Beyond the pixel-wise loss for topology-aware delineation

A Mosinska, P Marquez-Neila… - Proceedings of the …, 2018 - openaccess.thecvf.com
Delineation of curvilinear structures is an important problem in Computer Vision with
multiple practical applications. With the advent of Deep Learning, many current approaches …

TeraVR empowers precise reconstruction of complete 3-D neuronal morphology in the whole brain

Y Wang, Q Li, L Liu, Z Zhou, Z Ruan, L Kong… - Nature …, 2019 - nature.com
Neuron morphology is recognized as a key determinant of cell type, yet the quantitative
profiling of a mammalian neuron's complete three-dimensional (3-D) morphology remains …

Active, continual fine tuning of convolutional neural networks for reducing annotation efforts

Z Zhou, JY Shin, SR Gurudu, MB Gotway, J Liang - Medical image analysis, 2021 - Elsevier
The splendid success of convolutional neural networks (CNNs) in computer vision is largely
attributable to the availability of massive annotated datasets, such as ImageNet and Places …

Metabox+: A new region based active learning method for semantic segmentation using priority maps

P Colling, L Roese-Koerner, H Gottschalk… - arXiv preprint arXiv …, 2020 - arxiv.org
We present a novel region based active learning method for semantic image segmentation,
called MetaBox+. For acquisition, we train a meta regression model to estimate the segment …

Joint segmentation and path classification of curvilinear structures

A Mosinska, M Koziński, P Fua - IEEE transactions on pattern …, 2019 - ieeexplore.ieee.org
Detection of curvilinear structures in images has long been of interest. One of the most
challenging aspects of this problem is inferring the graph representation of the curvilinear …

Inference of cerebrovascular topology with geodesic minimum spanning trees

S Moriconi, MA Zuluaga, HR Jäger… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
A vectorial representation of the vascular network that embodies quantitative features—
location, direction, scale, and bifurcations—has many potential cardio-and neuro-vascular …

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

M Koziński, A Mosinska, M Salzmann, P Fua - Medical image analysis, 2020 - Elsevier
The difficulty of obtaining annotations to build training databases still slows down the
adoption of recent deep learning approaches for biomedical image analysis. In this paper …

Tracing cell lineages in videos of lens-free microscopy

M Rempfler, V Stierle, K Ditzel, S Kumar… - Medical image …, 2018 - Elsevier
In vitro experiments with cultured cells are essential for studying their growth and migration
pattern and thus, for gaining a better understanding of cancer progression and its treatment …

Cnn driven sparse multi-level b-spline image registration

P Jiang, JA Shackleford - Proceedings of the IEEE …, 2018 - openaccess.thecvf.com
Traditional single-grid and pyramidal B-spline parameterizations used in deformable image
registration require users to specify control point spacing configurations capable of …

Systems, methods, and/or media, for selecting candidates for annotation for use in training a classifier

J Liang, Z Zhou, J Shin - US Patent 12,118,455, 2024 - Google Patents
Abstract Systems for selecting candidates for labelling and use in training a convolutional
neural network (CNN) are provided, the systems comprising: a memory device; and at least …