Radiomics in medical imaging-"how-to" guide and critical reflection.

van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. · 2020

Read Radiomics in medical imaging-"how-to" guide and critical reflection. by van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. (2020) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc7423816.txt.

Introduction

van Timmeren and co-authors explain radiomics, a way to turn medical scans into numbers that can guide care. Software pulls patterns from signal strength and pixel links inside a scan. Those patterns form features that may say more than the eye can see.

The review walks through each step of a radiomics study, from scan to final model. It then turns critical. Many technical choices can shift the features a study finds, which hurts trust and repeat work. The authors urge teams to follow shared guidelines and quality checklists. Test images and open data can help prove that results hold up. Readers get both a how-to guide and a clear list of pitfalls.

Catalog record

CREATORvan Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B.
YEAR2020
COLLECTIONPAPERS
FORMATTXT
FILE SIZE66 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC7423816

Browse the full library · About the Tower of Babel

Full text

The opening of the work, from the library's hosted text:

Radiomics in medical imaging—“how-to” guide and critical reflection By Janita E. van Timmeren, Davide Cester, Stephanie Tanadini-Lang, Hatem Alkadhi, Bettina Baessler Published in: Insights into Imaging DOI: 10.1186/s13244-020-00887-2 ABSTRACT Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features. The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical “how-to” guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject. KEY POINTS Radiomics represents a method for the quantitative description of medical images.A step-by-step “how-to” guide is presented for radiomics analyses.Throughout the radiomics workflow, numerous factors influence radiomic features.Guidelines and quality checklists should be used to improve radiomics studies’ quality.Digital phantoms and open-source data help to improve the reproducibility of radiomics. BACKGROUND Like many other areas of human activity in the last decades, medicine has seen a constant increase in the digitalization of the information generated during clinical routine. As more medical data became available in digital format, new and always more sophisticated software was developed to analyze them. At the same time, the research on artificial intelligence (AI) has long reached a point where its methods and software tools have become not only powerful, but also accessible enough to leave the computer science departments and find applications in an increasing variety of domains. As a consequence, the recent years have witnessed a continuous increase of AI applications in the medical sector, aiming at facilitating repetitive tasks clinicians encounter in their daily clinical workflows and to support clinical decision-making. The different techniques used in AI—i.e., mainly machine learning and deep learning algorithms—are especially useful when it comes to the emerging field of “big data”. Big data is defined as “a term that describes large volumes of high velocity, complex and variable data that require advanced techniques and technologies to enable the capture, storage, distribution, management, and analysis of the information.” 1 Due to the high amount of multi-dimensional information, techniques from the field of AI are needed to extract the desired information from these data. In medicine, various ways to generate big data exist, including the widely known fields of genomics, proteomics, or metabolomics. Similar to these “omics” clusters, imaging has been used increasingly to generate a dedicated omics cluster itself called “radiomics”. Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced, and sometimes non-intuitive mathematical analysis. The concept of radiomics, which has most broadly (but not exclusively) been applied in the field of oncology, is based on the assumption that biomedical images contain information of disease-specific processes [1] that are imperceptible by the human eye [2] and thus not accessible through traditional visual inspection of the generated images. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information [3, 4] by using analysis methods from the field of AI. In addition, visual appreciable differences in image intensity, shape, or texture can be quantified by means of radiomics, thus overcoming the subjective nature of image interpretation. Thus, radiomics does not imply any automation of the diagnostic processes, rather it provides existing ones with additional data. Radiomics analysis can be performed on medical images from different modalities, allowing for an integrated cross-modality approach using the potential additive value of imaging information extracted, e.g., from magnetic resonance imaging (MRI), computed tomography (CT), and positron-emission-tomography (PET), instead of evaluating each modality by its own. However, the current state-of-the-art of the research still shows lack of stability and generalization, and the specific study conditions and the authors’ choices have still a great influence on the results. In this work, we present the typical workflow of a radiomics analysis, discussing the current limitations of this approach, suggesting potential improvements, and commenting relevant literature on the subject. RADIOMICS–HOW TO? The following section will give a practical advice on “how to do radiomics” by illustrating each of the required steps in the radiomics pipeline (illustrated in Fig. 1) and highlighting important points. Fig. 1The radiomics workflow. Schematic illustration of the patient journey including image acquisition, analysis utilizing radiomics, and derived patient-specific therapy and prognosis. After image acquisition and segmentation, radiomic features are extracted. High-level statistical modeling involving machine learning is applied for disease classification, patient clustering, and individual risk stratification Step 1: image segmentation For any radiomics approach, delineation of the region of interest (ROI) in two-dimensional (2D) or of the volume of interest (VOI) in three-dimensional (3D) approaches is the crucial first step in the pipeline. ROIs/VOIs define the region in which radiomic features are calculated. Image segmentation might be done manually, semi-automatically (using standard image segmentation algorithms such as region-growing or thresholding), or fully automatically (nowadays using deep learning algorithms). A variety of different software solutions—either open-source or commercial—are available, such as 3D Slicer 2 [5], MITK 3, ITK-SNAP 4, MeVisLab 5, LifEx 6, or ImageJ 7 [6], to name only some frequently used open-source tools. For reviews on various different tools for image segmentation, please refer to [7, 8]. Manual and semi-automated image segmentation (usually with manual correction) are the most often encountered methods but have several drawbacks. Firstly, manual segmentation is time-consuming – depending on how many images and datasets have to be segmented. Second, manual and semi-automated segmentation introduce a considerable observer-bias, and studies have shown that many radiomic features are not robust against intra- and inter-observer variations concerning ROI/VOI delineation [9]. Consequently, studies using manual or semi-automated image segmentation with manual correction should perform assessments of intra- and inter-observer reproducibility of the derived radiomic features and exclude non-reproducible features from further analyses. Deep learning-based image segmentation (often using some sort of U-Net [10]) is rapidly emerging and many different algorithms have already been trained for image segmentation tasks of various organs (currently, most of them being useful for the segmentation of entire organs, but not for segmentation of dedicated tumor regions), several of them being published as open-source. Since recently, there are also several possibilities for integration of such algorithms in platforms like 3D Slicer or MITK. Automated image segmentation certainly is the best option, since it avoids intra- and inter-observer variability of radiomic features. However, generalizability of trained algorithms currently is a major limitation, and applying those algorithms on a different dataset often results in complete failure. Thus, further research has to be devoted to the development of robust and generalizable algorithms for automated image segmentation. Step 2: image processing Image processing is located between the image segmentation and feature extraction step. It represents the attempt to homogenize images from which radiomic features will be extracted with respect to pixel spacing,

Read the complete text