Field of Interest Proposal for Augmented Mitotic Cell Count: Comparison of Two Convolutional Networks

Aubreville, Marc; Bertram, Christof A.; Klopfleisch, Robert; Maier, Andreas

doi:10.5220/0007365700300037

Cited by 3 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Importantly, selection of the evaluated hpf has been poorly standardized with vague selection criteria. 4,44 Therefore, we hypothesized that variable area selection may be another factor influencing the MC regardless of the tumor type. Most grading systems as well as general recommendations request that mitotic figures should be counted in a single area composed of 10 contiguous, nonoverlapping hpf located in the tumor region with the highest mitotic activity.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Computerized Calculation of Mitotic Count Distribution in Canine Cutaneous Mast Cell Tumor Sections: Mitotic Count Is Area Dependent

et al. 2019

Self Cite

View full text Add to dashboard Cite

Mitotic count (MC) is an important element for grading canine cutaneous mast cell tumors (ccMCTs) and is determined in ten consecutive high-power fields with the highest mitotic activity. However, there is variability in area selection between pathologists. In this study, the MC distribution and the effect of area selection on the MC were analyzed in ccMCTs. Two pathologists independently annotated all mitotic figures in whole-slide images of 28 ccMCTs (ground truth). Automated image analysis was used to examine the ground truth distribution of the MC throughout the tumor section area, which was compared with the manual MCs of 11 pathologists.Computerized analysis demonstrated high variability of the MC within different tumor areas. There were 6 MCTs with consistently low MCs (MC<7 in all tumor areas), 13 cases with mostly high MCs (MC ≥7 in ≥75% of 10-hpf-areas) and 9 borderline cases with variable MCs around 7, which is a cut-off value for ccMCT grading. There was inconsistency among pathologists in identifying the areas with the highest density of mitotic figures throughout the three ccMCT groups; only 51.9% of the counts were consistent with the highest 25% of the ground truth MC distribution. Regardless, there was substantial agreement between pathologists in detecting tumors with MC≥7.Falsely low MCs below 7 mainly occurred in 4/9 borderline cases that had very few ground truth areas with MC≥7. The findings of this study highlight the need to further standardize how to select the region of the tumor in which to determine the MC. Keywords: Area selection, high-power field, mitotic activity, mitotic figure distribution, tumor grading, tumor periphery. 3 Aubreville M, Bertram CA, Klopfleisch R, Maier A. Field of interest proposal for augmented mitotic cell count: Comparison of two convolutional networks.

show abstract

mentioning

confidence: 99%

“…Therefore, scanning the tumor section and selecting the one area with the highest MC might be problematic. 4,44 Some studies circumvented this problem by counting mitotic figures in randomly selected hpf. 19,22,41 Others chose the most cellular or most anaplastic part of the tumor as well as excluding areas with necrosis, hemorrhage, and other artifacts.…”

mentioning

confidence: 99%

Computerized Calculation of Mitotic Count Distribution in Canine Cutaneous Mast Cell Tumor Sections: Mitotic Count Is Area Dependent

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…To date, the topic of hemosiderophage classification and quantification has not been approached using computer vision methods. However, there have been numerous studies in the past decades with the goal of detecting cells, nuclei and mitotic figures for multiple modalities like digital fluorescence microscopy and histopathology [17][18][19] . Historically, this started as hand-crafted low-level feature extraction [20][21][22] .…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides

Marzahl

Aubreville

Bertram

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

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 intrarater variability, we propose our automated object detection pipeline, enabling accurate, reproducible and quick EIPH scoring in WSI. Patients with pulmonary hemorrhage (P-Hem) suffer from repeated bleeding into the lungs, which can result in dyspnea and if untreated, may have life threatening consequences 1. There are various causes which lead to P-Hem, including drug abuse, premature birth, leukaemia, autoimmune disorders and immunodeficiencies 2-6. In this paper, we focus on a special subtype of P-Hem called exercise-induced pulmonary hemorrhage (EIPH) in horses. Although EIPH also affects healthy human athletes 7 and racing greyhounds 8 , it is diagnosed most commonly in racing horses and causes reduced athletic performance 9-12. The gold standard for diagnosis of P-Hem in humans and equine animals is to perform cytology of bronchoalveolar lavage fluid (BALF) 4,13 using a scoring system as explained by Golde et al. 4. The red blood cells of the bleeding are degraded into an iron-storage complex called hemosiderin by alveolar macrophages. Hemosiderin-laden macrophages are called hemosiderophages. Prior to microscopic evaluation, the cells are extracted by the BALF procedure and stained with Perlss' Prussian Blue 14 or Turnbull's Blue 15 in order to visualise the iron pigments contained in the hemosiderin. According to the commonly used scoring system (macrophages hemosiderin score) by Golde et al. 4 , alveolar macrophages can be distinguished into five grades depending on their hemosiderin content. This scoring system is based on the principle that a higher score correlates with increased alveolar bleeding 16 .

show abstract

“…To date, the topic of hemosiderophage classification and quantification has not been solved using computer vision methods. However, there have been numerous studies in the past decades with the goal of detecting cells, nuclei and mitosis figures for multiple modalities like digital fluorescence microscopy and histopathology [14][15][16] . Historically, these methods started as hand-crafted low-level feature extraction methods [17][18][19] .…”

Section: Related Workmentioning

confidence: 99%

“…For the first session (V0) the f1 score per grade is 0 = 0.86 (σ =0.08), 1 = 0.74 (σ =0.08), 2 = 0.62 (σ =0.11), 3 = 0.50 (σ =0 16…”

mentioning

confidence: 99%

Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides

Marzahl,

Aubreville,

Bertram

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Exercise-induced pulmonary hemorrhage (EIPH) is a common syndrome 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. Methods: 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. Results: Our deep learning-based approach reached a concordance of 0.85, partially exceeding human expert concordance (0.68 to 0.86, µ=0.73, σ =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. Conclusion: 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.

show abstract

Field of Interest Proposal for Augmented Mitotic Cell Count: Comparison of Two Convolutional Networks

Cited by 3 publications

References 21 publications

Computerized Calculation of Mitotic Count Distribution in Canine Cutaneous Mast Cell Tumor Sections: Mitotic Count Is Area Dependent

Computerized Calculation of Mitotic Count Distribution in Canine Cutaneous Mast Cell Tumor Sections: Mitotic Count Is Area Dependent

Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides

Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides

Contact Info

Product

Resources

About