Skip to Main content Skip to Navigation
Conference papers

Confidence-based Training for Clinical Data Uncertainty in Image-based Prediction of Cardiac Ablation Targets

Abstract : Ventricular radio-frequency ablation (RFA) can have a critical impact on preventing sudden cardiac arrest but is challenging due to a highly complex arrhythmogenic substrate. This work aims to identify local image characteristics capable of predicting the presence of local abnormal ventricular activities (LAVA). This can allow, pre-operatively and non-invasively, to improve and accelerate the procedure. To achieve this, intensity and texture-based local image features are computed and random forests are used for classification. However using machine-learning approaches on such complex multimodal data can prove difficult due to the inherent errors in the training set. In this manuscript we present a detailed analysis of these error sources due in particular to catheter motion and the data fusion process. We derived a principled analysis of confidence impact on classification. Moreover, we demonstrate how formal integration of these uncertainties in the training process improves the algorithm's performance, opening up possibilities for non-invasive image-based prediction of RFA targets.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-01069085
Contributor : Rocio Cabrera Lozoya <>
Submitted on : Friday, September 26, 2014 - 7:46:27 PM
Last modification on : Thursday, January 16, 2020 - 4:44:02 PM
Document(s) archivé(s) le : Saturday, December 27, 2014 - 12:01:30 PM

File

RCL_miccai2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01069085, version 1

Collections

Citation

Rocio Cabrera Lozoya, Jan Margeta, Loic Le Folgoc, Yuki Komatsu, Berte Benjamin, et al.. Confidence-based Training for Clinical Data Uncertainty in Image-based Prediction of Cardiac Ablation Targets. bigMCV Workshop MICCAI 2014, Sep 2014, Boston, United States. ⟨hal-01069085⟩

Share

Metrics

Record views

659

Files downloads

563