Mei Haonan, Chen Hui, Zheng Qingyuan, Yang Rui, Wang Nanxi, Jiao Panpan, Wang Xiao, Chen Zhiyuan, Liu Xiuheng
Department of Urology, Renmin Hospital of Wuhan University, 238 Jiefang Road, Wuchang District, Wuhan, Hubei Province 430060, China (H.M., H.C., Q.Z., R.Y., P.J., X.W., Z.C., X.L.); Institute of Urologic Disease, Renmin Hospital of Wuhan University, Wuhan, Hubei, China (H.M., H.C., Q.Z., R.Y., P.J., X.W., Z.C., X.L.).
School of Software Engineering, Hubei Open University, Wuhan, China (N.W.).
Acad Radiol. 2025 Jul;32(7):4041-4049. doi: 10.1016/j.acra.2025.03.002. Epub 2025 Mar 24.
To quantitatively characterize the degree of perirenal fat adhesion using artificial intelligence in renal cell carcinoma.
This retrospective study analyzed a total of 596 patients from three cohorts, utilizing corticomedullary phase computed tomography urography (CTU) images. The nnUNet v2 network combined with numerical computation was employed to segment the perirenal fat region. Pyradiomics algorithms and a computed tomography foundation model were used to extract features from CTU images separately, creating single-modality predictive models for identifying perirenal fat adhesion. By concatenating the Pyradiomics and foundation model features, an early fusion multimodal predictive signature was developed. The prognostic performance of the single-modality and multimodality models was further validated in two independent cohorts.
The nnUNet v2 segmentation model accurately segmented both kidneys. The neural network and thresholding approach effectively delineated the perirenal fat region. Single-modality models based on radiomic and computed tomography foundation features demonstrated a certain degree of accuracy in diagnosing and identifying perirenal fat adhesion, while the early feature fusion diagnostic model outperformed the single-modality models. Also, the perirenal fat adhesion score showed a positive correlation with surgical time and intraoperative blood loss.
AI-based radiomics and foundation models can accurately identify the degree of perirenal fat adhesion and have the potential to be used for surgical risk assessment.
利用人工智能对肾细胞癌患者肾周脂肪粘连程度进行定量分析。
本回顾性研究分析了来自三个队列的596例患者，采用皮质髓质期计算机断层扫描尿路造影（CTU）图像。运用nnUNet v2网络结合数值计算对肾周脂肪区域进行分割。分别使用放射组学算法和计算机断层扫描基础模型从CTU图像中提取特征，构建用于识别肾周脂肪粘连的单模态预测模型。通过串联放射组学和基础模型的特征，开发了一种早期融合多模态预测特征。在两个独立队列中进一步验证了单模态和多模态模型的预后性能。
nnUNet v2分割模型准确分割了双侧肾脏。神经网络和阈值化方法有效地勾勒出肾周脂肪区域。基于放射组学和计算机断层扫描基础特征的单模态模型在诊断和识别肾周脂肪粘连方面具有一定的准确性，而早期特征融合诊断模型的表现优于单模态模型。此外，肾周脂肪粘连评分与手术时间和术中出血量呈正相关。
基于人工智能的放射组学和基础模型能够准确识别肾周脂肪粘连程度，具有用于手术风险评估的潜力。
