Abstract

PurposeCancers are almost always diagnosed by morphologic features in tissue sections. In this context, machine learning tools provide new opportunities to describe tumor immune cell interactions within the tumor microenvironment and thus provide phenotypic information that might be predictive for the response to immunotherapy.MethodsWe develop a machine learning approach using variational networks for joint image denoising and classification of tissue sections for melanoma, which is an established model tumor for immuno-oncology research. The manual annotation of real training data would require substantial user interaction of experienced pathologists for each single training image, and the training of larger networks would rely on a very large number of such data sets with ground truth annotation. To overcome this bottleneck, we synthesize training data together with a proper tissue structure classification. To this end, a stochastic data generation process is used to mimic cell morphology, cell distribution and tissue architecture in the tumor microenvironment. Particular components of this tool are random placement and rotation of a large number of patches for presegmented cell nuclei, a stochastic fast marching approach to mimic the geometry of cells and texture generation based on a color covariance analysis of real data. Here, the generated training data reflect a large range of interaction patterns.ResultsIn several applications to histological tissue sections, we analyze the efficiency and accuracy of the proposed approach. As a result, depending on the scenario considered, almost all cells and nuclei which ought to be detected are actually marked as classified and hardly any misclassifications occur.ConclusionsThe proposed method allows for a computer-aided screening of histological tissue sections utilizing variational networks with a particular emphasis on tumor immune cell interactions and on the robust cell nuclei classification.

Highlights

  • Solid cancers are almost always diagnosed by histopathologists, mainly based on hematoxylin and eosin (H&E)-stained slides

  • International Journal of Computer Assisted Radiology and Surgery (2019) 14:587–599 anti-PD1- and/or anti-CTLA4 antibody in different tumor entities has proven the importance of tumor immune cell interactions within the tumor microenvironment [12]

  • Scenario 3 we focus on the detection of tumor cell nuclei in H&E-stained melanoma section images neglecting any cell interactions

Read more

Summary

Introduction

Solid cancers are almost always diagnosed by histopathologists, mainly based on hematoxylin and eosin (H&E)-stained slides. Molecular and genomic approaches have revolutionized our understanding of tumor biology and are incorporated for diagnostic, prognostic and therapeutic purposes. There is a growing need to identify predictive biomarkers and to enhance our understanding of the complex interactions between the immune system and tumor cells. The evaluation of phenotypic information of tumor cells and the surrounding cells, including immune, vessel and stroma cells by detailed histopathological analyses, has become highly clinically relevant. Technological advances in digital pathology, imaging and computing are currently creating new tools for exploring relationships between morphology and molecular and genomic alterations in cancer tissues. Machine learning has emerged as an important image analysis tool that provides exciting opportunities to improve our understanding of cancer biology, immunology and patient care

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

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 call