Systematic Assessment of Tumor Purity and Its Clinical Implications

Haider, Syed; Tyekucheva, Svitlana; Prandi, Davide; Fox, Natalie S.; Ahn, Jaeil; Xu, Andrew Wei; Pantazi, Angeliki; Park, Peter J.; Laird, Peter W.; Sander, Chris; Wang, Wenyi; Demichelis, Francesca; Loda, Massimo; Boutros, Paul C.

doi:10.1200/po.20.00016

Cited by 31 publications

(37 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When interpreting the data, tumor content and heterogeneity of tested samples should be considered. 75 Since the fraction of non-tumor cells affects the sensitivity of every assay, it is advisable to evaluate tumor content appropriately. 75 For the integrated analysis of all markers covered by LYNX, a sample should contain at least 20% of tumor cells to ascertain clonally expanded molecular markers.…”

Section: Discussionmentioning

confidence: 99%

LYmphoid NeXt-Generation Sequencing (LYNX) Panel

Navrkalová

Plevová

Hynšt

et al. 2021

The Journal of Molecular Diagnostics

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Section: Discussionmentioning

confidence: 99%

LYmphoid NeXt-Generation Sequencing (LYNX) Panel

Navrkalová

Plevová

Hynšt

et al. 2021

The Journal of Molecular Diagnostics

View full text Add to dashboard Cite

show abstract

“…Traditionally, pathologists inspect stained tissue slides to determine tumor cellularity, an approach that is not just laborious but also highly subjective due to intraobserver and interobserver variability. Tumor cellularity can also be inferred computationally from NGS datasets, but there is limited concordance among available inference methods and heavy dependence on the presence of high numbers of genomic alterations for adequate accuracy (55). To address this task using an AI approach, Akbar 53 patients with breast cancer using DNN (InceptionNet architecture), eliminating the need for nuclei segmentation and classification, and feature extraction (56).…”

Section: Characterizing the Tumor Microenvironmentmentioning

confidence: 99%

Artificial Intelligence in Cancer Research and Precision Medicine

Bhinder

Gilvary²,

Madhukar³

et al. 2021

Cancer Discovery

310

153

View full text Add to dashboard Cite

Convolutional neural networks (CNN) have been the most popular deep learning architectures used for image classification in cancer ( Fig. 1 ). CNNs apply a series of nonlinear transformations to structured data (such as raw pixels of an image) to learn relevant features automatically, unlike conventional machine learning models that frequently require manual feature curation. On the fl ip side, it is diffi cult to tell what features are learned by the CNNs, making them what many have referred to as a "black box." One consequence is that images used for CNNs should be carefully prepro cessed to reduce the risk that the model learns from image artifacts. There are two major approaches for CNN models; one is transfer learning that uses images from a large collection of natural objects (such as in ImageNet) to train the initial layers of a model (where the model learns to identify general features such as shapes and edges) and then uses the diseasespecifi c data to fi ne-tune the training parameters in the last layers. The second variation of CNN is based on an autoencoder where the model learns background features from a subset of representative images and encodes a compressed representation of the basic features later used to initialize the CNN. In the CAMELYON16 Challenge-a crowdsourced competition to identify and classify lymph node metastasis in patients with breast cancer from whole slide images (WSI) of hematoxylin and eosin (H&E)-stained tumors-25 of the 32 submitted algorithms were CNNs, and the top 5 classifi cation models were exclusively based on transfer learning, which were GoogLeNet, ResNet, VGG-16 ( 2 ). Khosravi and colleagues trained and tested several state-of-the-art deep learning models to classify WSI from H&E-stained tumor tissues of The Cancer Genome Atlas (TCGA) cohort and reported on the

show abstract

“…It also provides information about the spatial organization of the tumor microenvironment. Furthermore, previous studies showed that percent tumor nuclei estimates by different pathologists are not only inconsistent but also different from genomic tumor purity values [4,12]. However, we still do not know the causes of the difference.…”

Section: Introductionmentioning

confidence: 77%

“…A sample selected based on an overestimated tumor purity, for example, may lead to a false-negative test result, which may withhold a patient from getting highly promising therapies [5]. Besides, the genomic analysis should incorporate the tumor purity to account for normal cell contamination, which can directly confound results and subsequent clinical decisions [4,[8][9][10][11][12][13]. A novel immunotherapy gene signature missed by traditional methods, for example, was discovered using a differential expression analysis incorporating tumor purity [4].…”

Section: Introductionmentioning

confidence: 99%

Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study

Öner

Chen

Revkov

et al. 2021

Preprint

View full text Add to dashboard Cite

Tumor purity is the proportion of cancer cells in the tumor tissue. An accurate tumor purity estimation is crucial for accurate pathologic evaluation and for sample selection to minimize normal cell contamination in high throughput genomic analysis. We developed a novel deep multiple instance learning model predicting tumor purity from H&E stained digital histopathology slides. Our model successfully predicted tumor purity from slides of fresh-frozen sections in eight different TCGA cohorts and formalin-fixed paraffin-embedded sections in a local Singapore cohort. The predictions were highly consistent with genomic tumor purity values, which were inferred from genomic data and accepted as the golden standard. Besides, we obtained spatially resolved tumor purity maps and showed that tumor purity varies spatially within a sample. Our analyses on tumor purity maps also suggested that pathologists might have chosen high tumor content regions inside the slides during tumor purity estimation in the TCGA cohorts, which resulted in higher values than genomic tumor purity values. In short, our model can be utilized for high throughput sample selection for genomic analysis, which will help reduce pathologists’ workload and decrease inter-observer variability. Moreover, spatial tumor purity maps can help better understand the tumor microenvironment as a key determinant in tumor formation and therapeutic response.

show abstract

Systematic Assessment of Tumor Purity and Its Clinical Implications

Cited by 31 publications

References 30 publications

LYmphoid NeXt-Generation Sequencing (LYNX) Panel

LYmphoid NeXt-Generation Sequencing (LYNX) Panel

Artificial Intelligence in Cancer Research and Precision Medicine

Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study

Contact Info

Product

Resources

About