Limits...
Robust peak recognition in intracranial pressure signals.

Scalzo F, Asgari S, Kim S, Bergsneider M, Hu X - Biomed Eng Online (2010)

Bottom Line: While current ICP pulse analysis frameworks offer satisfying results on most of the pulses, we observed that the performance of several of them deteriorates significantly on abnormal, or simply more challenging pulses.Second, it investigates the effect of incorporating, automatically identified, challenging pulses into the training set of peak recognition models.Experiments on a large dataset of ICP signals, as well as on a representative collection of sampled challenging ICP pulses, demonstrate that both contributions are complementary and significantly improve peak recognition performance in clinical conditions.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Neurosurgery, Geffen School of Medicine, Neural Systems and Dynamic Lab, University of California, Los Angeles, CA, USA. fscalzo@mednet.ucla.edu

ABSTRACT

Background: The waveform morphology of intracranial pressure pulses (ICP) is an essential indicator for monitoring, and forecasting critical intracranial and cerebrovascular pathophysiological variations. While current ICP pulse analysis frameworks offer satisfying results on most of the pulses, we observed that the performance of several of them deteriorates significantly on abnormal, or simply more challenging pulses.

Methods: This paper provides two contributions to this problem. First, it introduces MOCAIP++, a generic ICP pulse processing framework that generalizes MOCAIP (Morphological Clustering and Analysis of ICP Pulse). Its strength is to integrate several peak recognition methods to describe ICP morphology, and to exploit different ICP features to improve peak recognition. Second, it investigates the effect of incorporating, automatically identified, challenging pulses into the training set of peak recognition models.

Results: Experiments on a large dataset of ICP signals, as well as on a representative collection of sampled challenging ICP pulses, demonstrate that both contributions are complementary and significantly improve peak recognition performance in clinical conditions.

Conclusion: The proposed framework allows to extract more reliable statistics about the ICP waveform morphology on challenging pulses to investigate the predictive power of these pulses on the condition of the patient.

Show MeSH
Effect of the number of training samples on the average recognition accuracy (Eq. 21) for different models (KSR, SR, GMM, MOCAIP [15]) using a five-fold crossvalidation on our challenging dataset D'. Results correspond to the average for the three peaks (p1, p2, and p3).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2984490&req=5

Figure 5: Effect of the number of training samples on the average recognition accuracy (Eq. 21) for different models (KSR, SR, GMM, MOCAIP [15]) using a five-fold crossvalidation on our challenging dataset D'. Results correspond to the average for the three peaks (p1, p2, and p3).

Mentions: The accuracy of a peak p is obtained by averaging the accuracy over the five-folds. Similarly, the overall accuracy is obtained by averaging the accuracy of the three peaks, . The learning of the recognition models is supervised in the sense that it relies on a set of manually labelled ICP pulses. As the number of training examples increases, the overall accuracy is generally expected to improve as well. We report this aspect by plotting the average prediction accuracy for each method against the number of training samples in Figure 5. To test one of the 5 folds, a model is trained by randomly extracting n pulses from the remaining 4 folds.


Robust peak recognition in intracranial pressure signals.

Scalzo F, Asgari S, Kim S, Bergsneider M, Hu X - Biomed Eng Online (2010)

Effect of the number of training samples on the average recognition accuracy (Eq. 21) for different models (KSR, SR, GMM, MOCAIP [15]) using a five-fold crossvalidation on our challenging dataset D'. Results correspond to the average for the three peaks (p1, p2, and p3).
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2984490&req=5

Figure 5: Effect of the number of training samples on the average recognition accuracy (Eq. 21) for different models (KSR, SR, GMM, MOCAIP [15]) using a five-fold crossvalidation on our challenging dataset D'. Results correspond to the average for the three peaks (p1, p2, and p3).
Mentions: The accuracy of a peak p is obtained by averaging the accuracy over the five-folds. Similarly, the overall accuracy is obtained by averaging the accuracy of the three peaks, . The learning of the recognition models is supervised in the sense that it relies on a set of manually labelled ICP pulses. As the number of training examples increases, the overall accuracy is generally expected to improve as well. We report this aspect by plotting the average prediction accuracy for each method against the number of training samples in Figure 5. To test one of the 5 folds, a model is trained by randomly extracting n pulses from the remaining 4 folds.

Bottom Line: While current ICP pulse analysis frameworks offer satisfying results on most of the pulses, we observed that the performance of several of them deteriorates significantly on abnormal, or simply more challenging pulses.Second, it investigates the effect of incorporating, automatically identified, challenging pulses into the training set of peak recognition models.Experiments on a large dataset of ICP signals, as well as on a representative collection of sampled challenging ICP pulses, demonstrate that both contributions are complementary and significantly improve peak recognition performance in clinical conditions.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Neurosurgery, Geffen School of Medicine, Neural Systems and Dynamic Lab, University of California, Los Angeles, CA, USA. fscalzo@mednet.ucla.edu

ABSTRACT

Background: The waveform morphology of intracranial pressure pulses (ICP) is an essential indicator for monitoring, and forecasting critical intracranial and cerebrovascular pathophysiological variations. While current ICP pulse analysis frameworks offer satisfying results on most of the pulses, we observed that the performance of several of them deteriorates significantly on abnormal, or simply more challenging pulses.

Methods: This paper provides two contributions to this problem. First, it introduces MOCAIP++, a generic ICP pulse processing framework that generalizes MOCAIP (Morphological Clustering and Analysis of ICP Pulse). Its strength is to integrate several peak recognition methods to describe ICP morphology, and to exploit different ICP features to improve peak recognition. Second, it investigates the effect of incorporating, automatically identified, challenging pulses into the training set of peak recognition models.

Results: Experiments on a large dataset of ICP signals, as well as on a representative collection of sampled challenging ICP pulses, demonstrate that both contributions are complementary and significantly improve peak recognition performance in clinical conditions.

Conclusion: The proposed framework allows to extract more reliable statistics about the ICP waveform morphology on challenging pulses to investigate the predictive power of these pulses on the condition of the patient.

Show MeSH