Utility of CT Texture Analysis in Differentiating Low-Attenuation Renal Cell Carcinoma From Cysts: A Bi-Institutional Retrospective Study

Kim, Nathan Y.; Lubner, Meghan G.; Nystrom, Jered; Swietlik, John F.; Abel, E. Jason; Havighurst, Thomas C.; Silverman, Stuart G.; McGahan, John P.; Pickhardt, Perry J.

doi:10.2214/ajr.19.21182

Cited by 20 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the combined model, the top two radiomic features selected by LASSO in cohort A (wavelet-LLL_gldm_DependenceNonUniformityNormalized.Iodine and original_glszm_ZoneEntropy.75keV) and cohort B (wavelet-LLL_glcm_Correlation.75keV and wavelet-LLL_glszm_ZoneEntropy.75keV) were related to the distribution and dependency of gray level values, with a higher value indicating more heterogeneity (enhancing lesions) in the texture patterns. Our results were consistent with a previous study using texture analysis of unenhanced single-energy CT images for differentiating low attenuation (≤20 HU) RCCs from simple renal cysts, the diagnostic performance of entropy was comparable to subjective evaluation by two expert readers (AUC = 0.89 vs. 0.90, respectively) (31).…”

Section: Discussionsupporting

confidence: 92%

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

et al. 2021

View full text Add to dashboard Cite

Background The value of dual-energy computed tomography (DECT)-based radiomics in renal lesions is unknown. Purpose To develop DECT-based radiomic models and assess their incremental values in comparison to conventional measurements for differentiating enhancing from non-enhancing small renal lesions. Material and Methods A total of 349 patients with 519 small renal lesions (390 non-enhancing, 129 enhancing) who underwent contrast-enhanced nephrographic phase DECT examinations between June 2013 and January 2020 on multiple DECT platforms were retrospectively recruited. Cohort A included all lesions, while cohort B included Bosniak II–IV and solid enhancing renal lesions. Radiomic models were built with features selected by the least absolute shrinkage and selection operator regression (LASSO). ROC analyses were performed to compare the diagnostic accuracy among conventional and radiomic models for predicting enhancing renal lesions. Results The individual iodine concentration (IC), normalized IC, mean attenuation on 75-keV images, radiomic model of iodine images, 75-keV images and a combined model integrating all the above-mentioned features all demonstrated high AUCs for predicting renal lesion enhancement in cohort A (AUCs = 0.934–0.979) as well as in the test dataset (AUCs = 0.892–0.962) of cohort B ( P values with Bonferroni correction >0.003). The AUC (0.864) of mean attenuation on 75-keV images was significantly lower than those of other models (all P values ≤0.001) except the radiomic model of 75-keV images ( P = 0.038) in the training dataset of cohort B. Conclusion No incremental value was found by adding radiomic and machine learning analyses to iodine images for differentiating enhancing from non-enhancing renal lesions.

show abstract

Section: Discussionsupporting

confidence: 92%

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

et al. 2021

View full text Add to dashboard Cite

show abstract

“…When CTTA of unenhanced CT images was used in a study to distinguish benign cysts from low attenuation RCCs, the authors found that entropy was the most beneficial texture feature. By applying a 3.9 threshold determined by a ROC analysis, the two subtypes could be differentiated with a sensitivity of 81% and a specificity of 89% [29]. It is still highly challenging to interpret subtypes of RCC with high confidence based on visual inspection only because overlapping morphological characteristics may be present.…”

Section: Differentiating Between Renal Masses With Radiomicsmentioning

confidence: 99%

CT texture analysis of abdominal lesions – Part II: Tumors of the Kidney and Pancreas

Frank

Shariati

Budai

et al. 2021

Imaging

View full text Add to dashboard Cite

It has been proven in a few early studies that radiomic analysis offers a promising opportunity to detect or differentiate between organ lesions based on their unique texture parameters. Recently, the utilization of CT texture analysis (CTTA) has been receiving significant attention, especially for response evaluation and prognostication of different oncological diagnoses. In this review article, we discuss the unique ability of radiomics and its subfield CTTA to diagnose lesions in the pancreas and kidney. We review studies in which CTTA was used for the classification of histology grades in pancreas and kidney tumors. We also review the role of radiogenomics in the prediction of the molecular and genetic subtypes of pancreatic tumors. Furthermore, we provide a short report on recent advancements of radiomic analysis in predicting prognosis and survival of patients with pancreatic and renal cancers.

show abstract

“…CT texture analysis is an emerging imaging post-processing technique that can provide textural features by quantifying tissue grey-level patterns. Compared with conventional imaging alone, adding CT texture analysis can enhance the diagnosis ability in benign and malignant neoplasm differentiation 11 , the grading of tumours 12 , 13 and the prediction of a therapeutic response 14 , 15 . However, to our knowledge, no study has performed in vivo CT texture analysis to test the predictive value of the first postoperative CT for future aneurysm expansion.…”

Section: Introductionmentioning

confidence: 99%

CT texture analysis predicts abdominal aortic aneurysm post-endovascular aortic aneurysm repair progression

Ding

Hao

Wang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

The aim of this study is to investigate the role of early postoperative CT texture analysis in aneurysm progression. Ninety-nine patients who had undergone post-endovascular aneurysm repair (EVAR) infra-renal abdominal aortic aneurysm CT serial scans were enrolled from July 2014 to December 2019. The clinical and traditional imaging features were obtained. Aneurysm texture analysis was performed using three methods-the grey-level co-occurrence matrix (GLCM), the grey-level run length matrix (GLRLM), and the grey-level difference method (GLDM). A multilayer perceptron neural network was applied as a classifier, and receiver operating characteristic (ROC) curve analysis and area under the curve (AUC) analysis were employed to illustrate the classification performance. No difference was found in the morphological and clinical features between the expansion (+) and (−) groups. GLCM yielded the best performance with an accuracy of 85.17% and an AUC of 0.90, followed by GLRLM with an accuracy of 87.23% and an AUC of 0.8615, and GLDM with an accuracy of 86.09% and an AUC of 0.8313. All three texture analyses showed superior predictive ability over clinical risk factors (accuracy: 69.41%; AUC: 0.6649), conventional imaging features (accuracy: 69.02%; AUC: 0.6747), and combined (accuracy: 75.29%; AUC: 0.7249). Early post-EVAR arterial phase-derived aneurysm texture analysis is a better predictor of later aneurysm expansion than clinical factors and traditional imaging evaluation combined. Abdominal aortic aneurysm (AAA) is a prevalent irreversible cardiovascular disease with a high mortality rate that needs immediate surgical intervention. Endovascular aortic aneurysm repair (EVAR) is the preferable choice for patients with AAA as a minimally invasive procedure, but intensive surveillance is recommended to detect possible postoperative aneurysm sac enlargement, the most recognised indicator of AAA rupture 1 , and for which secondary intervention is often performed to prevent deadly progression 2,3. Computed tomography (CT) is commonly used after EVAR for follow-up surveillance, and enhanced CT is usually performed as the first postoperative imaging modality to evaluate the outcome of EVAR surgery and make further individual treatment plans 1,4. Endoleak can easily be observed on postoperative CT and is detected in nearly 32% of AAAs 5. A classic sign of an endoleak is the observation of contrast agent overflow out of the stent-graft. Nevertheless, the long-term significance of the first noticed endoleak is debatable, transient endoleaks can be resolved spontaneously without medical intervention 6,7. Additionally, late-onset endoleaks are typically detected 6 months later after EVAR and are usually occult on the first CT scan 8,9. Thus, the detection of endoleaks on the first operative CT alone is limited to guide clinical decisions, and periodic imaging follow-up is still needed to monitor the evolution of AAA 10 , thus raising the medical expenditure, ionisation radiation, and potential harm to renal function.

show abstract

Utility of CT Texture Analysis in Differentiating Low-Attenuation Renal Cell Carcinoma From Cysts: A Bi-Institutional Retrospective Study

Cited by 20 publications

References 32 publications

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

Can radiomic analysis of a single-phase dual-energy CT improve the diagnostic accuracy of differentiating enhancing from non-enhancing small renal lesions?

CT texture analysis of abdominal lesions – Part II: Tumors of the Kidney and Pancreas

CT texture analysis predicts abdominal aortic aneurysm post-endovascular aortic aneurysm repair progression

Contact Info

Product

Resources

About