Using Machine Learning Applied to Radiomic Image Features for Segmenting Tumour Structures

Clifton, Henry; Vial, Alanna; Miller, Andrew; Ritz, Christian; Field, Matthew; Holloway, Lois; Ros, Montserrat; Carolan, Martin G; Stirling, David

doi:10.1109/apsipaasc47483.2019.9023077

Cited by 9 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventionally, radiomic features determine a single scalar value to define a complete three-dimensional (3D) tumour volume; however, more recent research uses pixel-based features generating many values per feature for a 3D tumour volume [19]. These features can then be fed into a classifier to determine the features which have the strongest correlation with outcomes.…”

Section: Value Of Ai In Radiomic Feature Extraction and Selectionmentioning

confidence: 99%

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging

Currie¹,

Hawk

Rohren

et al. 2019

Journal of Medical Imaging and Radiation Sciences

Self Cite

321

151

View full text Add to dashboard Cite

Artificial intelligence (AI) in medical imaging is a potentially disruptive technology. An understanding of the principles and application of radiomics, artificial neural networks, machine learning, and deep learning is an essential foundation to weave design solutions that accommodate ethical and regulatory requirements, and to craft AIbased algorithms that enhance outcomes, quality, and efficiency. Moreover, a more holistic perspective of applications, opportunities, and challenges from a programmatic perspective contributes to ethical and sustainable implementation of AI solutions.

show abstract

Section: Value Of Ai In Radiomic Feature Extraction and Selectionmentioning

confidence: 99%

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging

Currie¹,

Hawk

Rohren

et al. 2019

Journal of Medical Imaging and Radiation Sciences

Self Cite

321

151

View full text Add to dashboard Cite

show abstract

“…Radiomics are imaging features that have been extracted from radiological data such as CT, MRI, nuclear medicine images, single photon emission computed tomography (SPECT) and PET data. 8 , 9 , 10 Traditionally in nuclear medicine, radiomics were extracted using hand‐crafted regions of interest (ROIs) or manually drawn ROIs as they are also referred to. Examples include the ROI for the left ventricle (LV) to determine the ejection fraction (EF) that required hand‐crafted regions around the ventricle for each of the gated bins.…”

Section: Radiomicsmentioning

confidence: 99%

“…While radiomics aim for higher dimensional data extraction and representation, radiomics can be classified into tiers or orders 8 , 9 , 10 : First‐order or primary radiomics capture the spatial characteristics of signal intensity such as size, shape and count density. Second‐order or secondary radiomics capture the mathematical relationships between pixels or voxels such as intensity histograms, mean intensity (e.g.…”

Section: Radiomicsmentioning

confidence: 99%

Section: Radiomicsmentioning

confidence: 99%

See 1 more Smart Citation

The transformational potential of molecular radiomics

Currie

Hawk

Rohren

2022

J of Medical Radiation Sci

View full text Add to dashboard Cite

Conventional radiomics in nuclear medicine involve hand‐crafted and computer‐assisted regions of interest. Recent developments in artificial intelligence (AI) have seen the emergence of AI‐augmented segmentation and extraction of lower order traditional radiomic features. Deep learning (DL) affords the opportunity to extract abstract radiomic features directly from input tensors (images) without the need for segmentation. These fourth‐order, high dimensional radiomics produce deep radiomics and are well suited to the data density associated with the molecular nature of hybrid imaging. Molecular radiomics and deep molecular radiomics provide insights beyond images and quantitation typical of semantic reporting. While the application of molecular radiomics using hand‐crafted and computer‐generated features is integrated into decision‐making in nuclear medicine, the acceptance of deep molecular radiomics is less universal. This manuscript aims to provide an understanding of the language and principles associated with radiomics and deep radiomics in nuclear medicine.

show abstract

“…However, this method can be subject to inter-observer variability. Automatic segmentation by arti cial intelligence shows great promise in solving this issue however is some way from being optimised (55).…”

Section: Radiomic Model With Estrogen Receptor Statusmentioning

confidence: 99%

A Radiomic Model To Classify Response To Neoadjuvant Chemotherapy in Breast Cancer

McAnena¹,

Moloney²,

Browne³

et al. 2021

Preprint

View full text Add to dashboard Cite

Background Medical image analysis has evolved to facilitate the development of methods for high-throughput extraction of quantitative features that can potentially contribute to the diagnostic and treatment paradigm of cancer. There is a need for further improvement in the accuracy of predictive markers of response to neo-adjuvant chemotherapy (NAC). The aim of this study was to develop a radiomic classifier to enhance current approaches to predicting the response to NAC breast cancer. Methods Data on patients treated for breast cancer with NAC prior to surgery who had a pre-NAC dynamic contrast enhanced (DCE) breast MRI were included. Response to NAC was assessed using the Miller-Payne system on the excised tumour. Tumour segmentation was carried out manually under the supervision of a consultant breast radiologist. Features were selected using least absolute shrinkage selection operator (LASSO) regression. A support vector machine (SVM) learning model was used to classify response to NAC. Results 74 patients were included. Patients were classified as having a poor response to NAC (reduction in cellularity <90%, n=44) and an excellent response (>90% reduction in cellularity, n=30). 4 radiomics features (discretized kurtosis, NGDLM contrast, GLZLM_SZE and GLZLM_ZP) were identified as pertinent predictors of response to NAC. A SVM model using these features stratified patients into poor and excellent response groups producing an AUC of 0.75. Addition of estrogen receptor (ER) status improved the accuracy of the model with an AUC of 0.811. Conclusion This study identified a radiomic classifier incorporating 4 radiomics features to augment subtype based classification of response to NAC in breast cancer.

show abstract

Using Machine Learning Applied to Radiomic Image Features for Segmenting Tumour Structures

Cited by 9 publications

References 37 publications

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging

Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging

The transformational potential of molecular radiomics

A Radiomic Model To Classify Response To Neoadjuvant Chemotherapy in Breast Cancer

Contact Info

Product

Resources

About