<?xml version="1.0" encoding="ISO-8859-1"?>
<metadatalist>
	<metadata ReferenceType="Conference Proceedings">
		<site>sibgrapi.sid.inpe.br 802</site>
		<holdercode>{ibi 8JMKD3MGPEW34M/46T9EHH}</holdercode>
		<identifier>8JMKD3MGPEW34M/45CUN9S</identifier>
		<repository>sid.inpe.br/sibgrapi/2021/09.06.21.31</repository>
		<lastupdate>2021:09.06.21.31.58 sid.inpe.br/banon/2001/03.30.15.38 administrator</lastupdate>
		<metadatarepository>sid.inpe.br/sibgrapi/2021/09.06.21.31.58</metadatarepository>
		<metadatalastupdate>2022:06.14.00.00.31 sid.inpe.br/banon/2001/03.30.15.38 administrator {D 2021}</metadatalastupdate>
		<doi>10.1109/SIBGRAPI54419.2021.00025</doi>
		<citationkey>OliveiraPePiFeTaBlCe:2021:AuSePo</citationkey>
		<title>Automatic Segmentation of Posterior Fossa Structures in Pediatric Brain MRIs</title>
		<format>On-line</format>
		<year>2021</year>
		<numberoffiles>1</numberoffiles>
		<size>2279 KiB</size>
		<author>Oliveira, Hugo Neves de,</author>
		<author>Penteado, Larissa de Oliveira,</author>
		<author>Pimenta, José Luiz Maciel,</author>
		<author>Ferraciolli, Suely Fazio,</author>
		<author>Takahashi, Marcelo Straus,</author>
		<author>Bloch, Isabelle,</author>
		<author>Cesar Junior, Roberto Marcondes,</author>
		<affiliation>Instituto de Matemática e Estatística - Universidade de São Paulo </affiliation>
		<affiliation>Instituto de Matemática e Estatística - Universidade de São Paulo </affiliation>
		<affiliation>Instituto de Matemática e Estatística - Universidade de São Paulo </affiliation>
		<affiliation>Faculdade de Medicina - Universidade de São Paulo </affiliation>
		<affiliation>Faculdade de Medicina - Universidade de São Paulo </affiliation>
		<affiliation>Sorbonne Universite </affiliation>
		<affiliation>Instituto de Matemática e Estatística - Universidade de São Paulo</affiliation>
		<editor>Paiva, Afonso ,</editor>
		<editor>Menotti, David ,</editor>
		<editor>Baranoski, Gladimir V. G. ,</editor>
		<editor>Proença, Hugo Pedro ,</editor>
		<editor>Junior, Antonio Lopes Apolinario ,</editor>
		<editor>Papa, João Paulo ,</editor>
		<editor>Pagliosa, Paulo ,</editor>
		<editor>dos Santos, Thiago Oliveira ,</editor>
		<editor>e Sá, Asla Medeiros ,</editor>
		<editor>da Silveira, Thiago Lopes Trugillo ,</editor>
		<editor>Brazil, Emilio Vital ,</editor>
		<editor>Ponti, Moacir A. ,</editor>
		<editor>Fernandes, Leandro A. F. ,</editor>
		<editor>Avila, Sandra,</editor>
		<e-mailaddress>oliveirahugo@dcc.ufmg.br</e-mailaddress>
		<conferencename>Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)</conferencename>
		<conferencelocation>Gramado, RS, Brazil (virtual)</conferencelocation>
		<date>18-22 Oct. 2021</date>
		<publisher>IEEE Computer Society</publisher>
		<publisheraddress>Los Alamitos</publisheraddress>
		<booktitle>Proceedings</booktitle>
		<tertiarytype>Full Paper</tertiarytype>
		<transferableflag>1</transferableflag>
		<versiontype>finaldraft</versiontype>
		<keywords>biomedical image segmentation, posterior fossa structures, deep learning.</keywords>
		<abstract>Pediatric brain MRI is a useful tool in assessing the healthy cerebral development of children. Since many pathologies may manifest in the brainstem and cerebellum, the objective of this study was to have an automated segmentation of pediatric posterior fossa structures. These pathologies include a myriad of etiologies from congenital malformations to tumors, which are very prevalent in this age group. We propose a pediatric brain MRI segmentation pipeline composed of preprocessing, semantic segmentation and post-processing steps. Segmentation modules are composed of two ensembles of networks: generalists and specialists. The generalist networks are responsible for locating and roughly segmenting the brain areas, yielding regions of interest for each target organ. Specialist networks can then improve the segmentation performance for underrepresented organs by learning only from the regions of interest from the generalist networks. At last, post-processing consists in merging the specialist and generalist networks predictions, and performing late fusion across the distinct architectures to generate a final prediction. We conduct a thorough ablation analysis on this pipeline and assess the superiority of the methodology in segmenting the brain stem, 4th ventricle and cerebellum. The proposed methodology achieved a macro-averaged Dice index of 0.855 with respect to manual segmentation, with only 32 labeled volumes used during training. Additionally, average distances between automatically and manually segmented surfaces remained around 1mm for the three structures, while volumetry results revealed high agreement between manually labeled and predicted regions.</abstract>
		<language>en</language>
		<targetfile>SIBGRAPI_2021_Segmentation_ICr_Camera_Ready.pdf</targetfile>
		<usergroup>oliveirahugo@dcc.ufmg.br</usergroup>
		<visibility>shown</visibility>
		<documentstage>not transferred</documentstage>
		<mirrorrepository>sid.inpe.br/banon/2001/03.30.15.38.24</mirrorrepository>
		<nexthigherunit>8JMKD3MGPEW34M/45PQ3RS</nexthigherunit>
		<nexthigherunit>8JMKD3MGPEW34M/4742MCS</nexthigherunit>
		<citingitemlist>sid.inpe.br/sibgrapi/2021/11.12.11.46 4</citingitemlist>
		<hostcollection>sid.inpe.br/banon/2001/03.30.15.38</hostcollection>
		<agreement>agreement.html .htaccess .htaccess2</agreement>
		<lasthostcollection>sid.inpe.br/banon/2001/03.30.15.38</lasthostcollection>
		<url>http://sibgrapi.sid.inpe.br/rep-/sid.inpe.br/sibgrapi/2021/09.06.21.31</url>
	</metadata>
</metadatalist>