<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>1441</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>134</pageFirst>
    <pageLast>139</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Springer Vieweg</publisherName>
    <publisherPlace>Wiesbaden</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2022-02-24</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Dataset on bi- and multi-nucleated tumor cells in canine cutaneous mast cell tumors</title>
    <parentTitle language="eng">Bildverarbeitung für die Medizin 2021: Proceedings, German Workshop&#13;
on Medical Image Computing, Regensburg, March 7–9, 2021</parentTitle>
    <identifier type="issn">1431-472X</identifier>
    <identifier type="isbn">978-3-658-33197-9</identifier>
    <identifier type="isbn">978-3-658-33198-6</identifier>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1007/978-3-658-33198-6_33</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_conferenceName">Bildverarbeitung für die Medizin 2021, Regensburg (Germany), 07-09.03.2021</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Taryn</first_name>
      <last_name>Donovan</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Tecilla</last_name>
    </author>
    <author>
      <first_name>Florian</first_name>
      <last_name>Bartenschlager</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Frauke</first_name>
      <last_name>Wilm</last_name>
    </author>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Katharina</first_name>
      <last_name>Breininger</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
  </doc>
  <doc>
    <id>1178</id>
    <completedYear>2020</completedYear>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>10</pageNumber>
    <edition/>
    <issue/>
    <volume>10</volume>
    <articleNumber>9795</articleNumber>
    <type>article</type>
    <publisherName>Springer Nature</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-02-10</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Deep Learning-based quantification of pulmonary hemosiderophages in cytology slides</title>
    <abstract language="eng">Exercise-induced pulmonary hemorrhage (EIPH) is a common condition in sport horses with negative impact on performance. Cytology of bronchoalveolar lavage fluid by use of a scoring system is considered the most sensitive diagnostic method. Macrophages are classified depending on the degree of cytoplasmic hemosiderin content. The current gold standard is manual grading, which is however monotonous and time-consuming. We evaluated state-of-the-art deep learning-based methods for single cell macrophage classification and compared them against the performance of nine cytology experts and evaluated inter- and intra-observer variability. Additionally, we evaluated object detection methods on a novel data set of 17 completely annotated cytology whole slide images (WSI) containing 78,047 hemosiderophages. Our deep learning-based approach reached a concordance of 0.85, partially exceeding human expert concordance (0.68 to 0.86, mean of 0.73, SD of 0.04). Intra-observer variability was high (0.68 to 0.88) and inter-observer concordance was moderate (Fleiss’ kappa = 0.67). Our object detection approach has a mean average precision of 0.66 over the five classes from the whole slide gigapixel image and a computation time of below two minutes. To mitigate the high inter- and intra-rater variability, we propose our automated object detection pipeline, enabling accurate, reproducible and quick EIPH scoring in WSI.</abstract>
    <parentTitle language="eng">Scientific Reports</parentTitle>
    <identifier type="issn">2045-2322</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-11783</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1038/s41598-020-65958-2</enrichment>
    <enrichment key="THI_openaccess">ja</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_articleversion">published</enrichment>
    <licence>Creative Commons BY 4.0</licence>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Jason</first_name>
      <last_name>Stayt</last_name>
    </author>
    <author>
      <first_name>Anne-Katherine</first_name>
      <last_name>Jasensky</last_name>
    </author>
    <author>
      <first_name>Florian</first_name>
      <last_name>Bartenschlager</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Ann K.</first_name>
      <last_name>Barton</last_name>
    </author>
    <author>
      <first_name>Svenja</first_name>
      <last_name>Elsemann</last_name>
    </author>
    <author>
      <first_name>Samir</first_name>
      <last_name>Jabari</last_name>
    </author>
    <author>
      <first_name>Jens</first_name>
      <last_name>Krauth</last_name>
    </author>
    <author>
      <first_name>Prathmesh</first_name>
      <last_name>Madhu</last_name>
    </author>
    <author>
      <first_name>Jörn</first_name>
      <last_name>Voigt</last_name>
    </author>
    <author>
      <first_name>Jenny</first_name>
      <last_name>Hill</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <collection role="open_access" number="">open_access</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/1178/s41598-020-65958-2.pdf</file>
  </doc>
  <doc>
    <id>1179</id>
    <completedYear>2020</completedYear>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>11</pageNumber>
    <edition/>
    <issue/>
    <volume>10</volume>
    <articleNumber>16447</articleNumber>
    <type>article</type>
    <publisherName>Springer Nature</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-02-10</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region</title>
    <abstract language="eng">Manual count of mitotic figures, which is determined in the tumor region with the highest mitotic activity, is a key parameter of most tumor grading schemes. It can be, however, strongly dependent on the area selection due to uneven mitotic figure distribution in the tumor section. We aimed to assess the question, how significantly the area selection could impact the mitotic count, which has a known high inter-rater disagreement. On a data set of 32 whole slide images of H&amp;E-stained canine cutaneous mast cell tumor, fully annotated for mitotic figures, we asked eight veterinary pathologists (five board-certified, three in training) to select a field of interest for the mitotic count. To assess the potential difference on the mitotic count, we compared the mitotic count of the selected regions to the overall distribution on the slide. Additionally, we evaluated three deep learning-based methods for the assessment of highest mitotic density: In one approach, the model would directly try to predict the mitotic count for the presented image patches as a regression task. The second method aims at deriving a segmentation mask for mitotic figures, which is then used to obtain a mitotic density. Finally, we evaluated a two-stage object-detection pipeline based on state-of-the-art architectures to identify individual mitotic figures. We found that the predictions by all models were, on average, better than those of the experts. The two-stage object detector performed best and outperformed most of the human pathologists on the majority of tumor cases. The correlation between the predicted and the ground truth mitotic count was also best for this approach (0.963–0.979). Further, we found considerable differences in position selection between pathologists, which could partially explain the high variance that has been reported for the manual mitotic count. To achieve better inter-rater agreement, we propose to use a computer-based area selection for support of the pathologist in the manual mitotic count.</abstract>
    <parentTitle language="eng">Scientific reports</parentTitle>
    <identifier type="issn">2045-2322</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-11794</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1038/s41598-020-73246-2</enrichment>
    <enrichment key="THI_articleversion">published</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">ja</enrichment>
    <licence>Creative Commons BY 4.0</licence>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Corinne</first_name>
      <last_name>Gurtner</last_name>
    </author>
    <author>
      <first_name>Martina</first_name>
      <last_name>Dettwiler</last_name>
    </author>
    <author>
      <first_name>Anja</first_name>
      <last_name>Schmidt</last_name>
    </author>
    <author>
      <first_name>Florian</first_name>
      <last_name>Bartenschlager</last_name>
    </author>
    <author>
      <first_name>Sophie</first_name>
      <last_name>Merz</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Olivia</first_name>
      <last_name>Kershaw</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <collection role="open_access" number="">open_access</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/1179/s41598-020-73246-2.pdf</file>
  </doc>
  <doc>
    <id>3881</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>preprint</type>
    <publisherName>arXiv</publisherName>
    <publisherPlace>Ithaca</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology</title>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.48550/arXiv.2211.16141</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">nein</enrichment>
    <enrichment key="THI_furtherversion">https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/4070</enrichment>
    <author>
      <first_name>Frauke</first_name>
      <last_name>Wilm</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Nikolas</first_name>
      <last_name>Stathonikos</last_name>
    </author>
    <author>
      <first_name>Mathias</first_name>
      <last_name>Öttl</last_name>
    </author>
    <author>
      <first_name>Jingna</first_name>
      <last_name>Qiu</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Katharina</first_name>
      <last_name>Breininger</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Histopathology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Domain Shift</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Representation Learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Barlow Twins</value>
    </subject>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
  </doc>
  <doc>
    <id>1917</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>24</pageFirst>
    <pageLast>32</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-03-11</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Are Fast Labeling Methods Reliable? A Case Study of Computer-Aided Expert Annotations on Microscopy Slides</title>
    <parentTitle language="eng">Medical Image Computing and Computer Assisted Intervention – MICCAI 2020</parentTitle>
    <identifier type="issn">1611-3349</identifier>
    <identifier type="isbn">978-3-030-59710-8</identifier>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1007/978-3-030-59710-8_3</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_conferenceName">Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, online, 04.-08.10.2020</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_furtherversion">https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/1257</enrichment>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Anne</first_name>
      <last_name>Petrick</last_name>
    </author>
    <author>
      <first_name>Kristina</first_name>
      <last_name>Weiler</last_name>
    </author>
    <author>
      <first_name>Agnes C.</first_name>
      <last_name>Gläsel</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Sophie</first_name>
      <last_name>Merz</last_name>
    </author>
    <author>
      <first_name>Florian</first_name>
      <last_name>Bartenschlager</last_name>
    </author>
    <author>
      <first_name>Judith</first_name>
      <last_name>Hoppe</last_name>
    </author>
    <author>
      <first_name>Alina</first_name>
      <last_name>Langenhagen</last_name>
    </author>
    <author>
      <first_name>Anne-Katherine</first_name>
      <last_name>Jasensky</last_name>
    </author>
    <author>
      <first_name>Jörn</first_name>
      <last_name>Voigt</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Pathology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Microscopy</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Computer-aided labelling</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Expert-algorithm collaboration</value>
    </subject>
  </doc>
  <doc>
    <id>4070</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>5</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace>Piscataway</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology</title>
    <parentTitle language="eng">2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)</parentTitle>
    <identifier type="isbn">978-1-6654-7358-3</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T05:24:19Z","timestamp":1695705859406},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,18]],"date-time":"2023-04-18T00:00:00Z","timestamp":1681776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher"},{"DOI":"10.13039\/100018696","name":"Health","doi-asserted-by":"publisher"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,4,18]]},"DOI":"10.1109\/isbi53787.2023.10230458","type":"proceedings-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T17:23:07Z","timestamp":1693588987000},"source":"Crossref","is-referenced-by-count":0,"title":["Mind the Gap: Scanner-Induced Domain Shifts Pose Challenges for Representation Learning in Histopathology"],"prefix":"10.1109","author":[{"given":"Frauke","family":"Wilm","sequence":"first","affiliation":[{"name":"Friedrich-Alexander-Universit&amp;#x00E4;t Erlangen-N&amp;#x00FC;rnberg,Pattern Recognition Lab,Germany"}]},{"given":"Marco","family":"Fragoso","sequence":"additional","affiliation":[{"name":"Freie Universit&amp;#x00E4;t Berlin,Institute of Veterinary Pathology,Germany"}]},{"given":"Christof A.","family":"Bertram","sequence":"additional","affiliation":[{"name":"University of Veterinary Medicine,Institute of Pathology,Vienna,Austria"}]},{"given":"Nikolas","family":"Stathonikos","sequence":"additional","affiliation":[{"name":"University Medical Centre Utrecht,Pathology Department,The Netherlands"}]},{"given":"Mathias","family":"\u00d6ttl","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit&amp;#x00E4;t Erlangen-N&amp;#x00FC;rnberg,Pattern Recognition Lab,Germany"}]},{"given":"Jingna","family":"Qiu","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit&amp;#x00E4;t Erlangen-N&amp;#x00FC;rnberg,Department AIBE,Germany"}]},{"given":"Robert","family":"Klopfleisch","sequence":"additional","affiliation":[{"name":"Freie Universit&amp;#x00E4;t Berlin,Institute of Veterinary Pathology,Germany"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit&amp;#x00E4;t Erlangen-N&amp;#x00FC;rnberg,Pattern Recognition Lab,Germany"}]},{"given":"Marc","family":"Aubreville","sequence":"additional","affiliation":[{"name":"Technische Hochschule Ingolstadt,Ingolstadt,Germany"}]},{"given":"Katharina","family":"Breininger","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit&amp;#x00E4;t Erlangen-N&amp;#x00FC;rnberg,Department AIBE,Germany"}]}],"member":"263","reference":[{"key":"ref13","first-page":"181","article-title":"Robust quad-tree based registration on whole slide images","author":"marzahl","year":"2021","journal-title":"Workshop on Computational Pathology MICCAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-56537-7_81"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","article-title":"CAnine CuTaneous Cancer Histology dataset (version 1)","author":"wilm","year":"2022","journal-title":"The Cancer Imaging Archive"},{"key":"ref10","first-page":"12310","article-title":"Barlow Twins: Self-supervised learning via redundancy reduction","volume":"139","author":"zbontar","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref2","article-title":"Quantifying the scanner-induced domain gap in mitosis detection","author":"aubreville","year":"2021","journal-title":"Medical Imaging with Deep Learning (MIDL)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-73246-2"},{"key":"ref17","first-page":"240","article-title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","author":"sudre","year":"2017","journal-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support"},{"key":"ref16","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01692-w"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/54\/9\/018"},{"key":"ref8","first-page":"309","article-title":"Predicting what you already know helps: Provable self-supervised learning","volume":"34","author":"lee","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"tian","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.59275\/j.melba.2022-f9a1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3032060"},{"key":"ref3","article-title":"Learning domain-invariant representations of histological images","volume":"6","author":"lafarge","year":"2019","journal-title":"Frontiers of Medicine"},{"key":"ref6","article-title":"Self-supervised learning from a multi-view perspective","author":"tsai","year":"2021","journal-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"}],"event":{"name":"2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)","location":"Cartagena, Colombia","start":{"date-parts":[[2023,4,18]]},"end":{"date-parts":[[2023,4,21]]}},"container-title":["2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10230311\/10230322\/10230458.pdf?arnumber=10230458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T17:57:09Z","timestamp":1695664629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10230458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,18]]},"references-count":19,"URL":"http:\/\/dx.doi.org\/10.1109\/isbi53787.2023.10230458","relation":{},"published":{"date-parts":[[2023,4,18]]}}}</enrichment>
    <enrichment key="local_crossrefDocumentType">proceedings-article</enrichment>
    <enrichment key="local_crossrefLicence">https://doi.org/10.15223/policy-029</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorFirstName_6,PersonAuthorLastName_6,PersonAuthorFirstName_7,PersonAuthorLastName_7,PersonAuthorFirstName_8,PersonAuthorLastName_8,PersonAuthorFirstName_9,PersonAuthorLastName_9,PersonAuthorFirstName_10,PersonAuthorLastName_10,Enrichmentconference_title,Enrichmentconference_place,PublisherName,TitleMain_1,TitleParent_1,CompletedYear,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="conference_title">2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)</enrichment>
    <enrichment key="conference_place">Cartagena, Colombia</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1109/ISBI53787.2023.10230458</enrichment>
    <enrichment key="THI_conferenceName">2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena (Colombia), 18.-21.04.2023</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_furtherversion">https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/3881</enrichment>
    <author>
      <first_name>Frauke</first_name>
      <last_name>Wilm</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Nikolas</first_name>
      <last_name>Stathonikos</last_name>
    </author>
    <author>
      <first_name>Mathias</first_name>
      <last_name>Öttl</last_name>
    </author>
    <author>
      <first_name>Jingna</first_name>
      <last_name>Qiu</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Katharina</first_name>
      <last_name>Breininger</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Histopathology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Domain Shift</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Representation Learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Barlow Twins</value>
    </subject>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
  </doc>
  <doc>
    <id>3832</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>865</pageFirst>
    <pageLast>875</pageLast>
    <pageNumber/>
    <edition/>
    <issue>6</issue>
    <volume>60</volume>
    <articleNumber/>
    <type>article</type>
    <publisherName>Sage</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Automated diagnosis of 7 canine skin tumors using machine learning on H&amp;E-stained whole slide images</title>
    <abstract language="eng">Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation ( n = 35 WSIs), and test sets ( n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95% (133/140 WSIs), with a patch-level precision of 85%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98% (137/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types.</abstract>
    <parentTitle language="eng">Veterinary Pathology</parentTitle>
    <identifier type="issn">0300-9858</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-38321</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T04:09:58Z","timestamp":1690690198246},"reference-count":31,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T00:00:00Z","timestamp":1690588800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003141","name":"consejo nacional de ciencia y tecnolog\u00eda","doi-asserted-by":"publisher"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Vet Pathol"],"abstract":"&lt;jats:p&gt; Microscopic evaluation of hematoxylin and eosin-stained slides is still the diagnostic gold standard for a variety of diseases, including neoplasms. Nevertheless, intra- and interrater variability are well documented among pathologists. So far, computer assistance via automated image analysis has shown potential to support pathologists in improving accuracy and reproducibility of quantitative tasks. In this proof of principle study, we describe a machine-learning-based algorithm for the automated diagnosis of 7 of the most common canine skin tumors: trichoblastoma, squamous cell carcinoma, peripheral nerve sheath tumor, melanoma, histiocytoma, mast cell tumor, and plasmacytoma. We selected, digitized, and annotated 350 hematoxylin and eosin-stained slides (50 per tumor type) to create a database divided into training, n = 245 whole-slide images (WSIs), validation ( n = 35 WSIs), and test sets ( n = 70 WSIs). Full annotations included the 7 tumor classes and 6 normal skin structures. The data set was used to train a convolutional neural network (CNN) for the automatic segmentation of tumor and nontumor classes. Subsequently, the detected tumor regions were classified patch-wise into 1 of the 7 tumor classes. A majority of patches-approach led to a tumor classification accuracy of the network on the slide-level of 95% (133\/140 WSIs), with a patch-level precision of 85%. The same 140 WSIs were provided to 6 experienced pathologists for diagnosis, who achieved a similar slide-level accuracy of 98% (137\/140 correct majority votes). Our results highlight the feasibility of artificial intelligence-based methods as a support tool in diagnostic oncologic pathology with future applications in other species and tumor types. &lt;\/jats:p&gt;","DOI":"10.1177\/03009858231189205","type":"journal-article","created":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T07:33:23Z","timestamp":1690616003000},"update-policy":"http:\/\/dx.doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated diagnosis of 7 canine skin tumors using machine learning on H&amp;amp;E-stained whole slide images"],"prefix":"10.1177","author":[{"given":"Marco","family":"Fragoso-Garcia","sequence":"first","affiliation":[{"name":"Freie Universit\u00e4t, Berlin, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9065-0554","authenticated-orcid":false,"given":"Frauke","family":"Wilm","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2402-9997","authenticated-orcid":false,"given":"Christof A.","family":"Bertram","sequence":"additional","affiliation":[{"name":"University of Veterinary Medicine, Vienna, Austria"}]},{"given":"Sophie","family":"Merz","sequence":"additional","affiliation":[{"name":"IDEXX GmbH, Kornwestheim, Germany"}]},{"given":"Anja","family":"Schmidt","sequence":"additional","affiliation":[{"name":"IDEXX GmbH, Kornwestheim, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-5740-9550","authenticated-orcid":false,"given":"Taryn","family":"Donovan","sequence":"additional","affiliation":[{"name":"Schwarzman Animal Medical Center, New York, NY"}]},{"given":"Andrea","family":"Fuchs-Baumgartinger","sequence":"additional","affiliation":[{"name":"University of Veterinary Medicine, Vienna, Austria"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1280-6138","authenticated-orcid":false,"given":"Alexander","family":"Bartel","sequence":"additional","affiliation":[{"name":"Freie Universit\u00e4t, Berlin, Germany"}]},{"given":"Christian","family":"Marzahl","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"given":"Laura","family":"Diehl","sequence":"additional","affiliation":[{"name":"Freie Universit\u00e4t, Berlin, Germany"}]},{"given":"Chloe","family":"Puget","sequence":"additional","affiliation":[{"name":"Freie Universit\u00e4t, Berlin, Germany"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5294-5247","authenticated-orcid":false,"given":"Marc","family":"Aubreville","sequence":"additional","affiliation":[{"name":"Technische Hochschule Ingolstadt, Ingolstadt, Germany"}]},{"given":"Katharina","family":"Breininger","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6308-0568","authenticated-orcid":false,"given":"Robert","family":"Klopfleisch","sequence":"additional","affiliation":[{"name":"Freie Universit\u00e4t, Berlin, Germany"}]}],"member":"179","published-online":{"date-parts":[[2023,7,29]]},"reference":[{"key":"bibr1-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1002\/path.5331"},{"key":"bibr2-03009858231189205","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2016-0386-RA"},{"key":"bibr3-03009858231189205","first-page":"309","volume-title":"Bildverarbeitung f\u00fcr die Medizin 2018","volume":"2018","author":"Aubreville M"},{"key":"bibr4-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/03009858211067478"},{"key":"bibr5-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/0300985819890686"},{"key":"bibr6-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/0300985818755254"},{"key":"bibr7-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/03009858221137582"},{"key":"bibr8-03009858231189205","doi-asserted-by":"publisher","DOI":"10.3390\/vetsci8010003"},{"key":"bibr9-03009858231189205","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1180773"},{"key":"bibr10-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2559.2004.01860.x"},{"key":"bibr11-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"bibr12-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1097\/00000478-200011000-00017"},{"key":"bibr13-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/0300985818789466"},{"key":"bibr14-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"bibr15-03009858231189205","first-page":"2424","volume":"2016","author":"Hou L","year":"2016","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"bibr16-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1292\/jvms.19-0248"},{"key":"bibr17-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-65958-2"},{"key":"bibr18-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01389-0"},{"key":"bibr19-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1002\/9781119181200"},{"key":"bibr20-03009858231189205","doi-asserted-by":"publisher","DOI":"10.4132\/jptm.2019.12.31"},{"key":"bibr21-03009858231189205","first-page":"595","volume":"98","author":"Norgan A","year":"2018","journal-title":"Lab Invest"},{"key":"bibr22-03009858231189205","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"Ronneberger O","year":"2015"},{"key":"bibr23-03009858231189205","doi-asserted-by":"publisher","DOI":"10.4103\/2153-3539.112693"},{"key":"bibr24-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"bibr25-03009858231189205","doi-asserted-by":"publisher","DOI":"10.3389\/fvets.2021.640944"},{"key":"bibr26-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/0192623320975841"},{"key":"bibr27-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.09.049"},{"key":"bibr28-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1177\/014107689308601204"},{"key":"bibr29-03009858231189205","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01692-w"},{"key":"bibr30-03009858231189205","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2018-0343-RA"},{"key":"bibr31-03009858231189205","author":"Tan M","year":"2019","journal-title":"ArXiv"}],"container-title":["Veterinary Pathology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/03009858231189205","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/03009858231189205","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/03009858231189205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,29]],"date-time":"2023-07-29T07:33:34Z","timestamp":1690616014000},"score":1,"resource":{"primary":{"URL":"http:\/\/journals.sagepub.com\/doi\/10.1177\/03009858231189205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,29]]},"references-count":31,"alternative-id":["10.1177\/03009858231189205"],"URL":"http:\/\/dx.doi.org\/10.1177\/03009858231189205","relation":{},"ISSN":["0300-9858","1544-2217"],"issn-type":[{"value":"0300-9858","type":"print"},{"value":"1544-2217","type":"electronic"}],"subject":["General Veterinary"],"published":{"date-parts":[[2023,7,29]]}}}</enrichment>
    <enrichment key="local_crossrefDocumentType">journal-article</enrichment>
    <enrichment key="local_crossrefLicence">https://creativecommons.org/licenses/by/4.0/</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">SubjectUncontrolled_1,PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorIdentifierOrcid_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorFirstName_6,PersonAuthorLastName_6,PersonAuthorIdentifierOrcid_6,PersonAuthorFirstName_7,PersonAuthorLastName_7,PersonAuthorFirstName_8,PersonAuthorLastName_8,PersonAuthorIdentifierOrcid_8,PersonAuthorFirstName_9,PersonAuthorLastName_9,PersonAuthorFirstName_10,PersonAuthorLastName_10,PersonAuthorFirstName_11,PersonAuthorLastName_11,PersonAuthorFirstName_12,PersonAuthorLastName_12,PersonAuthorFirstName_13,PersonAuthorLastName_13,PersonAuthorIdentifierOrcid_13,PersonAuthorFirstName_14,PersonAuthorLastName_14,PersonAuthorFirstName_15,PersonAuthorLastName_15,PersonAuthorIdentifierOrcid_15,PublisherName,TitleMain_1,Language,TitleAbstract_1,TitleParent_1,CompletedYear,IdentifierIssn,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="THI_articleversion">published</enrichment>
    <enrichment key="THI_openaccess">ja</enrichment>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1177/03009858231189205</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <licence>Creative Commons BY 4.0</licence>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Frauke</first_name>
      <last_name>Wilm</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Sophie</first_name>
      <last_name>Merz</last_name>
    </author>
    <author>
      <first_name>Anja</first_name>
      <last_name>Schmidt</last_name>
    </author>
    <author>
      <first_name>Taryn</first_name>
      <last_name>Donovan</last_name>
    </author>
    <author>
      <first_name>Andrea</first_name>
      <last_name>Fuchs-Baumgartinger</last_name>
    </author>
    <author>
      <first_name>Alexander</first_name>
      <last_name>Bartel</last_name>
    </author>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Laura</first_name>
      <last_name>Diehl</last_name>
    </author>
    <author>
      <first_name>Chloe</first_name>
      <last_name>Puget</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Katharina</first_name>
      <last_name>Breininger</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>computer-aided diagnosis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>computational pathology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>digital pathology</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>dog</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>machine learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>skin</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>veterinary oncology</value>
    </subject>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/3832/fragoso-garcia-et-al-2023-automated-diagnosis.pdf</file>
  </doc>
  <doc>
    <id>2874</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>13</pageNumber>
    <edition/>
    <issue/>
    <volume>9</volume>
    <articleNumber>588</articleNumber>
    <type>article</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>London</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2022-10-13</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset</title>
    <abstract language="eng">Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.</abstract>
    <parentTitle language="eng">Scientific Data</parentTitle>
    <identifier type="issn">2052-4463</identifier>
    <identifier type="urn">urn:nbn:de:bvb:573-28741</identifier>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.1038/s41597-022-01692-w</enrichment>
    <enrichment key="THI_articleversion">published</enrichment>
    <enrichment key="THI_review">peer-review</enrichment>
    <enrichment key="THI_openaccess">ja</enrichment>
    <enrichment key="THI_DownloadUrl">https://github.com/DeepPathology/CanineCutaneousTumors</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <licence>Creative Commons BY 4.0</licence>
    <author>
      <first_name>Frauke</first_name>
      <last_name>Wilm</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Jingna</first_name>
      <last_name>Qiu</last_name>
    </author>
    <author>
      <first_name>Chloé</first_name>
      <last_name>Puget</last_name>
    </author>
    <author>
      <first_name>Laura</first_name>
      <last_name>Diehl</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
    <author>
      <first_name>Katharina</first_name>
      <last_name>Breininger</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="19309">Fakultät Informatik</collection>
    <collection role="institutes" number="19379">AImotion Bavaria</collection>
    <thesisPublisher>Technische Hochschule Ingolstadt</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-haw/files/2874/s41597-022-01692-w.pdf</file>
  </doc>
  <doc>
    <id>1257</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>10</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <articleNumber/>
    <type>preprint</type>
    <publisherName>arXiv</publisherName>
    <publisherPlace>Ithaca</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2022-02-15</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Are Fast Labeling Methods Reliable? A Case Study of Computer-Aided Expert Annotations on Microscopy Slides</title>
    <enrichment key="THI_relatedIdentifier">https://doi.org/10.48550/arXiv.2004.05838</enrichment>
    <enrichment key="THI_review">nein</enrichment>
    <enrichment key="THI_openaccess">nein</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="THI_furtherversion">https://opus4.kobv.de/opus4-haw/frontdoor/index/index/docId/1917</enrichment>
    <author>
      <first_name>Christian</first_name>
      <last_name>Marzahl</last_name>
    </author>
    <author>
      <first_name>Christof</first_name>
      <last_name>Bertram</last_name>
    </author>
    <author>
      <first_name>Marc</first_name>
      <last_name>Aubreville</last_name>
    </author>
    <author>
      <first_name>Anne</first_name>
      <last_name>Petrick</last_name>
    </author>
    <author>
      <first_name>Kristina</first_name>
      <last_name>Weiler</last_name>
    </author>
    <author>
      <first_name>Agnes C.</first_name>
      <last_name>Gläsel</last_name>
    </author>
    <author>
      <first_name>Marco</first_name>
      <last_name>Fragoso-Garcia</last_name>
    </author>
    <author>
      <first_name>Sophie</first_name>
      <last_name>Merz</last_name>
    </author>
    <author>
      <first_name>Florian</first_name>
      <last_name>Bartenschlager</last_name>
    </author>
    <author>
      <first_name>Judith</first_name>
      <last_name>Hoppe</last_name>
    </author>
    <author>
      <first_name>Alina</first_name>
      <last_name>Langenhagen</last_name>
    </author>
    <author>
      <first_name>Anne-Katherine</first_name>
      <last_name>Jasensky</last_name>
    </author>
    <author>
      <first_name>Jörn</first_name>
      <last_name>Voigt</last_name>
    </author>
    <author>
      <first_name>Robert</first_name>
      <last_name>Klopfleisch</last_name>
    </author>
    <author>
      <first_name>Andreas</first_name>
      <last_name>Maier</last_name>
    </author>
  </doc>
</export-example>
