The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration
Neuroimage registration has an important role in clinical (for both diagnostic and therapeutic purposes) and research applications. In this article we describe the applicability of Tsallis Entropy as a new cost function for neuroimage registration through a comparative analysis based on the performa...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2014-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/16/3/1632 |
| _version_ | 1798004113130127360 |
|---|---|
| author | Henrique Amaral-Silva Lauro Wichert-Ana Luiz Otavio Murta Larissa Romualdo-Suzuki Emerson Itikawa Geraldo Filho Bussato Paulo Azevedo-Marques |
| author_facet | Henrique Amaral-Silva Lauro Wichert-Ana Luiz Otavio Murta Larissa Romualdo-Suzuki Emerson Itikawa Geraldo Filho Bussato Paulo Azevedo-Marques |
| author_sort | Henrique Amaral-Silva |
| collection | DOAJ |
| description | Neuroimage registration has an important role in clinical (for both diagnostic and therapeutic purposes) and research applications. In this article we describe the applicability of Tsallis Entropy as a new cost function for neuroimage registration through a comparative analysis based on the performance of the traditional approaches (correlation based: Entropy Correlation Coefficient (ECC) and Normalized Cross Correlation (NCC); and Mutual Information (MI) based: Mutual Information using Shannon Entropy (MIS) and Normalized Mutual Information (NMI)) and the proposed one based on MI using Tsallis entropy (MIT). We created phantoms with known geometric transformations using Single Photon Emission Computed Tomography (SPECT) and Magnetic Resonance Imaging from 3 morphologically normal subjects. The simulated volumes were registered to the original ones using both the proposed and traditional approaches. The comparative analysis of the Relative Error (RE) showed that MIT was more accurate in the intra-modality registration, whereas for inter-modality registration, MIT presented the lowest RE for rotational transformations, and the ECC the lowest RE for translational transformations. In conclusion, we have shown that, with certain limitations, Tsallis Entropy has application as a better cost function for reliable neuroimage registration. |
| first_indexed | 2024-04-11T12:18:26Z |
| format | Article |
| id | doaj.art-9ed4f4d7e1eb4e97858f3ae97f43ac26 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T12:18:26Z |
| publishDate | 2014-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-9ed4f4d7e1eb4e97858f3ae97f43ac262022-12-22T04:24:11ZengMDPI AGEntropy1099-43002014-03-011631632165110.3390/e16031632e16031632The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT RegistrationHenrique Amaral-Silva0Lauro Wichert-Ana1Luiz Otavio Murta2Larissa Romualdo-Suzuki3Emerson Itikawa4Geraldo Filho Bussato5Paulo Azevedo-Marques6Center of Imaging Sciences and Medical Physics, Internal Medicine Department and Graduate Program, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto 14049-900, BrazilCenter of Imaging Sciences and Medical Physics, Internal Medicine Department and Graduate Program, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto 14049-900, BrazilDepartment of Computing and Mathematics, University of São Paulo, Ribeirão Preto 14040-901, BrazilDepartment of Computer Science, University College London, London WC1E 6BT, UKNuclear Medicine Section, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto 14049-900, BrazilThe Center Interdisciplinary Research on Applied Neurosciences (NAPNA), University of São Paulo, São Paulo 05403-010, BrazilCenter of Imaging Sciences and Medical Physics, Internal Medicine Department and Graduate Program, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto 14049-900, BrazilNeuroimage registration has an important role in clinical (for both diagnostic and therapeutic purposes) and research applications. In this article we describe the applicability of Tsallis Entropy as a new cost function for neuroimage registration through a comparative analysis based on the performance of the traditional approaches (correlation based: Entropy Correlation Coefficient (ECC) and Normalized Cross Correlation (NCC); and Mutual Information (MI) based: Mutual Information using Shannon Entropy (MIS) and Normalized Mutual Information (NMI)) and the proposed one based on MI using Tsallis entropy (MIT). We created phantoms with known geometric transformations using Single Photon Emission Computed Tomography (SPECT) and Magnetic Resonance Imaging from 3 morphologically normal subjects. The simulated volumes were registered to the original ones using both the proposed and traditional approaches. The comparative analysis of the Relative Error (RE) showed that MIT was more accurate in the intra-modality registration, whereas for inter-modality registration, MIT presented the lowest RE for rotational transformations, and the ECC the lowest RE for translational transformations. In conclusion, we have shown that, with certain limitations, Tsallis Entropy has application as a better cost function for reliable neuroimage registration.http://www.mdpi.com/1099-4300/16/3/1632neuroimagingregistrationSPECTMRImutual informationTsallis entropy |
| spellingShingle | Henrique Amaral-Silva Lauro Wichert-Ana Luiz Otavio Murta Larissa Romualdo-Suzuki Emerson Itikawa Geraldo Filho Bussato Paulo Azevedo-Marques The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration Entropy neuroimaging registration SPECT MRI mutual information Tsallis entropy |
| title | The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration |
| title_full | The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration |
| title_fullStr | The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration |
| title_full_unstemmed | The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration |
| title_short | The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration |
| title_sort | superiority of tsallis entropy over traditional cost functions for brain mri and spect registration |
| topic | neuroimaging registration SPECT MRI mutual information Tsallis entropy |
| url | http://www.mdpi.com/1099-4300/16/3/1632 |
| work_keys_str_mv | AT henriqueamaralsilva thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT laurowichertana thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT luizotaviomurta thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT larissaromualdosuzuki thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT emersonitikawa thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT geraldofilhobussato thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT pauloazevedomarques thesuperiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT henriqueamaralsilva superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT laurowichertana superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT luizotaviomurta superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT larissaromualdosuzuki superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT emersonitikawa superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT geraldofilhobussato superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration AT pauloazevedomarques superiorityoftsallisentropyovertraditionalcostfunctionsforbrainmriandspectregistration |