Texture analysis of T1‐w and T2‐w MR images allows a quantitative evaluation of radiation‐induced changes of internal obturator muscles after radiotherapy for prostate cancer

Scalco, Elisa; Rancati, T.; Pirovano, Ileana; Mastropietro, Alfonso; Palorini, F.; Cicchetti, A.; Messina, A.; Avuzzi, B.; Valdagni, Riccardo; Rizzo, Giovanna

doi:10.1002/mp.12798

Cited by 7 publications

(14 citation statements)

References 51 publications

(114 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of these features have been also reported as predictive of treatment response in esophageal cancer, 36 able in differentiating prostate cancer aggressiveness 37 or able in characterizing structural modifications induced by RT in normal tissues. 23 Other studies focused on the reproducibility of T2w-MRI radiomic features in the prostate using different scanners, 20,24 and, among the considered features families, GLCM was the most reproducible and with higher ability in discriminating tumor and nontumor regions. Duron et al 26 found that the method used for image discretization has a major impact on the stability of MRI features and that the adoption of a fixed bin-width is preferable to the fixed bin number.…”

Section: Discussionmentioning

confidence: 99%

“…A more detailed description of the image registration and contour propagation procedure can be found in previous works. 23,28…”

Section: B Roi Identificationmentioning

confidence: 99%

“…14 Features extraction was performed in 2D, since the slice thickness was much larger than the in-plane dimension (3 mm vs. 0.456 mm). 23 For this reason, images were not resampled to isotropic voxels, in order to not introduce another step involving interpolation, as pixels were already isotropic in the in-plane resolution. No filtering was applied to the images.…”

Section: D Features Computationmentioning

confidence: 99%

“…19 In the context of prostate cancer, radiomics is currently routinely performed on T2w-MRI, as the most commonly available MRI acquisition, 15,20 to detect the tumor 21 or to explore the association with biochemical recurrence after radiotherapy (RT) 22 and to assess the effect of irradiation on organs at risk, such as the internal obturator muscles. 23 It is known that the performance of radiomic features are dependent on the type of analyzed tissue, for example tumor or normal tissue. Therefore, the reproducibility evaluation should be performed taking into consideration both pathological and healthy tissues in order to improve knowledge about how the structural properties of the different organs can impact the radiomics estimation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

T2w‐MRI signal normalization affects radiomics features reproducibility

et al. 2020

Self Cite

View full text Add to dashboard Cite

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 (Dfeature). 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 Dfeature 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 Dfeature 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 ...

show abstract

Section: Discussionmentioning

confidence: 99%

“…A more detailed description of the image registration and contour propagation procedure can be found in previous works. 23,28…”

Section: B Roi Identificationmentioning

confidence: 99%

Section: D Features Computationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

T2w‐MRI signal normalization affects radiomics features reproducibility

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…ΔIntensity and Δ95th percentile showed an upward trend with the dose, and the Gray‐level Co‐occurrence Matrix (ΔGLCM)‐contrast showed a decreasing trend with the dose. It is an imaging level reflection of the physiological structure change 30 …”

Section: Application Of Radiomics In Radiotherapymentioning

confidence: 99%

Radiomics in radiotherapy: Applications and future challenges

Qiu

Duan

Yin

2020

Precision Radiation Oncology

View full text Add to dashboard Cite

Radiomics has the potential to personalize patient treatment by using medical images that are already being acquired in clinical practice. Recently, with the development of computational and imaging technology, radiotherapy has brought unlimited opportunities driven by radiomics in individual cancer treatment and precision medicine care. This article reviews the advances in the application of radiomics in lung cancer, head and neck cancer, and other cancer sites. Additionally, we comment on the future challenges of radiomic research.

show abstract