Next Article in Journal
A Novel Immunomodulatory 27-Gene Signature to Predict Response to Neoadjuvant Immunochemotherapy for Primary Triple-Negative Breast Cancer
Previous Article in Journal
Risks and Benefits of Fiducial Marker Placement in Tumor Lesions for Robotic Radiosurgery: Technical Outcomes of 357 Implantations
Previous Article in Special Issue
Global Trends in Cancer Nanotechnology: A Qualitative Scientific Mapping Using Content-Based and Bibliometric Features for Machine Learning Text Classification
 
 
Article

Morphological Features Extracted by AI Associated with Spatial Transcriptomics in Prostate Cancer

1
Science for Life Laboratory, Department of Information Technology, Uppsala University, 752 37 Uppsala, Sweden
2
Department of Medical Epidemiology and Biostatistics, Karolinska Institute, 171 77 Stockholm, Sweden
3
Science for Life Laboratory, Department of Gene Technology, KTH Royal Institute of Technology, 171 65 Solna, Sweden
4
Department of Clinical Pathology, Uppsala University Hospital, 752 37 Uppsala, Sweden
5
Department of Pathology, Research Program in Systems Oncology, University of Helsinki, Helsinki University Hospital, 00100 Helsinki, Finland
6
Nuffield Department of Surgical Sciences, University of Oxford, Oxford OX3 7DQ, UK
7
Department of Cellular Pathology, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
8
Department of Urology, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 7LE, UK
*
Authors to whom correspondence should be addressed.
Academic Editors: Ognjen Arandjelović and Christine Decaestecker
Cancers 2021, 13(19), 4837; https://doi.org/10.3390/cancers13194837
Received: 14 July 2021 / Revised: 21 September 2021 / Accepted: 22 September 2021 / Published: 28 September 2021
(This article belongs to the Special Issue Machine Learning Techniques in Cancer)
Prostate cancer has very varied appearances when examined under the microscope, and it is difficult to distinguish clinically significant cancer from indolent disease. In this study, we use computer analyses inspired by neurons, so-called ‘neural networks’, to gain new insights into the connection between how tissue looks and underlying genes which program the function of prostate cells. Neural networks are ‘trained’ to carry out specific tasks, and training requires large numbers of training examples. Here, we show that a network pre-trained on different data can still identify biologically meaningful regions, without the need for additional training. The neural network interpretations matched independent manual assessment by human pathologists, and even resulted in more refined interpretation when considering the relationship with the underlying genes. This is a new way to automatically detect prostate cancer and its genetic characteristics without the need for human supervision, which means it could possibly help in making better treatment decisions.
Prostate cancer is a common cancer type in men, yet some of its traits are still under-explored. One reason for this is high molecular and morphological heterogeneity. The purpose of this study was to develop a method to gain new insights into the connection between morphological changes and underlying molecular patterns. We used artificial intelligence (AI) to analyze the morphology of seven hematoxylin and eosin (H&E)-stained prostatectomy slides from a patient with multi-focal prostate cancer. We also paired the slides with spatially resolved expression for thousands of genes obtained by a novel spatial transcriptomics (ST) technique. As both spaces are highly dimensional, we focused on dimensionality reduction before seeking associations between them. Consequently, we extracted morphological features from H&E images using an ensemble of pre-trained convolutional neural networks and proposed a workflow for dimensionality reduction. To summarize the ST data into genetic profiles, we used a previously proposed factor analysis. We found that the regions were automatically defined, outlined by unsupervised clustering, associated with independent manual annotations, in some cases, finding further relevant subdivisions. The morphological patterns were also correlated with molecular profiles and could predict the spatial variation of individual genes. This novel approach enables flexible unsupervised studies relating morphological and genetic heterogeneity using AI to be carried out. View Full-Text
Keywords: prostate cancer; morphological features; spatial transcriptomics; deep learning prostate cancer; morphological features; spatial transcriptomics; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Chelebian, E.; Avenel, C.; Kartasalo, K.; Marklund, M.; Tanoglidi, A.; Mirtti, T.; Colling, R.; Erickson, A.; Lamb, A.D.; Lundeberg, J.; Wählby, C. Morphological Features Extracted by AI Associated with Spatial Transcriptomics in Prostate Cancer. Cancers 2021, 13, 4837. https://doi.org/10.3390/cancers13194837

AMA Style

Chelebian E, Avenel C, Kartasalo K, Marklund M, Tanoglidi A, Mirtti T, Colling R, Erickson A, Lamb AD, Lundeberg J, Wählby C. Morphological Features Extracted by AI Associated with Spatial Transcriptomics in Prostate Cancer. Cancers. 2021; 13(19):4837. https://doi.org/10.3390/cancers13194837

Chicago/Turabian Style

Chelebian, Eduard, Christophe Avenel, Kimmo Kartasalo, Maja Marklund, Anna Tanoglidi, Tuomas Mirtti, Richard Colling, Andrew Erickson, Alastair D. Lamb, Joakim Lundeberg, and Carolina Wählby. 2021. "Morphological Features Extracted by AI Associated with Spatial Transcriptomics in Prostate Cancer" Cancers 13, no. 19: 4837. https://doi.org/10.3390/cancers13194837

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop