Patch-MI 2015: Patch-Based Techniques in Medical Imaging pp 137-145 | Cite as
Correlating Tumour Histology and ex vivo MRI Using Dense Modality-Independent Patch-Based Descriptors
Abstract
Histological images provide reliable information on tissue characteristics which can be used to validate and improve our understanding for developing radiological imaging analysis methods. However, due to the large amount of deformation in histology stemming from resected tissues, estimating spatial correspondence with other imaging modalities is a challenging image registration problem. In this work we develop a three-stage framework for nonlinear registration between ex vivo MRI and histology of rectal cancer. For this multi-modality image registration task, two similarity metrics from patch-based feature transformations were used: the dense Scale Invariant Feature Transform (dense SIFT) and the Modality Independent Neighbourhood Descriptor (MIND). The potential of our method is demonstrated on a dataset of eight rectal histology images from two patients using annotated landmarks. The mean registration error was 1.80 mm after the rigid registration steps which improved to 1.08 mm after nonlinear motion correction using dense SIFT and to 1.52 mm using MIND.
Keywords
Scale Invariant Feature Transform Histology Image Rigid Registration Histological Slice Nonlinear RegistrationNotes
Acknowledgements
We would like to acknowledge the funding from CRUK/EPSRC Cancer Imaging Centre at Oxford. AH also acknowledges the support of the Research Council UK Digital Economy Programme EP/G036861/1 (Oxford Centre for Doctoral Training in Healthcare Innovation) and CAPES Foundation, process BEX 0725/12-9.
References
- 1.Ceritoglu, C., Wang, L., Selemon, L.D., Csernansky, J.G., Miller, M.I., Ratnanather, J.T.: Large deformation diffeomorphic metric mapping registration of reconstructed 3D histological section images and in vivo MR images. Front Hum. Neurosci. 4, 43 (2010)Google Scholar
- 2.Chicherova, N., Fundana, K., Müller, B., Cattin, P.C.: Histology to \(\mu \)CT data matching using landmarks and a density biased RANSAC. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I. LNCS, vol. 8673, pp. 243–250. Springer, Heidelberg (2014)Google Scholar
- 3.Cho, H., Ackerstaff, E., Carlin, S., Lupu, M.E., Wang, Y., Rizwan, A., O’Donoghue, J., Ling, C.C., Humm, J.L., Zanzonico, P.B., et al.: Noninvasive multimodality imaging of the tumor microenvironment: registered dynamic MRI and PET studies of a preclinical tumor model of tumor hypoxia. Neoplasia 11(3), 247–259 (2009)CrossRefGoogle Scholar
- 4.Feldman, M., Tomaszewski, J., Davatzikos, C.: Non-rigid registration between histological and MR images of the prostate: a joint segmentation and registration framework. In: IEEE CVPR, pp. 125–132 (2009)Google Scholar
- 5.Heinrich, M.P., Jenkinson, M., Bhushan, M., Matin, T., Gleeson, F., Brady, M., Schnabel, J.A.: MIND: modality independent neighbourhood descriptor for multi-modal deformable registration. Med. Image Anal. 16(7), 1423–1435 (2012)CrossRefGoogle Scholar
- 6.Hermosillo, G., Chefd’hotel, C., Faugeras, O.: Variational methods for multimodal image matching. Int. J. Comput. Vis. 50(3), 329–343 (2002)MATHCrossRefGoogle Scholar
- 7.Irving, B., Cifor, A., Papież, B.W., Franklin, J., Anderson, E.M., Brady, S.M., Schnabel, J.A.: Automated colorectal tumour segmentation in DCE-MRI using supervoxel neighbourhood contrast characteristics. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I. LNCS, vol. 8673, pp. 609–616. Springer, Heidelberg (2014)Google Scholar
- 8.Koh, W.J., Bergman, K.S., Rasey, J.S., Peterson, L.M., Evans, M.L., Graham, M.M., Grierson, J.R., Lindsley, K.L., Lewellen, T.K., Krohn, K.A.: Evaluation of oxygenation status during fractionated radiotherapy in human nonsmall cell lung cancers using [f-18]fluoromisonidazole PET. Int. J. Radiat. Oncol. Biol. Phys. 33(2), 391–398 (1995)CrossRefGoogle Scholar
- 9.Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)CrossRefGoogle Scholar
- 10.Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV, vol. 2, pp. 1150–1157. IEEE (1999)Google Scholar
- 11.Ou, Y., Sotiras, A., Paragios, N., Davatzikos, C.: DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting. Med. Image Anal. 15(4), 622–639 (2011)CrossRefGoogle Scholar
- 12.Seroul, P., Sarrut, D.: VV: a viewer for the evaluation of 4D image registration. In: MICCAI-Systems and Architectures for Computer Assisted Interventions (2008)Google Scholar
- 13.Stoyanova, R., Huang, K., Sandler, K., Cho, H., Carlin, S., Zanzonico, P.B., Koutcher, J.A., Ackerstaff, E.: Mapping tumor hypoxia in vivo using pattern recognition of dceMRI data. Trans. Oncol. 5(6), 437–447 (2012)CrossRefGoogle Scholar
- 14.Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric log-domain diffeomorphic registration: a demons-based approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 15.Zahra, M.A., Hollingsworth, K.G., Sala, E., Lomas, D.J., Tan, L.T.: Dynamic contrast-enhanced MRI as a predictor of tumour response to radiotherapy. Lancet Oncol. 8(1), 63–74 (2007)CrossRefGoogle Scholar