Deep learning in cancer diagnosis, prognosis and treatment selection
Deep learning is a subdiscipline of artificial intelligence that uses a machine learning
technique called artificial neural networks to extract patterns and make predictions from …
technique called artificial neural networks to extract patterns and make predictions from …
Deep learning in histopathology: the path to the clinic
Abstract Machine learning techniques have great potential to improve medical diagnostics,
offering ways to improve accuracy, reproducibility and speed, and to ease workloads for …
offering ways to improve accuracy, reproducibility and speed, and to ease workloads for …
Deep learning in cancer pathology: a new generation of clinical biomarkers
Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers.
However, the growing number of these complex biomarkers tends to increase the cost and …
However, the growing number of these complex biomarkers tends to increase the cost and …
Data-efficient and weakly supervised computational pathology on whole-slide images
Deep-learning methods for computational pathology require either manual annotation of
gigapixel whole-slide images (WSIs) or large datasets of WSIs with slide-level labels and …
gigapixel whole-slide images (WSIs) or large datasets of WSIs with slide-level labels and …
The impact of site-specific digital histology signatures on deep learning model accuracy and bias
Abstract The Cancer Genome Atlas (TCGA) is one of the largest biorepositories of digital
histology. Deep learning (DL) models have been trained on TCGA to predict numerous …
histology. Deep learning (DL) models have been trained on TCGA to predict numerous …
Lizard: A large-scale dataset for colonic nuclear instance segmentation and classification
S Graham, M Jahanifar, A Azam… - Proceedings of the …, 2021 - openaccess.thecvf.com
The development of deep segmentation models for computational pathology (CPath) can
help foster the investigation of interpretable morphological biomarkers. Yet, there is a major …
help foster the investigation of interpretable morphological biomarkers. Yet, there is a major …
Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes
Computational methods have made substantial progress in improving the accuracy and
throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still …
throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still …
[HTML][HTML] Gastrointestinal cancer classification and prognostication from histology using deep learning: Systematic review
S Kuntz, E Krieghoff-Henning, JN Kather, T Jutzi… - European Journal of …, 2021 - Elsevier
Background Gastrointestinal cancers account for approximately 20% of all cancer diagnoses
and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence–based …
and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence–based …
Spatially resolved transcriptomics reveals the architecture of the tumor-microenvironment interface
During tumor progression, cancer cells come into contact with various non-tumor cell types,
but it is unclear how tumors adapt to these new environments. Here, we integrate spatially …
but it is unclear how tumors adapt to these new environments. Here, we integrate spatially …
Cancer‐associated fibroblasts: key players in shaping the tumor immune microenvironment
M Desbois, Y Wang - Immunological reviews, 2021 - Wiley Online Library
Cancer immunotherapies have rapidly changed the therapeutic landscape for cancer.
Nevertheless, most of the patients show innate or acquired resistance to these therapies …
Nevertheless, most of the patients show innate or acquired resistance to these therapies …