Automated detection and segmentation of focal cortical dysplasias (FCDs) with artificial intelligence: Presentation of a novel convolutional neural network and its prospective clinical validation.

作者: Thomas Sauvigny , Patrick M. House , Brigitte Holst , Stefan Stodieck , Sirko Pelzl

DOI: 10.1016/J.EPLEPSYRES.2021.106594

关键词:

摘要: Abstract Purpose Focal cortical dysplasias (FCDs) represent one of the most frequent causes pharmaco-resistant focal epilepsies. Despite improved clinical imaging methods over past years, FCD detection remains challenging, as FCDs vary in location, size, and shape commonly blend into surrounding tissues without clear definable boundaries. We developed a novel convolutional neural network for segmentation validated it prospectively on daily-routine MRIs. Material The was trained 201 T1 FLAIR 3 T MRI volume sequences 158 patients with mainly FCDs, regardless type, 7 PMG. Non-FCD/PMG MRIs, drawn from 100 normal MRIs 50 non-FCD/PMG pathologies, were added to training. applied algorithm consecutive epilepsy daily practice. results compared corresponding neuroradiological reports morphometric analyses evaluated by an experienced epileptologist. Results Best training reached sensitivity (recall) 70.1 % precision 54.3 detecting FCDs. Applied out 9 detected segmented correctly 77.8 specificity 5.5 %. conventional visual 33.3 94.5 %, respectively (3/9 detected); overall epileptologic evaluation both (9/9 detected) thus served reference. Conclusion 3D autoencoder regularization segmentation. Our employs largest dataset date various types some It provided higher than analyses. its low specificity, number false positively predicted lesions per lower analysis. consider our already useful pre-screening everyday

参考文章(46)
Philipp Fischer, Thomas Brox, None, U-Net: Convolutional Networks for Biomedical Image Segmentation medical image computing and computer assisted intervention. pp. 234- 241 ,(2015) , 10.1007/978-3-319-24574-4_28
Patrick M. House, Brigitte Holst, Matthias Lindenau, Berthold Voges, Bernhard Kohl, Tobias Martens, Michael Lanz, Stefan Stodieck, Hans-Jürgen Huppertz, Morphometric MRI analysis enhances visualization of cortical tubers in tuberous sclerosis. Epilepsy Research. ,vol. 117, pp. 29- 34 ,(2015) , 10.1016/J.EPLEPSYRES.2015.08.002
Patrick M. House, Michael Lanz, Brigitte Holst, Tobias Martens, Stefan Stodieck, Hans-Jürgen Huppertz, Comparison of morphometric analysis based on T1- and T2-weighted MRI data for visualization of focal cortical dysplasia. Epilepsy Research. ,vol. 106, pp. 403- 409 ,(2013) , 10.1016/J.EPLEPSYRES.2013.06.016
Hans-Jürgen Huppertz, Jörg Wellmer, Anke Maren Staack, Dirk-Matthias Altenmüller, Horst Urbach, Judith Kröll, Voxel-based 3D MRI analysis helps to detect subtle forms of subcortical band heterotopia. Epilepsia. ,vol. 49, pp. 772- 785 ,(2008) , 10.1111/J.1528-1167.2007.01436.X
Charles Mellerio, Marc-Antoine Labeyrie, Francine Chassoux, Pauline Roca, Odile Alami, Monique Plat, Olivier Naggara, Bertrand Devaux, Jean-François Meder, Catherine Oppenheim, 3T MRI improves the detection of transmantle sign in type 2 focal cortical dysplasia. Epilepsia. ,vol. 55, pp. 117- 122 ,(2014) , 10.1111/EPI.12464
Imad M Najm, Richard A Prayson, Z Irene Wang, Andreas V Alexopoulos, Stephen E Jones, Zeenat Jaisani, The pathology of magnetic-resonance-imaging-negative epilepsy. Modern Pathology. ,vol. 26, pp. 1051- 1058 ,(2013) , 10.1038/MODPATHOL.2013.52
Hans-Jürgen Huppertz, Christina Grimm, Susanne Fauser, Jan Kassubek, Irina Mader, Albrecht Hochmuth, Joachim Spreer, Andreas Schulze-Bonhage, Enhanced visualization of blurred gray–white matter junctions in focal cortical dysplasia by voxel-based 3D MRI analysis Epilepsy Research. ,vol. 67, pp. 35- 50 ,(2005) , 10.1016/J.EPLEPSYRES.2005.07.009
A. James Barkovich, Ruben I. Kuzniecky, Neuroimaging of focal malformations of cortical development. Journal of Clinical Neurophysiology. ,vol. 13, pp. 481- 494 ,(1996) , 10.1097/00004691-199611000-00003
J. Wagner, B. Weber, H. Urbach, C. E. Elger, H.-J. Huppertz, Morphometric MRI analysis improves detection of focal cortical dysplasia type II. Brain. ,vol. 134, pp. 2844- 2854 ,(2011) , 10.1093/BRAIN/AWR204
Jason T. Lerner, Noriko Salamon, Jason S. Hauptman, Tonicarlo R. Velasco, Marta Hemb, Joyce Y. Wu, Raman Sankar, W. Donald Shields, Jerome Engel Jr, Itzhak Fried, Carlos Cepeda, Veronique M. Andre, Michael S. Levine, Hajime Miyata, William H. Yong, Harry V. Vinters, Gary W. Mathern, Assessment and surgical outcomes for mild type I and severe type II cortical dysplasia: A critical review and the UCLA experience Epilepsia. ,vol. 50, pp. 1310- 1335 ,(2009) , 10.1111/J.1528-1167.2008.01998.X