English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Manual delineation of volumes of interest (VOIs) by experts is considered thegold-standard method in radiomics analysis. However, it suffers from inter- andintra-operator variability. A quantitative assessment of the impact ofvariations in these delineations on the performance of the radiomics predictorsis required to develop robust radiomics based prediction models. In this study,we developed radiomics models for the prediction of pathological completeresponse to neoadjuvant chemotherapy in patients with two different breastcancer subtypes based on contrast-enhanced magnetic resonance imaging acquiredprior to treatment (baseline MRI scans). Different mathematical operations suchas erosion, smoothing, dilation, randomization, and ellipse fitting wereapplied to the original VOIs delineated by experts to simulate variations ofsegmentation masks. The effects of such VOI modifications on various steps ofthe radiomics workflow, including feature extraction, feature selection, andprediction performance, were evaluated. Using manual tumor VOIs and radiomicsfeatures extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 wasachieved for human epidermal growth receptor 2 positive and triple-negativebreast cancer, respectively. For smoothing and erosion, VOIs yielded thehighest number of robust features and the best prediction performance, whileellipse fitting and dilation lead to the lowest robustness and predictionperformance for both breast cancer subtypes. At most 28% of the selectedfeatures were similar to manual VOIs when different VOI delineation data wereused. Differences in VOI delineation affects different steps of radiomicsanalysis, and their quantification is therefore important for development ofstandardized radiomics research.

Breast MRI radiomics and machine learning radiomics-based predictions of  response to neoadjuvant chemotherapy -- how are they affected by variations  in tumour delineation?