Abstract
Magnetic Resonance Imaging (MRI) is used in everyday clinical practice to assess brain tumors. Deep Convolutional Neural Networks (DCNN) have recently shown very promising results in brain tumor segmentation tasks; however, DCNN models fail the task when applied to volumes that are different from the training dataset. One of the reasons is due to the lack of data standardization to adjust for different models and MR machines. In this work, a 3D spherical coordinates transform during the pre-processing phase has been hypothesized to improve DCNN models’ accuracy and to allow more generalizable results even when the model is trained on small and heterogeneous datasets and translated into different domains. Indeed, the spherical coordinate system avoids several standardization issues since it works independently of resolution and imaging settings. The model trained on spherical transform pre-processed inputs resulted in superior performance over the Cartesian-input trained model on predicting gliomas’ segmentation on Tumor Core and Enhancing Tumor classes, achieving a further improvement in accuracy by merging the two models together. The proposed model is not resolution-dependent, thus improving segmentation accuracy and theoretically solving some transfer learning problems related to the domain shifting, at least in terms of image resolution in the datasets.
Graphical abstract
Similar content being viewed by others
References
Thrall JH, Li X, Li Q et al (2018) Artificial intelligence and machine learning in radiology: opportunities, challenges, pitfalls, and criteria for success. J Am Coll Radiol 15:504–508. https://doi.org/10.1016/j.jacr.2017.12.026
Menze BH, Jakab A, Bauer S et al (2015) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34:1993–2024. https://doi.org/10.1109/TMI.2014.2377694
Bakas S, Reyes M, Jakab A, et al. (2018) Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge
Challen R, Denny J, Pitt M et al (2019) Artificial intelligence, bias and clinical safety. BMJ Qual Saf 28:231–237. https://doi.org/10.1136/bmjqs-2018-008370
Allen B, Seltzer SE, Langlotz CP et al (2019) A road map for translational research on artificial intelligence in medical imaging: from the 2018 National Institutes of Health/RSNA/ACR/The Academy Workshop. J Am Coll Radiol 16:1179–1189. https://doi.org/10.1016/j.jacr.2019.04.014
Kundel HL, Nodine CF (1983) A visual concept shapes image perception. Radiology 146:363–368. https://doi.org/10.1148/radiology.146.2.6849084
Nodine CF, Krupinski EA (1998) Perceptual skill, radiology expertise, and visual test performance with NINA and WALDO. Acad Radiol 5:603–612. https://doi.org/10.1016/S1076-6332(98)80295-X
Isensee F, Kickingereder P, Wick W, et al. (2019) No New-Net. pp 234–244
Manning D, Ethell S, Donovan T, Crawford T (2006) How do radiologists do it? The influence of experience and training on searching for chest nodules. Radiography 12:134–142. https://doi.org/10.1016/j.radi.2005.02.003
Bertram R, Helle L, Kaakinen JK, Svedström E (2013) The effect of expertise on eye movement behaviour in medical image perception. PLoS ONE 8:e66169. https://doi.org/10.1371/journal.pone.0066169
Donovan T, Manning DJ (2007) The radiology task: Bayesian theory and perception. Br J Radiol 80:389–391. https://doi.org/10.1259/bjr/98148548
Kundel HL, Nodine CF, Conant EF, Weinstein SP (2007) Holistic component of image perception in mammogram interpretation: gaze-tracking study. Radiology 242:396–402. https://doi.org/10.1148/radiol.2422051997
Kundel HL, La Follette PS (1972) Visual search patterns and experience with radiological images. Radiology 103:523–528. https://doi.org/10.1148/103.3.523
Kundel HL, John Wright D (1969) The influence of prior knowledge on visual search strategies during the viewing of chest radioqraphs. Radiology 93:315–320. https://doi.org/10.1148/93.2.315
Thorpe S, Fize D, Marlot C (1996) Speed of processing in the human visual system. Nature 381:520–522. https://doi.org/10.1038/381520a0
Antonopoulos M, Dionysiou D, Stamatakos G, Uzunoglu N (2019) Three-dimensional tumor growth in time-varying chemical fields: a modeling framework and theoretical study. BMC Bioinformatics 20:442. https://doi.org/10.1186/s12859-019-2997-9
Torres Hoyos F, Navarro RB, Vergara Villadiego J, Guerrero-Martelo M (2018) Geometrical study of astrocytomas through fractals and scaling analysis. Appl Radiat Isot 141:250–256. https://doi.org/10.1016/j.apradiso.2018.05.020
Murray JM, Kaissis G, Braren R, Kleesiek J (2020) A primer on radiomics. Radiologe 60:32–41. https://doi.org/10.1007/s00117-019-00617-w
Fan Y, Feng M, Wang R (2019) Application of radiomics in central nervous system diseases: a systematic literature review. Clin Neurol Neurosurg 187:105565. https://doi.org/10.1016/j.clineuro.2019.105565
Jang K, Russo C, Di Ieva A (2020) Radiomics in gliomas: clinical implications of computational modeling and fractal-based analysis. Neuroradiology 62:771–790. https://doi.org/10.1007/s00234-020-02403-1
Di Ieva A (2016) The fractal geometry of the brain. Springer New York, New York
Di Ieva A, Grizzi F, Ceva-Grimaldi G et al (2007) Fractal dimension as a quantitator of the microvasculature of normal and adenomatous pituitary tissue. J Anat 211:673–680. https://doi.org/10.1111/j.1469-7580.2007.00804.x
Di Ieva A, Le Reste P-J, Carsin-Nicol B et al (2016) Diagnostic value of fractal analysis for the differentiation of brain tumors using 3-Tesla magnetic resonance susceptibility-weighted imaging. Neurosurgery 79:839–846. https://doi.org/10.1227/NEU.0000000000001308
Milosevic NT, Di Ieva A, Jelinek H, Rajkovic N (2017) Box-counting method in quantitative analysis of images of the brain. In: 2017 21st International Conference on Control Systems and Computer Science (CSCS). pp 343–349
Di Ieva A, Göd S, Grabner G et al (2013) Three-dimensional susceptibility-weighted imaging at 7 T using fractal-based quantitative analysis to grade gliomas. Neuroradiology 55:35–40. https://doi.org/10.1007/s00234-012-1081-1
Di Ieva A, Esteban FJ, Grizzi F et al (2015) Fractals in the neurosciences, Part II. Neurosci 21:30–43. https://doi.org/10.1177/1073858413513928
Grizzi F, Castello A, Qehajaj D et al (2019) The complexity and fractal geometry of nuclear medicine images. Mol Imaging Biol 21:401–409. https://doi.org/10.1007/s11307-018-1236-5
Petrujkić K, Milošević N, Rajković N et al (2019) Computational quantitative MR image features - a potential useful tool in differentiating glioblastoma from solitary brain metastasis. Eur J Radiol 119:108634. https://doi.org/10.1016/j.ejrad.2019.08.003
Worrall DE, Garbin SJ, Turmukhambetov D, Brostow GJ (2017) Harmonic networks: deep translation and rotation equivariance. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 7168–7177
Depeursinge A, Fageot J, Andrearczyk V, et al. (2018) Rotation invariance and directional sensitivity: spherical harmonics versus radiomics features. pp 107–115
Cohen TS, Welling M (2016) Group equivariant convolutional networks. Proc Int Conf Mach Learn
Winkels M, Cohen TS (2019) Pulmonary nodule detection in CT scans with equivariant CNNs. Med Image Anal 55:15–26. https://doi.org/10.1016/j.media.2019.03.010
Andrearczyk V, Oreiller V, Fageot J, et al. (2019) Solid spherical energy (SSE) CNNs for efficient 3D medical image analysis. Irish Mach Vis Image Process Conf
Andrearczyk V, Fageot J, Oreiller V, et al. (2019) Exploring local rotation invariance in 3D CNNs with steerable filters. Proc Mach Learn Res
Xu Y, Xiao T, Zhang J, et al. (2014) Scale-invariant convolutional neural networks. ArXiv
Edelman JA, Mieses AM, Konnova K, Shiu D (2017) The effect of object-centered instructions in Cartesian and polar coordinates on saccade vector. J Vis 17:2. https://doi.org/10.1167/17.3.2
LIN C-S, CHEN H-T, LIN C-H, et al (2005) Polar coordinate mapping method for an improved infrared eye-tracking system. Biomed Eng Appl Basis Commun 17:141–146. https://doi.org/10.4015/S1016237205000226
Cantoni V (1994) Human and machine vision : analogies and divergencies. Springer
Esteves C, Allen-Blanchette C, Zhou X, Daniilidis K (2018) Polar transformer networks. ArXiv
Eric W. Weisstein (2005) Spherical coordinates -- from MathWorld-a Wolfram web resource
Myronenko A (2019) 3D MRI brain tumor segmentation using autoencoder regularization. In: Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries. BrainLes 2018. Lecture Notes in Computer Science, Springer. Cham, pp 311–320
Kingma DP, Welling M (2014) Auto-encoding variational Bayes. ICLR 2014 - Conf Track Proc
Doersch C (2016) Tutorial on variational autoencoders. ArXiv
Liu L, Jiang H, He P, et al. (2019) On the variance of the adaptive learning rate and beyond. ICLR 2019
Simpson AL, Antonelli M, Bakas S, et al. (2019) A large annotated medical image dataset for the development and evaluation of segmentation algorithms. ArXiv
Nalepa J, Cwiek M, Dudzik W, et al. (2019) Data augmentation via image registration. In: 2019 IEEE International Conference on Image Processing (ICIP). IEEE, pp 4250–4254
Nalepa J, Marcinkiewicz M, Kawulok M (2019) Data augmentation for brain-tumor segmentation: a review. Front Comput Neurosci 13:. https://doi.org/10.3389/fncom.2019.00083
Ribalta Lorenzo P, Nalepa J, Bobek-Billewicz B et al (2019) Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks. Comput Methods Programs Biomed 176:135–148. https://doi.org/10.1016/j.cmpb.2019.05.006
Xu Y, Goodacre R (2018) On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J Anal Test 2:249–262. https://doi.org/10.1007/s41664-018-0068-2
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Russo, C., Liu, S. & Di Ieva, A. Spherical coordinates transformation pre-processing in Deep Convolution Neural Networks for brain tumor segmentation in MRI. Med Biol Eng Comput 60, 121–134 (2022). https://doi.org/10.1007/s11517-021-02464-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-021-02464-1