Automatic assessment of corpus callosum malformation from structural MRI images to improve diagnosis reproducibility.
Denis Peruzzo1, Umberto Castellani2, Fabio Triulzi1,3, Andrea Righini4, Cecilia Parazzini4, and Filippo Arrigoni1

1Neuroimaging Unit, Scientific Institute IRCCS “Eugenio Medea”, Bosisio Parini, Italy, 2Department of Computer Science, University of Verona, Verona, Italy, 3Department of Neuroradiolody, Fondazione IRCCS “Ca’ Granda” Ospedale Maggiore Policlinico, Milano, Italy, 4Department of Pediatric Radiology and Neuroradiology, Children Hospital “Vittorio Buzzi”, Milano, Italy

Synopsis

The diagnosis of brain malformations is usually based on the visual inspection of MRI images by trained neuroradiologists. The resulting procedure is therefore subjective and mainly provides a qualitative description of the detected malformations. In this study, we propose an assisted diagnosis tool (ADT) for the analysis of the corpus callosum from structural T1-weighted images. The method detects and characterizes different kind of malformations (local/diffuse, homogeneous/heterogeneous). Inter-subject reproducibility experiments showed that the agreement rate significantly improved from 67.5% to 79.3% using the proposed method.

PURPOSE

Brain malformation assessment is usually performed by visual inspection of MRI images by experienced neuroradiologists. Such approach is therefore subjective and provides only a qualitative description of the detected malformations. The purpose of this study is to exploit machine learning methods to automatically detect and quantitatively characterize corpus callosum (CC) malformations, improving the inter-subject diagnostic reproducibility.

METHODS

Dataset: 128 subjects (Age mean and SD: 7.3 ± 1.9 yo; males/females: 85/43), including healthy, mentally retarded and syndromic subjects, were recruited. The MRI protocol included a T1-weighted sequence at a resolution of 1x1x1 mm3 in a 3T Philips Achieva scanner with a 32-channel head coil.

Image analysis: image preprocessing and segmentation were performed using FSL tools1. The CC was extracted as in Herron et al2 and geometric features were computed using home-made scripts. The feature set included the area, the perimeter length, the skeleton length and curvature, the splenium-rostrum distance, and the thickness profile. A one-class multiple-kernel Support Vector Machine (SVM) classifier was used to assess the CC diagnosis. The classifier assigned a label to each object (i.e. “normal-shaped”/”malformed” CC), but did not provide any information about what led to the classification. This problem was overcome by providing a new regularized Discriminative Direction (DD) analysis3, which was applied to multiple-kernel SMV classifiers4. The DD analysis computed the minimum transformations required to change a “malformed” CC into a “normal-shaped” one. Consequently, the DD analysis provided a quantitative assessment of the malformation pattern and severity.

Inter-subject reproducibility experiment: four neuroradiologists, with more than 10 years of experience in pediatric neuroimaging, were asked to classify on a visual base each CC as “normal-shaped” or “malformed”, being blind about the patient clinical picture (“blind-diagnoses”). The “normal-shaped” CCs from the consensus among three neuroradiologists were used to train the SVM classifier. One year later, all physicians were asked to repeat the classification of the same dataset using the classifier output as Assisted Diagnosis Tool (ADT) (“ADT-diagnoses”). Agreement rates were computed for each couple of physicians to assess the inter-subject reproducibility.

RESULTS

Figure 1 reports an example of the ADT output. A large panel shows the middle sagittal slice of the T1 image where the CC is located, while several smaller panels in the lower part of the image report the classifier diagnosis and DD analysis. The latter is reported both with a graphical representation of some features (e.g. thickness profile or skeleton curvature) and with a numeric assessment of the malformation degree for the others (e.g. area, perimeter length, etc). A color and intensity code was used to visualize the versus and the magnitude of the malformation, respectively. Red color is used to indicate the features that are too small with respect to a normal-shaped CC. Conversely, blue color indicates the features that are too large. The method detects both local and diffuse malformations, as well as heterogeneous malformations in the same subject.

Table 1 shows the inter-subject agreement rates among neuroradiologists and with the classifier in the “blind-diagnoses” experiment. The average agreement rate among neuroradiologists is 67.6%, with a SD of 6.4%, while the classifier shows a higher agreement rate (average=73.6%, SD=7.4%). In particular, the classifier shows the highest agreement rate with the neuroradiologist not involved in the training-set selection (NR#4).

Table 2 reports the agreement rates from the ADT-diagnoses experiment. They significantly improved in comparison with the “blind-diagnoses” ones (p=0.002). More precisely, all of them increased, with the only exception of the NR#1-#4 combination, that did not change. The average agreement rate among neuroradiologists in the ADT-diagnoses is 79.3% with a SD of 4.2% and it is due to a larger agreement with the classifier suggested diagnosis (average=83.4%, SD=3.4%).

CONCLUSIONS

In this study, we proposed a tool that not only automatically detects the malformations of the corpus callosum from MRI images, but also provides their quantitative characterization at single-subject level. This method can be used to support physicians in the evaluation of the shape of the corpus callosum, significantly improving the inter-subject reliability. Moreover, it can be used for quantitative research studies. DD analysis results can be used in studies with a small amount of patients, where the group tests do not have sufficient statistical power. Moreover, it can be used to correlate the malformation degree to the clinical outcome, to monitor the development of the malformative pattern in pediatric patients, to detect pathology subtypes. Finally, the method has been proposed and validated on the corpus callosum, but can be extended to other brain districts.

Acknowledgements

No acknowledgement found.

References

[1] Jenkinson, M., Beckmann, C.F., Behrens, T.E.J., Woolrich, M.W., Smith, S.M. 2012. Fsl. NeuroImage 62, 782–790.

[2] Herron, T.J., Kang, X., Woods, D.L. 2012. Automated measurement of the human corpus callosum using mri. Frontiers in Neuroinformatics 6, 1–15.

[3] Zhou, L., Hartley, R., Wang, L., Lieby, P., Barnes, N. 2009. Identifying anatomical shape difference by regularized discriminative direction. IEEE transaction on medical imaging 28, 937–950.

[4] Peruzzo, D., Arrigoni, F., Triulzi, F., Parazzini, C., Castellani, U. 2014. Detection of corpus callosum malformations in pediatric population using the discriminative direction in multiple kernel learning. Medical Image Computing & Computer Assisted Intervention 17(2), 300-307.

Figures

Figure 1: Output of the ADT. The large middle panel shows the original sagittal slice while the lower panels report the classifier and DD analysis. Results for each feature are reported independently, using a color and intensity code to visualize the versus and the magnitude of the malformation, respectively.

Table 1: Inter-subject and classifier agreement rates obtained in the “blind-diagnoses” experiment. (NR: NeuroRadiologist)

Table 2: Inter-subject and classifier agreement rates obtained in the “ADT-diagnoses” experiment. (NR: NeuroRadiologist)



Proc. Intl. Soc. Mag. Reson. Med. 24 (2016)
3313