Malignancy risk stratification of cystic renal lesions based on a contrast-enhanced CT-based machine learning model and a clinical decision algorithm

Dana, Jérémy; Lefebvre, Thierry L.; Savadjiev, Peter; Bodard, Sylvain; Gauvin, Simon; Bhatnagar, Sahir; Forghani, Reza; Hélénon, O.; Reinhold, Caroline

doi:10.1007/s00330-021-08449-w

Cited by 17 publications

(15 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 33 An ML model allowed to distinguish benign from malignant cystic renal lesions on CT with an AUC of 0.96 and a benefit in the clinical decision algorithm over management guidelines based on Bosniak classification. 34 Similarly, an AI-based DL model correctly predicted the majority of benign and malignant pancreatic cystic lesions and outperformed Fukuoka guidelines. 35 In the risk stratification of endometrial cancer, several features identified on T2-weighted MRI were selected to build a predictive ML model, which demonstrated an accuracy of 71% and 72% in the training and test datasets, respectively.…”

Section: Risk Stratificationmentioning

confidence: 87%

Artificial Intelligence in the Era of Precision Oncological Imaging

Cellina

Cè

Khenkina

et al. 2022

Technol Cancer Res Treat

View full text Add to dashboard Cite

Rapid-paced development and adaptability of artificial intelligence algorithms have secured their almost ubiquitous presence in the field of oncological imaging. Artificial intelligence models have been created for a variety of tasks, including risk stratification, automated detection, and segmentation of lesions, characterization, grading and staging, prediction of prognosis, and treatment response. Soon, artificial intelligence could become an essential part of every step of oncological workup and patient management. Integration of neural networks and deep learning into radiological artificial intelligence algorithms allow for extrapolating imaging features otherwise inaccessible to human operators and pave the way to truly personalized management of oncological patients. Although a significant proportion of currently available artificial intelligence solutions belong to basic and translational cancer imaging research, their progressive transfer to clinical routine is imminent, contributing to the development of a personalized approach in oncology. We thereby review the main applications of artificial intelligence in oncological imaging, describe the example of their successful integration into research and clinical practice, and highlight the challenges and future perspectives that will shape the field of oncological radiology.

show abstract

Section: Risk Stratificationmentioning

confidence: 87%

Artificial Intelligence in the Era of Precision Oncological Imaging

Cellina

Cè

Khenkina

et al. 2022

Technol Cancer Res Treat

View full text Add to dashboard Cite

show abstract

“…In addition, we evaluated the accuracy of our SVC against that of an expert radiologist, which showed that the performance of the machine learning model is comparable (accuracy of 0.79 vs. 0.78 on the external dataset) which further supports the current literature and demonstrates the potential of CT texture analysis in this application. The majority of the previously published studies focused on differentiating between benign and malignant kidney lesions (28)(29)(30) or identifying aggressive tumor features of ccRCCs (31-37), and only a handful of studies aimed to distinguish between the RCC subtypes (20,(38)(39)(40)(41). It is important to highlight that previous studies used different softwares for radiomics feature extraction including both in-house developed algorithms (40,41), and open-source tools such as the MaZda software (39) and the pyRadiomics package (38) which complicates the direct comparison of the previously published results.…”

Section: Discussionmentioning

confidence: 99%

“…The majority of the previously published studies focused on differentiating between benign and malignant kidney lesions ( 28 – 30 ) or identifying aggressive tumor features of ccRCCs ( 31 – 37 ), and only a handful of studies aimed to distinguish between the RCC subtypes ( 20 , 38 – 41 ). It is important to highlight that previous studies used different softwares for radiomics feature extraction including both in-house developed algorithms ( 40 , 41 ), and open-source tools such as the MaZda software ( 39 ) and the pyRadiomics package ( 38 ) which complicates the direct comparison of the previously published results.…”

Section: Discussionmentioning

confidence: 99%

“…Previously published studies have focused mainly on distinguishing between benign and malignant renal lesions ( 28 – 30 ) or on identifying aggressive tumor features of ccRCCs ( 31 – 37 ), and only a minority of studies have sought to distinguish between subtypes of RCC ( 20 , 38 – 41 ). A few studies also showed that radiomics analysis combined with machine learning could facilitate the non-invasive diagnostics of kidney cancers including both classification of renal tumors, prediction of nuclear grade, identification of patients with poor prognosis, and prediction of treatment response ( 42 , 43 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Budai

Stollmayer²,

Rónaszéki³

et al. 2022

Front. Med.

View full text Add to dashboard Cite

IntroductionThis study aimed to construct a radiomics-based machine learning (ML) model for differentiation between non-clear cell and clear cell renal cell carcinomas (ccRCC) that is robust against institutional imaging protocols and scanners.Materials and methodsPreoperative unenhanced (UN), corticomedullary (CM), and excretory (EX) phase CT scans from 209 patients diagnosed with RCCs were retrospectively collected. After the three-dimensional segmentation, 107 radiomics features (RFs) were extracted from the tumor volumes in each contrast phase. For the ML analysis, the cases were randomly split into training and test sets with a 3:1 ratio. Highly correlated RFs were filtered out based on Pearson’s correlation coefficient (r > 0.95). Intraclass correlation coefficient analysis was used to select RFs with excellent reproducibility (ICC ≥ 0.90). The most predictive RFs were selected by the least absolute shrinkage and selection operator (LASSO). A support vector machine algorithm-based binary classifier (SVC) was constructed to predict tumor types and its performance was evaluated based-on receiver operating characteristic curve (ROC) analysis. The “Kidney Tumor Segmentation 2019” (KiTS19) publicly available dataset was used during external validation of the model. The performance of the SVC was also compared with an expert radiologist’s.ResultsThe training set consisted of 121 ccRCCs and 38 non-ccRCCs, while the independent internal test set contained 40 ccRCCs and 13 non-ccRCCs. For external validation, 50 ccRCCs and 23 non-ccRCCs were identified from the KiTS19 dataset with the available UN, CM, and EX phase CTs. After filtering out the highly correlated and poorly reproducible features, the LASSO algorithm selected 10 CM phase RFs that were then used for model construction. During external validation, the SVC achieved an area under the ROC curve (AUC) value, accuracy, sensitivity, and specificity of 0.83, 0.78, 0.80, and 0.74, respectively. UN and/or EX phase RFs did not further increase the model’s performance. Meanwhile, in the same comparison, the expert radiologist achieved similar performance with an AUC of 0.77, an accuracy of 0.79, a sensitivity of 0.84, and a specificity of 0.69.ConclusionRadiomics analysis of CM phase CT scans combined with ML can achieve comparable performance with an expert radiologist in differentiating ccRCCs from non-ccRCCs.

show abstract

“…However, the Bosniak classification does not have a precise pathological standard, and benign lesions may still be present in these potentially malignant groups, which limited the clinical value. Recently, Reinhold et al used a CT-based radiomics model with a clinical decision algorithm to distinguish malignant CRLs from CRLs (27). However, they defined benign CRLs as non-imaging changes over 4 years' follow-up rather than pathological diagnostic criteria that could lead to actual biases, and the ability to distinguish benign from malignant CRLs remains debatable since benign CRLs were not defined by a pathological standard.…”

Section: Discussionmentioning

confidence: 99%

Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm

Tan

Liao

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

Using nephrographic phase CT images combined with pathology diagnosis, we aim to develop and validate a fusion feature-based stacking ensemble machine learning model to distinguish malignant renal neoplasms from cystic renal lesions (CRLs). This retrospective research includes 166 individuals with CRLs for model training and 47 individuals with CRLs in another institution for model testing. Histopathology results are adopted as diagnosis criterion. Nephrographic phase CT scans are selected to build the fusion feature-based machine learning algorithms. The pretrained 3D-ResNet50 CNN model and radiomics methods are selected to extract deep features and radiomics features, respectively. Fivefold cross-validated least absolute shrinkage and selection operator (LASSO) regression methods are adopted to identify the most discriminative candidate features in the development cohort. Intraclass correlation coefficients and interclass correlation coefficients are employed to evaluate feature’s reproducibility. Pearson correlation coefficients for normal distribution features and Spearman’s rank correlation coefficients for non-normal distribution features are used to eliminate redundant features. After that, stacking ensemble machine learning models are developed in the training cohort. The area under the receiver operator characteristic curve (ROC), calibration curve, and decision curve analysis (DCA) are adopted in the testing cohort to evaluate the performance of each model. The stacking ensemble machine learning algorithm reached excellent diagnostic performance in the testing dataset. The calibration plot shows good stability when using the stacking ensemble model. Net benefits presented by DCA are higher than the Bosniak 2019 version classification when employing any machine learning algorithm. The fusion feature-based machine learning algorithm accurately distinguishes malignant renal neoplasms from CRLs, which outperformed the Bosniak 2019 version classification, and proves to be more applicable for clinical decision-making.

show abstract

Malignancy risk stratification of cystic renal lesions based on a contrast-enhanced CT-based machine learning model and a clinical decision algorithm

Cited by 17 publications

References 35 publications

Artificial Intelligence in the Era of Precision Oncological Imaging

Artificial Intelligence in the Era of Precision Oncological Imaging

Radiomics analysis of contrast-enhanced CT scans can distinguish between clear cell and non-clear cell renal cell carcinoma in different imaging protocols

Stratification of malignant renal neoplasms from cystic renal lesions using deep learning and radiomics features based on a stacking ensemble CT machine learning algorithm

Contact Info

Product

Resources

About