TY - CHAP A1 - Marzahl, Christian A1 - Aubreville, Marc A1 - Voigt, Jörn A1 - Maier, Andreas T1 - Classification of leukemic b-lymphoblast cells from blood smear microscopic images with an attention-based deep learning method and advanced augmentation techniques T2 - ISBI 2019 C-NMC challenge: classification in cancer cell imaging UR - https://doi.org/10.1007/978-981-15-0798-4_2 Y1 - 2019 UR - https://doi.org/10.1007/978-981-15-0798-4_2 SN - 978-981-15-0797-7 SN - 978-981-15-0798-4 SN - 978-981-15-0800-4 SN - 2195-271X SN - 2195-2728 SP - 13 EP - 22 PB - Springer CY - Singapore ER - TY - CHAP A1 - Bertram, Christof A1 - Veta, Mitko A1 - Marzahl, Christian A1 - Stathonikos, Nikolas A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Are Pathologist-Defined Labels Reproducible? Comparison of the TUPAC16 Mitotic Figure Dataset with an Alternative Set of Labels T2 - Interpretable and Annotation-Efficient Learning for Medical Image Computing UR - https://doi.org/10.1007/978-3-030-61166-8_22 KW - Breast cancer KW - Mitotic figures KW - Computer-aided annotation KW - Deep learning Y1 - 2020 UR - https://doi.org/10.1007/978-3-030-61166-8_22 SN - 978-3-030-61166-8 SN - 1611-3349 SP - 204 EP - 213 PB - Springer CY - Cham ER - TY - JOUR A1 - Ganz, Jonathan A1 - Marzahl, Christian A1 - Ammeling, Jonas A1 - Rosbach, Emely A1 - Richter, Barbara A1 - Puget, Chloé A1 - Denk, Daniela A1 - Demeter, Elena A. A1 - Tabaran, Flaviu A. A1 - Wasinger, Gabriel A1 - Lipnik, Karoline A1 - Tecilla, Marco A1 - Valentine, Matthew J. A1 - Dark, Michael A1 - Abele, Niklas A1 - Bolfa, Pompei A1 - Erber, Ramona A1 - Klopfleisch, Robert A1 - Merz, Sophie A1 - Donovan, Taryn A1 - Jabari, Samir A1 - Bertram, Christof A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Information mismatch in PHH3-assisted mitosis annotation leads to interpretation shifts in H&E slide analysis JF - Scientific Reports N2 - The count of mitotic figures (MFs) observed in hematoxylin and eosin (H&E)-stained slides is an important prognostic marker, as it is a measure for tumor cell proliferation. However, the identification of MFs has a known low inter-rater agreement. In a computer-aided setting, deep learning algorithms can help to mitigate this, but they require large amounts of annotated data for training and validation. Furthermore, label noise introduced during the annotation process may impede the algorithms’ performance. Unlike H&E, where identification of MFs is based mainly on morphological features, the mitosis-specific antibody phospho-histone H3 (PHH3) specifically highlights MFs. Counting MFs on slides stained against PHH3 leads to higher agreement among raters and has therefore recently been used as a ground truth for the annotation of MFs in H&E. However, as PHH3 facilitates the recognition of cells indistinguishable from H&E staining alone, the use of this ground truth could potentially introduce an interpretation shift and even label noise into the H&E-related dataset, impacting model performance. This study analyzes the impact of PHH3-assisted MF annotation on inter-rater reliability and object level agreement through an extensive multi-rater experiment. Subsequently, MF detectors, including a novel dual-stain detector, were evaluated on the resulting datasets to investigate the influence of PHH3-assisted labeling on the models’ performance. We found that the annotators’ object-level agreement significantly increased when using PHH3-assisted labeling (F1: 0.53 to 0.74). However, this enhancement in label consistency did not translate to improved performance for H&E-based detectors, neither during the training phase nor the evaluation phase. Conversely, the dual-stain detector was able to benefit from the higher consistency. This reveals an information mismatch between the H&E and PHH3-stained images as the cause of this effect, which renders PHH3-assisted annotations not well-aligned for use with H&E-based detectors. Based on our findings, we propose an improved PHH3-assisted labeling procedure. UR - https://doi.org/10.1038/s41598-024-77244-6 Y1 - 2024 UR - https://doi.org/10.1038/s41598-024-77244-6 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-53559 SN - 2045-2322 VL - 14 IS - 1 PB - Springer Nature CY - London ER - TY - JOUR A1 - Fragoso-Garcia, Marco A1 - Wilm, Frauke A1 - Bertram, Christof A1 - Merz, Sophie A1 - Schmidt, Anja A1 - Donovan, Taryn A1 - Fuchs-Baumgartinger, Andrea A1 - Bartel, Alexander A1 - Marzahl, Christian A1 - Diehl, Laura A1 - Puget, Chloe A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina A1 - Klopfleisch, Robert T1 - Automated diagnosis of 7 canine skin tumors using machine learning on H&E-stained whole slide images JF - Veterinary Pathology N2 - 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. UR - https://doi.org/10.1177/03009858231189205 KW - computer-aided diagnosis KW - computational pathology KW - digital pathology KW - dog KW - machine learning KW - skin KW - veterinary oncology Y1 - 2023 UR - https://doi.org/10.1177/03009858231189205 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-38321 SN - 0300-9858 VL - 60 IS - 6 SP - 865 EP - 875 PB - Sage CY - London ER - TY - JOUR A1 - Aubreville, Marc A1 - Stathonikos, Nikolas A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Hoeve, Natalie ter A1 - Ciompi, Francesco A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Donovan, Taryn A1 - Maier, Andreas A1 - Breen, Jack A1 - Ravikumar, Nishant A1 - Chung, Youjin A1 - Park, Jinah A1 - Nateghi, Ramin A1 - Pourakpour, Fattaneh A1 - Fick, Rutger H. J. A1 - Ben Hadj, Saima A1 - Jahanifar, Mostafa A1 - Shepard, Adam A1 - Dexl, Jakob A1 - Wittenberg, Thomas A1 - Kondo, Satoshi A1 - Lafarge, Maxime W. A1 - Kolezer, Viktor H. A1 - Liang, Jingtang A1 - Wang, Yubo A1 - Long, Xi A1 - Liu, Jingxin A1 - Razavi, Salar A1 - Khademi, April A1 - Yang, Sen A1 - Wang, Xiyue A1 - Erber, Ramona A1 - Klang, Andrea A1 - Lipnik, Karoline A1 - Bolfa, Pompei A1 - Dark, Michael A1 - Wasinger, Gabriel A1 - Veta, Mitko A1 - Breininger, Katharina T1 - Mitosis domain generalization in histopathology images — The MIDOG challenge JF - Medical Image Analysis UR - https://doi.org/10.1016/j.media.2022.102699 KW - Domain generalization KW - Histopathology KW - Challenge KW - Deep Learning KW - Mitosis Y1 - 2022 UR - https://doi.org/10.1016/j.media.2022.102699 SN - 1361-8423 SN - 1361-8415 VL - 2023 IS - 84 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Theelke, Luisa A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas A1 - Aubreville, Marc A1 - Breininger, Katharina T1 - Iterative Cross-Scanner Registration for Whole Slide Images T2 - 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) UR - https://doi.org/10.1109/ICCVW54120.2021.00071 KW - Pathology KW - Computer vision KW - Image resolution KW - Microscopy KW - Conferences KW - Estimation KW - Registers Y1 - 2021 UR - https://doi.org/10.1109/ICCVW54120.2021.00071 SN - 978-1-6654-0191-3 SN - 2473-9944 N1 - Eine frei zugängliche Version ist veröffentlicht unter: https://openaccess.thecvf.com/content/ICCV2021W/CDPath/html/Theelke_Iterative_Cross-Scanner_Registration_for_Whole_Slide_Images_ICCVW_2021_paper.html SP - 582 EP - 590 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Stathonikos, Nikolas A1 - ter Hoeve, Natalie A1 - Ciompi, Francesco A1 - Klopfleisch, Robert A1 - Veta, Mitko A1 - Donovan, Taryn A1 - Marzahl, Christian A1 - Wilm, Frauke A1 - Breininger, Katharina A1 - Maier, Andreas T1 - Quantifying the Scanner-Induced Domain Gap in Mitosis Detection T2 - MIDL: Medical Imaging with Deep Learning 2021 Y1 - 2021 UR - https://2021.midl.io/papers/i6 PB - MIDL Foundation CY - Nijmegen ER - TY - CHAP A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Breininger, Katharina A1 - Aubreville, Marc ED - Aubreville, Marc ED - Zimmerer, David ED - Heinrich, Mattias T1 - Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge T2 - Biomedical Image Registration, Domain Generalisation and Out-of-Distribution Analysis : MICCAI 2021 Challenges UR - https://doi.org/10.1007/978-3-030-97281-3_1 Y1 - 2022 UR - https://doi.org/10.1007/978-3-030-97281-3_1 SN - 978-3-030-97281-3 SP - 5 EP - 13 PB - Springer CY - Cham ER - TY - JOUR A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Bartel, Alexander A1 - Stayt, Jason A1 - Bonsembiante, Federico A1 - Beeler-Marfisi, Janet A1 - Barton, Ann K. A1 - Brocca, Ginevra A1 - Gelain, Maria Elena A1 - Gläsel, Agnes C. A1 - du Preez, Kelly A1 - Weiler, Kristina A1 - Weissenbacher-Lang, Christiane A1 - Breininger, Katharina A1 - Aubreville, Marc A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Hill, Jenny T1 - Cytologic scoring of equine exercise-induced pulmonary hemorrhage: Performance of human experts and a deep learning-based algorithm JF - Veterinary Pathology N2 - Exercise-induced pulmonary hemorrhage (EIPH) is a relevant respiratory disease in sport horses, which can be diagnosed by examination of bronchoalveolar lavage fluid (BALF) cells using the total hemosiderin score (THS). The aim of this study was to evaluate the diagnostic accuracy and reproducibility of annotators and to validate a deep learning-based algorithm for the THS. Digitized cytological specimens stained for iron were prepared from 52 equine BALF samples. Ten annotators produced a THS for each slide according to published methods. The reference methods for comparing annotator’s and algorithmic performance included a ground truth dataset, the mean annotators’ THSs, and chemical iron measurements. Results of the study showed that annotators had marked interobserver variability of the THS, which was mostly due to a systematic error between annotators in grading the intracytoplasmatic hemosiderin content of individual macrophages. Regarding overall measurement error between the annotators, 87.7% of the variance could be reduced by using standardized grades based on the ground truth. The algorithm was highly consistent with the ground truth in assigning hemosiderin grades. Compared with the ground truth THS, annotators had an accuracy of diagnosing EIPH (THS of < or ≥ 75) of 75.7%, whereas, the algorithm had an accuracy of 92.3% with no relevant differences in correlation with chemical iron measurements. The results show that deep learning-based algorithms are useful for improving reproducibility and routine applicability of the THS. For THS by experts, a diagnostic uncertainty interval of 40 to 110 is proposed. THSs within this interval have insufficient reproducibility regarding the EIPH diagnosis. UR - https://doi.org/10.1177/03009858221137582 KW - artificial intelligence KW - automated image analysis KW - bronchoalveolar lavage fluid KW - computational pathology KW - digital pathology KW - equine KW - pulmonary hemorrhage KW - respiratory disease KW - total hemosiderin score Y1 - 2022 UR - https://doi.org/10.1177/03009858221137582 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-35196 SN - 1544-2217 VL - 60 IS - 1 SP - 75 EP - 85 PB - Sage CY - London ER - TY - CHAP A1 - Wilm, Frauke A1 - Bertram, Christof A1 - Marzahl, Christian A1 - Bartel, Alexander A1 - Donovan, Taryn A1 - Assenmacher, Charles-Antoine A1 - Becker, Kathrin A1 - Bennett, Mark A1 - Corner, Sarah M. A1 - Cossic, Brieuc A1 - Denk, Daniela A1 - Dettwiler, Martina A1 - Garcia Gonzalez, Beatriz A1 - Gurtner, Corinne A1 - Heier, Annabelle A1 - Lehmbecker, Annika A1 - Merz, Sophie A1 - Plog, Stephanie A1 - Schmidt, Anja A1 - Sebastian, Franziska A1 - Smedley, Rebecca C. A1 - Tecilla, Marco A1 - Thaiwong, Tuddow A1 - Breininger, Katharina A1 - Kiupel, Matti A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Influence of inter-annotator variability on automatic mitotic figure assessment T2 - Bildverarbeitung für die Medizin 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_56 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_56 SN - 978-3-658-33198-6 SP - 241 EP - 246 PB - Springer CY - Wiesbaden ER - TY - CHAP A1 - Bertram, Christof A1 - Donovan, Taryn A1 - Tecilla, Marco A1 - Bartenschlager, Florian A1 - Fragoso-Garcia, Marco A1 - Wilm, Frauke A1 - Marzahl, Christian A1 - Breininger, Katharina A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Dataset on bi- and multi-nucleated tumor cells in canine cutaneous mast cell tumors T2 - Bildverarbeitung für die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7–9, 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_33 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_33 SN - 978-3-658-33197-9 SN - 978-3-658-33198-6 SN - 1431-472X SP - 134 EP - 139 PB - Springer Vieweg CY - Wiesbaden ER - TY - CHAP A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Wilm, Frauke A1 - Voigt, Jörn A1 - Barton, Ann K. A1 - Klopfleisch, Robert A1 - Breininger, Katharina A1 - Maier, Andreas A1 - Aubreville, Marc T1 - Cell detection for asthma on partially annotated whole slide images BT - learning to be EXACT T2 - Bildverarbeitung für die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7–9, 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_36 Y1 - 2021 UR - https://doi.org/10.1007/978-3-658-33198-6_36 SN - 978-3-658-33197-9 SN - 978-3-658-33198-6 SN - 1431-472X SP - 147 EP - 152 PB - Springer Vieweg CY - Wiesbaden ER - TY - JOUR A1 - Wilm, Frauke A1 - Fragoso-Garcia, Marco A1 - Marzahl, Christian A1 - Qiu, Jingna A1 - Puget, Chloé A1 - Diehl, Laura A1 - Bertram, Christof A1 - Klopfleisch, Robert A1 - Maier, Andreas A1 - Breininger, Katharina A1 - Aubreville, Marc T1 - Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset JF - Scientific Data N2 - 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. UR - https://doi.org/10.1038/s41597-022-01692-w Y1 - 2022 UR - https://doi.org/10.1038/s41597-022-01692-w UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-28741 SN - 2052-4463 VL - 9 PB - Springer CY - London ER - TY - JOUR A1 - Aubreville, Marc A1 - Bertram, Christof A1 - Donovan, Taryn A1 - Marzahl, Christian A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research JF - Scientific data N2 - Canine mammary carcinoma (CMC) has been used as a model to investigate the pathogenesis of human breast cancer and the same grading scheme is commonly used to assess tumor malignancy in both. One key component of this grading scheme is the density of mitotic figures (MF). Current publicly available datasets on human breast cancer only provide annotations for small subsets of whole slide images (WSIs). We present a novel dataset of 21 WSIs of CMC completely annotated for MF. For this, a pathologist screened all WSIs for potential MF and structures with a similar appearance. A second expert blindly assigned labels, and for non-matching labels, a third expert assigned the final labels. Additionally, we used machine learning to identify previously undetected MF. Finally, we performed representation learning and two-dimensional projection to further increase the consistency of the annotations. Our dataset consists of 13,907 MF and 36,379 hard negatives. We achieved a mean F1-score of 0.791 on the test set and of up to 0.696 on a human breast cancer dataset. UR - https://doi.org/10.1038/s41597-020-00756-z Y1 - 2020 UR - https://doi.org/10.1038/s41597-020-00756-z UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11765 SN - 2052-4463 VL - 7 PB - Springer CY - London ER - TY - JOUR A1 - Marzahl, Christian A1 - Hill, Jenny A1 - Stayt, Jason A1 - Bienzle, Dorothee A1 - Welker, Lutz A1 - Wilm, Frauke A1 - Voigt, Jörn A1 - Aubreville, Marc A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Breininger, Katharina A1 - Bertram, Christof T1 - Inter-species cell detection - datasets on pulmonary hemosiderophages in equine, human and feline specimens JF - Scientific Data N2 - Pulmonary hemorrhage (P-Hem) occurs among multiple species and can have various causes. Cytology of bronchoalveolar lavage fluid (BALF) using a 5-tier scoring system of alveolar macrophages based on their hemosiderin content is considered the most sensitive diagnostic method. We introduce a novel, fully annotated multi-species P-Hem dataset, which consists of 74 cytology whole slide images (WSIs) with equine, feline and human samples. To create this high-quality and high-quantity dataset, we developed an annotation pipeline combining human expertise with deep learning and data visualisation techniques. We applied a deep learning-based object detection approach trained on 17 expertly annotated equine WSIs, to the remaining 39 equine, 12 human and 7 feline WSIs. The resulting annotations were semi-automatically screened for errors on multiple types of specialised annotation maps and finally reviewed by a trained pathologist. Our dataset contains a total of 297,383 hemosiderophages classified into five grades. It is one of the largest publicly available WSIs datasets with respect to the number of annotations, the scanned area and the number of species covered. UR - https://doi.org/10.1038/s41597-022-01389-0 Y1 - 2022 UR - https://doi.org/10.1038/s41597-022-01389-0 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-29319 SN - 2052-4463 VL - 9 PB - Springer CY - London ER - TY - JOUR A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Marzahl, Christian A1 - Maier, Andreas A1 - Klopfleisch, Robert T1 - A large-scale dataset for mitotic figure assessment on whole slide images of canine cutaneous mast cell tumor JF - Scientific data N2 - We introduce a novel, large-scale dataset for microscopy cell annotations. The dataset includes 32 whole slide images (WSI) of canine cutaneous mast cell tumors, selected to include both low grade cases as well as high grade cases. The slides have been completely annotated for mitotic figures and we provide secondary annotations for neoplastic mast cells, inflammatory granulocytes, and mitotic figure look-alikes. Additionally to a blinded two-expert manual annotation with consensus, we provide an algorithm-aided dataset, where potentially missed mitotic figures were detected by a deep neural network and subsequently assessed by two human experts. We included 262,481 annotations in total, out of which 44,880 represent mitotic figures. For algorithmic validation, we used a customized RetinaNet approach, followed by a cell classification network. We find F1-Scores of 0.786 and 0.820 for the manually labelled and the algorithm-aided dataset, respectively. The dataset provides, for the first time, WSIs completely annotated for mitotic figures and thus enables assessment of mitosis detection algorithms on complete WSIs as well as region of interest detection algorithms. UR - https://doi.org/10.1038/s41597-019-0290-4 Y1 - 2019 UR - https://doi.org/10.1038/s41597-019-0290-4 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-11838 SN - 2052-4463 VL - 6 PB - Springer CY - London ER - TY - INPR A1 - Marzahl, Christian A1 - Bertram, Christof A1 - Aubreville, Marc A1 - Petrick, Anne A1 - Weiler, Kristina A1 - Gläsel, Agnes C. A1 - Fragoso-Garcia, Marco A1 - Merz, Sophie A1 - Bartenschlager, Florian A1 - Hoppe, Judith A1 - Langenhagen, Alina A1 - Jasensky, Anne-Katherine A1 - Voigt, Jörn A1 - Klopfleisch, Robert A1 - Maier, Andreas T1 - Are Fast Labeling Methods Reliable? A Case Study of Computer-Aided Expert Annotations on Microscopy Slides UR - https://doi.org/10.48550/arXiv.2004.05838 Y1 - 2020 UR - https://doi.org/10.48550/arXiv.2004.05838 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Bertram, Christof A1 - Veta, Mitko A1 - Marzahl, Christian A1 - Stathonikos, Nikolas A1 - Maier, Andreas A1 - Klopfleisch, Robert A1 - Aubreville, Marc T1 - Are pathologist-defined labels reproducible? Comparison of the TUPAC16 mitotic figure dataset with an alternative set of labels UR - https://doi.org/10.48550/arXiv.2007.05351 Y1 - 2020 UR - https://doi.org/10.48550/arXiv.2007.05351 PB - arXiv CY - Ithaca ER -