Deep learning based tissue analysis predicts outcome in colorectal cancer

By Dmitrii Bychkov, N. Linder, Riku Turkki, S. Nordling, P. Kovanen, C. Verrill, Margarita Walliander, M. Lundin, C. Haglund, J. Lundin. Scientific Reports, 2018

565 citations recorded by the source corpus.

Image-based machine learning and deep learning in particular has recently shown expert-level accuracy in medical image classification. In this study, we combine convolutional and recurrent architectures to train a deep network to predict colorectal cancer outcome based on images of tumour tissue samples. The novelty of our approach is that we directly predict patient outcome, without any intermediate tissue classification. We evaluate a set of digitized haematoxylin-eosin-stained tumour tissue microarray (TMA) samples from 420 colorectal cancer patients with clinicopathological and outcome data available. The results show that deep learning-based outcome prediction with only small tissue areas as input outperforms (hazard ratio 2.3; CI 95% 1.79–3.03; AUC 0.69) visual histological assessment performed by human experts on both TMA spot (HR 1.67; CI 95% 1.28–2.19; AUC 0.58) and whole-slide level (HR 1.65; CI 95% 1.30–2.15; AUC 0.57) in the stratification into low- and high-risk patients. Our results suggest that state-of-the-art deep learning techniques can extract more prognostic information from the tissue morphology of colorectal cancer than an experienced human observer.

Subfields: Artificial Intelligence, Health Informatics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/39b7971c483eca7b032e5bfd826fc693a7e27bb5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Informatics

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. (2023, methodology): “53 In contrast to methods using histology images, Xu et al. take advantage of the fact that radiology is non-invasive and can easily be repeated over time to develop a combined CNN + RNN model that updates its survival predictions over the course of treatment.”
Tumor-infiltrating lymphocytes in the immunotherapy era (2020, methodology): “With automatic machine learning, these limitations may be overcome by the quantification and classification of digitized tissue samples by supervised deep learning.(185) Studies presenting deep learningbased models for nuclei segmentation have been published.”
Deep learning in cancer diagnosis, prognosis and treatment selection (2021, background): “In addition to prognosis predictions from transcriptomic data, CNN models trained on histopathology images have been used to infer survival in several cancers including brain [122], colorectal [123], renal cell [124], liver cancers [125] and mesothelioma [65].”
Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study (2019, background): “In thecontextof medicalimaging,CNNshavebeenusedto classifymedicalimages[20], detectcancertissuein histopathological images[21], extractprognosticators from tissuemicroarrays(TMAs) of humansolid tumors[22], andclassifytumor cellnuclei accordingto chromatinpatterns[23].”
Artificial intelligence for digital and computational pathology (2023, background): “…are all based on the findings that molecular alterations can influence cellular morphology and the surrounding tumour micro-environment in different ways 152 ; for example, histology slides can be used to predict certain mutations, as shown in pan-cancer 29,153 and disease-specific…”
Deep neural network models for computational histopathology: A survey (2019, background): “, 2019) or adopt a RNN to generate a single prediction from a sequence of patches (Bychkov et al., 2018).”
The need for uncertainty quantification in machine-assisted medical decision making (2019, methodology): “…DL methods have been used in the predictive scenarios related to quality of care, and clinical outcomes where large neural networks were used as function estimators in place of classical predictive models, with reported performance better than the state-of-the-art, classical model approaches 9–11 .”