Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors
The increasing evidence of oncocytic renal tumors positive in <sup>99m</sup>Tc 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 combine...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/14/3553 |
| _version_ | 1797589937874272256 |
|---|---|
| author | Michail E. Klontzas Emmanouil Koltsakis Georgios Kalarakis Kiril Trpkov Thomas Papathomas Apostolos H. Karantanas Antonios Tzortzakakis |
| author_facet | Michail E. Klontzas Emmanouil Koltsakis Georgios Kalarakis Kiril Trpkov Thomas Papathomas Apostolos H. Karantanas Antonios Tzortzakakis |
| author_sort | Michail E. Klontzas |
| collection | DOAJ |
| description | The increasing evidence of oncocytic renal tumors positive in <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc Sestamibi uptake was the most influential attribute in the combined model. This study highlights the potential of combining radiomics analysis with <sup>99m</sup>Tc Sestamibi SPECT/CT to improve the preoperative characterization of benign renal oncocytic neoplasms. The proposed SPECT/radiomics classifier outperformed the visual evaluation of <sup>99m</sup>Tc Sestamibii SPECT/CT and the radiomics-only model, demonstrating that the integration of <sup>99m</sup>Tc Sestamibi SPECT/CT and radiomics data provides improved diagnostic performance, with minimal false positive and false negative results. |
| first_indexed | 2024-03-11T01:13:14Z |
| format | Article |
| id | doaj.art-06c65198288243edadccc7ef61d2dbf9 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-11T01:13:14Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-06c65198288243edadccc7ef61d2dbf92023-11-18T18:40:40ZengMDPI AGCancers2072-66942023-07-011514355310.3390/cancers15143553Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic TumorsMichail E. Klontzas0Emmanouil Koltsakis1Georgios Kalarakis2Kiril Trpkov3Thomas Papathomas4Apostolos H. Karantanas5Antonios Tzortzakakis6Department of Medical Imaging, University Hospital of Heraklion, Heraklion 71110, GreeceDepartment of Diagnostic Radiology, Karolinska University Hospital, Stockholm 17177, SwedenDepartment of Diagnostic Radiology, Karolinska University Hospital, Stockholm 17177, SwedenAlberta Precision Labs, Department of Pathology and Laboratory Medicine, Cumming School of Medicine, University of Calgary, Calgary, AB T2L 2K5, CanadaInstitute of Metabolism and Systems Research, University of Birmingham, Birmingham B15 2TT, UKDepartment of Medical Imaging, University Hospital of Heraklion, Heraklion 71110, GreeceDivision of Radiology, Department for Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm 14152, SwedenThe increasing evidence of oncocytic renal tumors positive in <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc 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 <sup>99m</sup>Tc Sestamibi uptake was the most influential attribute in the combined model. This study highlights the potential of combining radiomics analysis with <sup>99m</sup>Tc Sestamibi SPECT/CT to improve the preoperative characterization of benign renal oncocytic neoplasms. The proposed SPECT/radiomics classifier outperformed the visual evaluation of <sup>99m</sup>Tc Sestamibii SPECT/CT and the radiomics-only model, demonstrating that the integration of <sup>99m</sup>Tc Sestamibi SPECT/CT and radiomics data provides improved diagnostic performance, with minimal false positive and false negative results.https://www.mdpi.com/2072-6694/15/14/3553<sup>99m</sup>Tc Sestamibi SPECT/CTartificial intelligencemachine learningradiomicsrenal cell carcinomarenal oncocytoma |
| spellingShingle | Michail E. Klontzas Emmanouil Koltsakis Georgios Kalarakis Kiril Trpkov Thomas Papathomas Apostolos H. Karantanas Antonios Tzortzakakis Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors Cancers <sup>99m</sup>Tc Sestamibi SPECT/CT artificial intelligence machine learning radiomics renal cell carcinoma renal oncocytoma |
| title | Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors |
| title_full | Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors |
| title_fullStr | Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors |
| title_full_unstemmed | Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors |
| title_short | Machine Learning Integrating <sup>99m</sup>Tc Sestamibi SPECT/CT and Radiomics Data Achieves Optimal Characterization of Renal Oncocytic Tumors |
| title_sort | machine learning integrating sup 99m sup tc sestamibi spect ct and radiomics data achieves optimal characterization of renal oncocytic tumors |
| topic | <sup>99m</sup>Tc Sestamibi SPECT/CT artificial intelligence machine learning radiomics renal cell carcinoma renal oncocytoma |
| url | https://www.mdpi.com/2072-6694/15/14/3553 |
| work_keys_str_mv | AT michaileklontzas machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT emmanouilkoltsakis machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT georgioskalarakis machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT kiriltrpkov machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT thomaspapathomas machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT apostoloshkarantanas machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors AT antoniostzortzakakis machinelearningintegratingsup99msuptcsestamibispectctandradiomicsdataachievesoptimalcharacterizationofrenaloncocytictumors |