Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides

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 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 .

Reducing Domain Shift For Mitosis Detection Using Preprocessing Homogenizers

“…Our algorithm was trained on MItosis DOmain Generalization (MIDOG) dataset only.The algorithm consists of a homogenizer followed by RetinaNet [2].…”

A completely annotated whole slide image dataset of canine breast cancer to aid human breast cancer research

“…For the detection of mitotic figures on whole slide images (WSIs), we employed two state-of-the-art methods: As the primary stage, we used a customized 26 RetinaNet 16 approach. We used RetinaNet, since it represents a good performance to complexity trade-off, and is available for many machine learning frameworks.…”

Revamping the Cytological Quantitation of Lipid Laden Macrophages in Bronchoalveolar Lavage

“…Theoretically, the presence of exogenous lipid scavenged form the distal airways and alveoli would indicate aspiration of fatcontaining food or liquid, either from dysfunctional swallowing or gastro esophageal reflux.However, studies reach conflicting conclusions regarding the accuracy of LLMI in predicting aspiration [5][6][7].Furthermore, there are striking differences in LLMI results across different studies, such that the control groups of some studies had higher indices than other studies' aspiration groups [8,9].Thus, LLMI, as currently assessed appears to have insufficient sensitivity and specificity to be clinically useful. There are several ways in which lipid laden macrophages can be better quantified.Marzahl et al [11].used a deep learning-based method of annotated cytology from whole slide digital images of BAL to achieve high concordance in quantification of hemosiderophages.…”