Machine Learning Integrating 99mTc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors

Abstract

The increasing evidence of oncocytic renal tumors positive in ^99mTc Sestamibi Single Photon Emission Tomography/Computed Tomography (SPECT/CT) examination calls for the development of diagnostic tools to differentiate these tumors from more aggressive forms. This study combined radiomics analysis with the uptake of ^99mTc Sestamibi on SPECT/CT to differentiate benign renal oncocytic neoplasms from renal cell carcinoma. A total of 57 renal tumors were prospectively collected. Histopathological analysis and radiomics data extraction were performed. XGBoost classifiers were trained using the radiomics features alone and combined with the results from the visual evaluation of ^99mTc Sestamibi SPECT/CT examination. The combined SPECT/radiomics model achieved higher accuracy (95%) with an area under the curve (AUC) of 98.3% (95% CI 93.7-100%) than the radiomics-only model (71.67%) with an AUC of 75% (95% CI 49.7-100%) and visual evaluation of ^99mTc Sestamibi SPECT/CT alone (90.8%) with an AUC of 90.8% (95%CI 82.5-99.1%). The positive predictive values of SPECT/radiomics, radiomics-only, and ^99mTc Sestamibi SPECT/CT-only models were 100%, 85.71%, and 85%, respectively, whereas the negative predictive values were 85.71%, 55.56%, and 94.6%, respectively. Feature importance analysis revealed that ^99mTc Sestamibi uptake was the most influential attribute in the combined model. This study highlights the potential of combining radiomics analysis with ^99mTc Sestamibi SPECT/CT to improve the preoperative characterization of benign renal oncocytic neoplasms. The proposed SPECT/radiomics classifier outperformed the visual evaluation of ^99mTc Sestamibii SPECT/CT and the radiomics-only model, demonstrating that the integration of ^99mTc Sestamibi SPECT/CT and radiomics data provides improved diagnostic performance, with minimal false positive and false negative results.

Keywords: 99mTc Sestamibi SPECT/CT; XGboost; artificial intelligence; machine learning; radiomics; renal cell carcinoma; renal oncocytic neoplasia; renal oncocytoma.

Figure 1

Flowchart outlining the design of the radiomics arm of this study. White arrows indicate a renal tumor of the inferior pole of the left kidney with visible ^99mTc Sestamibi SPECT/CT uptake (Sestamibi-positive) (created with biorender.com, accessed on 12 June 2023).

Figure 2

Boruta feature selection results in the SPECT/radiomics (A) and radiomics-only (B) groups. RF: radiomics features; SPECT/CT: uptake (±) of 99mTc Sestamibi on SPECT/CT. Blue box, red, yeallow and green plots represent shadow, not important, tentative and confirmed important attributes, respectively.

Figure 3

Receiver operating characteristics (ROC) curves of the combined SPECT/radiomics (red line) and the radiomics-only (blue line) XGboost models. AUC: area under the curve; CI: confidence interval.

Figure 4

Feature important graphs of XGboost models demonstrating features important for the performance of the combined SPECT/radiomics (A) and the radiomics-only (B) model.

Figure 5

Individual radiomics feature values were important for classifying the combined SPECT/radiomics model. Barplots represent normalized feature values in the benign (pink) and malignant (cyan); six wavelet transformations of texture features (A–E,I), two wavelet transformations of first-order features (G,H), and one original texture radiomics feature (F) are compared between the benign and malignant group. Boxplot statistics have been derived with the geom_boxplot function of the ggplot2 package in R; y-axis: standardized relative value of radiomics features; dots represent outlier data beyond the end of the whiskers *: p < 0.05.