PO-0981: Results from the Image Biomarker Standardisation Initiative

Zwanenburg, Alex; Abdalah, Mahmoud A.; Apte, Aditya; Ashrafinia, Saeed; Beukinga, J.; Bogowicz, Marta; Dinh, C. V.; Goetz, MP; Hatt, Mathieu; Leijenaar, Ralph T.H.; Lenkowicz, Jacopo; Morin, Olivier; Rao, Arvind; Fernandez, Jairo Socarras; Vallières, Martin; Dijk, Lisanne V. van; Griethuysen, Jennifer van; Velden, Floris H. P. van; Whybra, Philip; Troost, Esther G.C.; Richter, Corinna; Loeck, S.

doi:10.1016/s0167-8140(18)31291-x

Cited by 334 publications

(561 citation statements)

References 0 publications

Supporting

Mentioning

540

Contrasting

Unclassified

Order By: Relevance

“…Then, a set of CT images of a lung cancer patient was used to standardize the image-processing steps. The initiative is now reaching completion, and a consensus on image processing and computation of features was reached over time (20,21). However, more work is likely necessary to define and benchmark MRI-and PET-specific imageprocessing steps.…”

Section: Guidelines For Improving Quality Of Radiomics Analysesmentioning

confidence: 99%

Responsible Radiomics Research for Faster Clinical Translation

et al. 2017

View full text Add to dashboard Cite

show abstract

Section: Guidelines For Improving Quality Of Radiomics Analysesmentioning

confidence: 99%

Responsible Radiomics Research for Faster Clinical Translation

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The new interpolation grid must be defined by mean of its size and positioning with respect to the original grid. Several techniques exist for grid positioning, and three are reported by IBSI as “fit to original grid,” “align grid origins,” and “align grid centers.” Image biomarker standardization initiative guidelines also state that both the interpolated image and binary mask must retain their original data type. As for the latter, if interpolation does not preserve its Boolean data type, the mask should be converted to logical values by using a threshold

δ

(default value equal to 0.5).…”

Section: Methodsmentioning

confidence: 99%

“…In S‐IBEX, both aspects have been conformed to the standard, and all feature definitions have been re‐implemented. IS and IH categories: water CT number resetting was necessary for both feature categories. IBSI compliant discretization has been adopted for IH category. GLCM category: the IBEX approach to GLCM matrix calculation has been modified to support the five aggregation methods defined for directionally dependent feature families (2D:avg, 2D:mrg, 2D:vmrg, 3D:avg, and 3D:mrg) . Methods identified with “avg” average features extracted from different textural matrices, while those identified by “mrg” merge textural matrices before feature extraction. GLRLM category: in IBEX, textural matrix extraction is only implemented in a by‐slice manner.…”

Section: Methodsmentioning

confidence: 99%

“…Methods identified with “avg” average features extracted from different textural matrices, while those identified by “mrg” merge textural matrices before feature extraction. GLRLM category: in IBEX, textural matrix extraction is only implemented in a by‐slice manner. In S‐IBEX all five aforementioned approaches have been implemented. NGTDM category: the IBEX approach to NGTDM matrix calculation has been modified to support the three aggregation methods defined for rotationally invariant feature families (2D:avg, 2D:mrg, and 3D). LI, IVH, GLSZM, GLDZM, and NGLDM: those categories are not available in IBEX and have been implemented in S‐IBEX following IBSI guidelines . The filtering step required by LI is achieved using a proper ellipsoidal mean convolution filter as suggested by IBSI.…”

Section: Methodsmentioning

confidence: 99%

“…The complete list of all S‐IBEX features, grouped by type of intervention and by category, can be found in Table . The detailed definition of each feature and explanation can be found in the original IBSI text …”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Technical Note: An IBEX adaption toward image biomarker standardization

et al. 2020

View full text Add to dashboard Cite

Purpose Interest in the field of radiomics is rapidly growing because of its potential to characterize tumor phenotype and provide predictive and prognostic information. Nevertheless, the reproducibility and robustness of radiomics studies are hampered by the lack of standardization in feature definition and calculation. In the context of the image biomarker standardization initiative (IBSI), we investigated the grade of compliance of the image biomarker explorer (IBEX), a free open‐source radiomic software, and we developed and validated standardized‐IBEX (S‐IBEX), an adaptation of IBEX to IBSI. Methods Image biomarker explorer source code was checked against IBSI standard. Both the feature implementation and the overall image preprocessing chain were evaluated. Sections were re‐implemented wherever differences emerged: in particular, contour‐to‐binary‐mask conversion, image sub‐portion extraction, re‐segmentation, gray‐level discretization and interpolation were aligned to IBSI. All reported IBSI features were implemented in S‐IBEX. On a patient phantom, S‐IBEX was validated by benchmarking five different preprocessing configurations proposed by IBSI. Results Most IBEX feature definitions are IBSI compliant; however, IBEX preprocessing introduces non‐negligible nonconformities, resulting in feature values not aligned with the corresponding IBSI benchmarks. On the contrary, S‐IBEX features are in agreement with the standard regardless of preprocessing configurations: the percentage of features equal to their benchmark values ranges from 98.1% to 99.5%, with overall maximum percentage error below 1%. Moreover, the impact of noncompliant preprocessing steps has been assessed: in these cases, the percentage of features equal to the standard drops below 35%. Conclusions The use of standardized software for radiomic feature extraction is essential to ensure the reproducibility of results across different institutions, easing at the same time their external validation. This work presents and validates S‐IBEX, a free IBSI‐compliant software, developed upon IBEX, for feature extraction that is both easy to use and quantitatively accurate.

show abstract

Computational approaches to detect small lesions in ¹⁸F‐FDG PET/CT scans

Nichols

DiFilippo

Palestro

2021

J Applied Clin Med Phys

View full text Add to dashboard Cite

When physicians interpret 18 F-FDG PET/CT scans, they rely on their subjective visual impression of the presence of small lesions, the criteria for which may vary among readers. Our investigation used physical phantom scans to evaluate whether image texture analysis metrics reliably correspond to visual criteria used to identify lesions and accurately differentiate background regions from sub-centimeter simulated lesions. Methods: Routinely collected quality assurance test data were processed retrospectively for 65 different 18 F-FDG PET scans performed of standardized phantoms on eight different PET/CT systems. Phantoms included 8-, 12-, 16-, and 25-mm diameter cylinders embedded in a cylindrical water bath, prepared with 2.5:1 activity-to-background ratio emulating typical whole-body PET protocols. Voxel values in cylinder regions and background regions were sampled to compute several classes of image metrics. Two experienced physicists, blinded to quantified image metrics and to each other's readings, independently graded cylinder visibility on a 5-level scale (0 = definitely not visible to 4 = definitely visible). Results:The three largest cylinders were visible in 100% of cases with a mean visibility score of 3.3 ± 1.2, while the smallest 8-mm cylinder was visible in 58% of cases with a significantly lower mean visibility score of 1.5±1.1 (P < 0.0001). By ROC analysis, the polynomial-fit signal-to-noise ratio was the most accurate at discriminating 8-mm cylinders from the background, with accuracy greater than visual detection (93% ± 2% versus 76% ± 4%, P = 0.0001), and better sensitivity (94% versus 58%, P < 0.0001). Conclusion: Image texture analysis metrics are more sensitive than visual impressions for detecting sub-centimeter simulated lesions. Therefore, image texture analysis metrics are potentially clinically useful for 18 F-FDG PET/CT studies.

show abstract

PO-0981: Results from the Image Biomarker Standardisation Initiative

Cited by 334 publications

References 0 publications

Responsible Radiomics Research for Faster Clinical Translation

Responsible Radiomics Research for Faster Clinical Translation

Technical Note: An IBEX adaption toward image biomarker standardization

Computational approaches to detect small lesions in ¹⁸F‐FDG PET/CT scans

Contact Info

Product

Resources

About

PO-0981: Results from the Image Biomarker Standardisation Initiative

Cited by 334 publications

References 0 publications

Responsible Radiomics Research for Faster Clinical Translation

Responsible Radiomics Research for Faster Clinical Translation

Technical Note: An IBEX adaption toward image biomarker standardization

Computational approaches to detect small lesions in 18F‐FDG PET/CT scans

Contact Info

Product

Resources

About

Computational approaches to detect small lesions in ¹⁸F‐FDG PET/CT scans