Differentiation of benign from malignant solid renal lesions using CT-based radiomics and machine learning: comparison with radiologist interpretation

Artificial intelligence support in MR imaging of incidental renal masses: an early health technology assessment

OBJECTIVE

This study analyzes the potential cost-effectiveness of integrating an artificial intelligence (AI)-assisted system into the differentiation of incidental renal lesions as benign or malignant on MR images during follow-up.

MATERIALS AND METHODS

For estimation of quality-adjusted life years (QALYs) and lifetime costs, a decision model was created, including the MRI strategy and MRI + AI strategy. Model input parameters were derived from recent literature. Willingness to pay (WTP) was set to $100,000/QALY. Costs of $0 for the AI were assumed in the base-case scenario. Model uncertainty and costs of the AI system were assessed using deterministic and probabilistic sensitivity analysis.

RESULTS

Average total costs were at $8054 for the MRI strategy and $7939 for additional use of an AI-based algorithm. The model yielded a cumulative effectiveness of 8.76 QALYs for the MRI strategy and of 8.77 for the MRI + AI strategy. The economically dominant strategy was MRI + AI. Deterministic and probabilistic sensitivity analysis showed high robustness of the model with the incremental cost-effectiveness ratio (ICER), which represents the incremental cost associated with one additional QALY gained, remaining below the WTP for variation of the input parameters. If increasing costs for the algorithm, the ICER of $0/QALY was exceeded at $115, and the defined WTP was exceeded at $667 for the use of the AI.

CONCLUSIONS

This analysis, rooted in assumptions, suggests that the additional use of an AI-based algorithm may be a potentially cost-effective alternative in the differentiation of incidental renal lesions using MRI and needs to be confirmed in the future.

CLINICAL RELEVANCE STATEMENT

These results hint at AI's the potential impact on diagnosing renal masses. While the current study urges careful interpretation, ongoing research is essential to confirm and seamlessly integrate AI into clinical practice, ensuring its efficacy in routine diagnostics.

KEY POINTS

• This is a model-based study using data from literature where AI has been applied in the diagnostic workup of incidental renal lesions. • MRI + AI has the potential to be a cost-effective alternative in the differentiation of incidental renal lesions. • The additional use of AI can reduce costs in the diagnostic workup of incidental renal lesions.

Interpretable multiphasic CT-based radiomic analysis for preoperatively differentiating benign and malignant solid renal tumors: a multicenter study

BACKGROUND

To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.

MATERIALS AND METHODS

In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.

RESULTS

A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The "original_shape_Flatness" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.

CONCLUSIONS

The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.

Non-Invasive Tumor Grade Evaluation in Von Hippel-Lindau-Associated Clear Cell Renal Cell Carcinoma: A Magnetic Resonance Imaging-Based Study

BACKGROUND

Pathology grading is an essential step for the treatment and evaluation of the prognosis in patients with clear cell renal cell carcinoma (ccRCC).

PURPOSE

To investigate the utility of texture analysis in evaluating Fuhrman grades of renal tumors in patients with Von Hippel-Lindau (VHL)-associated ccRCC, aiming to improve non-invasive diagnosis and personalized treatment.

STUDY TYPE

Retrospective analysis of a prospectively maintained cohort.

POPULATION

One hundred and thirty-six patients, 84 (61%) males and 52 (39%) females with pathology-proven ccRCC with a mean age of 52.8 ± 12.7 from 2010 to 2023.

FIELD STRENGTH AND SEQUENCES

1.5 and 3 T MRIs. Segmentations were performed on the T1-weighted 3-minute delayed sequence and then registered on pre-contrast, T1-weighted arterial and venous sequences.

ASSESSMENT

A total of 404 lesions, 345 low-grade tumors, and 59 high-grade tumors were segmented using ITK-SNAP on a T1-weighted 3-minute delayed sequence of MRI. Radiomics features were extracted from pre-contrast, T1-weighted arterial, venous, and delayed post-contrast sequences. Preprocessing techniques were employed to address class imbalances. Features were then rescaled to normalize the numeric values. We developed a stacked model combining random forest and XGBoost to assess tumor grades using radiomics signatures.

STATISTICAL TESTS

The model's performance was evaluated using positive predictive value (PPV), sensitivity, F1 score, area under the curve of receiver operating characteristic curve, and Matthews correlation coefficient. Using Monte Carlo technique, the average performance of 100 benchmarks of 85% train and 15% test was reported.

RESULTS

The best model displayed an accuracy of 0.79. For low-grade tumor detection, a sensitivity of 0.79, a PPV of 0.95, and an F1 score of 0.86 were obtained. For high-grade tumor detection, a sensitivity of 0.78, PPV of 0.39, and F1 score of 0.52 were reported.

DATA CONCLUSION

Radiomics analysis shows promise in classifying pathology grades non-invasively for patients with VHL-associated ccRCC, potentially leading to better diagnosis and personalized treatment.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

CT-Based Radiomics Models for Differentiation of Benign and Malignant Thyroid Nodules: A Multicenter Development and Validation Study

BACKGROUND. CT is increasingly detecting thyroid nodules. Prior studies indicated a potential role of CT-based radiomics models in characterizing thyroid nodules, although these studies lacked external validation. OBJECTIVE. The purpose of this study was to develop and validate a CT-based radiomics model for the differentiation of benign and malignant thyroid nodules. METHODS. This retrospective study included 378 patients (mean age, 46.3 ± 13.9 [SD] years; 86 men, 292 women) with 408 resected thyroid nodules (145 benign, 263 malignant) from two centers (center 1: 293 nodules, January 2018 to December 2022; center 2: 115 nodules, January 2020 to December 2022) who underwent preoperative multiphase neck CT (noncontrast, arterial, and venous phases). Nodules from center 1 were divided into training (n = 206) and internal validation (n = 87) sets; all nodules from center 2 formed an external validation set. Radiologists assessed nodules for morphologic CT features. Nodules were manually segmented on all phases, and radiomic features were extracted. Conventional (clinical and morphologic CT), noncontrast CT radiomics, arterial phase CT radiomics, venous phase CT radiomics, multiphase CT radiomics, and combined (clinical, morphologic CT, and multiphase CT radiomics) models were established using feature selection methods and evaluated by ROC curve analysis, calibration-curve analysis, and decision-curve analysis. RESULTS. The combined model included patient age, three morphologic features (cystic change, "edge interruption" sign, abnormal cervical lymph nodes), and 28 radiomic features (from all three phases). In the external validation set, the combined model had an AUC of 0.923, and, at an optimal threshold derived in the training set, sensitivity of 84.0%, specificity of 94.1%, and accuracy of 87.0%. In the external validation set, the AUC was significantly higher for the combined model than for the conventional model (0.827), noncontrast CT radiomics model (0.847), arterial phase CT radiomics model (0.826), venous phase CT radiomics model (0.773), and multiphase CT radiomics model (0.824) (all p < .05). In the external validation set, the calibration curves indicated the lowest (i.e., best) Brier score for the combined model; in the decision-curve analysis, the combined model had the highest net benefit for most of the range of threshold probabilities. CONCLUSION. A combined model incorporating clinical, morphologic CT, and multiphase CT radiomics features exhibited robust performance in differentiating benign and malignant thyroid nodules. CLINICAL IMPACT. The combined radiomics model may help guide further management for thyroid nodules detected on CT.

Deep Learning Assessment of Small Renal Masses at Contrast-enhanced Multiphase CT

Background Accurate characterization of suspicious small renal masses is crucial for optimized management. Deep learning (DL) algorithms may assist with this effort. Purpose To develop and validate a DL algorithm for identifying benign small renal masses at contrast-enhanced multiphase CT. Materials and Methods Surgically resected renal masses measuring 3 cm or less in diameter at contrast-enhanced CT were included. The DL algorithm was developed by using retrospective data from one hospital between 2009 and 2021, with patients randomly allocated in a training and internal test set ratio of 8:2. Between 2013 and 2021, external testing was performed on data from five independent hospitals. A prospective test set was obtained between 2021 and 2022 from one hospital. Algorithm performance was evaluated by using the area under the receiver operating characteristic curve (AUC) and compared with the results of seven clinicians using the DeLong test. Results A total of 1703 patients (mean age, 56 years ± 12 [SD]; 619 female) with a single renal mass per patient were evaluated. The retrospective data set included 1063 lesions (874 in training set, 189 internal test set); the multicenter external test set included 537 lesions (12.3%, 66 benign) with 89 subcentimeter (≤1 cm) lesions (16.6%); and the prospective test set included 103 lesions (13.6%, 14 benign) with 20 (19.4%) subcentimeter lesions. The DL algorithm performance was comparable with that of urological radiologists: for the external test set, AUC was 0.80 (95% CI: 0.75, 0.85) versus 0.84 (95% CI: 0.78, 0.88) (P = .61); for the prospective test set, AUC was 0.87 (95% CI: 0.79, 0.93) versus 0.92 (95% CI: 0.86, 0.96) (P = .70). For subcentimeter lesions in the external test set, the algorithm and urological radiologists had similar AUC of 0.74 (95% CI: 0.63, 0.83) and 0.81 (95% CI: 0.68, 0.92) (P = .78), respectively. Conclusion The multiphase CT-based DL algorithm showed comparable performance with that of radiologists for identifying benign small renal masses, including lesions of 1 cm or less. Published under a CC BY 4.0 license. Supplemental material is available for this article.

AI-powered radiomics: revolutionizing detection of urologic malignancies

PURPOSE OF REVIEW

This review aims to highlight the integration of artificial intelligence-powered radiomics in urologic oncology, focusing on the diagnostic and prognostic advancements in the realm of managing prostate, kidney, and bladder cancers.

RECENT FINDINGS

As artificial intelligence continues to shape the medical imaging landscape, its integration into the field of urologic oncology has led to impressive results. For prostate cancer diagnostics, machine learning has shown promise in refining clinically-significant lesion detection, with some success in deciphering ambiguous lesions on multiparametric MRI. For kidney cancer, radiomics has emerged as a valuable tool for better distinguishing between benign and malignant renal masses and predicting tumor behavior from CT or MRI scans. Meanwhile, in the arena of bladder cancer, there is a burgeoning emphasis on prediction of muscle invasive cancer and forecasting disease trajectory. However, many studies showing promise in these areas face challenges due to limited sample sizes and the need for broader external validation.

SUMMARY

Radiomics integrated with artificial intelligence offers a pioneering approach to urologic oncology, ushering in an era of enhanced diagnostic precision and reduced invasiveness, guiding patient-tailored treatment plans. Researchers must embrace broader, multicentered endeavors to harness the full potential of this field.

Exploratory Analysis of the Role of Radiomic Features in the Differentiation of Oncocytoma and Chromophobe RCC in the Nephrographic CT Phase

In diagnostic imaging, distinguishing chromophobe renal cell carcinomas (chRCCs) from renal oncocytomas (ROs) is challenging, since they both present similar radiological characteristics. Radiomics has the potential to help in the differentiation between chRCCs and ROs by extracting quantitative imaging. This is a preliminary study of the role of radiomic features in the differentiation of chRCCs and ROs using machine learning models. In this retrospective work, 38 subjects were involved: 19 diagnosed with chRCCs and 19 with ROs. The CT nephrographic contrast phase was selected in each case. Three-dimensional segmentations of the lesions were performed and the radiomic features were extracted. To assess the reliability of the features, the intraclass correlation coefficient was calculated from the segmentations performed by three radiologists with different degrees of expertise. The selection of features was based on the criteria of excellent intraclass correlation coefficient (ICC), high correlation, and statistical significance. Three machine learning models were elaborated: support vector machine (SVM), random forest (RF), and logistic regression (LR). From 105 extracted features, 41 presented an excellent ICC and 6 were not highly correlated with each other. Only two features showed significant differences according to histological type and machine learning models were developed with them. LR was the better model, in particular, with an 83% precision.

The Use of Radiomic Tools in Renal Mass Characterization

The incidence of renal mass detection has increased during recent decades, with an increased diagnosis of small renal masses, and a final benign diagnosis in some cases. To avoid unnecessary surgeries, there is an increasing interest in using radiomics tools to predict histological results, using radiological features. We performed a narrative review to evaluate the use of radiomics in renal mass characterization. Conventional images, such as computed tomography (CT) and magnetic resonance (MR), are the most common diagnostic tools in renal mass characterization. Distinguishing between benign and malignant tumors in small renal masses can be challenging using conventional methods. To improve subjective evaluation, the interest in using radiomics to obtain quantitative parameters from medical images has increased. Several studies have assessed this novel tool for renal mass characterization, comparing its ability to distinguish benign to malign tumors, the results in differentiating renal cell carcinoma subtypes, or the correlation with prognostic features, with other methods. In several studies, radiomic tools have shown a good accuracy in characterizing renal mass lesions. However, due to the heterogeneity in the radiomic model building, prospective and external validated studies are needed.