Super-Resolution Digital Pathology Image Processing of Bone Marrow Aspirate and Cytology Smears and Tissue Sections

Abstract

Background:Accurate digital pathology image analysis depends on high-quality images. As such, it is imperative to obtain digital images with high resolution for downstream data analysis. While hematoxylin and eosin (H&E)-stained tissue section slides from solid tumors contain three-dimensional information, these data have been ignored in digital pathology. In addition, in cytology and bone marrow aspirate smears, the three-dimensional nature of the specimen has precluded efficient analysis of such morphologic data. An individual image snapshot at a single focal distance is often not sufficient for accurate diagnoses and multiple whole-slide images at different focal distances are necessary for diagnostics.Materials and Methods:We describe a novel computational pipeline and processing program for obtaining a super-resolved image from multiple static images at different z-planes in overlapping but separate frames. This program, MULTI-Z, performs image alignment, Gaussian smoothing, and Laplacian filtering to construct a final super-resolution image from multiple images.Results:We applied this algorithm and program to images of cytology and H&E-stained sections and demonstrated significant improvements in both resolution and image quality by objective data analyses (24% increase in sharpness and focus).Conclusions:With the use of our program, super-resolved images of cytology and H&E-stained tissue sections can be obtained to potentially allow for more optimal downstream computational analysis. This method is applicable to whole-slide scanned images.

New software for automated cilia detection in cells (ACDC)

“…The notable performance of the software stems partly from its pre-processing algorithm. While we utilize standard equalization and smoothing operations seen in other studies [41–43], we also employ an enhanced binarizations step with a Gaussian filter to better account for the dynamic intensity variations of different cilia candidates (Fig. 2).…”

Application of Single-Cell Approaches to Study Myeloproliferative Neoplasm Biology

“… 75 , 76 , 77 In contrast to common solid tumors, image analysis has seen relatively limited application to disorders of the bone marrow, with most studies describing strategies for cell identification, quantification, and the resolution of specific leukemic differential diagnoses including B-ALL and common B-cell lymphoma/leukemia subtypes. 78 , 79 , 80 , 81 , 82 , 83 These machine learning strategies have generally relied on morphology-based criteria to distinguish tumor cell subtypes rather than interrogate tumor cells with the intention of gaining novel insights into disease biology. However, recently machine learning has been used to correlate bone marrow aspirate morphologic features with somatic mutations in myelodysplastic syndrome, with specific morphologic profiles linked to unique clinical characteristics.…”

Artificial Intelligence and Digital Microscopy Applications in Diagnostic Hematopathology

“…The program consists of constructing a super-resolution image from multiple images to create a three-dimensional digital picture. The algorithm allowed a significant improvement in image sharpness and resolution when applied to BM aspirate smears [33].…”

“…Other groups trained supervised models for segmentation and classification of ALL, mainly the support vector machine (SVM) algorithm. The overall accuracy for the detection of lymphoblasts and differentiating them from reactive lymphoid cells ranged from 74% to 99%, with a sensitivity as high as 100% and a specificity up to 95% [33]. The best outcomes were obtained by Bhattacharjee et al, who collected 120 cases and used pattern recognition-based segmentation to train and compare the results of multiple classifiers, including artificial neural network (ANN), k-nearest neighbor (kNN), k-means, and support vector machine (SVM) [47].…”