Abstract

Radiomics refers to the extraction of mineable data from medical imaging and has been applied within oncology to improve diagnosis, prognostication, and clinical decision support, with the goal of delivering precision medicine. The authors provide a practical approach for successfully implementing a radiomic workflow from planning and conceptualization through manuscript writing. Applications in oncology typically are either classification tasks that involve computing the probability of a sample belonging to a category, such as benign versus malignant, or prediction of clinical events with a time-to-event analysis, such as overall survival. The radiomic workflow is multidisciplinary, involving radiologists and data and imaging scientists, and follows a stepwise process involving tumor segmentation, image preprocessing, feature extraction, model development, and validation. Images are curated and processed before segmentation, which can be performed on tumors, tumor subregions, or peritumoral zones. Extracted features typically describe the distribution of signal intensities and spatial relationship of pixels within a region of interest. To improve model performance and reduce overfitting, redundant and nonreproducible features are removed. Validation is essential to estimate model performance in new data and can be performed iteratively on samples of the dataset (cross-validation) or on a separate hold-out dataset by using internal or external data. A variety of noncommercial and commercial radiomic software applications can be used. Guidelines and artificial intelligence checklists are useful when planning and writing up radiomic studies. Although interest in the field continues to grow, radiologists should be familiar with potential pitfalls to ensure that meaningful conclusions can be drawn. Online supplemental material is available for this article. Published under a CC BY 4.0 license.

Highlights

  • SA-CME LEARNING OBJECTIVESAfter completing this journal-based SA-CME activity, participants will be able to: List the main applications of radiomic studies in oncology.Understand the use of image preprocessing, segmentation, and validation in radiomic studies.Describe the main radiomic feature classes and how they are calculated.See www.rsna.org/education/search/RG.Radiomics refers to the extraction of mineable high-dimensional data from radiologic images [1,2,3] and has been applied within oncology to improve diagnosis and prognostication [4,5] with the aim of delivering precision medicine

  • We find a radiomic study proforma useful when assessing proposed studies (Appendix E1)

  • Texture features Contrast, correlation, Second-order features describe spatial complexity and relationships entropy, run emphasis, of signal intensities (SIs) between neighboring pixels; often computed from the gray-level nonuniforco-occurrence matrix (GLCM) described by Haralick [8] or the mity run-length matrix (GLRLM) described by Galloway [29]. Other classes include those derived from the gray-level size-zone matrix (GLSZM) [30], gray-level distance-zone matrix (GLDZM) [30], neighborhood gray-tone difference matrix (NGTDM) [31], and neighborhood gray-level dependence matrix (NGLDM) [32]

Read more

Summary

Introduction

After completing this journal-based SA-CME activity, participants will be able to: List the main applications of radiomic studies in oncology. Understand the use of image preprocessing, segmentation, and validation in radiomic studies. Radiomics refers to the extraction of mineable high-dimensional data from radiologic images [1,2,3] and has been applied within oncology to improve diagnosis and prognostication [4,5] with the aim of delivering precision medicine. The premise is that imaging data convey meaningful information about tumor biology, behavior, and pathophysiology [6] and may reveal information that is not otherwise apparent to current radiologic and clinical interpretation. The radiomic workflow involves curation of clinical and imaging data and is a stepwise process involving image preprocessing, tumor segmentation, feature extraction, model development, and validation [7]. Features are derived at single (usually pretreatment) or multiple (eg, δ radiomics) time points and can be applied to the whole spectrum of imaging data

TEACHING POINTS
Applications in Oncology
Planning a Radiomic Study
Image Acquisition
Univariate Unsupervised learning Validation dataset
How heterogeneous are the data?
Data Curation
Image Preprocessing
Image thresholding
Feature Class
Feature Extraction
Model Building
Feature Stability
Univariate Feature Discovery
Feature Selection and Dimensionality Reduction
Multivariate Models
Manually remove Selecting a feature or features to Simple to apply
Feature stability Assess temporal stability in the
Manuscript Writing
Future Directions and Challenges
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call