<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jhimli Mitra</style></author><author><style face="normal" font="default" size="100%">Zoltan Kato</style></author><author><style face="normal" font="default" size="100%">Soumya Ghose</style></author><author><style face="normal" font="default" size="100%">Desire Sidibe</style></author><author><style face="normal" font="default" size="100%">Robert Martí</style></author><author><style face="normal" font="default" size="100%">Xavier Lladó</style></author><author><style face="normal" font="default" size="100%">Oliver Arnau</style></author><author><style face="normal" font="default" size="100%">Joan C Vilanova</style></author><author><style face="normal" font="default" size="100%">Fabrice Meriaudeau</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Jan-Olof Eklundh</style></author><author><style face="normal" font="default" size="100%">Yuichi Ohta</style></author><author><style face="normal" font="default" size="100%">Steven Tanimoto</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Spectral clustering to model deformations for fast multimodal prostate registration</style></title><secondary-title><style face="normal" font="default" size="100%">International Conference on Pattern Recognition (ICPR)</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2012</style></year><pub-dates><date><style  face="normal" font="default" size="100%">Nov 2012</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://hal.archives-ouvertes.fr/docs/00/71/09/43/PDF/ICPR_Jhimli.pdf</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Tsukuba, Japan</style></pub-location><pages><style face="normal" font="default" size="100%">2622 - 2625</style></pages><isbn><style face="normal" font="default" size="100%">978-1-4673-2216-4 </style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;div class=&quot;article&quot;&gt;&lt;p&gt;This paper proposes a method &lt;span class=&quot;snippet&quot;&gt;to&lt;/span&gt; learn &lt;span class=&quot;snippet&quot;&gt;deformation&lt;/span&gt; parameters off-line for &lt;span class=&quot;snippet&quot;&gt;fast&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;multimodal&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; of ultrasound and magnetic resonance &lt;span class=&quot;snippet&quot;&gt;prostate&lt;/span&gt; images during ultrasound guided needle biopsy. The &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; method involves &lt;span class=&quot;snippet&quot;&gt;spectral&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;clustering&lt;/span&gt; of the &lt;span class=&quot;snippet&quot;&gt;deformation&lt;/span&gt; parameters obtained from a spline-based nonlinear diffeomorphism between training magnetic resonance and ultrasound &lt;span class=&quot;snippet&quot;&gt;prostate&lt;/span&gt; images. The &lt;span class=&quot;snippet&quot;&gt;deformation&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;models&lt;/span&gt; built from the principal eigen-modes of the &lt;span class=&quot;snippet&quot;&gt;clusters&lt;/span&gt; are then applied on a test magnetic resonance image &lt;span class=&quot;snippet&quot;&gt;to&lt;/span&gt; register with the test ultrasound &lt;span class=&quot;snippet&quot;&gt;prostate&lt;/span&gt; image. The &lt;span class=&quot;snippet&quot;&gt;deformation&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;model&lt;/span&gt; with the least &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; error is finally chosen as the optimal &lt;span class=&quot;snippet&quot;&gt;model&lt;/span&gt; for deformable &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt;. The rationale behind &lt;span class=&quot;snippet&quot;&gt;modeling&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;deformations&lt;/span&gt; is &lt;span class=&quot;snippet&quot;&gt;to&lt;/span&gt; achieve &lt;span class=&quot;snippet&quot;&gt;fast&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;multimodal&lt;/span&gt; &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; of &lt;span class=&quot;snippet&quot;&gt;prostate&lt;/span&gt; images while maintaining &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; accuracies which is otherwise computationally expensive. The method is validated for 25 patients each with a pair of corresponding magnetic resonance and ultrasound images in a leave-one-out validation framework. The average &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; accuracies i.e. Dice similarity coefficient of 0.927 ± 0.025, 95% Hausdorff distance of 5.14 ± 3.67 mm and target &lt;span class=&quot;snippet&quot;&gt;registration&lt;/span&gt; error of 2.44 ± 1.17 mm are obtained by our method with a speed-up in computation time by 98% when compared &lt;span class=&quot;snippet&quot;&gt;to&lt;/span&gt; Mitra et al. [7].&lt;/p&gt;&lt;/div&gt;&lt;p&gt;&amp;nbsp;&lt;/p&gt;</style></abstract><work-type><style face="normal" font="default" size="100%">Conference paper</style></work-type><accession-num><style face="normal" font="default" size="100%">13325059</style></accession-num></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jhimli Mitra</style></author><author><style face="normal" font="default" size="100%">Zoltan Kato</style></author><author><style face="normal" font="default" size="100%">Robert Martí</style></author><author><style face="normal" font="default" size="100%">Oliver Arnau</style></author><author><style face="normal" font="default" size="100%">Xavier Lladó</style></author><author><style face="normal" font="default" size="100%">Desire Sidibe</style></author><author><style face="normal" font="default" size="100%">Soumya Ghose</style></author><author><style face="normal" font="default" size="100%">Joan C Vilanova</style></author><author><style face="normal" font="default" size="100%">Josep Comet</style></author><author><style face="normal" font="default" size="100%">Fabrice Meriaudeau</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A spline-based non-linear diffeomorphism for multimodal prostate registration.</style></title><secondary-title><style face="normal" font="default" size="100%">MEDICAL IMAGE ANALYSIS</style></secondary-title><short-title><style face="normal" font="default" size="100%">MED IMAGE ANAL</style></short-title></titles><dates><year><style  face="normal" font="default" size="100%">2012</style></year><pub-dates><date><style  face="normal" font="default" size="100%">Aug 2012</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">16</style></volume><pages><style face="normal" font="default" size="100%">1259 - 1279</style></pages><isbn><style face="normal" font="default" size="100%">1361-8415</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This paper presents a novel method for non-rigid registration of transrectal ultrasound and magnetic resonance prostate images based on a non-linear regularized framework of point correspondences obtained from a statistical measure of shape-contexts. The segmented prostate shapes are represented by shape-contexts and the Bhattacharyya distance between the shape representations is used to find the point correspondences between the 2D fixed and moving images. The registration method involves parametric estimation of the non-linear diffeomorphism between the multimodal images and has its basis in solving a set of non-linear equations of thin-plate splines. The solution is obtained as the least-squares solution of an over-determined system of non-linear equations constructed by integrating a set of non-linear functions over the fixed and moving images. However, this may not result in clinically acceptable transformations of the anatomical targets. Therefore, the regularized bending energy of the thin-plate splines along with the localization error of established correspondences should be included in the system of equations. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate mid-gland ultrasound and magnetic resonance images. The results obtained in terms of Dice similarity coefficient show an average of 0.980+/-0.004, average 95% Hausdorff distance of 1.63+/-0.48mm and mean target registration and target localization errors of 1.60+/-1.17mm and 0.15+/-0.12mm respectively.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">6</style></issue><work-type><style face="normal" font="default" size="100%">Journal article</style></work-type><notes><style face="normal" font="default" size="100%">UT: 000309694100015ScopusID: 84866118888doi: 10.1016/j.media.2012.04.006</style></notes></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jhimli Mitra</style></author><author><style face="normal" font="default" size="100%">Zoltan Kato</style></author><author><style face="normal" font="default" size="100%">Robert Martí</style></author><author><style face="normal" font="default" size="100%">Oliver Arnau</style></author><author><style face="normal" font="default" size="100%">Xavier Lladó</style></author><author><style face="normal" font="default" size="100%">Soumya Ghose</style></author><author><style face="normal" font="default" size="100%">Joan C Vilanova</style></author><author><style face="normal" font="default" size="100%">Fabrice Meriaudeau</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A non-linear diffeomorphic framework for prostate multimodal registration</style></title><secondary-title><style face="normal" font="default" size="100%">International Conference on Digital Image Computing: Techniques and Applications (DICTA)</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2011</style></year><pub-dates><date><style  face="normal" font="default" size="100%">Dec 2011</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">IEEE</style></publisher><pub-location><style face="normal" font="default" size="100%">Noosa, QLD </style></pub-location><pages><style face="normal" font="default" size="100%">31 - 36</style></pages><isbn><style face="normal" font="default" size="100%">978-1-4577-2006-2 </style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;This paper presents a novel method for non-rigid registration of prostate multimodal images based on a nonlinear framework. The parametric estimation of the non-linear diffeomorphism between the 2D fixed and moving images has its basis in solving a set of non-linear equations of thin-plate splines. The regularized bending energy of the thin-plate splines along with the localization error of established correspondences is jointly minimized with the fixed and transformed image difference, where, the transformed image is represented by the set of non-linear equations defined over the moving image. The traditional thin-plate splines with established correspondences may provide good registration of the anatomical targets inside the prostate but may fail to provide improved contour registration. On the contrary, the proposed framework maintains the accuracy of registration in terms of overlap due to the non-linear thinplate spline functions while also producing smooth deformations of the anatomical structures inside the prostate as a result of established corrspondences. The registration accuracies of the proposed method are evaluated in 20 pairs of prostate midgland ultrasound and magnetic resonance images in terms of Dice similarity coefficient with an average of 0.982 ± 0.004, average 95% Hausdorff distance of 1.54 ± 0.46 mm and mean target registration and target localization errors of 1.90±1.27 mm and 0.15 ± 0.12 mm respectively. © 2011 IEEE.&lt;/p&gt;</style></abstract><work-type><style face="normal" font="default" size="100%">Conference paper</style></work-type><accession-num><style face="normal" font="default" size="100%">12476651 </style></accession-num><notes><style face="normal" font="default" size="100%">ScopusID: 84856980939doi: 10.1109/DICTA.2011.14</style></notes></record></records></xml>