquez-Corral, S. Waqas Zamir, A. Galdran, D. Pardo, M. Bertalmio, IS&T International Symposium on Electronic Imaging, San Francisco (CA, USA), Feb/2016, [DOI], [PDF].
Enhanced Variational Image Dehazing, A. Galdran, J. Vazquez-Corral, D. Pardo, M. Bertalmio, SIAM Journal on Imaging Sciences (Q1), Jul/2015, [DOI], [PDF], [Code].
Automatic 3D model-based method for liver segmentation in MRI based on active contours and total variation minimization, A. Bereciartua, A. Picon, A. Galdran, P. Iriondo, Computer Methods and Programs in Biomedicine (Q3), Jul/2015, [DOI], [PDF].
Automatic Red-Channel underwater image restoration, A. Galdran, D. Pardo, A. Picón, A. Alvarez-Gila, Journal of Visual Communication and Image Representation (Q1), Jan/2015, [DOI], [PDF].
Pectoral muscle segmentation in mammograms based on cartoon-texture decomposition, A. Galdran, A. Picón, E. Garrote, D. Pardo, Iberian Conference on Pattern Recognition and Image Analysis (IBPRIA), Santiago de Compostela (Spain), Jun/2015, [DOI], [PDF].
A Variational Framework for Single Image Dehazing, A. Galdran, J. Vazquez-Corral, D. Pardo, M. Bertalmio, European Conference on Computer Vision - Workshop on Color and Photometry in Computer Vision (ECCV-W), Zurich (Switzerland), Jul/2014, [DOI], [PDF].
I am/have been a teaching instructor for the following courses:
Below you can find some supporting material for my teaching activities:
This will host material for the theoretical lessons I will be teaching.
Where we introduce the one of the most simple machine learning models, and show how to obtain a numerical solution.
Where we learn about simple neural networks, the predecessor of the nowadays almighty Deep Learning models.
Here you can find practical material for the Computer-Aided Diagnosis (DACO) course, taught at the Faculty of Engineering/University of Porto, in its 2017⁄18 edition.
This year, I am the teaching instructor for the practical sessions, and I also teach some theory. Below you will find content associated to the practical lectures. I will probably be updating this each week.
Where we learn the basics of how set up a Python-based system to develop Machine Learning, Computer Vision, and Image Processing projects.
Where we introduce the scikit-learn library for Machine Learning. We learn about Classification with the Naive Bayes classifier, and Regression with a simple Linear Regression model.