Research Machine learning for biological and medical image computing

During the last century, continuous advances in biomedical imaging technologies gave rise to a wide variety of visual representations of the interior of living organisms at the organ, tissue, cellular and molecular level. Modalities such as x-ray, nuclear and molecular imaging, ultrasound, MRI and CT play a crucial role in clinical practice and basic life sciences research. Nowadays it is possible to process and understand this data thanks to the development of computational methods for the analysis of biological and medical images.
The aim of this research line is to develop novel machine learning methods to tackle some of the main problems in the field of biological and medical image analysis, including image registration, segmentation and classification, with particular focus on deep learning models. Our goal is to address fundamental machine learning problems such as domain adaptation, algorithmic fairness, learning with limited data and non-regular structures which arise in the context of image analysis for biology and medicine.

Team members

Enzo Ferrante
Diego Milone
Rodrigo Echeveste
Lucas Mansilla
Franco Matzkin
Nicolas Gaggion
Agostina Larrazabal
Nicolas Nieto
Victoria Peterson

Demos

Post-DAE: a post-processing method to improve the anatomical plausibility of segmentation masks using denoising autoencoders.
Orthogonal Ensemble Networks for Image Segmentation: ining strategy for deep ensembles of segmentation networks that boosts discrimination and calibration performance.
Head CT Tools: a toolkit that includes a bunch of algorithms for preprocessing CT images & PyTorch based models for brain segmentation or skull reconstruction on craniectomy images.
ChronoRoot: a system for high-throughput plant root phenotyping composed of 3D printed hardware and deep learning methods for image analysis.
HybridGNet: a new hybrid graph convolutional neural network architecture for landmark-based anatomical segmentation.
AC-RegNet: a new method to regularize CNN-based deformable image registration by considering global anatomical priors in the form of segmentation masks.
BLAST: the Brain Lesion Analysis & Segmentation Tool, implements pre-processing pipelines and several CNN architectures (DeepMedic, UNet3D, etc) for lesion and anatomy segmentation in brain images using Lasagne (Theano).
GenderBiasX-Ray: a fairness study where we show that computer assisted diagnosis systems acquire gender bias when training datasets are highly imbalanced.

Selected publications

Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis    

A. Larrazabal, N. Nieto, V. Peterson, D. H. Milone, E. Ferrante

Proceedings of the National Academy of Sciences – 2020

Learning deformable registration of medical images with anatomical constraints    

L. Mansilla, D. H. Milone, E. Ferrante

Neural Networks, Volume 124, page 269–279 – 2020

Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders    

A. Larrazabal, C. E. Martínez, B. Glocker, E. Ferrante

IEEE Transactions on Medical Imaging – 2020

Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy   

F. Matzkin, V. F. J. Newcombe, S. Stevenson, A. Khetani, T. Newman, R. Digby, A. Stevens, B. Glocker, E. Ferrante

Medical Image Computing and Computer Assisted Intervention — MICCAI 2020 – 2020

Análisis automático de radiografías torácicas por medio de redes neuronales profundas   

E. Fernández, E. Ferrante

Master thesis from Facultad de Ciencias Exactas y Naturales – Universidad de Buenos Aires – 2019

Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders   

A. Larrazabal, C. E. Martínez, E. Ferrante

MICCAI 2019: International Conference on Medical Image Computing and Computer-Assisted Intervention – 2019

Diseño y desarrollo de una herramienta para la segmentación automática en imágenes TAC de pacientes con traumatismo de cráneo mediante redes neuronales convolucionales. (Undergraduate project)   

F. Matzkin, E. Ferrante

Master thesis from Facultad de Ingeniería y Ciencias Hídricas – Universidad Nacional del Litoral – 2019

TBI Lesion Segmentation in Head CT: Impact of Preprocessing and Data Augmentation   

M. Monteiro, Kamnitsas K., E. Ferrante, et al.

MICCAI Brain Lesion Workshop – 2019

Deep learning with ultrasound physics for fetal skull segmentation.    

J. Cerrolaza, M. Sinclair, Y. Li, A. Gómez, E. Ferrante, J. Matthew, C. Gupta, C. Knight, D. Rueckert

Biomedical Imaging (ISBI 2018), 2018 IEEE 15th International Symposium on, page 564–567 – 2018

Disease prediction using graph convolutional networks: application to autism spectrum disorder and alzheimer’s disease.    

S. Parisot, S. I. Ktena, E. Ferrante, M. Lee, R. Guerrero, B. Glocker, D. Rueckert

Medical Image Analysis – 2018

Graphs in Biomedical Image Analysis and Integrating Medical Imaging and Non-Imaging Modalities   

D. Stoyanov, Z. Taylor, E. Ferrante, A. Dalca, A. Martel, L. Maier-Hein, S. Parisot, A. Sotiras, B. Papiez, M. Sabuncu, L. Shen

Springer – 2018

Left ventricle quantification through spatio-temporal CNNs   

A. Debus, E. Ferrante

Statistical Atlases and Computational Modeling of the Heart (STACOM 2018) – 2018

On the adaptability of unsupervised cnn-based deformable image registration to unseen image domains   

E. Ferrante, O. Oktay, B. Glocker, D. H. Milone

International Workshop on Machine Learning in Medical Imaging, page 294–302 – 2018

Segmentación automática multi-tarea de imágenes médicas utilizando redes neuronales profundas   

N. Roulet, D. Fernandez Slezak, E. Ferrante

Master thesis from Facultad de Ciencias Exactas y Naturales – Universidad de Buenos Aires – 2018

Segmentación multi-atlas de imágenes médicas con selección de atlas inteligente y control de calidad automático   

L. Mansilla, E. Ferrante

XXIV Congreso Argentino de Ciencias de la Computación (La Plata, 2018). – 2018

Weakly-supervised learning of metric aggregations for deformable image registration   

E. Ferrante, P. Dokania, R. Marini, P. Nikos

IEEE journal of biomedical and health informatics – 2018

Anatomically Constrained Neural Networks (ACNN): Application to cardiac image enhancement and segmentation   

O. Oktay, E. Ferrante, K. Kamnitsas, M. Heinrich, W. Bai, J. Caballero, R. Guerrero, S. Cook, A. Marvao, T. Dawes, D. O Regan, B. Kainz, B. Glocker, D. Rueckert

IEEE Transactions on Medical Imaging – 2017

Deformable registration through learning of context-specific metric aggregation   

E. Ferrante, P. Dokania, R. Marini, N. Paragios

8th International Workshop on Machine Learning in Medical Imaging – 2017