Novel Methods for Oncologic Imaging Analysis: Radiomics, Machine Learning, and Artificial Intelligence

196.8K

views

283

authors

38

articles

Editorial

22 July 2021

Editorial: Novel Methods for Oncologic Imaging Analysis: Radiomics, Machine Learning, and Artificial Intelligence

Hanyue Xu

,

Lei Deng

,

Rong Tian

and

Xuelei Ma

2,258 views

4 citations

Editors

4

Sichuan University

Roswell Park Comprehensive Cancer Center, University at Buffalo

Sichuan University

Medical School, University of Minnesota

Impact

Fetching...

About

Radiomics is a high-throughput quantitative feature extraction method used to discover clinically relevant data that are not detectable from radiological images, such as size and shape based–features, texture, tumor intensity histogram and wavelet features.

To facilitate the process of detection and analysis, artificial intelligence is increasingly developed, fuelled by an adequate database, computing technology, and new machine-learning algorithms. The machine learning method in radiology, the main subset of artificial intelligence, learns laws by a large number of data/experiences to obtain precise predictions based on these laws. Its accuracy is based on the sufficiency and reliability of data resource, and appropriate models, like neural networks, support vector machines, and deep learning, for feature extraction and classification. Application of machine learning method in radiology can improve diagnosis, treatment, and prognosis, especially for cancer patients, as the tumor stage takes an important part in cancer diagnosis
and treatment. Using radiomics combining machine learning can promote the discrimination of benign and malignant tumors, forecast the response of possible treatment and optimize individually medical care.

This Research Topic aims to provide a forum to update and discuss new discoveries in the field of applying radiomics, machine learning and artificial intelligence in imaging tests for cancer. The studies should focus on major trends and challenges in this field, and the manuscripts include but are not limited to the application of radiomics, machine learning, and artificial intelligence in:

- Contrast-enhanced imaging (e.g. contrast-enhanced ultrasound, CT, MRI, PET/CT, and PET/MRI) for cancer detection
- Contrast-enhanced imaging for cancer grading and staging
- Contrast-enhanced imaging for detection and prediction of cancer therapy response
- Imaging diagnosis or prognosis of cancer
- Cancer pathology imaging (e.g. comparison of central nervous system lymphoma and glioblastoma)
- Medical image reconstruction
- Cellular image analysis

Radiomics is a high-throughput quantitative feature extraction method used to discover clinically relevant data that are not detectable from radiological images, such as size and shape based–features, texture, tumor intensity histogram and wavelet features.

To facilitate the process of detection and analysis, artificial intelligence is increasingly developed, fuelled by an adequate database, computing technology, and new machine-learning algorithms. The machine learning method in radiology, the main subset of artificial intelligence, learns laws by a large number of data/experiences to obtain precise predictions based on these laws. Its accuracy is based on the sufficiency and reliability of data resource, and appropriate models, like neural networks, support vector machines, and deep learning, for feature extraction and classification. Application of machine learning method in radiology can improve diagnosis, treatment, and prognosis, especially for cancer patients, as the tumor stage takes an important part in cancer diagnosis
and treatment. Using radiomics combining machine learning can promote the discrimination of benign and malignant tumors, forecast the response of possible treatment and optimize individually medical care.

This Research Topic aims to provide a forum to update and discuss new discoveries in the field of applying radiomics, machine learning and artificial intelligence in imaging tests for cancer. The studies should focus on major trends and challenges in this field, and the manuscripts include but are not limited to the application of radiomics, machine learning, and artificial intelligence in:

- Contrast-enhanced imaging (e.g. contrast-enhanced ultrasound, CT, MRI, PET/CT, and PET/MRI) for cancer detection
- Contrast-enhanced imaging for cancer grading and staging
- Contrast-enhanced imaging for detection and prediction of cancer therapy response
- Imaging diagnosis or prognosis of cancer
- Cancer pathology imaging (e.g. comparison of central nervous system lymphoma and glioblastoma)
- Medical image reconstruction
- Cellular image analysis

Download ebook

Share

Editors

Sichuan University

Roswell Park Comprehensive Cancer Center, University at Buffalo

Sichuan University

Medical School, University of Minnesota

Impact

196,781 Total views

138,334 Article views

55,832 Article downloads

2,615 Topic views

Published In

Journal Thumbnail

Frontiers in Oncology

Cancer Imaging and Image-directed Interventions

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Suggest a topic