1
|
Smeets EMM, Trajkovic-Arsic M, Geijs D, Karakaya S, van Zanten M, Brosens LAA, Feuerecker B, Gotthardt M, Siveke JT, Braren R, Ciompi F, Aarntzen EHJG. Histology-Based Radiomics for [ 18F]FDG PET Identifies Tissue Heterogeneity in Pancreatic Cancer. J Nucl Med 2024:jnumed.123.266262. [PMID: 38782455 DOI: 10.2967/jnumed.123.266262] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2023] [Revised: 04/22/2024] [Indexed: 05/25/2024] Open
Abstract
Radiomics features can reveal hidden patterns in a tumor but usually lack an underlying biologic rationale. In this work, we aimed to investigate whether there is a correlation between radiomics features extracted from [18F]FDG PET images and histologic expression patterns of a glycolytic marker, monocarboxylate transporter-4 (MCT4), in pancreatic cancer. Methods: A cohort of pancreatic ductal adenocarcinoma patients (n = 29) for whom both tumor cross sections and [18F]FDG PET/CT scans were available was used to develop an [18F]FDG PET radiomics signature. By using immunohistochemistry for MCT4, we computed density maps of MCT4 expression and extracted pathomics features. Cluster analysis identified 2 subgroups with distinct MCT4 expression patterns. From corresponding [18F]FDG PET scans, radiomics features that associate with the predefined MCT4 subgroups were identified. Results: Complex heat map visualization showed that the MCT4-high/heterogeneous subgroup was correlating with a higher MCT4 expression level and local variation. This pattern linked to a specific [18F]FDG PET signature, characterized by a higher SUVmean and SUVmax and second-order radiomics features, correlating with local variation. This MCT4-based [18F]FDG PET signature of 7 radiomics features demonstrated prognostic value in an independent cohort of pancreatic cancer patients (n = 71) and identified patients with worse survival. Conclusion: Our cross-modal pipeline allows the development of PET scan signatures based on immunohistochemical analysis of markers of a particular biologic feature, here demonstrated on pancreatic cancer using intratumoral MCT4 expression levels to select [18F]FDG PET radiomics features. This study demonstrated the potential of radiomics scores to noninvasively capture intratumoral marker heterogeneity and identify a subset of pancreatic ductal adenocarcinoma patients with a poor prognosis.
Collapse
Affiliation(s)
- Esther M M Smeets
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Marija Trajkovic-Arsic
- German Cancer Consortium, partner site Essen, a partnership between DKFZ and University Hospital Essen, Essen, Germany
- Bridge Institute of Experimental Tumor Therapy and Division of Solid Tumor Translational Oncology, West German Cancer Center, University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - Daan Geijs
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Sinan Karakaya
- German Cancer Consortium, partner site Essen, a partnership between DKFZ and University Hospital Essen, Essen, Germany
- Bridge Institute of Experimental Tumor Therapy and Division of Solid Tumor Translational Oncology, West German Cancer Center, University Hospital Essen, University of Duisburg-Essen, Essen, Germany
| | - Monica van Zanten
- Department of Pathology, Canisius Wilhelmina Ziekenhuis, Nijmegen, The Netherlands
| | - Lodewijk A A Brosens
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Benedikt Feuerecker
- Department of Nuclear Medicine, School of Medicine, Technical University of Munich, Munich, Germany
- Department of Radiology, School of Medicine, Technical University of Munich, Munich, Germany
- German Cancer Consortium, partner site Munich, a partnership between DKFZ and Technical University of Munich, Munich, Germany
- Department of Radiology, Ludwig Maximilians University, Munich, Germany; and
| | - Martin Gotthardt
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Jens T Siveke
- German Cancer Consortium, partner site Essen, a partnership between DKFZ and University Hospital Essen, Essen, Germany
- Bridge Institute of Experimental Tumor Therapy and Division of Solid Tumor Translational Oncology, West German Cancer Center, University Hospital Essen, University of Duisburg-Essen, Essen, Germany
- National Center for Tumor Diseases West, Campus Essen, Essen, Germany
| | - Rickmer Braren
- Department of Radiology, School of Medicine, Technical University of Munich, Munich, Germany
| | - Francesco Ciompi
- Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Erik H J G Aarntzen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands;
| |
Collapse
|
2
|
Ahmed HS. BEYOND TRADITIONAL TOOLS: EXPLORING CONVOLUTIONAL NEURAL NETWORKS AS INNOVATIVE PROGNOSTIC MODELS IN PANCREATIC DUCTAL ADENOCARCINOMA. ARQUIVOS DE GASTROENTEROLOGIA 2024; 61:e23107. [PMID: 38511794 DOI: 10.1590/s0004-2803.24612023-117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Accepted: 02/07/2024] [Indexed: 03/22/2024]
Abstract
BACKGROUND Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive and lethal form of cancer with limited prognostic accuracy using traditional factors. This has led to the exploration of innovative prognostic models, including convolutional neural networks (CNNs), in PDAC. CNNs, a type of artificial intelligence algorithm, have shown promise in various medical applications, including image analysis and pattern recognition. Their ability to extract complex features from medical images makes them suitable for improving prognostication in PDAC. However, implementing CNNs in clinical practice poses challenges, such as data availability and interpretability. Future research should focus on multi-center studies, integrating multiple data modalities, and combining CNN outputs with biomarker panels. Collaborative efforts and patient autonomy should be considered to ensure the ethical implementation of CNN-based prognostic models. Further validation and optimisation of CNN-based models are necessary to enhance their reliability and clinical utility in PDAC prognostication. BACKGROUND •Pancreatic ductal adenocarcinoma (PDAC) is an aggressive cancer with limited prognostic accuracy through traditional methods. BACKGROUND •Convolutional neural networks (CNNs) are being explored for prognostic models in PDAC. BACKGROUND •They can extract complex features from images, aiding PDAC prognostication. BACKGROUND •Further validation and optimization of CNN-based models are needed for better reliability and clinical utility in PDAC.
Collapse
|
3
|
Sanjaya P, Maljanen K, Katainen R, Waszak SM, Aaltonen LA, Stegle O, Korbel JO, Pitkänen E. Mutation-Attention (MuAt): deep representation learning of somatic mutations for tumour typing and subtyping. Genome Med 2023; 15:47. [PMID: 37420249 DOI: 10.1186/s13073-023-01204-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2022] [Accepted: 06/21/2023] [Indexed: 07/09/2023] Open
Abstract
BACKGROUND Cancer genome sequencing enables accurate classification of tumours and tumour subtypes. However, prediction performance is still limited using exome-only sequencing and for tumour types with low somatic mutation burden such as many paediatric tumours. Moreover, the ability to leverage deep representation learning in discovery of tumour entities remains unknown. METHODS We introduce here Mutation-Attention (MuAt), a deep neural network to learn representations of simple and complex somatic alterations for prediction of tumour types and subtypes. In contrast to many previous methods, MuAt utilizes the attention mechanism on individual mutations instead of aggregated mutation counts. RESULTS We trained MuAt models on 2587 whole cancer genomes (24 tumour types) from the Pan-Cancer Analysis of Whole Genomes (PCAWG) and 7352 cancer exomes (20 types) from the Cancer Genome Atlas (TCGA). MuAt achieved prediction accuracy of 89% for whole genomes and 64% for whole exomes, and a top-5 accuracy of 97% and 90%, respectively. MuAt models were found to be well-calibrated and perform well in three independent whole cancer genome cohorts with 10,361 tumours in total. We show MuAt to be able to learn clinically and biologically relevant tumour entities including acral melanoma, SHH-activated medulloblastoma, SPOP-associated prostate cancer, microsatellite instability, POLE proofreading deficiency, and MUTYH-associated pancreatic endocrine tumours without these tumour subtypes and subgroups being provided as training labels. Finally, scrunity of MuAt attention matrices revealed both ubiquitous and tumour-type specific patterns of simple and complex somatic mutations. CONCLUSIONS Integrated representations of somatic alterations learnt by MuAt were able to accurately identify histological tumour types and identify tumour entities, with potential to impact precision cancer medicine.
Collapse
Affiliation(s)
- Prima Sanjaya
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland
- Applied Tumor Genomics Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland
- iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland
| | - Katri Maljanen
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland
- Applied Tumor Genomics Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland
- iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland
| | - Riku Katainen
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland
- Applied Tumor Genomics Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland
- iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland
- Department of Medical and Clinical Genetics, Faculty of Medicine, University of Helsinki, Helsinki, Finland
| | - Sebastian M Waszak
- Centre for Molecular Medicine Norway (NCMM), Nordic EMBL Partnership, University of Oslo and Oslo University Hospital, Oslo, Norway
- Swiss Institute for Experimental Cancer Research School of Life Sciences, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Department of Neurology, University of California, San Francisco (UCSF), San Francisco, CA, USA
| | - Lauri A Aaltonen
- Applied Tumor Genomics Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland
- Department of Medical and Clinical Genetics, Faculty of Medicine, University of Helsinki, Helsinki, Finland
| | - Oliver Stegle
- Division of Computational Genomics and Systems Genetics, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Genome Biology Unit, European Molecular Biology Laboratory, Heidelberg, Germany
| | - Jan O Korbel
- Division of Computational Genomics and Systems Genetics, German Cancer Research Center (DKFZ), Heidelberg, Germany
- Genome Biology Unit, European Molecular Biology Laboratory, Heidelberg, Germany
- European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, UK
| | - Esa Pitkänen
- Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
- Applied Tumor Genomics Research Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland.
- iCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland.
- Genome Biology Unit, European Molecular Biology Laboratory, Heidelberg, Germany.
| |
Collapse
|
4
|
Huang H, Zhou G, Liu X, Deng L, Wu C, Zhang D, Liu H. Contrastive learning-based computational histopathology predict differential expression of cancer driver genes. Brief Bioinform 2022; 23:6651307. [PMID: 35901472 DOI: 10.1093/bib/bbac294] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2022] [Revised: 06/16/2022] [Accepted: 06/29/2022] [Indexed: 11/14/2022] Open
Abstract
MOTIVATION Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells. RESULTS In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.
Collapse
Affiliation(s)
- Haojie Huang
- School of Computer Science and Engineering, Central South University, 410075, Changsha, China
| | - Gongming Zhou
- School of Computer Science and Engineering, Central South University, 410075, Changsha, China
| | - Xuejun Liu
- School of Computer Science and Technology, Nanjing Tech University, 211816, Nanjing, China
| | - Lei Deng
- School of Computer Science and Engineering, Central South University, 410075, Changsha, China
| | - Chen Wu
- The third affiliated hospital of Soochow University, 213100, Changzhou, China
| | - Dachuan Zhang
- The third affiliated hospital of Soochow University, 213100, Changzhou, China
| | - Hui Liu
- School of Computer Science and Technology, Nanjing Tech University, 211816, Nanjing, China
| |
Collapse
|