Background: Radiomics is a promising methodology for quantitative analysis and description of radiological images using advanced mathematics and statistics. Tumor delineation, which is still often done manually, is an essential step in radiomics, however, inter-observer variability is a well-known uncertainty in radiation oncology. This study investigated the impact of inter-observer variability (IOV) in manual tumor delineation on the reliability of radiomic features (RF).

Methods: Three different tumor types (head and neck squamous cell carcinoma (HNSCC), malignant pleural mesothelioma (MPM) and non-small cell lung cancer (NSCLC)) were included. For each site, eleven individual tumors were contoured on CT scans by three experienced radiation oncologists. Dice coefficients (DC) were calculated for quantification of delineation variability. RF were calculated with an in-house developed software implementation, which comprises 1404 features: shape (n = 18), histogram (n = 17), texture (n = 137) and wavelet (n = 1232). The IOV of RF was studied using the intraclass correlation coefficient (ICC). An ICC >0.8 indicates a good reproducibility. For the stable RF, an average linkage hierarchical clustering was performed to identify classes of uncorrelated features.

Results: Median DC was high for NSCLC (0.86, range 0.57-0.90) and HNSCC (0.72, 0.21-0.89), whereas it was low for MPM (0.26, 0-0.9) indicating substantial IOV. Stability rate of RF correlated with DC and depended on tumor site, showing a high stability in NSCLC (90% of total parameters), acceptable stability in HNSCC (59% of total parameters) and low stability in MPM (36% of total parameters). Shape features showed the weakest stability across all tumor types. Hierarchical clustering revealed 14 groups of correlated and stable features for NSCLC and 6 groups for both HNSCC and MPM.

Conclusion: Inter-observer delineation variability has a relevant influence on radiomics analysis and is strongly influenced by tumor type. This leads to a reduced number of suitable imaging features.

Download full-text PDF

Source
http://dx.doi.org/10.1080/0284186X.2018.1445283DOI Listing

Publication Analysis

Top Keywords

delineation variability
12
total parameters
12
inter-observer delineation
8
stability tumor
8
tumor delineation
8
inter-observer variability
8
tumor types
8
hierarchical clustering
8
tumor
7
stability
6

Similar Publications

Objective: To delineate, within the framework of current clinical practice and criteria, the sustainability of first-line immuno-suppressive treatment discontinuation in rheumatoid arthritis (RA) and the impact of residual disease in remission on long-term drug-free (DF) outcomes.

Methods: RA patients, referring to the Pavia early arthritis clinic (EAC) between 2009 and 2021 and achieving remission after Disease Activity Score-driven methotrexate (MTX) monotherapy, were recruited. Eligible patients underwent DF follow-up at 3-month intervals over 5 years after MTX discontinuation.

View Article and Find Full Text PDF

Mitral Valve Prolapse Caused by TLL1 Gain-of-Function Mutation.

Can J Cardiol

January 2025

The Morris Kahn Laboratory of Human Genetics, Faculty of Health Sciences and National Institute of Biotechnology in the Negev, Ben Gurion University of the Negev, Be'er Sheva, Israel; Genetics Institute, Soroka University Medical Center, Be'er Sheva, Israel; The Danek Gertner Institute of Human Genetics, Sheba Medical Center, Ramat Gan, Israel. Electronic address:

Background: Mitral valve prolapse (MVP) is a common cardiac valvular anomaly that can be caused by mutations in genes of various biological pathways. Individuals of three generations of a kindred presented with apparently dominant heredity of isolated MVP.

Methods: Clinical evaluation and echocardiography for all complying family members (n=13).

View Article and Find Full Text PDF

Stabilised hyaluronic acid gel marker versus surgical clips for tumour bed delineation in breast cancer radiotherapy using MRI-simulation.

Radiother Oncol

January 2025

Department of Radiation Oncology Olivia Newton-John Cancer Wellness & Research Centre Austin Health Victoria Australia; Department of Medical Imaging and Radiation Sciences, Monash University Clayton Victoria Australia; Genesis Care, Ringwood Private Hospital Victoria Australia.

Background And Purpose: Compare breast cancer tumour bed (TB) delineation using stabilised hyaluronic acid (sHA) gel and MRI-simulation versus surgical clips and CT-simulation within same patient cohort.

Materials And Methods: Prospective single arm study of patients undergoing breast conserving surgery. Patients had both clips (≥5) and sHA gel markers inserted to define the TB and underwent MRI and CT simulation scans.

View Article and Find Full Text PDF

The Society of Thoracic Surgeons General Thoracic Surgery Database (STS GTSD) remains the largest and most comprehensive audited thoracic surgical database in the world. As the STS GTSD grows to nearly 1 million cases, the pulmonary resection for cancer and esophagectomy short-term risk models have been refined to provide participants with benchmarked performance reports to facilitate quality improvement efforts. New for 2025 will be the development of long-term risk models and the online release of both short- and long-term risk calculators.

View Article and Find Full Text PDF

SEEG guided mapping of primary motor cortex in children with epilepsy.

Epilepsy Res

January 2025

Epilepsy Program, Division of Neurology, Department of Pediatrics, Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada. Electronic address:

Background: Direct cortical electrical stimulation remains the gold standard for delineation of the primary motor cortex in patients with drug-resistant epilepsy (DRE) undergoing epilepsy surgery evaluation OBJECTIVE: This study aimed to explore the efficacy and safety of functional motor mapping through Stereo-EEG (SEEG) electrode contacts in children with DRE at our institute.

Methods: We performed a retrospective analysis of children who underwent SEEG evaluation and functional cortical mapping via bipolar electrical stimulation at our institution between July 2020 and June 2024. Detailed clinical, radiological and neurophysiological variable were extracted; qualitative and quantitative variables were summarized using appropriate descriptive statistics.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!