Moozhan Nikpanah1, Ziyue Xu2, Dakai Jin3, Faraz Farhadi4, Babak Saboury5, Mark W Ball6, Rabindra Gautam7, Maria J Merino8, Bradford J Wood9, Baris Turkbey10, Elizabeth C Jones5, W Marston Linehan11, Ashkan A Malayeri12. 1. Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA. Electronic address: https://twitter.com/MoozhanNikpanah. 2. NVIDIA Corporation, Bethesda, MD, USA. 3. PAII Inc., Bethesda, MD, USA. 4. Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA. Electronic address: https://twitter.com/Faraz_Farhadi. 5. Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA. 6. Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. Electronic address: https://twitter.com/markballmd. 7. Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. 8. Laboratory of Pathology, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. 9. Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA. Electronic address: https://twitter.com/BradWoodMD. 10. Molecular Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda, USA. Electronic address: https://twitter.com/radiolobt. 11. Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA. Electronic address: linehanm@mail.nih.gov. 12. Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA. Electronic address: ashkan.malayeri@nih.gov.
Abstract
PURPOSE: To investigate the diagnostic performance of a deep convolutional neural network for differentiation of clear cell renal cell carcinoma (ccRCC) from renal oncocytoma. METHODS: In this retrospective study, 74 patients (49 male, mean age 59.3) with 243 renal masses (203 ccRCC and 40 oncocytoma) that had undergone MR imaging 6 months prior to pathologic confirmation of the lesions were included. Segmentation using seed placement and bounding box selection was used to extract the lesion patches from T2-WI, and T1-WI pre-contrast, post-contrast arterial and venous phases. Then, a deep convolutional neural network (AlexNet) was fine-tuned to distinguish the ccRCC from oncocytoma. Five-fold cross validation was used to evaluate the AI algorithm performance. A subset of 80 lesions (40 ccRCC, 40 oncocytoma) were randomly selected to be classified by two radiologists and their performance was compared to the AI algorithm. Intra-class correlation coefficient was calculated using the Shrout-Fleiss method. RESULTS: Overall accuracy of the AI system was 91% for differentiation of ccRCC from oncocytoma with an area under the curve of 0.9. For the observer study on 80 randomly selected lesions, there was moderate agreement between the two radiologists and AI algorithm. In the comparison sub-dataset, classification accuracies were 81%, 78%, and 70% for AI, radiologist 1, and radiologist 2, respectively. CONCLUSION: The developed AI system in this study showed high diagnostic performance in differentiation of ccRCC versus oncocytoma on multi-phasic MRIs.
PURPOSE: To investigate the diagnostic performance of a deep convolutional neural network for differentiation of clear cell renal cell carcinoma (ccRCC) from renal oncocytoma. METHODS: In this retrospective study, 74 patients (49 male, mean age 59.3) with 243 renal masses (203 ccRCC and 40 oncocytoma) that had undergone MR imaging 6 months prior to pathologic confirmation of the lesions were included. Segmentation using seed placement and bounding box selection was used to extract the lesion patches from T2-WI, and T1-WI pre-contrast, post-contrast arterial and venous phases. Then, a deep convolutional neural network (AlexNet) was fine-tuned to distinguish the ccRCC from oncocytoma. Five-fold cross validation was used to evaluate the AI algorithm performance. A subset of 80 lesions (40 ccRCC, 40 oncocytoma) were randomly selected to be classified by two radiologists and their performance was compared to the AI algorithm. Intra-class correlation coefficient was calculated using the Shrout-Fleiss method. RESULTS: Overall accuracy of the AI system was 91% for differentiation of ccRCC from oncocytoma with an area under the curve of 0.9. For the observer study on 80 randomly selected lesions, there was moderate agreement between the two radiologists and AI algorithm. In the comparison sub-dataset, classification accuracies were 81%, 78%, and 70% for AI, radiologist 1, and radiologist 2, respectively. CONCLUSION: The developed AI system in this study showed high diagnostic performance in differentiation of ccRCC versus oncocytoma on multi-phasic MRIs.