@article{MarzahlAubrevilleBertrametal.2020, author = {Marzahl, Christian and Aubreville, Marc and Bertram, Christof and Stayt, Jason and Jasensky, Anne-Katherine and Bartenschlager, Florian and Fragoso-Garcia, Marco and Barton, Ann K. and Elsemann, Svenja and Jabari, Samir and Krauth, Jens and Madhu, Prathmesh and Voigt, J{\"o}rn and Hill, Jenny and Klopfleisch, Robert and Maier, Andreas}, title = {Deep Learning-based quantification of pulmonary hemosiderophages in cytology slides}, volume = {10}, pages = {9795}, journal = {Scientific reports}, publisher = {Springer Nature}, address = {London}, issn = {2045-2322}, doi = {https://doi.org/10.1038/s41598-020-65958-2}, year = {2020}, abstract = {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.}, language = {en} } @article{BertramMarzahlBarteletal.2022, author = {Bertram, Christof and Marzahl, Christian and Bartel, Alexander and Stayt, Jason and Bonsembiante, Federico and Beeler-Marfisi, Janet and Barton, Ann K. and Brocca, Ginevra and Gelain, Maria Elena and Gl{\"a}sel, Agnes C. and du Preez, Kelly and Weiler, Kristina and Weissenbacher-Lang, Christiane and Breininger, Katharina and Aubreville, Marc and Maier, Andreas and Klopfleisch, Robert and Hill, Jenny}, title = {Cytologic scoring of equine exercise-induced pulmonary hemorrhage}, volume = {60}, journal = {Veterinary Pathology}, subtitle = {Performance of human experts and a deep learning-based algorithm}, number = {1}, publisher = {Sage}, address = {London}, issn = {1544-2217}, doi = {https://doi.org/10.1177/03009858221137582}, pages = {75 -- 85}, year = {2022}, abstract = {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.}, language = {en} } @inproceedings{MarzahlBertramWilmetal.2021, author = {Marzahl, Christian and Bertram, Christof and Wilm, Frauke and Voigt, J{\"o}rn and Barton, Ann K. and Klopfleisch, Robert and Breininger, Katharina and Maier, Andreas and Aubreville, Marc}, title = {Cell detection for asthma on partially annotated whole slide images}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2021: Proceedings, German Workshop on Medical Image Computing, Regensburg, March 7-9, 2021}, subtitle = {learning to be EXACT}, publisher = {Springer Vieweg}, address = {Wiesbaden}, isbn = {978-3-658-33197-9}, issn = {1431-472X}, doi = {https://doi.org/10.1007/978-3-658-33198-6_36}, pages = {147 -- 152}, year = {2021}, language = {en} }