<?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>0188-9532</journal-id>
<journal-title><![CDATA[Revista mexicana de ingeniería biomédica]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. mex. ing. bioméd]]></abbrev-journal-title>
<issn>0188-9532</issn>
<publisher>
<publisher-name><![CDATA[Sociedad Mexicana de Ingeniería Biomédica]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0188-95322022000200102</article-id>
<article-id pub-id-type="doi">10.17488/rmib.43.2.4</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Retinal Lesion Segmentation Using Transfer Learning with an Encoder-Decoder CNN]]></article-title>
<article-title xml:lang="es"><![CDATA[Segmentación de Lesiones en la Retina Usando Transferencia de Conocimiento con CNN Encoder-Decoder]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Ortiz-Feregrino]]></surname>
<given-names><![CDATA[Rafael]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Tovar-Arriaga]]></surname>
<given-names><![CDATA[Saúl]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Pedraza-Ortega]]></surname>
<given-names><![CDATA[Jesús Carlos]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Takacs]]></surname>
<given-names><![CDATA[Andras]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Autónoma de Querétaro  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Mexico</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>08</month>
<year>2022</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>08</month>
<year>2022</year>
</pub-date>
<volume>43</volume>
<numero>2</numero>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S0188-95322022000200102&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S0188-95322022000200102&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S0188-95322022000200102&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[ABSTRACT Deep learning (DL) techniques achieve high performance in the detection of illnesses in retina images, but the majority of models are trained with different databases for solving one specific task. Consequently, there are currently no solutions that can be used for the detection/segmentation of a variety of illnesses in the retina in a single model. This research uses Transfer Learning (TL) to take advantage of previous knowledge generated during model training of illness detection to segment lesions with encoder-decoder Convolutional Neural Networks (CNN), where the encoders are classical models like VGG-16 and ResNet50 or variants with attention modules. This shows that it is possible to use a general methodology using a single fundus image database for the detection/segmentation of a variety of retinal diseases achieving state-of-the-art results. This model could be in practice more valuable since it can be trained with a more realistic database containing a broad spectrum of diseases to detect/segment illnesses without sacrificing performance. TL can help achieve fast convergence if the samples in the main task (Classification) and sub-tasks (Segmentation) are similar. If this requirement is not fulfilled, the parameters start from scratch.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[RESUMEN Las técnicas de Deep Learning (DL) han demostrado un buen desempeño en la detección de anomalías en imágenes de retina, pero la mayoría de los modelos son entrenados en diferentes bases de datos para resolver una tarea en específico. Como consecuencia, actualmente no se cuenta con modelos que se puedan usar para la detección/segmentación de varias lesiones o anomalías con un solo modelo. En este artículo, se utiliza Transfer Learning (TL) con la cual se aprovecha el conocimiento adquirido para determinar si una imagen de retina tiene o no una lesión. Con este conocimiento se segmenta la imagen utilizando una red neuronal convolucional (CNN), donde los encoders o extractores de características son modelos clásicos como VGG-16 y ResNet50 o variantes con módulos de atención. Se demuestra así, que es posible utilizar una metodología general con bases de datos de retina para la detección/ segmentación de lesiones en la retina alcanzando resultados como los que se muestran en el estado del arte. Este modelo puede ser entrenado con bases de datos más reales que contengan una gama de enfermedades para detectar/ segmentar sin sacrificar rendimiento. TL puede ayudar a conseguir una convergencia rápida del modelo si la base de datos principal (Clasificación) se parece a la base de datos de las tareas secundarias (Segmentación), si esto no se cumple los parámetros básicamente comienzan a ajustarse desde cero.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Transfer learning]]></kwd>
<kwd lng="en"><![CDATA[Encoder-decoder]]></kwd>
<kwd lng="en"><![CDATA[Retinal images]]></kwd>
<kwd lng="en"><![CDATA[Lesion segmentation]]></kwd>
<kwd lng="en"><![CDATA[Deep learning]]></kwd>
<kwd lng="es"><![CDATA[Transferencia de conocimiento]]></kwd>
<kwd lng="es"><![CDATA[Codificador-decodificador]]></kwd>
<kwd lng="es"><![CDATA[Imágenes de retina]]></kwd>
<kwd lng="es"><![CDATA[Segmentación de lesiones]]></kwd>
<kwd lng="es"><![CDATA[Aprendizaje profundo]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Trucco]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[MacGillivray]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<source><![CDATA[Computational Retinal Image Analysis]]></source>
<year>2019</year>
<publisher-loc><![CDATA[Cambridge, United States ]]></publisher-loc>
<publisher-name><![CDATA[Elsevier]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Prado-Serrano]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Guido-Jiménez]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Camas-Benítez]]></surname>
<given-names><![CDATA[JT]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Prevalencia de retinopatía diabética en población mexicana]]></article-title>
<source><![CDATA[Rev Mex Oftalmol]]></source>
<year>2009</year>
<volume>83</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>261-6</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ricci]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Perfetti]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification]]></article-title>
<source><![CDATA[IEEE Trans Med Imaging]]></source>
<year>2007</year>
<volume>26</volume>
<numero>10</numero>
<issue>10</issue>
<page-range>1357-65</page-range></nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sarhan]]></surname>
<given-names><![CDATA[MH]]></given-names>
</name>
<name>
<surname><![CDATA[Nasseri]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Zapp]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Maier]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Machine Learning Techniques for Ophthalmic Data Processing: A Review]]></article-title>
<source><![CDATA[IEEE J Biomed Health Inform]]></source>
<year>2020</year>
<volume>24</volume>
<numero>12</numero>
<issue>12</issue>
<page-range>3338-50</page-range></nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ammu]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Sinha]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<source><![CDATA[Small Segment Emphasized Performance Evaluation Metric for Medical Images]]></source>
<year>2020</year>
<conf-name><![CDATA[ International Conference on Signal Processing and Communications (SPCOM)]]></conf-name>
<conf-date>2020</conf-date>
<conf-loc> </conf-loc>
<page-range>1-5</page-range><publisher-loc><![CDATA[Bangalore ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Quellec]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Charrière]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Boudi]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Cochener]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep image mining for diabetic retinopathy screening]]></article-title>
<source><![CDATA[Med Image Anal]]></source>
<year>2017</year>
<volume>39</volume>
<page-range>178-93</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Thibault]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Decencière]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Marcotegui]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Exudate detection in color retinal images for mass screening of diabetic retinopathy]]></article-title>
<source><![CDATA[Med Image Anal]]></source>
<year>2014</year>
<volume>18</volume>
<numero>7</numero>
<issue>7</issue>
<page-range>1026-43</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Yao]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Qiao]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep Retinal Image Segmentation: A FCN-Based Architecture with Short and Long Skip Connections for Retinal Image Segmentation]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Xie]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural Information Processing ICONIP 2017. Lecture Notes in Computer Science]]></source>
<year>2017</year>
<volume>10637</volume>
<page-range>713-22</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ye]]></surname>
<given-names><![CDATA[JC]]></given-names>
</name>
<name>
<surname><![CDATA[Sung]]></surname>
<given-names><![CDATA[WK]]></given-names>
</name>
</person-group>
<source><![CDATA[Understanding Geometry of Encoder-Decoder CNNs]]></source>
<year>2019</year>
<volume>97</volume>
<conf-name><![CDATA[ 36International Conference on Machine Learning, ICML 2019]]></conf-name>
<conf-loc> </conf-loc>
<page-range>12245-54</page-range><publisher-loc><![CDATA[Long Beach ]]></publisher-loc>
<publisher-name><![CDATA[Proceedings of Machine Learning Research]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tan]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Kong]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Survey on Deep Transfer Learning]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Manolopoulos]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Hammer]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Iliadis]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Maglogiannis]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
</person-group>
<source><![CDATA[Artificial Neural Networks and Machine Learning - ICANN 2018. ICANN 2018. Lecture Notes in Computer Science]]></source>
<year>2018</year>
<volume>11041</volume>
<page-range>270-9</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tang]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Qi]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Granley]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Beyeler]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[U-Net with Hierarchical Bottleneck Attention for Landmark Detection in Fundus Images of the Degenerated Retina]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Fu]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Garvin]]></surname>
<given-names><![CDATA[MK]]></given-names>
</name>
<name>
<surname><![CDATA[MacGillivray]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<source><![CDATA[Ophthalmic Medical Image Analysis. OMIA 2021. Lecture Notes in Computer Science]]></source>
<year>2021</year>
<volume>12970</volume>
<page-range>62-71</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Welikala]]></surname>
<given-names><![CDATA[RA]]></given-names>
</name>
<name>
<surname><![CDATA[Foster]]></surname>
<given-names><![CDATA[PJ]]></given-names>
</name>
<name>
<surname><![CDATA[Whincup]]></surname>
<given-names><![CDATA[PH]]></given-names>
</name>
<name>
<surname><![CDATA[Rudnicka]]></surname>
<given-names><![CDATA[AR]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automated arteriole and venule classification using deep learning for retinal images from the UK Biobank cohort]]></article-title>
<source><![CDATA[Comput Biol Med]]></source>
<year>2017</year>
<volume>90</volume>
<page-range>23-32</page-range></nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fraz]]></surname>
<given-names><![CDATA[MM]]></given-names>
</name>
<name>
<surname><![CDATA[Rudnicka]]></surname>
<given-names><![CDATA[AR]]></given-names>
</name>
<name>
<surname><![CDATA[Owen]]></surname>
<given-names><![CDATA[CG]]></given-names>
</name>
<name>
<surname><![CDATA[Barman]]></surname>
<given-names><![CDATA[SA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Delineation of blood vessels in pediatric retinal images using decision trees-based ensemble classification]]></article-title>
<source><![CDATA[Int J Comput Assist Radiol Surg]]></source>
<year>2014</year>
<volume>9</volume>
<page-range>795-811</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Adel]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Soliman]]></surname>
<given-names><![CDATA[MM]]></given-names>
</name>
<name>
<surname><![CDATA[Khalifa]]></surname>
<given-names><![CDATA[NEM]]></given-names>
</name>
<name>
<surname><![CDATA[Mostafa]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic Classification of Retinal Eye Diseases from Optical Coherence Tomography using Transfer Learning]]></source>
<year>2020</year>
<conf-name><![CDATA[ 16International Computer Engineering Conference (ICENCO)]]></conf-name>
<conf-date>2020</conf-date>
<conf-loc> </conf-loc>
<page-range>37-42</page-range><publisher-loc><![CDATA[Cairo ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Xiao]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Adel]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Bourennane]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Bayesian Method with Spatial Constraint for Retinal Vessel Segmentation]]></article-title>
<source><![CDATA[Comput Math Methods Med]]></source>
<year>2013</year>
<volume>401413</volume>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lam]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Rubin]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Retinal Lesion Detection with Deep Learning Using Image Patches]]></article-title>
<source><![CDATA[Invest Ophthalmol Vis Sci]]></source>
<year>2018</year>
<volume>59</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>590-6</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Xie]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Cross- Modality Learning Approach for Vessel Segmentation in Retinal Images]]></article-title>
<source><![CDATA[IEEE Trans Med Imaging]]></source>
<year>2016</year>
<volume>35</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>109-18</page-range></nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Long]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Hu]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Microaneurysms detection in color fundus images using machine learning based on directional local contrast]]></article-title>
<source><![CDATA[Biomed Eng Online]]></source>
<year>2020</year>
<volume>19</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>21</page-range></nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Aziz]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Ilesanmi]]></surname>
<given-names><![CDATA[AE]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Charoenlarpnopparut C. Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features]]></article-title>
<source><![CDATA[Appl Sci]]></source>
<year>2021</year>
<volume>11</volume>
<numero>14</numero>
<issue>14</issue>
<page-range>6391</page-range></nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Dual-Branch Network with DualSampling Modulated Dice Loss for Hard Exudate Segmentation in Colour Fundus Images]]></article-title>
<source><![CDATA[IEEE J Biomed Health Inform]]></source>
<year>2022</year>
<volume>26</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>1091-102</page-range></nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zong]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Tao]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[U-net Based Method for Automatic Hard Exudates Segmentation in Fundus Images Using Inception Module and Residual Connection]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2020</year>
<volume>8</volume>
<page-range>167225-35</page-range></nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tan]]></surname>
<given-names><![CDATA[JH]]></given-names>
</name>
<name>
<surname><![CDATA[Fujita]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Sivaprasad]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Bhandary]]></surname>
<given-names><![CDATA[SV]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Automated segmentation of exudates, haemorrhages, microaneurysms using single convolutional neural network]]></article-title>
<source><![CDATA[Inf Sci]]></source>
<year>2017</year>
<volume>420</volume>
<page-range>66-76</page-range></nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kou]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Yuan]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An Enhanced Residual U-Net for Microaneurysms and Exudates Segmentation in Fundus Images]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2020</year>
<volume>8</volume>
<page-range>185514-25</page-range></nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gondal]]></surname>
<given-names><![CDATA[WM]]></given-names>
</name>
<name>
<surname><![CDATA[Köhler]]></surname>
<given-names><![CDATA[JM]]></given-names>
</name>
<name>
<surname><![CDATA[Grzeszick]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Fink]]></surname>
<given-names><![CDATA[GA]]></given-names>
</name>
</person-group>
<source><![CDATA[Weaklysupervised localization of diabetic retinopathy lesions in retinal fundus images]]></source>
<year>2017</year>
<conf-name><![CDATA[ IEEE International Conference on Image Processing (ICIP)]]></conf-name>
<conf-date>2017</conf-date>
<conf-loc> </conf-loc>
<page-range>2069-73</page-range><publisher-loc><![CDATA[Beijing ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Joshi]]></surname>
<given-names><![CDATA[GD]]></given-names>
</name>
<name>
<surname><![CDATA[Sivaswamy]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Krishnadas]]></surname>
<given-names><![CDATA[SR]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Optic Disk and Cup Segmentation From Monocular Color Retinal Images for Glaucoma Assessment]]></article-title>
<source><![CDATA[IEEE Trans Med Imaging]]></source>
<year>2011</year>
<volume>30</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>1192-205</page-range></nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Harangi]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Antal]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Hajdu]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Automatic exudate detection with improved naïve-Bayes classifier]]></source>
<year>2012</year>
<conf-name><![CDATA[ 25IEEE International Symposium on Computer- Based Medical Systems (CBMS)]]></conf-name>
<conf-date>2012</conf-date>
<conf-loc> </conf-loc>
<page-range>1-4</page-range><publisher-loc><![CDATA[Rome ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cheung]]></surname>
<given-names><![CDATA[CY]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Cheng]]></surname>
<given-names><![CDATA[CY]]></given-names>
</name>
<name>
<surname><![CDATA[Sabanayagam]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel caliber]]></article-title>
<source><![CDATA[Nat Biomed Eng]]></source>
<year>2021</year>
<volume>5</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>498-508</page-range></nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dai]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Cai]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A deep learning system for detecting diabetic retinopathy across the disease spectrum]]></article-title>
<source><![CDATA[Nat Commun]]></source>
<year>2021</year>
<volume>12</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>3242</page-range></nlm-citation>
</ref>
<ref id="B29">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kou]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Microaneurysms segmentation with a U-Net based on recurrent residual convolutional neural network]]></article-title>
<source><![CDATA[J Med Imaging]]></source>
<year>2019</year>
<volume>6</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>025008</page-range></nlm-citation>
</ref>
<ref id="B30">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Tan]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An Improved U-Net Architecture for Simultaneous Arteriole and Venule Segmentation in Fundus Image]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Nixon]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Mahmoodi]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Zwiggelaar]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<source><![CDATA[Understanding and Analysis. MIUA 2018. Communications in Computer and Information Science]]></source>
<year>2018</year>
<page-range>333-40</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B31">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yadav]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Maheshwari]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Agarwal]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Contrast limited adaptive histogram equalization based enhancement for real time video system]]></source>
<year>2014</year>
<conf-name><![CDATA[ International Conference on Advances in Computing, Communications and Informatics (ICACCI)]]></conf-name>
<conf-date>2014</conf-date>
<conf-loc> </conf-loc>
<page-range>2392-7</page-range><publisher-loc><![CDATA[Delhi ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B32">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Decencière]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Cazuguel]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Lay]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Feedback on a publicly distributed image database: The Messidor database]]></article-title>
<source><![CDATA[Image Anal Stereol]]></source>
<year>2014</year>
<volume>33</volume>
<numero>3</numero>
<issue>3</issue>
<page-range>231</page-range></nlm-citation>
</ref>
<ref id="B33">
<nlm-citation citation-type="book">
<collab>Kaggle</collab>
<source><![CDATA[Diabetic Retinopathy Detection]]></source>
<year>2015</year>
<publisher-name><![CDATA[Kaggle]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B34">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Porwal]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Pachade]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Kamble]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Kokare]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<source><![CDATA[Indian Diabetic Retinopathy Image Dataset (IDRiD)]]></source>
<year>2018</year>
<publisher-name><![CDATA[IEEE Dataport]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B35">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Decencière]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Cazuguel]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Thibault]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[TeleOphta: Machine learning and image processing methods for teleophthalmology]]></article-title>
<source><![CDATA[IRBM]]></source>
<year>2013</year>
<volume>34</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>196-203</page-range></nlm-citation>
</ref>
<ref id="B36">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Simonyan]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Zisserman]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[LeCun]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<source><![CDATA[Very deep convolutional networks for large-scale image recognition]]></source>
<year>2015</year>
<conf-name><![CDATA[ 3International Conference on Learning Representations, ICLR 2015]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1-14</page-range><publisher-loc><![CDATA[San Diego ]]></publisher-loc>
<publisher-name><![CDATA[arXiv]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B37">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[He]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Ren]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<source><![CDATA[Deep Residual Learning for Image Recognition]]></source>
<year>2016</year>
<conf-name><![CDATA[ IEEE Conference on Computer Vision and Pattern Recognition (CVPR)]]></conf-name>
<conf-date>2016</conf-date>
<conf-loc> </conf-loc>
<page-range>770-8</page-range><publisher-loc><![CDATA[Las Vegas ]]></publisher-loc>
<publisher-name><![CDATA[IEEE]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B38">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Woo]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Park]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[JY]]></given-names>
</name>
<name>
<surname><![CDATA[Kweon]]></surname>
<given-names><![CDATA[IS]]></given-names>
</name>
<name>
<surname><![CDATA[Ferrari]]></surname>
<given-names><![CDATA[V]]></given-names>
</name>
<name>
<surname><![CDATA[Hebert]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Sminchisescu]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Weiss]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<source><![CDATA[CBAM: Convolutional Block Attention Module]]></source>
<year>2018</year>
<page-range>3-19</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B39">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cortes]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Research]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Mohri]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Rostamizadeh]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[L2 Regularization for Learning Kernels]]></source>
<year>2009</year>
<conf-name><![CDATA[ 25Conference on Uncertainty in Artificial Intelligence (UAI 2009)]]></conf-name>
<conf-loc> </conf-loc>
<page-range>109-16</page-range><publisher-loc><![CDATA[Montreal ]]></publisher-loc>
<publisher-name><![CDATA[Association for Uncertainty in Artificial Intelligence (AUAI)]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B40">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ioffe]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Szegedy]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Batch normalization: Accelerating deep network training by reducing internal covariate shift]]></article-title>
<source><![CDATA[Proceedings of the 32nd International Conference on International Conference on Machine Learning]]></source>
<year>2015</year>
<volume>37</volume>
<page-range>448-56</page-range><publisher-loc><![CDATA[Lille ]]></publisher-loc>
<publisher-name><![CDATA[JMLR]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B41">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Srivastava]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
<name>
<surname><![CDATA[Hinton]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Krizhevsky]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Sutskever]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Dropout: A Simple Way to Prevent Neural Networks from Overfitting]]></article-title>
<source><![CDATA[J Mach Learn Res]]></source>
<year>2014</year>
<volume>15</volume>
<numero>56</numero>
<issue>56</issue>
<page-range>1929-58</page-range></nlm-citation>
</ref>
<ref id="B42">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wisaeng]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Sa-Ngiamvibool]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Exudates Detection Using Morphology Mean Shift Algorithm in Retinal Images]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2019</year>
<volume>7</volume>
<page-range>11946-58</page-range></nlm-citation>
</ref>
<ref id="B43">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[van Grinsven]]></surname>
<given-names><![CDATA[MJJP]]></given-names>
</name>
<name>
<surname><![CDATA[van Ginneken]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Hoyng]]></surname>
<given-names><![CDATA[CB]]></given-names>
</name>
<name>
<surname><![CDATA[Theelen]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images]]></article-title>
<source><![CDATA[IEEE Trans Med Imaging]]></source>
<year>2016</year>
<volume>35</volume>
<numero>5</numero>
<issue>5</issue>
<page-range>1273-84</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
