Computational Image Analysis Techniques, Programming Languages and Software Platforms Used in Cancer Research: A Scoping Review
Arafat, Y.; Reyes Aldasoro, C.-C.
Show abstract
BackgroundCancer-related research, as indicated by the number of entries in Medline, the National Library of Medicine of the USA, has dominated the medical literature. An important component of this research is based on the use of computational techniques to analyse the data produced by the many acquisition modalities. This paper presents a review of the computational image analysis techniques that have been applied to cancer. The review was performed through automated mining of Medline/PubMed entries with a combination of keywords. In addition, the programming languages and software platforms through which these techniques are applied were also reviewed. MethodsAutomatic mining of Medline/PubMed was performed with a series of specific keywords that identified different computational techniques. These keywords focused on traditional image processing and computer vision techniques, machine learning techniques, deep learning techniques, programming languages and software platforms. ResultsThe entries related to traditional image processing and computer vision techniques have decreased at the same time that machine learning and deep learning have increased significantly. Within deep learning, the keyword that returned the highest number of entries was convolutional neural network. Within the programming languages and software environments, Fiji and ImageJ were the most popular, followed by Matlab, R, and Python. Within the more specialised softwares, QuPath has had a sharp growth overtaking other platforms like ICY and CellProfiler. ConclusionsThe techniques of artificial intelligence techniques and deep learning have grown to overtake most other image analysis techniques and the trend at which they grow is still rising. The most used technique has been convolutional neural networks, commonly used to analyse and classify images. All the code related to this work is available through GitHub: https://github.com/youssefarafat/Scoping-Review.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A machine learning approach for identification of gastrointestinal predictors for the risk of COVID-19 related hospitalization 93%
- Prognostic Analysis of Histopathological Images Using Pre-Trained Convolutional Neural Networks 92%
- Estimating body volumes and surface areas of animalsfrom cross-sections 92%
Similar papers in this journal
- Estimation of Three-Dimensional Chromatin Morphology for Nuclear Classification and Characterisation 95%
- Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning 95%
- On evaluation metrics for medical applications of artificial intelligence 93%
Similar papers in this journal
- Prediction of high-risk liver cancer patients from their mutation profile: Benchmarking of mutation calling techniques 94%
- Unpacking Unstructured Data: A Pilot Study on Extracting Insights from Neuropathological Reports of Parkinson's Disease Patients using Large Language Models 90%
- Machine Classification of Methylomes in Cancer 90%
Similar papers in this journal
- Building Large-Scale Registries from Unstructured Clinical Notes using a Low-Resource Natural Language Processing Pipeline 94%
- The role of natural language processing in cancer care: a systematic scoping review with narrative synthesis 92%
- Stability of feature selection utilizing Graph Convolutional Neural Network and Layer-wise Relevance Propagation 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.