Local Time : 00:55 CET

ESR/ESTRO - Radiomics and imaging databases for precision radiation oncology

Friday, March 3, 08:30 - 10:00 Room: X Session Type: Joint Session of the ESR and ESTRO Topics: Imaging Methods, Oncologic Imaging Digital Evaluation: Open Digital Evaluation for this Session Moderators: K. Riklund (Umea/SE), L. P. Muren (Aarhus/DK) Add session to my schedule In your schedule (remove)

A-373

Chairmen's introduction (part 1)

K. Riklund; Umea/SE

Learning Objectives

1. To discuss how radiomics will change the clinical practice both in radiology and oncology.
2. To understand the impact of quantitative imaging data uncertainties in the prognosis and predictive models.
3. To discuss the potential and challenges of large multicentre imaging datasets.

Abstract

In this session, biomarkers in imaging will be discussed as used in treatment planning, prognosis and prediction. Furthermore, we will learn about the potential of using big data analysis in imaging in radiation treatment. When using quantitative imaging biomarkers, it is also important to be aware of potential shortnesses of the methods and you will also hear about this in the joint session between ESR and ESTRO.

A-374

Chairmen's introduction (part 2)

L. P. Muren1, V. Valentini2; 1 Aarhus/DK 2 Rome/IT
Sorry
no recording
available

Learning Objectives

1. To discuss how radiomics will change the clinical practice both in radiology and oncology.
2. To understand the impact of quantitative imaging data uncertainties in the prognosis and predictive models.
3. To discuss the potential and challenges of large multicentre imaging datasets.

Abstract

Radiomics is gaining an always greater attention in our scientific communities. Images are always less pictures and more mines of information that can be used by clinicians as decision-making tools, from prognosis assessment to therapy choice and outcome prediction. New paradigms, new uncertainty measurements, new statistical and mathematical tools are required to take advantage of radiomics potentialities and to become familiar with these approaches is unavoidable. Facing the entity of the challenge, an interdisciplinary approach is mandatory with all the imaging-based medical specialities hinged on imaging knowledge and images sharing in big data biobanks and DICOM repositories.

A-375

Radiomics in radiology, what are the parameters of interest for different imaging modalities?

H. Ahlström; Uppsala/SE

Learning Objectives

1. To learn how radiomics can be measured with imaging methods.
2. To discuss how radiomics can be integrated in “omics” analysis.
3. To explore the potential of radiomics analysis in cancer care.

Abstract

CT, MRI, PET, PET-CT and PET-MRI datasets contain huge amounts of spatially detailed morphological, functional and metabolic information. Today, when analysed, these detailed datasets are typically heavily reduced to a few measurements of a priori specified measurements of interest (e.g. volumes, areas, diameters, average/maximum tracer concentrations, etc.) and/or visually - and, therefore, inevitably subjectively - assessed by a human operator. As a result, normality/non-normality can only be assessed on these measurements and not on the entire data collected, and statistical interaction with non-imaging parameters can also be assessed only on these a priori specified measurements. To utilise the full potential of these image datasets, new analysis tools included in the concept radiomics, which allow objective or quantitative assessment of all imaging data (including, e.g. previously discarded information about texture), are needed. Radiomics can be divided into distinct processes: (a) image acquisition and reconstruction, (b) image segmentation and rendering, (c) feature extraction and feature qualification and (d) databases and data sharing with non-imaging data (e.g. different “omics” and clinical data) for (e) informatics analyses. Statistical knowledge of the normal range of radiomics features are needed for the analyses. These analyses are anticipated to bring out new associations and understandings that traditional approaches could not achieve. Radiomics features can, together with non-imaging data, be included in models that have shown to provide valuable diagnostic, prognostic or predictive information for oncological diseases. This information aims at improving individual patients’ outcomes by a better treatment selection.

A-376

Radiomics in radiotherapy: how is it used to personalise treatment and to predict toxicity and/or tumour control

C. Gani; Tübingen/DE

Learning Objectives

1. To understand how radiomics can be used to identify patients at high risk for failure after radiotherapy.
2. To discuss how radiomics can be integrated into radiotherapy treatment planning.
3. To explore the potential of radiomics to predict acute and long-term toxicity after radiotherapy.

Abstract

Radiomics is defined as the automated or semi-automated extraction of a large number of features from imaging datasets resulting an individual “imaging phenotype”. These features and the imaging phenotype can then be correlated with a variety of other parameters: from genetic phenotypes to oncological outcome data. Radiomics as a non-invasive procedure is of particular interest for the radiation oncologist in times of precision radiation oncology: The radiomics phenotype might help to identify patients at high risk for treatment failure and, therefore, candidates for more aggressive treatment. Furthermore, radiomics can also be a helpful tool to predict the risk for radiation-induced toxicities and guide the dose distribution within normal tissues. This lecture will give an overview about the existing data on radiomics in the field of radiation oncology.

A-377

Uncertainties in imaging: how they should be reported and propagated in prediction models using radiomics

L. P. Muren; Aarhus/DK

Learning Objectives

1. To understand how to incorporate radiomics into RT response models.
2. To discuss how uncertainties should be estimated and reported.
3. To explore the effect of image uncertainties in RT response models.

Abstract

"no abstract submitted"

A-378

Imaging banks: challenges and opportunities

A. Van der Lugt; Rotterdam/NL

Learning Objectives

1. To understand what is an imaging biobank.
2. To discuss how an imaging biobank can be integrated in cancer care.
3. To explore the intraoperability of clinical imaging biobank and other data repositories.

Abstract

An imaging biobank can be defined as an organised database of medical images and associated imaging biomarkers (radiology and beyond) shared among multiple researchers, and linked to other biorepositories. An imaging biobank is designed for scientific use. Image data are systematically analysed visually, manual, or (semi)-automated with the main aim to extract imaging biomarkers than can be related to patient characteristics such as medical history, genomic data, and outcome or disease characteristics such as genomic data, biomaterials or response to treatment. The data storage is structured in a way that the database can be queried and retrieved based on available metadata. To exploit the available information interactions with other databases are a perquisite. General requirements with respect to the data collection are, therefore, a database facilitating storage of image data and metadata, storage of derived image-based measurements, and storage of associated non-imaging data, taking into account the need to deal with longitudinal data, and to cope with multiple file formats. Finally, automated retrieval is needed for image analysis pipelines that extract image features for radiomics signatures or for hypothesis-free deep learning algorithms.

Discussion

Sorry
no recording
available

(no abstract)