UZH-Logo

Randomized tree ensembles for object detection in computational pathology


Fuchs, T J; Haybaeck, J; Wild, P J; Heikenwalder, M; Moch, H; Aguzzi, A; Buhmann, J M (2009). Randomized tree ensembles for object detection in computational pathology. In: Bebis, G; et al. Advances in Visual Computing : 5th International Symposium, ISVC 2009, Las Vegas, NV, USA, November 30 - December 2, 2009, Proceedings, Part 1. Berlin: Springer, 367-380.

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.

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.

Altmetrics

Downloads

70 downloads since deposited on 28 Jan 2010
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Institute of Neuropathology
04 Faculty of Medicine > University Hospital Zurich > Institute of Surgical Pathology
Dewey Decimal Classification:570 Life sciences; biology
610 Medicine & health
Language:English
Date:2009
Deposited On:28 Jan 2010 13:00
Last Modified:05 Apr 2016 13:44
Publisher:Springer
Series Name:Lecture Notes in Computer Science
Number:5875
ISSN:0302-9743 (P) 1611-3349 (E)
ISBN:978-3-642-10330-8 (P)
Additional Information:The original publication is available at www.springerlink.com
Publisher DOI:10.1007/978-3-642-10331-5_35
Permanent URL: http://doi.org/10.5167/uzh-27166

Download

[img]
Preview
Content: Accepted Version
Filetype: PDF
Size: 12MB
View at publisher

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations