A deep learning-based cancer survival time classifier for small datasets

Cancer survival time prediction using Deep Learning (DL) has been an emerging area of research. However, non-availability of large-sized annotated medical imaging databases affects the training performance of DL models leading to their arguable usage in many clinical applications. In this research w...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2023-06, Vol.160, p.106896-106896, Article 106896
Main Authors: Shakir, Hina, Aijaz, Bushra, Khan, Tariq Mairaj Rasool, Hussain, Muhammad
Format: Article
Language:English
Subjects:
Biometry
Cancer
Classifiers
Deep Learning
Diagnostic Imaging
Feature selection
Humans
Iterative methods
Lung cancer
Lung cancer survival
Lung Neoplasms - pathology
Machine learning
Medical image processing
Medical imaging
Neural networks
Neural Networks, Computer
Radiomic features
Radiomics
Survival
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cancer survival time prediction using Deep Learning (DL) has been an emerging area of research. However, non-availability of large-sized annotated medical imaging databases affects the training performance of DL models leading to their arguable usage in many clinical applications. In this research work, a neural network model is customized for small sample space to avoid data over-fitting for DL training. A set of prognostic radiomic features is selected through an iterative process using average of multiple dropouts which results in back-propagated gradients with low variance, thus increasing the network learning capability, reliable feature selection and better training over a small database. The proposed classifier is further compared with erasing feature selection method proposed in the literature for improved network training and with other well-known classifiers on small sample size. Achieved results which were statistically validated show efficient and improved classification of cancer survival time into three intervals of 6 months, between 6 months up to 2 years, and above 2 years; and has the potential to aid health care professionals in lung tumor evaluation for timely treatment and patient care. •A robust cancer survival time classification model for small datasets•Data overfitting problem addressed using customized neural network architecture•Prognostic radiomic feature selection leads to a good estimate of cancer survival time for better decision-making on interventions.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2023.106896