The Application of Deep Learning in Cancer Prognosis Prediction

Abstract

Deep learning has been applied to many areas in health care, including imaging diagnosis, digital pathology, prediction of hospital admission, drug design, classification of cancer and stromal cells, doctor assistance, etc. Cancer prognosis is to estimate the fate of cancer, probabilities of cancer recurrence and progression, and to provide survival estimation to the patients. The accuracy of cancer prognosis prediction will greatly benefit clinical management of cancer patients. The improvement of biomedical translational research and the application of advanced statistical analysis and machine learning methods are the driving forces to improve cancer prognosis prediction. Recent years, there is a significant increase of computational power and rapid advancement in the technology of artificial intelligence, particularly in deep learning. In addition, the cost reduction in large scale next-generation sequencing, and the availability of such data through open source databases (e.g., TCGA and GEO databases) offer us opportunities to possibly build more powerful and accurate models to predict cancer prognosis more accurately. In this review, we reviewed the most recent published works that used deep learning to build models for cancer prognosis prediction. Deep learning has been suggested to be a more generic model, requires less data engineering, and achieves more accurate prediction when working with large amounts of data. The application of deep learning in cancer prognosis has been shown to be equivalent or better than current approaches, such as Cox-PH. With the burst of multi-omics data, including genomics data, transcriptomics data and clinical information in cancer studies, we believe that deep learning would potentially improve cancer prognosis.

miR-497-5p Decreased Expression Associated with High-Risk Endometrial Cancer

“…The application of ML models may decrease interobserver variability in histopathological diagnosis, which could result in less heterogeneous practice among pathologists [ 46 ]. In addition to routinely collected clinical data, histopathologic characteristics, and immunohistochemical results, multi-omics data such as genomics and transcriptomics data have been included in ML prediction models [ 45 , 47 ]. Among these, the ML models utilizing gene expression data can prevent potential errors in survival evaluation, help in the management of appropriate and individualized therapy and improve cancer prognosis [ 48 ].…”

Deep Learning for Locally Advanced Nasopharyngeal Carcinoma Prognostication Based on Pre- and Post-treatment MRI

“…However, more "hidden" information that contains personal data, such as the individual prognosis and response to speci c drug treatment, cannot be recognized. With the development of algorithms, the e cacy and e ciency of information extraction from images have signi cantly improved, thus enabling researchers to make more accurate predictions of prognosis, and greatly bene t the clinical management of cancer (31). It has been reported that DL matches and even surpasses human performance in task-speci c applications (32,33).…”

A bird’s-eye view of deep learning in bioimage analysis

“…Pathological imaging plays a prominent role especially in cancer diagnosis and prognosis, and the impact of deep learning has been reviewed in various areas of oncological pathology, including in histopathology [141] , cytopathology [146] , and hematopathology [147] . Deep learning in pathology has been surveyed more specifically for breast cancer [142] , [148] , lung cancer [149] , [150] , tumor pathology in many other forms of cancer [151] , and cancer prognosis [152] , with many opinion articles commenting on challenges and opportunities [153] , [154] , [155] , [156] , [157] . As in medical imaging, there is mounting evidence for the potential of deep learning to provide fast and reliable image analysis at a performance level of a seasoned pathologist, or to serve as a synergistic tool for the latter to improve accuracy and throughput [131] .…”