Abstract
Nucleus detection is a fundamental task in histological image analysis and an important tool for many follow up analyses. It is known that sample preparation and scanning procedure of histological slides introduce a great amount of variability to the histological images and poses challenges for automated nucleus detection. Here, we studied the effect of histopathological sample fixation on the accuracy of a deep learning based nuclei detection model trained with hematoxylin and eosin stained images. We experimented with training data that includes three methods of fixation; PAXgene, formalin and frozen, and studied the detection accuracy results of various convolutional neural networks. Our results indicate that the variability introduced during sample preparation affects the generalization of a model and should be considered when building accurate and robust nuclei detection algorithms. Our dataset includes over 67 000 annotated nuclei locations from 16 patients and three different sample fixation types. The dataset provides excellent basis for building an accurate and robust nuclei detection model, and combined with unsupervised domain adaptation, the workflow allows generalization to images from unseen domains, including different tissues and images from different labs.
Highlights
H ISTOPATHOLOGICAL examination is an important step in diagnosis of many diseases
We implemented a workflow for nuclei detection that utilizes pseudo-label based unsupervised domain adaptation in order to generalize to images from new domains, including different tissues and images from different labs
We studied the effect of three histopathological sample fixation types on the accuracy of a nuclei detection trained with H&E stained images
Summary
H ISTOPATHOLOGICAL examination is an important step in diagnosis of many diseases. Examination usually includes analysis of nuclei morphology, nucleus detection is a fundamental step for many follow up analyses, such as phenotyping on a single-cell level [1], or cancer grading [2]. Building a robust and generalizable nuclei detection model is a challenging task due to the high amount of variability present in histological images. This variability is caused by the underlying biological variation, such as variation in nuclei shape, size, and texture of different tissue types and by the technical variation introduced during the tissue preparation, such as in fixation process, and scanning procedure [4]. While freezing tissue typically provides excellent preservation of biomolecules, freezing disrupts the structure of the tissue and is not used for routine morphologic analysis. PAXgene is an alcohol-based fixative that, in contrast to formalin, simultaneously preserves both tissue morphology and biomolecule integrity. We studied the feasibility of PAXgene fixation for molecular and diagnostic studies [5], but the fixation effect on modern deep learning based analytics remains unknown
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
