<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0120-4157</journal-id>
<journal-title><![CDATA[Biomédica]]></journal-title>
<abbrev-journal-title><![CDATA[Biomed.]]></abbrev-journal-title>
<issn>0120-4157</issn>
<publisher>
<publisher-name><![CDATA[Instituto Nacional de Salud]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0120-41572024000500089</article-id>
<article-id pub-id-type="doi">10.7705/biomedica.7115</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Cardiac disease discrimination from 3D-convolutional kinematic patterns on cine-MRI sequences]]></article-title>
<article-title xml:lang="es"><![CDATA[Discriminación de enfermedades cardiacas utilizando patrones cinemáticos codificados con convoluciones 3D en secuencias de cine-RM]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Moreno]]></surname>
<given-names><![CDATA[Alejandra]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Bautista]]></surname>
<given-names><![CDATA[Lola Xiomara]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Martínez]]></surname>
<given-names><![CDATA[Fabio]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Industrial de Santander  ]]></institution>
<addr-line><![CDATA[Bucaramanga ]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>05</month>
<year>2024</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>05</month>
<year>2024</year>
</pub-date>
<volume>44</volume>
<fpage>89</fpage>
<lpage>100</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0120-41572024000500089&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0120-41572024000500089&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0120-41572024000500089&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract  Introduction.  Cine-MRI (cine-magnetic resonance imaging) sequences are a key diagnostic tool to visualize anatomical information, allowing experts to localize and determine suspicious pathologies. Nonetheless, such analysis remains subjective and prone to diagnosis errors.  Objective.  To develop a binary and multi-class classification considering various cardiac conditions using a spatiotemporal model that highlights kinematic movements to characterize each disease.  Materials and methods.  This research focuses on a 3D convolutional representation to characterize cardiac kinematic patterns during the cardiac cycle, which may be associated with pathologies. The kinematic maps are obtained from the apparent velocity maps computed from a dense optical flow strategy. Then, a 3D convolutional scheme learns to differentiate pathologies from kinematic maps.  Results.  The proposed strategy was validated with respect to the capability to discriminate among myocardial infarction, dilated cardiomyopathy, hypertrophic cardiomyopathy, abnormal right ventricle, and normal cardiac sequences. The proposed method achieves an average accuracy of 78.00% and a F1 score of 75.55%. Likewise, the approach achieved 92.31% accuracy for binary classification between pathologies and control cases.  Conclusion.  The proposed method can support the identification of kinematically abnormal patterns associated with a pathological condition. The resultant descriptor, learned from the 3D convolutional net, preserves detailed spatiotemporal correlations and could emerge as possible digital biomarkers of cardiac diseases.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen  Introducción.  Las secuencias del cine-resonancia magnética (cine-MRI, cine magnetic resonance imaging) son una herramienta diagnóstica clave para visualizar la información anatómica que les permite a los expertos localizar y determinar aquellas anomalías que resulten sospechosas. No obstante, este análisis sigue siendo subjetivo y propenso a errores de diagnóstico.  Objetivo.  Desarrollar una clasificación binaria y multiclase, considerando diferentes condiciones cardiacas, mediante un modelo espaciotemporal que permita resaltar los movimientos cinéticos para caracterizar cada enfermedad.  Materiales y métodos.  Este estudio se centra en el uso de una representación de convolución 3D para caracterizar los patrones cinéticos durante el ciclo cardiaco que puedan estar asociados con enfermedades. Para ello, se obtienen mapas cinéticos a partir de mapas de velocidad aparente, calculados mediante una estrategia de flujo óptico denso. A continuación, un esquema de convolución 3D "aprende" a diferenciar patologías a partir de mapas cinemáticos.  Resultados.  La estrategia propuesta se validó según la capacidad de discriminar entre infarto de miocardio, miocardiopatía dilatada, miocardiopatía hipertrófica, ventrículo derecho anormal y un examen normal. El método propuesto alcanza una precisión media del 78,0 % y una puntuación F1 score del 75,55 %. Asimismo, el enfoque alcanzó el 92,31 % de precisión para la clasificación binaria entre enfermedades y casos de control.  Conclusiones.  El método propuesto es capaz de apoyar la identificación de patrones cinéticos anormales asociados con una condición patológica. El descriptor resultante, aprendido de la red de convolución 3D, conserva correlaciones espaciotemporales detalladas y podría surgir como posible biomarcador digital de enfermedades cardiacas.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Heart diseases]]></kwd>
<kwd lng="en"><![CDATA[diagnostic imaging]]></kwd>
<kwd lng="en"><![CDATA[magnetic resonance spectroscopy.]]></kwd>
<kwd lng="es"><![CDATA[cardiopatías]]></kwd>
<kwd lng="es"><![CDATA[diagnóstico por imagen]]></kwd>
<kwd lng="es"><![CDATA[espectroscopia de resonancia magnética.]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>1.</label><nlm-citation citation-type="">
<collab>World Health Organization</collab>
<source><![CDATA[World Health Statistics 2021. Geneva: World Health Organization]]></source>
<year>2021</year>
</nlm-citation>
</ref>
<ref id="B2">
<label>2.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cetin]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Sanroma]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Petersen]]></surname>
<given-names><![CDATA[SE]]></given-names>
</name>
<name>
<surname><![CDATA[Napel]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Camara]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
<name>
<surname><![CDATA[Ballester]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A radiomics approach to computer-aided diagnosis with cardiac cine-MRI]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2019</year>
<volume>1909</volume>
</nlm-citation>
</ref>
<ref id="B3">
<label>3.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Jung]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automatic cardiac MRI segmentation and permutation-invariant pathology classification using deep neural networks and point clouds]]></article-title>
<source><![CDATA[Neurocomputing]]></source>
<year>2020</year>
<volume>418</volume>
<page-range>270-9</page-range></nlm-citation>
</ref>
<ref id="B4">
<label>4.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Song]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Jung]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automatic segmentation and cardiopathy classification in cardiac MRI images based on deep neural networks]]></article-title>
<source><![CDATA[ICASSP]]></source>
<year>2018</year>
<page-range>1020-4</page-range></nlm-citation>
</ref>
<ref id="B5">
<label>5.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Khened]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Kollerathu]]></surname>
<given-names><![CDATA[VA]]></given-names>
</name>
<name>
<surname><![CDATA[Krishnamurthi]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Fully convolutional multi-scale residual DenseNets for cardiac segmentation and automated cardiac diagnosis using ensemble of classifiers]]></article-title>
<source><![CDATA[Med Image Anal]]></source>
<year>2019</year>
<volume>51</volume>
<page-range>21-45</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>6.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Puyol-Anton]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Ruijsink]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Gerber]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Amzulescu]]></surname>
<given-names><![CDATA[MS]]></given-names>
</name>
<name>
<surname><![CDATA[Langet]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[De Craene]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Regional multi-view learning for cardiac motion analysis: Application to identification of dilated cardiomyopathy patients]]></article-title>
<source><![CDATA[IEEE Trans Biomed Eng]]></source>
<year>2019</year>
<volume>66</volume>
<page-range>956-66</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>7.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Tan]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Pohl]]></surname>
<given-names><![CDATA[KM]]></given-names>
</name>
<name>
<surname><![CDATA[Axel]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Metaxas]]></surname>
<given-names><![CDATA[DN]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[3D motion modeling and reconstruction of left ventricle wall in cardiac MRI]]></article-title>
<source><![CDATA[Funct Imaging Model Heart]]></source>
<year>2017</year>
<volume>10263</volume>
<page-range>481-92</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>8.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Isensee]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Jaeger]]></surname>
<given-names><![CDATA[PT]]></given-names>
</name>
<name>
<surname><![CDATA[Full]]></surname>
<given-names><![CDATA[PM]]></given-names>
</name>
<name>
<surname><![CDATA[Wolf]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Engelhardt]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Maier-Hein]]></surname>
<given-names><![CDATA[KH]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2017</year>
<volume>1707</volume>
</nlm-citation>
</ref>
<ref id="B9">
<label>9.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wolterink]]></surname>
<given-names><![CDATA[JM]]></given-names>
</name>
<name>
<surname><![CDATA[Leiner]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Viergever]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Isgum]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automatic segmentation and disease classification using cardiac cine MR images]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2017</year>
<volume>1708</volume>
<numero>01141</numero>
<issue>01141</issue>
</nlm-citation>
</ref>
<ref id="B10">
<label>10.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Qin]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Bai]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Schlemper]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Petersen]]></surname>
<given-names><![CDATA[SE]]></given-names>
</name>
<name>
<surname><![CDATA[Piechnik]]></surname>
<given-names><![CDATA[SK]]></given-names>
</name>
<name>
<surname><![CDATA[Neubauer]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Joint motion estimation and segmentation from undersampled cardiac MR image]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B11">
<label>11.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhen]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Islam]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Bhaduri]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Chan]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multi-scale deep networks and regression forests for direct bi-ventricular volume estimation]]></article-title>
<source><![CDATA[Medical Image Analysis]]></source>
<year>2016</year>
<volume>30</volume>
<page-range>120-9</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>12.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Punithakumar]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Ben Ayed]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Islam]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Goela]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Ross]]></surname>
<given-names><![CDATA[IG]]></given-names>
</name>
<name>
<surname><![CDATA[Chong]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Regional heart motion abnormality detection: An information theoretic approach]]></article-title>
<source><![CDATA[Medical Image Analysis]]></source>
<year>2013</year>
<volume>17</volume>
<page-range>311-24</page-range></nlm-citation>
</ref>
<ref id="B13">
<label>13.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zheng]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Delingette]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Ayache]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow]]></article-title>
<source><![CDATA[Medical Image Analysis]]></source>
<year>2019</year>
<volume>56</volume>
<page-range>80-95</page-range></nlm-citation>
</ref>
<ref id="B14">
<label>14.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Brox]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Malik]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Large displacement optical flow: Descriptor matching in variational motion etimation]]></article-title>
<source><![CDATA[IEEE Trans Pattern Anal Mach Intell]]></source>
<year>2011</year>
<volume>33</volume>
<page-range>500-13</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>15.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Varol]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Laptev]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Schmid]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Long-term temporal convolutions for action recognition]]></article-title>
<source><![CDATA[IEEE Trans Pattern Anal Mach Intell]]></source>
<year>2018</year>
<volume>40</volume>
<page-range>1510-7</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>16.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bernard]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
<name>
<surname><![CDATA[Lalande]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Zotti]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Cervenansky]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Heng]]></surname>
<given-names><![CDATA[PA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: Is the problem solved?]]></article-title>
<source><![CDATA[IEEE Trans Med Imaging]]></source>
<year>2018</year>
<volume>37</volume>
<page-range>2514-25</page-range></nlm-citation>
</ref>
<ref id="B17">
<label>17.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Broncano]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Bhalla]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Caro]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Hidalgo]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Vargas]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Williamson]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Cardiac MRI in patients with acute chest pain]]></article-title>
<source><![CDATA[Radiographics]]></source>
<year>2021</year>
<volume>41</volume>
<page-range>8-31</page-range></nlm-citation>
</ref>
<ref id="B18">
<label>18.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fotaki]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Puyol-Antón]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Chiribiri]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Botnar]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Pushparajah]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Prieto]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Artificial intelligence in cardiac MRI: Is clinical adoption forthcoming?]]></article-title>
<source><![CDATA[Front Cardiovasc Med]]></source>
<year>2022</year>
<volume>8</volume>
<numero>818765</numero>
<issue>818765</issue>
</nlm-citation>
</ref>
<ref id="B19">
<label>19.</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Clough]]></surname>
<given-names><![CDATA[JR]]></given-names>
</name>
<name>
<surname><![CDATA[Oksuz]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Puyol-Antón]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Ruijsink]]></surname>
<given-names><![CDATA[Bram]]></given-names>
</name>
<name>
<surname><![CDATA[King]]></surname>
<given-names><![CDATA[AP]]></given-names>
</name>
<name>
<surname><![CDATA[Schnabel]]></surname>
<given-names><![CDATA[JA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Global and local interpretability for cardiac MRI classification]]></article-title>
<source><![CDATA[Springer]]></source>
<year>2019</year>
<volume>1767</volume>
<page-range>656-64</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
