Randomized Tree Ensembles for Object Detection in Computational Pathology

Authors:
Thomas J. Fuchs;Johannes Haybaeck;Peter J. Wild;Mathias Heikenwalder;Holger Moch;Adriano Aguzzi;Joachim M. Buhmann
Affiliations:
Department of Computer Science, ETH Zürich, Zürich, Switzerland and Competence Center for Systems Physiology and Metabolic Diseases, ETH Zürich,;Department of Pathology, Institute for Neuropathology, University Hospital, Zürich;Department of Pathology, Institute of Surgical Pathology, University Hospital Zürich,;Department of Pathology, Institute for Neuropathology, University Hospital, Zürich;Department of Pathology, Institute of Surgical Pathology, University Hospital Zürich, and Competence Center for Systems Physiology and Metabolic Diseases, ETH Zürich,;Department of Pathology, Institute for Neuropathology, University Hospital, Zürich;Department of Computer Science, ETH Zürich, Zürich, Switzerland and Competence Center for Systems Physiology and Metabolic Diseases, ETH Zürich,
Venue:
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Year:
2009

Citing 9
Cited 0

Random Forests

Machine Learning
Morphological Image Analysis: Principles and Applications

Morphological Image Analysis: Principles and Applications
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Extremely randomized trees

Machine Learning
Weakly Supervised Cell Nuclei Detection and Segmentation on Tissue Microarrays of Renal Clear Cell Carcinoma

Proceedings of the 30th DAGM symposium on Pattern Recognition
Semi-supervised On-Line Boosting for Robust Tracking

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
A clinically motivated 2-fold framework for quantifying and classifying immunohistochemically stained specimens

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
High throughput analysis of breast cancer specimens on the grid

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Unsupervised segmentation based on robust estimation and color active contour models

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Modern pathology broadly searches for biomarkers which are predictive for the survival of patients or the progression of cancer. Due to the lack of robust analysis algorithms this work is still performed manually by estimating staining on whole slides or tissue microarrays (TMA). Therefore, the design of decision support systems which can automate cancer diagnosis as well as objectify it pose a highly challenging problem for the medical imaging community. In this paper we propose Relational Detection Forests (RDF) as a novel object detection algorithm, which can be applied in an off-the-shelf manner to a large variety of tasks. The contributions of this work are twofold: (i) we describe a feature set which is able to capture shape information as well as local context. Furthermore, the feature set is guaranteed to be generally applicable due to its high flexibility. (ii) we present an ensemble learning algorithm based on randomized trees, which can cope with exceptionally high dimensional feature spaces in an efficient manner. Contrary to classical approaches, subspaces are not split based on thresholds but by learning relations between features. The algorithm is validated on tissue from 133 human clear cell renal cell carcinoma patients (ccRCC) and on murine liver samples of eight mice. On both species RDFs compared favorably to state of the art methods and approaches the detection accuracy of trained pathologists.