Objective Renal cell carcinoma (RCC) is a malignant renal tumor that poses a significant threat to patient health. Accurate preoperative pathological grading plays a crucial role in determining the appropriate treatment for this disease. Currently, deep learning technology has become an important method for pathological grading of RCC. However, existing methods primarily rely on single-phase computed tomography (CT) imaging for analysis and prediction, which has limitations such as missing small lesions, one-sided evaluation, and local focusing issues. Therefore, this study proposes a multi-modal deep learning algorithm that integrates multi-phase enhanced CT images with clinical variable data, aiming to provide a basis for predicting the pathological grading of RCC. Methods First, the algorithm took four-phase enhanced CT images from the plain scan, arterial phase, venous phase, and delayed phase, along with clinical variables, as inputs. Then, an embedding encoding module was used to extract heterogeneous information from the clinical variables, and a 3-dimensional (3D) ResNet50 model was employed to capture spatial information from the multi-phase enhanced CT image data. Finally, a Fusion module deeply integrated the feature information from clinical variables and each phase’s CT image features, further utilizing a cross-self-attention mechanism to achieve multi-phase feature fusion. This approach comprehensively captures the deep semantic information from the patient data, fully leveraging the complementary advantages of multi-modal and multi-phase data. To validate the effectiveness of the proposed method, a total of 1 229 RCC patients were approved by ethics review were included to train the model. Results Experimental results demonstrated superior performance compared to traditional radiomics and state-of-the-art deep learning methods, achieving an accuracy of 83.87%, a recall rate of 95.04%, and an F1-score of 82.23%. Conclusion The proposed algorithm exhibits strong stability and sensitivity, significantly enhancing the predictive performance of RCC pathological grading. It offers a novel approach for accurate RCC diagnosis and personalized treatment planning.
以卷积神经网络(convolutional neural network,CNN)为核心的DL方法具有强大的图像信息捕捉能力,在医学影像分析领域中展现出巨大潜力[9]。一项研究[10]针对ccRCC分级预测构建了融合自监督预训练方法的DL框架,该框架引入混合损失策略和样本重加权技术来识别高分级ccRCC患者,结果显示该框架的曲线下面积(area under the curve,AUC)高达0.864,验证了DL方法在ccRCC分级评估中的有效性。Wang等[11]的研究也验证了CNN模型在肾肿瘤识别与分类中的有效性,体现了DL方法在良恶性肿瘤识别方面的巨大潜力。此外,Aziz等[12]基于DL方法和CT图像数据实现了肾癌病理分级及分子亚型的精准预测,为患者的个体化治疗提供了科学依据。Chanchal等[13]提出一种改进的DL框架,采用半自动与全自动方法分割肾肿瘤,并使用CNN模型进行分类,结果显示该框架在良恶性肿瘤识别方面具有较高的准确性。这些方法有效推动了RCC临床决策模式从经验判断向数据驱动的转变。
YUWei, YANGYang, WUYinghua. Research progress of multimodal MRI in renal cell carcinoma[J]. Chinese Journal of Magnetic Resonance Imaging, 2021, 12(9): 113-115.
[4]
ChangK, BaiHX, ZhouH, et al. Residual convolutional neural network for the determination of IDH status in low- and high-grade gliomas from MR imaging[J]. Clin Cancer Res, 2018, 24(5): 1073-1081.
[5]
IshigamiK, PakalniskisMG, LeiteLV, et al. Characterization of renal cell carcinoma, oncocytoma, and lipid-poor angiomyolipoma by unenhanced, nephrographic, and delayed phase contrast-enhanced computed tomography[J]. Clin Imaging, 2015, 39(1): 76-84.
[6]
RossiSH, PrezziD, Kelly-MorlandC, et al. Imaging for the diagnosis and response assessment of renal tumours[J]. World J Urol, 2018, 36(12): 1927-1942. PubMed]
JIAOPanpan, YANGRui, ZHENGQingyuan, et al. Application of deep learning technology in diagnosis of renal cell carcinoma[J]. Medical Journal of Wuhan University, 2025, 46(3): 321-326.
[9]
DingJ, XingZ, JiangZ, et al. CT-based radiomic model predicts high grade of clear cell renal cell carcinoma[J]. Eur J Radiol, 2018, 103: 51-56.
LILiangshan, HONGMinping, HaijuanLÜ, et al. Study on preoperative prediction of WHO/ISUP grade of renal clear cell carcinoma based on MRI imaging model[J]. Modern Practical Medicine, 2023, 35(6): 803-806.
LIUXulei, LIULin. Research progress of imaging and deep learning in the diagnosis of pancreatic cancer[J]. Chinese Journal of Laboratory Diagnosis, 2024, 28(6): 754-757.
[14]
XuL, YangC, ZhangF, et al. Deep learning using CT images to grade clear cell renal cell carcinoma: development and validation of a prediction model[J]. Cancers (Basel), 2022, 14(11): 2574.
[15]
WangZ, ZhangX, WangX, et al. Deep learning techniques for imaging diagnosis of renal cell carcinoma: current and emerging trends[J]. Front Oncol, 2023, 13: 1152622.
[16]
AzizMA, JavadianF, MathewSS, et al. Deep learning approach for renal cell carcinoma detection, subtyping, and grading[C]//2024 IEEE International Conference on Image Processing (ICIP). October 27-30, 2024, Abu Dhabi, United Arab Emirates. IEEE, 2024: 3861-3867.
[17]
ChanchalAK, LalS, KumarR, et al. A novel dataset and efficient deep learning framework for automated grading of renal cell carcinoma from kidney histopathology images[J]. Sci Rep, 2023, 13(1): 5728.
[18]
GuY, WuQ, ZouJ, et al. Multi-modal clear cell renal cell carcinoma grading with the segment anything model[J]. Multimed Syst, 2024, 31(1): 19.
[19]
WangF, ChenQ, ChenY, et al. A novel multimodal deep learning model for preoperative prediction of microvascular invasion and outcome in hepatocellular carcinoma[J]. Eur J Surg Oncol, 2023, 49(1): 156-164.
[20]
LuoY, YangQ, HuJ, et al. Preliminary study on detection and diagnosis of focal liver lesions based on a deep learning model using multimodal PET/CT images[J]. Eur J Radiol Open, 2024, 14: 100624.
YAOChangyin. Predicting the prognosis of clear cell renal cell carcinoma after surgery using CT-based deep learning model [D]. Zhanjiang: Guangdong Medical University, 2024.
LIUHuayun. Artificial intelligence-based CT radiomics models for prediction of the LEIBOVICHRISK groups in renal clear cell carcinoma[D]. Chongqing: Chongqing Medical University, 2024.
[25]
MochH, CubillaAL, HumphreyPA, et al. The 2016 WHO classification of tumours of the urinary system and male genital organs-part A: renal, penile, and testicular tumours[J]. Eur Urol, 2016, 70(1): 93-105.
[26]
HeK, ZhangX, RenS, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA. IEEE, 2016: 770-778.
ZHANGWenjuan, ZHANGLiwen, DENGJuan, et al. The value of deep learning in the construction of survival prediction models for advanced gastric cancer based on enhanced CT[J]. Radiologic Practice, 2024, 39(4): 488-495.
LIDongming. Prediction of pathological grading of clear cell renal cell carcinoma using deep learning model based on CT images[D]. Baoding: Hebei University, 2022.
YANGKun, CHANGShilong, WANGYucheng, et al. Predict the ISUP grade of clear cell renal cell carcinoma using pathological images based on sECANet chanel attention[J]. Journal of Electronics & Information Technology, 2022, 44(1): 138-148.
[35]
BaiY, AnZC, LiF, et al. Deep learning using contrast-enhanced ultrasound images to predict the nuclear grade of clear cell renal cell carcinoma[J]. World J Urol, 2024, 42(1): 184.