Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
03 08 2020
03 08 2020
Historique:
received:
26
08
2019
accepted:
04
05
2020
entrez:
5
8
2020
pubmed:
5
8
2020
medline:
15
12
2020
Statut:
epublish
Résumé
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.
Identifiants
pubmed: 32747665
doi: 10.1038/s41598-020-65958-2
pii: 10.1038/s41598-020-65958-2
pmc: PMC7398908
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
9795Références
Ahmad, K. A., Bennett, M. M., Ahmad, S. F., Clark, R. H. & Tolia, V. N. Morbidity and mortality with early pulmonary haemorrhage in preterm neonates. Archives of Disease in Childhood-Fetal and Neonatal Edition 104, F63–F68 (2019).
doi: 10.1136/archdischild-2017-314172
Maldonado, F., Parambil, J. G., Yi, E., Decker, P. A. & Ryu, J. H. Haemosiderin-laden macrophages in the bronchoalveolar lavage fluid of patients with diffuse alveolar damage. European Respiratory Journal 33, 1361–1366 (2009).
doi: 10.1183/09031936.00119108
van Houten, J. et al. Pulmonary hemorrhage in premature infants after treatment with synthetic surfactant: an autopsy evaluation. The Journal of Pediatrics 120, S40–S44 (1992).
doi: 10.1016/S0022-3476(05)81232-6
Golde, D. W., Drew, W. L., Klein, H. Z., Finley, T. N. & Cline, M. J. Occult pulmonary haemorrhage in leukaemia. Br Med J 2, 166–168 (1975).
doi: 10.1136/bmj.2.5964.166
Martínez-Martínez, M. U., Herrera-van Oostdam, D. A. & Abud-Mendoza, C. Diffuse alveolar hemorrhage in autoimmune diseases. Current rheumatology reports 19, 27 (2017).
Kahn, F. W., Jones, J. M. & England, D. M. Diagnosis of pulmonary hemorrhage in the immunocompromised host. American Review of Respiratory Disease 136, 155–160 (1987).
doi: 10.1164/ajrccm/136.1.155
Hopkins, S. R. et al. Intense exercise impairs the integrity of the pulmonary blood-gas barrier in elite athletes. Am J Respir Crit Care Med 155, 1090–1094 (1997).
doi: 10.1164/ajrccm.155.3.9116992
Epp, T. et al. Evidence supporting exercise-induced pulmonary haemorrhage in racing greyhounds. Comp. Exerc. Physiol. 5, 21–32 (2008).
Morley, P. S., Bromberek, J., Saulez, M. N., Hinchcliff, K. W. & Guthrie, A. J. Exercise-induced pulmonary haemorrhage impairs racing performance in t horoughbred racehorses. Equine Vet. J. 47, 358–365 (2015).
doi: 10.1111/evj.12368
Hinchcliff, K. W. et al. Association between exercise-induced pulmonary hemorrhage and performance in thoroughbred racehorses. Journal of the American Veterinary Medical Association 227, 768–774 (2005).
doi: 10.2460/javma.2005.227.768
Birks, E. K., Durando, M. M. & McBride, S. Exercise-induced pulmonary hemorrhage. Veterinary Clinics: Equine Practice 19, 87–100 (2003).
doi: 10.1016/S0749-0739(02)00068-8
Hinchcliff, K. et al. Exercise induced pulmonary hemorrhage in horses: American college of veterinary internal medicine consensus statement. J. Vet. Intern. Med. 29, 743–758 (2015).
doi: 10.1111/jvim.12593
Hoffman, A. M. Bronchoalveolar lavage: sampling technique and guidelines for cytologic preparation and interpretation. Veterinary Clinics of North America: Equine Practice 24, 423–435 (2008).
pubmed: 18652963
Depecker, M. et al. Comparison of two cytological methods for detecting pulmonary haemorrhage in horses. Veterinary Record 177, 305–305 (2015).
doi: 10.1136/vr.103332
Denk, H., Künzele, H., Plenk, H., Rüschoff, J. & Seller, W. Romeis mikroskopische technik. Urban und Schwarzenberg, München-Wien. Baltimore 439–450 (1989).
Doucet, M. Y. & Viel, L. Alveolar macrophage graded hemosiderin score from bronchoalveolar lavage in horses with exercise-induced pulmonary hemorrhage and controls. J Vet Intern Med 16, 281–286 (2002).
doi: 10.1111/j.1939-1676.2002.tb02370.x
Waithe, D. et al. Object detection networks and augmented reality for cellular detection in fluorescence microscopy acquisition and analysis. bioRxiv 544833 (2019).
Baykal, E., Dogan, H., Ercin, M. E., Ersoz, S. & Ekinci, M. Modern convolutional object detectors for nuclei detection on pleural effusion cytology images. Multimedia Tools and Applications 1–20 (2019).
Aubreville, M., Bertram, C., Klopfleisch, R. & Maier, A. Field Of Interest Proposal for Augmented Mitotic Cell Count: A Comparison of Two Networks. In SciTePress (ed.) Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, 30–37, https://doi.org/10.5220/0007365700300037 (2019).
Lowe, D. G. et al. Object recognition from local scale-invariant features. In ICCV, 99, 1150–1157 (1999).
Ojala, T., Pietikäinen, M. & Harwood, D. A comparative study of texture measures with classification based on featured distributions. PATTERN RECOGN 29, 51–59 (1996).
doi: 10.1016/0031-3203(95)00067-4
Dalal, N. & Triggs, B. Histograms of oriented gradients for human detection. In CVPR, vol. 1, 886–893 (IEEE Computer Society, 2005).
Maier, A., Syben, C., Lasser, T. & Riess, C. A gentle introduction to deep learning in medical image processing. Zeitschrift für Medizinische Physik 29, 86–101 (2019).
doi: 10.1016/j.zemedi.2018.12.003
Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. In Adv Neural Inf Process Syst, 91–99 (2015).
Liu, W. et al. Ssd: Single shot multibox detector. In ECCV, 21–37 (Springer, 2016).
Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. In ICCV, 2980–2988 (2017).
Everingham, M., Van Gool, L., Williams, C. K., Winn, J. & Zisserman, A. The pascal visual object classes (voc) challenge. International journal of computer vision 88, 303–338 (2010).
doi: 10.1007/s11263-009-0275-4
Lin, T.-Y. et al. Microsoft coco: Common objects in context. In ECCV, 740–755 (Springer, 2014).
Zou, Z., Shi, Z., Guo, Y. & Ye, J. Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055 (2019).
Mundhenk, T. N., Konjevod, G., Sakla, W. A. & Boakye, K. A large contextual dataset for classification, detection and counting of cars with deep learning. In ICCV, 785–800 (Springer, 2016).
Litjens, G. et al. A survey on deep learning in medical image analysis. Med Imag Anal 42, 60–88 (2017).
doi: 10.1016/j.media.2017.07.005
Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Med Image Comput Comput Assist Interv, 234–241 (Springer, 2015).
Ferlaino, M. et al. Towards deep cellular phenotyping in placental histology. arXiv preprint arXiv:1804.03270 (2018).
Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: Unified, real-time object detection. In Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 779–788 (2016).
Huang, J. et al. Speed/accuracy trade-offs for modern convolutional object detectors. In Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 7310–7311 (2017).
Aubreville, M., Bertram, C., Klopfleisch, R. & Maier, A. Sliderunner. In Bildverarbeitung für die Medizin 2018, 309–314 (Springer, 2018).
He, K., Zhang, X., Ren, S. & Sun, J. Deep Residual Learning for Image Recognition. In CVPR, 770–778 (IEEE, 2016).
Russakovsky, O. et al. Imagenet large scale visual recognition challenge. Int J Comput Vis 115, 211–252 (2015).
doi: 10.1007/s11263-015-0816-y
Lin, T.-Y. et al. Feature pyramid networks for object detection. In Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 2117–2125 (2017).
Paszke, A. et al. Automatic differentiation in PyTorch. In NIPS Autodiff Workshop (2017).
Bertram, C. A. et al. Computerized calculation of mitotic distribution in canine cutaneous mast cell tumor sections: Mitotic count is area dependent. Veterinary Pathology (in press) (2019).