Deep Learning Algorithm for Fully Automated Detection of Small (≤4 cm) Renal Cell Carcinoma in Contrast-Enhanced Computed Tomography Using a Multicenter Database

Abstract

Objectives: Renal cell carcinoma (RCC) is often found incidentally in asymptomatic individuals undergoing abdominal computed tomography (CT) examinations. The purpose of our study is to develop a deep learning-based algorithm for fully automated detection of small (≤4 cm) RCCs in contrast-enhanced CT images using a multicenter database and to evaluate its performance. Materials and Methods: For the algorithmic detection of RCC, we retrospectively selected contrast-enhanced CT images of patients with histologically confirmed single RCC with a tumor diameter of 4 cm or less between January 2005 and May 2020 from 7 centers in the Japan Medical Image Database. A total of 453 patients from 6 centers were selected as dataset A, and 132 patients from 1 center were selected as dataset B. Dataset A was used for training and internal validation. Dataset B was used only for external validation. Nephrogenic phase images of multiphase CT or single-phase postcontrast CT images were used. Our algorithm consisted of 2-step segmentation models, kidney segmentation and tumor segmentation. For internal validation with dataset A, 10-fold cross-validation was applied. For external validation, the models trained with dataset A were tested on dataset B. The detection performance of the models was evaluated using accuracy, sensitivity, specificity, and the area under the curve (AUC). Results: The mean ± SD diameters of RCCs in dataset A and dataset B were 2.67 ± 0.77 cm and 2.64 ± 0.78 cm, respectively. Our algorithm yielded an accuracy, sensitivity, and specificity of 88.3%, 84.3%, and 92.3%, respectively, with dataset A and 87.5%, 84.8%, and 90.2%, respectively, with dataset B. The AUC of the algorithm with dataset A and dataset B was 0.930 and 0.933, respectively. Conclusions: The proposed deep learning-based algorithm achieved high accuracy, sensitivity, specificity, and AUC for the detection of small RCCs with both internal and external validations, suggesting that this algorithm could contribute to the early detection of small RCCs.

Artificial intelligence and radiomics in evaluation of kidney lesions: a comprehensive literature review

“… 143 , 144 Toda et al . 145 demonstrated that DL algorithms in contrast-enhanced CT have high accuracy for the diagnoses of SRMs with both internal and external validation. Manual or semi-automated segmentation have been used in most of the studies (either on CT or MRI platforms); Kart et al ., 146 using national databases of whole-body MR imaging from United Kingdom and Germany, developed and trained an automated segmentation DL model for abdominal organs; and Zhao et al 147 clinically assessed assisted compressed sensing technology in renal MRI imaging with an AI algorithm that can adjust scanner settings to improve image acquisition and automatically adjust images to patients’ movements, and can allow ultra-fast MR imaging acquisition.…”

Radiomics and Deep Learning for Disease Detection in Musculoskeletal Radiology

“…During the last 10 years, machine learning, and in particular deep convolutional neural networks (DCNNs), have gained considerable popularity in medicine and radiology for disease detection, image reconstruction, and tissue segmentation, which was accompanied by an almost exponential increase in the number of peer-reviewed publications. [34][35][36][37][38][39][40] The increase in research output and development of clinical applications was fueled by the development of DCNNs and the broadening availability of high-performance computer systems with powerful graphical processing units. Furthermore, the accessibility of open-source deep learning (DL) toolkits provided access to a worldwide community for exploring and performing research on this topic with limited expert knowledge requirements in artificial intelligence (AI) and computer sciences.…”

“…During the last 10 years, machine learning, and in particular deep convolutional neural networks (DCNNs), have gained considerable popularity in medicine and radiology for disease detection, image reconstruction, and tissue segmentation, which was accompanied by an almost exponential increase in the number of peer-reviewed publications 34–40 . The increase in research output and development of clinical applications was fueled by the development of DCNNs and the broadening availability of high-performance computer systems with powerful graphical processing units.…”

Automatic Detection of Pancreatic Lesions and Main Pancreatic Duct Dilatation on Portal Venous CT Scans Using Deep Learning

“…Promising results have already been obtained for several diseases such as bone tumors, 12 prostate cancer, 13 and kidney cancer. 14 In addition, DL models could help radiologists in their daily practice. Recently, an algorithm for breast cancer detection significantly decreased the false-positive and false-negative rates on 2 large data sets, while substantially reducing the radiologists' workload.…”

“…Given this context, deep learning (DL) methods could play an important role to assist with diagnosis, by issuing alerts for patients at risk of pancreatic cancer. Promising results have already been obtained for several diseases such as bone tumors, 12 prostate cancer, 13 and kidney cancer 14 . In addition, DL models could help radiologists in their daily practice.…”