Fast and smart segmentation of paraspinal muscles in magnetic resonance imaging with CleverSeg

• Jonathan da Silva Ramos University of São Paulo
• Mirela Cazzolato University of São Paulo
• Bruno Faiçal University of São Paulo
• Oscar Cuadros University of São Paulo
• Marcello Nogueira-Barbosa Universidade de São Paulo
• Caetano Traina Jr. USP
• Agma J. Traina University of São Paulo

DOI: https://doi.org/10.5753/sibgrapi.2019.9775

Resumo

Magnetic Resonance Imaging (MRI) is a non-invasive technique, which has been employed to detect and diagnose many spine pathologies. In a Computer-Aided Diagnosis (CAD) context, the segmentation of the paraspinal musculature from MRI may support measurement, quantification, and analysis of muscle-related pathologies. Current semi-automatic segmentation techniques require too much time from the physicians to annotate all slices in the exams. In this work, we focus on minimizing the time spent on manual annotation as well as on the overall segmentation processing time. We use the mean absolute error between slices in order to minimize the number of annotated slices in each exam. Moreover, we optimize the manual annotation time by estimating the inside annotation based on the outside annotation, while the competitors demand the annotation of inside and outside annotation (seeds). The experimental evaluation shows that our proposed approach is able to speed up the manual annotation process in up to 50% by annotating only a few representative slices, without loss of accuracy. By annotating only the outside region, the process can be further speed up by another 50%, reducing the total time to only 25% of the previously required. Despite that, our proposed CleverSeg method presented accuracy similar or better than the competitors, while managing a faster processing time.

Palavras-chave: Segmentation, Muscle, MRI, CleverSeg

Referências

M. G. Fehlings, L. Tetreault, A. Nater, T. Choma, J. Harrop, T. Mroz, C. Santaguida, J. S. Smith, "The aging of the global populationthe changing epidemiology of disease and spinal disorders", Neurosurgery, vol. no. 1, pp. 1-5, 2015.

M. Rak, K. D. Tönnies, "On computerized methods for spine analysis in MRI: a systematic review", Int. J. Computed Assisted Radiology and Surgery, vol. no. 8, pp. 1445-14Aug 2016.

Y. X. J. Wang, F. R. Santiago, M. Deng, M. H. Nogueira-Barbosa, "Identifying osteoporotic vertebral endplate and cortex fractures", Quant Imaging Medical Surgery (QIMS), vol. 7, no. 5, pp. 555-591, Oct 2017.

E. Klupp, B. Cervantes, S. Schlaeger, S. Inhuber, F. Kreuzpointer, A. Schwirtz, A. Rohrmeier, M. Dieckmeyer, D. M. Hedderich, M. N. Diefenbach, F. Freitag, E. J. Rummeny, C. Zimmer, J. S. Kirschke, D. C. Karampinos, T. Baum, "Paraspinal muscle DTI metrics predict muscle strength", J. of Magnetic Res. Imaging (JMRI), pp. 1-8, 2019.

G. Hille, S. Saalfeld, S. Serowy, K. Tnnies, "Vertebral body segmentation in wide range clinical routine spine MRI data", Computer Methods and Programs in Biomedicine, vol. 1pp. 93-99, 2018.

C. M. Engstrom, J. Fripp, V. Jurcak, D. G. Walker, O. Salvado, S. Crozier, "Segmentation of the quadratus lumborum muscle using statistical shape modeling", J. of Magnetic Resonance Imaging (JMRI), vol. no. 6, pp. 1422-142011.

Z. Dženan, V. Aleš, E. Jan, H. Daniel, N. Christopher, K. Andreas, "Robust detection and segmentation for diagnosis of vertebral diseases using routine MR images", Computer Graphics Forum, vol. no. 6, pp. 190-204, 2014.

R. J. Gillies, P. E. Kinahan, H. Hricak, "Radiomics: images are more than pictures they are data", Radiology, vol. 2no. 2, pp. 563-5Feb 2016.

G. Jader, J. Fontineli, M. Ruiz, K. Abdalla, M. Pithon, L. Oliveira, "Deep instance segmentation of teeth in panoramic X-Ray images", SIBGRAPI, pp. 400-407, Oct 2018.

H. Oliveira, J. dos Santos, "Deep transfer learning for segmentation of anatomical structures in chest radiographs", SIBGRAPI, pp. 204-2Oct 2018.

J. Egger, C. Nimsky, X. Chen, "Vertebral body segmentation with GrowCut: Initial experience workflow and practical application", SAGE Open Med, vol. 5, pp. 1-5, 2017.

E. Burian, A. Rohrmeier, S. Schlaeger, M. Dieckmeyer, M. N. Diefenbach, J. Syväri, E. Klupp, D. Weidlich, C. Zimmer, E. J. Rummeny, D. C. Karampinos, J. S. Kirschke, T. Baum, "Lumbar muscle and vertebral bodies segmentation of chemical shift encoding-based water-fat MRI: the reference database myosegmentum spine", BMC Musculoskeletal Disorders, vol. no. 1, pp. 1Apr 2019.

T. Huber, G. Alber, S. Bette, T. Boeckh-Behrens, J. Gempt, F. Ringel, E. Alberts, C. Zimmer, J. S. Bauer, "Reliability of semi-automated segmentations in glioblastoma", Clinical Neuroradiology, vol. no. 2, pp. 153-1Jun 2017.

J. R. F., M. Koenigkam-Santos, F. E. G. Cipriano, A. T. Fabro, P. M. de Azevedo-Marques, "Radiomics-based features for pattern recognition of lung cancer histopathology and metastases", Computer Methods and Programs in Biomedicine, vol. 1pp. 23-2018.

P. Casti, A. Mencattini, M. H. Nogueira-Barbosa, L. Frighetto-Pereira, P. M. Azevedo-Marques, E. Martinelli, C. di Natale, "Cooperative strategy for a dynamic ensemble of classification models in clinical applications: the case of MRI vertebral compression fractures", IJCARS, vol. no. pp. 1971-19Nov 2017.

Z. Xue, L. R. Long, S. Antani, G. R. Thoma, "Spine X-ray image retrieval using partial vertebral boundaries", Symposium on Computer-Based Medical Systems (CBMS), pp. 1-6, June 2011.

L. Bergamasco, K. Lima, C. Rochitte, F. d. L.d. S. Nunes, "3d medical objects retrieval approach using spharms descriptor and network flow as similarity measure", SIBGRAPI, pp. 329-3Oct 2018.

D. Karimi, G. Samei, C. Kesch, G. Nir, S. E. Salcudean, "Prostate segmentation in MRI using a convolutional neural network architecture and training strategy based on statistical shape models", IJCARS, vol. no. 8, pp. 1211-122018.

P. Stefan, S. Habert, A. Winkler, M. Lazarovici, J. Fürmetz, U. Eck, N. Navab, "A radiation-free mixed-reality training environment and assessment concept for C-arm-based surgery", IJCARS, vol. no. 9, pp. 1335-13Sep 2018.

P. Banerjee, M. Hu, R. Kannan, S. Krishnaswamy, "A semiautomated approach to improve the efficiency of medical imaging segmentation for haptic rendering", Journal of Digital Imaging (JDI), vol. no. 4, pp. 519-Aug 2017.

R. Korez, B. Likar, F. Pernuš, T. Vrtovec, S. Ourselin, L. Joskowicz, M. R. Sabuncu, G. Unal, W. Wells, "Model-based segmentation of vertebral bodies from MR images with 3D CNNs" in Medical Image Computing and Computer-Assisted Intervention (MICCAI), Cham:Springer Int. Publishing, pp. 433-42016.

N. Kamiya, J. Li, M. Kume, H. Fujita, D. Shen, G. Zheng, "Fully automatic segmentation of paraspinal muscles from 3D torso CT images via multi-scale iterative random forest classifications", IJCARS, vol. no. pp. 1697-1706, Nov 2018.

J. S. Ramos, M. T. Cazzolato, B. S. Faiçal, M. H. Nogueira-Barbosa, C. Traina, A. J. M. Traina, "3DBGrowth: volumetric vertebrae segmentation and reconstruction in magnetic resonance imaging", Computer-Based Medical Systems (CBMS), pp. 1-6, June 2019.

B. Gaonkar, Y. Xia, D. S. Villaroman, A. Ko, M. Attiah, J. S. Beckett, L. Macyszyn, "Multi-parameter ensemble learning for automated vertebral body segmentation in heterogeneously acquired clinical MR images", Journal of Translational Engineering in Health and Medicine (JTEHM), vol. 5, pp. 1-2017.

J. S. Ramos, C. Y. V. Watanabe, M. H. Nogueira-Barbosa, A. J. M. Traina, "BGrowth: an efficient approach for the segmentation of vertebral compression fractures in magnetic resonance imaging", Symposium on Applied Computing (SAC), pp. 1-8, April 2019.

V. Vezhnevets, V. Konouchine, "GrowCut - interactive multi-label N-D image segmentation by cellular automata", International Conference on Computer Graphics and Vision (GraphiCon), vol. 1, Nov 2005.

L. Zhu, I. Kolesov, Y. Gao, R. Kikinis, A. Tannenbaum, "An effective interactive medical image segmentation method using Fast GrowCut", Medical Image Computing and Computed-Assisted Intervention (MICCAI), vol. 2014.

R. Kikinis, S. D. Pieper, K. G. Vosburgh, 3D Slicer: A Platform for Subject-Specific Image Analysis Visualization and Clinical Support, New York, NY:Springer New York, pp. 277-289, 2014.

W. S. Silva, D. L. Jasbick, R. E. Wilson, P. M. Azevedo-Marques, A. J. M. Traina, L. F. D. Santos, A. E. S. Jorge, D. de Oliveira, M. V. N. Bedo, "A two-phase learning approach for the segmentation of dermatological wounds", Computer-Based Medical Systems (CBMS), pp. 1-6, June 2019.

W. Wang, Y. Lu, "Analysis of the mean absolute error (MAE) and the root mean square error (RMSE) in assessing rounding model", IOP Conference Series: Materials Science and Engineering, vol. 3pp. 0120mar 2018.

R. C. Gonzalez, R. E. Woods, Digital image processing, Upper Saddle River, N.J.:Prentice Hall, 2008.

P. D. Barbieri, G. V. Pedrosa, A. J. M. Traina, M. H. Nogueira-Barbosa, C. T., P. P. Rodrigues, B. Kane, P. M. de Azevedo Marques, A. J. M. Traina, "Vertebral body segmentation of spine MR images using Su-perpixels", Symposium on Computer-Based Medical Systems (CBMS), pp. 44-June 2015.

P. Jaccard, "The distribution of the flora in the alpine zone", New Phytologist, vol. no. 2, pp. 37-Feb. 1912.

T. SØrensen, A Method of Establishing Groups of Equal Amplitude in Plant Sociology Based on Similarity of Species Content and Its Application to Analyses of the Vegetation on Danish Commons ser. Biologiske skrifter. I kommission hos E. Munksgaard, 1948.

T. Marošević, "The hausdorff distance between some sets of points", Mathematical Communications, vol. no. 2, Jan 2018.

M. M. Deza, E. Deza, Encyclopedia of Distances, Springer Berlin Heidelberg, 2009.

F. J. Massey, "The Kolmogorov-Smirnov test for goodness of fit", J. of the American Statistical Association, vol. no. 2pp. 68-1951.

F. Wilcoxon, S. Katti, R. Wilcox, "Critical values and probability levels for the Wilcoxon rank sum test and the Wilcoxon signed rank test", Selected Tables in Math. Statistics, vol. 1, pp. 171-21970.