<i>In Vivo</i> Prediction of Kidney Stone Fragility Using Radiomics-Based Regression Models

Pillai, Parvathy Sudhir; Hsieh, Scott S.; Vercnocke, Andrew J.; Potretzke, Aaron M.; Koo, Kevin; McCollough, Cynthia H.; Ferrero, Andrea

doi:10.1089/end.2022.0483

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patro et al [18] enhanced network computational efficiency and diagnostic performance for kidney stone detection by introducing a Kronecker product-based convolution. Sudhir Pillai et al [19] integrated handcrafted features of kidney stone regions using a linear regression model to diagnose fragility. Additionally, as a crucial component of radiomics, research on automatic segmentation algorithms for the kidney and related lesions has been initiated.…”

Section: Introductionmentioning

confidence: 99%

CT-based radiomics: predicting early outcomes after percutaneous transluminal renal angioplasty in patients with severe atherosclerotic renal artery stenosis

Fu,

Fang,

Lin

et al. 2024

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

This study aimed to comprehensively evaluate non-contrast computed tomography (CT)-based radiomics for predicting early outcomes in patients with severe atherosclerotic renal artery stenosis (ARAS) after percutaneous transluminal renal angioplasty (PTRA). A total of 52 patients were retrospectively recruited, and their clinical characteristics and pretreatment CT images were collected. During a median follow-up period of 3.7 mo, 18 patients were confirmed to have benefited from the treatment, defined as a 20% improvement from baseline in the estimated glomerular filtration rate. A deep learning network trained via self-supervised learning was used to enhance the imaging phenotype characteristics. Radiomics features, comprising 116 handcrafted features and 78 deep learning features, were extracted from the affected renal and perirenal adipose regions. More features from the latter were correlated with early outcomes, as determined by univariate analysis, and were visually represented in radiomics heatmaps and volcano plots. After using consensus clustering and the least absolute shrinkage and selection operator method for feature selection, five machine learning models were evaluated. Logistic regression yielded the highest leave-one-out cross-validation accuracy of 0.780 (95%CI: 0.660–0.880) for the renal signature, while the support vector machine achieved 0.865 (95%CI: 0.769–0.942) for the perirenal adipose signature. SHapley Additive exPlanations was used to visually interpret the prediction mechanism, and a histogram feature and a deep learning feature were identified as the most influential factors for the renal signature and perirenal adipose signature, respectively. Multivariate analysis revealed that both signatures served as independent predictive factors. When combined, they achieved an area under the receiver operating characteristic curve of 0.888 (95%CI: 0.784–0.992), indicating that the imaging phenotypes from both regions complemented each other. In conclusion, non-contrast CT-based radiomics can be leveraged to predict the early outcomes of PTRA, thereby assisting in identifying patients with ARAS suitable for this treatment, with perirenal adipose tissue providing added predictive value.

show abstract

Section: Introductionmentioning

confidence: 99%

CT-based radiomics: predicting early outcomes after percutaneous transluminal renal angioplasty in patients with severe atherosclerotic renal artery stenosis

Fu,

Fang,

Lin

et al. 2024

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

show abstract

“…Statistical hypothesis testing and linear regression models are widely utilised in analysing the correlation between surgical parameters, conditions, and outcomes 15,16 . For SRI, the relationship between age and injection pressure has been found and modelled to assist surgeons in determining a better surgical setup 17 .…”

Section: Introductionmentioning

confidence: 99%

“…Statistical hypothesis testing and linear regression models are widely utilised in analysing the correlation between surgical parameters, conditions, and outcomes. 15,16 For SRI, the relationship between age and injection pressure has been found and modelled to assist surgeons in determining a better surgical setup. 17 However, establishing a comprehensive predictive model for bleb formation in SRI requires precise control of experimental variables and a large collection of experimental results.…”

mentioning

confidence: 99%

Analysis on key parameters in subretinal injection facilitating a predictable and automated robot‐assisted treatment in gene therapy

Huang

Yang

Chen

et al. 2023

Robotics Computer Surgery

View full text Add to dashboard Cite

BackgroundSubretinal injection (SRI) has become an important surgical method for treating vitreoretinal diseases. Nevertheless, the optimisation of bleb formation in SRI, for the attainment of desired therapeutic outcomes, still requires further investigation.MethodsThis study analysed the influence of surgical parameters on SRI using a robotic setup. The surgical procedure was automated using visual guidance. A predictive model for bleb formation was established through regression analysis. To validate the model, we compared the clinical data's target area with the simulated SRI's actual area using parameters determined by the predictive model.ResultsThe insertion angle dominated the eccentricity and area of the bleb. The injection speed dominated the axial angle. Automated SRI increased success rate and produced predictable outcomes.ConclusionsWe could provide accurate SRI on phantom models by adjusting surgical parameters based on the patient's clinical information. Automatic robot‐assisted SRI is a promising surgical technique with highly predictable results.

show abstract

Opportunities in Primary and Enteric Hyperoxaluria at the Cross-Roads Between the Clinic and Laboratory

Cellini,

Baum,

Frishberg

et al. 2024

Kidney International Reports

View full text Add to dashboard Cite

In Vivo Prediction of Kidney Stone Fragility Using Radiomics-Based Regression Models

Cited by 3 publications

References 21 publications

CT-based radiomics: predicting early outcomes after percutaneous transluminal renal angioplasty in patients with severe atherosclerotic renal artery stenosis

CT-based radiomics: predicting early outcomes after percutaneous transluminal renal angioplasty in patients with severe atherosclerotic renal artery stenosis

Analysis on key parameters in subretinal injection facilitating a predictable and automated robot‐assisted treatment in gene therapy

Opportunities in Primary and Enteric Hyperoxaluria at the Cross-Roads Between the Clinic and Laboratory

Contact Info

Product

Resources

About