T2w‐MRI signal normalization affects radiomics features reproducibility

Published on Apr 1, 2020in Medical Physics3.317
· DOI :10.1002/MP.14038
Elisa Scalco11
Estimated H-index: 11
,
Antonella Belfatto5
Estimated H-index: 5
+ 5 AuthorsGiovanna Rizzo34
Estimated H-index: 34
Sources
Abstract
PURPOSE: Despite its increasing application, radiomics has not yet demonstrated a solid reliability, due to the difficulty in replicating analyses. The extraction of radiomic features from clinical MRI (T1w/T2w) presents even more challenges because of the absence of well-defined units (e.g. HU). Some preprocessing steps are required before the estimation of radiomic features and one of this is the intensity normalization, that can be performed using different methods. The aim of this work was to evaluate the effect of three different normalization techniques, applied on T2w-MRI images of the pelvic region, on radiomic features reproducibility. METHODS: T2w-MRI acquired before (MRI1) and 12 months after radiotherapy (MRI2) from 14 patients treated for prostate cancer were considered. Four different conditions were analyzed: (a) the original MRI (No_Norm); (b) MRI normalized by the mean image value (Norm_Mean); (c) MRI normalized by the mean value of the urine in the bladder (Norm_ROI); (d) MRI normalized by the histogram-matching method (Norm_HM). Ninety-one radiomic features were extracted from three organs of interest (prostate, internal obturator muscles and bulb) at both time-points and on each image discretized using a fixed bin-width approach and the difference between the two time-points was calculated (Deltafeature). To estimate the effect of normalization methods on the reproducibility of radiomic features, ICC was calculated in three analyses: (a) considering the features extracted on MRI2 in the four conditions together and considering the influence of each method separately, with respect to No_Norm; (b) considering the features extracted on MRI2 in the four conditions with respect to the inter-observer variability in region of interest (ROI) contouring, considering also the effect of the discretization approach; (c) considering Deltafeature to evaluate if some indices can recover some consistency when differences are calculated. RESULTS: Nearly 60% of the features have shown poor reproducibility (ICC < 0.5) on MRI2 and the method that most affected features reliability was Norm_ROI (average ICC of 0.45). The other two methods were similar, except for first-order features, where Norm_HM outperformed Norm_Mean (average ICC = 0.33 and 0.76 for Norm_Mean and Norm_HM, respectively). In the inter-observer setting, the number of reproducible features varied in the three structures, being higher in the prostate than in the penile bulb and in the obturators. The analysis on Deltafeature highlighted that more than 60% of the features were not consistent with respect to the normalization method and confirmed the high reproducibility of the features between Norm_Mean and Norm_HM, whereas Norm_ROI was the less reproducible method. CONCLUSIONS: The normalization process impacts the reproducibility of radiomic features, both in terms of changes in the image information content and in the inter-observer setting. Among the considered methods, Norm_Mean and Norm_HM seem to provide the most reproducible features with respect to the original image and also between themselves, whereas Norm_ROI generates less reproducible features. Only a very small subset of feature remained reproducible and independent in any tested condition, regardless the ROI and the adopted algorithm: skewness or kurtosis, correlation and one among Imc2, Idmn and Idn from GLCM group.
📖 Papers frequently viewed together
20207.93Radiology
63 Authors (Alex Zwanenburg, ..., Steffen Löck)
354 Citations
7 Citations
11 Citations
References40
Newest
#1Helen Yu Chi Wang (University of Surrey)H-Index: 1
#2Ellen M. Donovan (University of Surrey)H-Index: 23
Last. Philip M. Evans (University of Surrey)H-Index: 53
view all 11 authors...
This paper studies the sensitivity of a range of image texture parameters used in radiomics to: i) the number of intensity levels, ii) the method of quantisation to select the intensity levels and iii) the use of an intensity threshold. 43 commonly used texture features were studied for the gross target volume outlined on the CT component of PET/CT scans of 50 patients with non-small cell lung carcinoma (NSCLC). All cases were quantised for all values between 4 and 128 intensity levels using fou...
3 CitationsSource
#1Michael Schwier (Harvard University)H-Index: 13
#2Joost J. M. van Griethuysen (NKI-AVL: Netherlands Cancer Institute)H-Index: 9
Last. Andrey Fedorov (Harvard University)H-Index: 3
view all 10 authors...
In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics fe...
60 CitationsSource
#1Sandra Fiset (Princess Margaret Cancer Centre)H-Index: 2
#2Mattea L Welch (Princess Margaret Cancer Centre)H-Index: 4
Last. Kathy Han (U of T: University of Toronto)H-Index: 5
view all 12 authors...
Abstract Purpose The aims of this study are to evaluate the stability of radiomic features from T2-weighted MRI of cervical cancer in three ways: (1) repeatability via test–retest; (2) reproducibility between diagnostic MRI and simulation MRI; (3) reproducibility in inter-observer setting. Materials and methods This retrospective cohort study included FIGO stage IB-IVA cervical cancer patients treated with chemoradiation between 2005 and 2014. There were three cohorts of women corresponding to e...
36 CitationsSource
#1Prathyush Chirra (Case Western Reserve University)H-Index: 3
#2Patrick Leo (Case Western Reserve University)H-Index: 6
Last. Satish Viswanath (Case Western Reserve University)H-Index: 15
view all 9 authors...
Recent advances in the field of radiomics have enabled the development of a number of prognostic and predictive imaging-based tools for a variety of diseases. However, wider clinical adoption of these tools is contingent on their generalizability across multiple sites and scanners. This may be particularly relevant in the context of radiomic features derived from T1- or T2-weighted magnetic resonance images (MRIs), where signal intensity values are known to lack tissue-specific meaning and vary ...
14 CitationsSource
#1Loïc Duron (Paris V: Paris Descartes University)H-Index: 6
#2Daniel Balvay (Paris V: Paris Descartes University)H-Index: 20
Last. Augustin LeclerH-Index: 14
view all 9 authors...
OBJECTIVES: To assess the influence of gray-level discretization on inter- and intra-observer reproducibility of texture radiomics features on clinical MR images. MATERIALS AND METHODS: We studied two independent MRI datasets of 74 lacrymal gland tumors and 30 breast lesions from two different centers. Two pairs of readers performed three two-dimensional delineations for each dataset. Texture features were extracted using two radiomics softwares (Pyradiomics and an in-house software). Reproducib...
44 CitationsSource
#1Mattea L Welch (Princess Margaret Cancer Centre)H-Index: 4
#1Mattea Welch (Princess Margaret Cancer Centre)H-Index: 6
Last. David A. JaffrayH-Index: 96
view all 11 authors...
Abstract Purpose Refinement of radiomic results and methodologies is required to ensure progression of the field. In this work, we establish a set of safeguards designed to improve and support current radiomic methodologies through detailed analysis of a radiomic signature. Methods A radiomic model (MW2018) was fitted and externally validated using features extracted from previously reported lung and head and neck (HN i.e. images without meaningful texture. To determine MW2018’s added benefit, t...
96 CitationsSource
#1Alberto Traverso (UM: Maastricht University)H-Index: 10
#2Leonard Wee (UM: Maastricht University)H-Index: 15
Last. Robert J. GilliesH-Index: 106
view all 4 authors...
Purpose An ever-growing number of predictive models used to inform clinical decision making have included quantitative, computer-extracted imaging biomarkers, or “radiomic features.” Broadly generalizable validity of radiomics-assisted models may be impeded by concerns about reproducibility. We offer a qualitative synthesis of 41 studies that specifically investigated the repeatability and reproducibility of radiomic features, derived from a systematic review of published peer-reviewed literatur...
198 CitationsSource
#1Karen Buch (BU: Boston University)H-Index: 14
#2Hirofumi Kuno (BU: Boston University)H-Index: 9
Last. Osamu Sakai (BU: Boston University)H-Index: 30
view all 5 authors...
OBJECTIVES: To evaluate the influence of MRI scanning parameters on texture analysis features. METHODS: Publicly available data from the Reference Image Database to Evaluate Therapy Response (RIDER) project sponsored by The Cancer Imaging Archive included MRIs on a phantom comprised of 18 25-mm doped, gel-filled tubes, and 1 20-mm tube containing 0.25 mM Gd-DTPA (EuroSpinII Test Object5, Diagnostic Sonar, Ltd, West Lothian, Scotland). MRIs performed on a 1.5 T GE HD, 1.5 T Siemens Espree (VB13),...
26 CitationsSource
#1Dongdong Xiao (HUST: Huazhong University of Science and Technology)H-Index: 3
#2Pengfei Yan (HUST: Huazhong University of Science and Technology)H-Index: 39
Last. Hongyang Zhao (HUST: Huazhong University of Science and Technology)H-Index: 14
view all 5 authors...
Abstract Objectives To investigate the diagnostic value of magnetic resonance imaging (MRI)-based 3D texture and shape features in the differentiation of glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL). Patients and methods A total of eighty-two patients, including sixty patients with GBM and twenty-two patients with PCNSL were followed up retrospectively from January 2012 to September 2017. MRI-based 3D texture and shape analysis were performed to evaluate the detectable ...
16 CitationsSource
#1Elisa ScalcoH-Index: 11
#2Tiziana RancatiH-Index: 27
Last. Giovanna RizzoH-Index: 34
view all 10 authors...
PURPOSE: To investigate the potential of texture analysis applied on T2-w and postcontrast T1-w images acquired before radiotherapy for prostate cancer (PCa) and 12 months after its completion in quantitatively characterizing local radiation effect on the muscular component of internal obturators, as organs potentially involved in urinary toxicity. METHODS: T2-w and postcontrast T1-w MR images were acquired at 1.5 T before treatment (MRI1) and at 12 months of follow-up (MRI2) in 13 patients trea...
4 CitationsSource
Cited By19
Newest
#1Nikita Sushentsev (University of Cambridge)H-Index: 5
#2Leonardo Rundo (University of Cambridge)H-Index: 18
Last. Tristan Barrett (University of Cambridge)H-Index: 36
view all 0 authors...
Nearly half of patients with prostate cancer (PCa) harbour low- or intermediate-risk disease considered suitable for active surveillance (AS). However, up to 44% of patients discontinue AS within the first five years, highlighting the unmet clinical need for robust baseline risk-stratification tools that enable timely and accurate prediction of tumour progression. In this proof-of-concept study, we sought to investigate the added value of MRI-derived radiomic features to standard-of-care clinica...
Source
PURPOSE Many studies of MRI radiomics do not include the discretization method used for the analyses, which might indicate that the discretization methods used are considered irrelevant. Our goals were to compare three frequently used discretization methods (lesion relative resampling (LRR), lesion absolute resampling (LAR) and absolute resampling (AR)) applied to the same data set, along with two different lesion segmentation approaches. METHODS We analyzed the effects of altering bin widths or...
Source
#3Corinne Balleyguier (Commissariat à l'énergie atomique et aux énergies alternatives)
In brain MRI radiomics studies, the non-biological variations introduced by different image acquisition settings, namely scanner effects, affect the reliability and reproducibility of the radiomics results. This paper assesses how the preprocessing methods (including N4 bias field correction and image resampling) and the harmonization methods (either the six intensity normalization methods working on brain MRI images or the ComBat method working on radiomic features) help to remove the scanner e...
Source
#2Abdalla IbrahimH-Index: 8
Last. Marjolein L. SmidtH-Index: 28
view all 13 authors...
This retrospective study investigated the value of pretreatment contrast-enhanced Magnetic Resonance Imaging (MRI)-based radiomics for the prediction of pathologic complete tumor response to neoadjuvant systemic therapy in breast cancer patients. A total of 292 breast cancer patients, with 320 tumors, who were treated with neo-adjuvant systemic therapy and underwent a pretreatment MRI exam were enrolled. As the data were collected in two different hospitals with five different MRI scanners and v...
Source
#1Stefanie J. Hectors (Cornell University)H-Index: 16
#2Christine P. Chen (Cornell University)H-Index: 10
Last. Jim C. Hu (Cornell University)H-Index: 68
view all 9 authors...
Background While Prostate Imaging Reporting and Data System (PI-RADS) 4 and 5 lesions typically warrant prostate biopsy and PI-RADS 1 and 2 lesions may be safely observed, PI-RADS 3 lesions are equivocal. Purpose To construct and cross-validate a machine learning model based on radiomics features from T2 -weighted imaging (T2 WI) of PI-RADS 3 lesions to identify clinically significant prostate cancer (csPCa), that is, pathological Grade Group ≥ 2. Study type Single-center retrospective study. Po...
1 CitationsSource
Source
#1Yu Guo (JLU: Jilin University)H-Index: 3
#2Quan Wang (JLU: Jilin University)
Last. Huimao Zhang (JLU: Jilin University)H-Index: 10
view all 6 authors...
Perineural invasion (PNI) as a grossly underreported independent risk predictor in rectal cancer is hard to identify preoperatively. We aim to predict PNI status in rectal cancer using multi-modality radiomics. In total, 396 radiomics features were extracted from T2-weighted images (T2WIs), diffusion-weighted images (DWIs), and portal venous phase of contrast-enhanced CT (CE-CT) respectively of 94 consecutive patients with histologically confirmed rectal cancer. T2WI score, DWI score, and CT sco...
Source
#1Lorena Escudero Sanchez (University of Cambridge)
#2Leonardo Rundo (University of Cambridge)H-Index: 18
Last. Evis Sala (University of Cambridge)H-Index: 56
view all 6 authors...
Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for ...
Source
Abstract Immunotherapies are leading to improved outcomes for many cancers, including those with devastating prognoses. As therapies like immune checkpoint inhibitors (ICI) become a mainstay in treatment regimens, many concurrent challenges have arisen – for instance, delineating clinical responders from non-responders. Predicting response has proven to be difficult given a lack of consistent and accurate biomarkers, heterogeneity of the tumor microenvironment (TME), and a poor understanding of ...
Source
#1Isabella Castiglioni (University of Milan)H-Index: 30
#2Leonardo Rundo (University of Cambridge)H-Index: 18
Last. Francesco Sardanelli (University of Milan)H-Index: 58
view all 10 authors...
Abstract Purpose Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context. Methods A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections. Results We first illustrate the architectural characte...
2 CitationsSource