• Corpus ID: 250607766

Self-supervised learning in non-small cell lung cancer discovers novel morphological clusters linked to patient outcome and molecular phenotypes

  title={Self-supervised learning in non-small cell lung cancer discovers novel morphological clusters linked to patient outcome and molecular phenotypes},
  author={Adalberto Claudio Quiros and Nicolas Coudray and Anna H. Yeaton and Xinyu Yang and Luis A. Chiriboga and Afreen Karimkhan and Navneet Narula and Harvey I. Pass and Andre L. Moreira and John Le Quesne and Aristotelis Tsirigos and Ke-Fei Yuan},
Histopathological images provide the definitive source of cancer diagnosis, containing information used by pathologists to identify and subclassify malignant disease, and to guide therapeutic choices. These images contain vast amounts of information, much of which is currently unavailable to human interpretation. Supervised deep learning approaches have been powerful for classification tasks, but they are inherently limited by the cost and quality of annotations. Therefore, we developed… 

Figures from this paper



Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features

It is suggested that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology.

Pan-Cancer Integrative Histology-Genomic Analysis via Interpretable Multimodal Deep Learning

A pan-cancer integrative platform for biomarker discovery in both histology slides and molecular profile data is presented and performance increase in risk stratification on 9 out of 14 cancers is demonstrated, as well as shifts in feature importance when conditioned on more than one modality.

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

A deep convolutional neural network model is trained on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue and predicts the ten most commonly mutated genes in LUAD.

Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study

It is shown that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images and was an independent prognostic factor for overall survival in a multivariable Cox proportional hazard model.

Weakly-supervised learning for lung carcinoma classification using deep learning

A Convolution Neural Network based on the EfficientNet-B3 architecture is trained, using transfer learning and weakly-supervised learning, to predict carcinoma in Whole Slide Images using a training dataset of 3,554 WSIs.

Deep learning-based survival prediction for multiple cancer types using histopathology images

This work developed a deep learning system (DLS) to predict disease specific survival across 10 cancer types from The Cancer Genome Atlas, using a weakly-supervised approach without pixel-level annotations, and tested three different survival loss functions.

Adversarial learning of cancer tissue representations

This work presents an adversarial learning model to extract feature representations of cancer tissue, without the need for manual annotations, and shows that these representations are able to identify a variety of morphological characteristics across three cancer types: Breast, colon, and lung.

A Weak Supervision-based Framework for Automatic Lung Cancer Classification on Whole Slide Image

A pixel-level annotation-free framework was proposed to classify normal tissue, LUAD and LUSC slides and achieved superiority in lung pathological image classification compared with other methods.

Optimize Deep Learning Models for Prediction of Gene Mutations Using Unsupervised Clustering

This study validated the hypothesis that the prediction of gene mutations solely based on tumor regions on the WSI slides may not always provide the best performance and highlighted the heterogeneity in the tumor microenvironment and the important of identification of predictive image patches in digital pathology prediction tasks.

Self supervised contrastive learning for digital histopathology