A framework for the automatic detection and characterization of brain malformations

Validation on the corpus callosum

Denis Peruzzo, Filippo Arrigoni, Fabio Triulzi, Andrea Righini, Cecilia Parazzini, Umberto Castellani

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we extend the one-class Support Vector Machine (SVM) and the regularized discriminative direction analysis to the Multiple Kernel (MK) framework, providing an effective analysis pipeline for the detection and characterization of brain malformations, in particular those affecting the corpus callosum.The detection of the brain malformations is currently performed by visual inspection of MRI images, making the diagnostic process sensible to the operator experience and subjectiveness. The method we propose addresses these problems by automatically reproducing the neuroradiologist's approach. One-class SVMs are appropriate to cope with heterogeneous brain abnormalities that are considered outliers. The MK framework allows to efficiently combine the different geometric features that can be used to describe brain structures. Moreover, the regularized discriminative direction analysis is exploited to highlight the specific malformative patterns for each patient.We performed two different experiments. Firstly, we tested the proposed method to detect the malformations of the corpus callosum on a 104 subject dataset. Results showed that the proposed pipeline can classify the subjects with an accuracy larger than 90% and that the discriminative direction analysis can highlight a wide range of malformative patterns (e.g., local, diffuse, and complex abnormalities). Secondly, we compared the diagnosis of four neuroradiologists on a dataset of 128 subjects. The diagnosis was performed both in blind condition and using the classifier and the discriminative direction outputs. Results showed that the use of the proposed pipeline as an assisted diagnosis tool improves the inter-subject variability of the diagnosis.Finally, a graphical representation of the discriminative direction analysis was proposed to enhance the interpretability of the results and provide the neuroradiologist with a tool to fully and clearly characterize the patient malformations at single-subject level.

Original languageEnglish
Pages (from-to)233-242
Number of pages10
JournalMedical Image Analysis
Volume32
DOIs
Publication statusPublished - Aug 1 2016

Fingerprint

Corpus Callosum
Brain
Pipelines
Agenesis of Corpus Callosum
Magnetic resonance imaging
Support vector machines
Classifiers
Inspection
Direction compound
Experiments
Datasets

Keywords

  • Computer aided diagnosis
  • Discriminative direction
  • Malformation detection
  • Support vector machines

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology

Cite this

A framework for the automatic detection and characterization of brain malformations : Validation on the corpus callosum. / Peruzzo, Denis; Arrigoni, Filippo; Triulzi, Fabio; Righini, Andrea; Parazzini, Cecilia; Castellani, Umberto.

In: Medical Image Analysis, Vol. 32, 01.08.2016, p. 233-242.

Research output: Contribution to journalArticle

@article{15c3142c7aa648b591dbe7033deb2b01,
title = "A framework for the automatic detection and characterization of brain malformations: Validation on the corpus callosum",
abstract = "In this paper, we extend the one-class Support Vector Machine (SVM) and the regularized discriminative direction analysis to the Multiple Kernel (MK) framework, providing an effective analysis pipeline for the detection and characterization of brain malformations, in particular those affecting the corpus callosum.The detection of the brain malformations is currently performed by visual inspection of MRI images, making the diagnostic process sensible to the operator experience and subjectiveness. The method we propose addresses these problems by automatically reproducing the neuroradiologist's approach. One-class SVMs are appropriate to cope with heterogeneous brain abnormalities that are considered outliers. The MK framework allows to efficiently combine the different geometric features that can be used to describe brain structures. Moreover, the regularized discriminative direction analysis is exploited to highlight the specific malformative patterns for each patient.We performed two different experiments. Firstly, we tested the proposed method to detect the malformations of the corpus callosum on a 104 subject dataset. Results showed that the proposed pipeline can classify the subjects with an accuracy larger than 90{\%} and that the discriminative direction analysis can highlight a wide range of malformative patterns (e.g., local, diffuse, and complex abnormalities). Secondly, we compared the diagnosis of four neuroradiologists on a dataset of 128 subjects. The diagnosis was performed both in blind condition and using the classifier and the discriminative direction outputs. Results showed that the use of the proposed pipeline as an assisted diagnosis tool improves the inter-subject variability of the diagnosis.Finally, a graphical representation of the discriminative direction analysis was proposed to enhance the interpretability of the results and provide the neuroradiologist with a tool to fully and clearly characterize the patient malformations at single-subject level.",
keywords = "Computer aided diagnosis, Discriminative direction, Malformation detection, Support vector machines",
author = "Denis Peruzzo and Filippo Arrigoni and Fabio Triulzi and Andrea Righini and Cecilia Parazzini and Umberto Castellani",
year = "2016",
month = "8",
day = "1",
doi = "10.1016/j.media.2016.05.001",
language = "English",
volume = "32",
pages = "233--242",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",

}

TY - JOUR

T1 - A framework for the automatic detection and characterization of brain malformations

T2 - Validation on the corpus callosum

AU - Peruzzo, Denis

AU - Arrigoni, Filippo

AU - Triulzi, Fabio

AU - Righini, Andrea

AU - Parazzini, Cecilia

AU - Castellani, Umberto

PY - 2016/8/1

Y1 - 2016/8/1

N2 - In this paper, we extend the one-class Support Vector Machine (SVM) and the regularized discriminative direction analysis to the Multiple Kernel (MK) framework, providing an effective analysis pipeline for the detection and characterization of brain malformations, in particular those affecting the corpus callosum.The detection of the brain malformations is currently performed by visual inspection of MRI images, making the diagnostic process sensible to the operator experience and subjectiveness. The method we propose addresses these problems by automatically reproducing the neuroradiologist's approach. One-class SVMs are appropriate to cope with heterogeneous brain abnormalities that are considered outliers. The MK framework allows to efficiently combine the different geometric features that can be used to describe brain structures. Moreover, the regularized discriminative direction analysis is exploited to highlight the specific malformative patterns for each patient.We performed two different experiments. Firstly, we tested the proposed method to detect the malformations of the corpus callosum on a 104 subject dataset. Results showed that the proposed pipeline can classify the subjects with an accuracy larger than 90% and that the discriminative direction analysis can highlight a wide range of malformative patterns (e.g., local, diffuse, and complex abnormalities). Secondly, we compared the diagnosis of four neuroradiologists on a dataset of 128 subjects. The diagnosis was performed both in blind condition and using the classifier and the discriminative direction outputs. Results showed that the use of the proposed pipeline as an assisted diagnosis tool improves the inter-subject variability of the diagnosis.Finally, a graphical representation of the discriminative direction analysis was proposed to enhance the interpretability of the results and provide the neuroradiologist with a tool to fully and clearly characterize the patient malformations at single-subject level.

AB - In this paper, we extend the one-class Support Vector Machine (SVM) and the regularized discriminative direction analysis to the Multiple Kernel (MK) framework, providing an effective analysis pipeline for the detection and characterization of brain malformations, in particular those affecting the corpus callosum.The detection of the brain malformations is currently performed by visual inspection of MRI images, making the diagnostic process sensible to the operator experience and subjectiveness. The method we propose addresses these problems by automatically reproducing the neuroradiologist's approach. One-class SVMs are appropriate to cope with heterogeneous brain abnormalities that are considered outliers. The MK framework allows to efficiently combine the different geometric features that can be used to describe brain structures. Moreover, the regularized discriminative direction analysis is exploited to highlight the specific malformative patterns for each patient.We performed two different experiments. Firstly, we tested the proposed method to detect the malformations of the corpus callosum on a 104 subject dataset. Results showed that the proposed pipeline can classify the subjects with an accuracy larger than 90% and that the discriminative direction analysis can highlight a wide range of malformative patterns (e.g., local, diffuse, and complex abnormalities). Secondly, we compared the diagnosis of four neuroradiologists on a dataset of 128 subjects. The diagnosis was performed both in blind condition and using the classifier and the discriminative direction outputs. Results showed that the use of the proposed pipeline as an assisted diagnosis tool improves the inter-subject variability of the diagnosis.Finally, a graphical representation of the discriminative direction analysis was proposed to enhance the interpretability of the results and provide the neuroradiologist with a tool to fully and clearly characterize the patient malformations at single-subject level.

KW - Computer aided diagnosis

KW - Discriminative direction

KW - Malformation detection

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84966389310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966389310&partnerID=8YFLogxK

U2 - 10.1016/j.media.2016.05.001

DO - 10.1016/j.media.2016.05.001

M3 - Article

VL - 32

SP - 233

EP - 242

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

ER -