Guo Jia, Li Yi-Ming, Guo Hongwei, Hao Da-Peng, Xu Jing-Xu, Huang Chen-Cui, Han Hua-Wei, Hou Feng, Yang Shi-Feng, Cui Jian-Ling, Wang He-Xiang
Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
Department of Research Collaboration, Research and Development (R&D) center, Beijing Deepwise and League of Philosophy Doctor (PHD) Technology Co., Ltd, Beijing, China.
J Magn Reson Imaging. 2025 Feb;61(2):807-819. doi: 10.1002/jmri.29474. Epub 2024 Jun 10.
Traditional biopsies pose risks and may not accurately reflect soft tissue sarcoma (STS) heterogeneity. MRI provides a noninvasive, comprehensive alternative.
To assess the diagnostic accuracy of histological grading and prognosis in STS patients when integrating clinical-imaging parameters with deep learning (DL) features from preoperative MR images.
Retrospective/prospective.
354 pathologically confirmed STS patients (226 low-grade, 128 high-grade) from three hospitals and the Cancer Imaging Archive (TCIA), divided into training (n = 185), external test (n = 125), and TCIA cohorts (n = 44). 12 patients (6 low-grade, 6 high-grade) were enrolled into prospective validation cohort.
FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T/Unenhanced T1-weighted and fat-suppressed-T2-weighted.
DL features were extracted from MR images using a parallel ResNet-18 model to construct DL signature. Clinical-imaging characteristics included age, gender, tumor-node-metastasis stage and MRI semantic features (depth, number, heterogeneity at T1WI/FS-T2WI, necrosis, and peritumoral edema). Logistic regression analysis identified significant risk factors for the clinical model. A DL clinical-imaging signature (DLCS) was constructed by incorporating DL signature with risk factors, evaluated for risk stratification, and assessed for progression-free survival (PFS) in retrospective cohorts, with an average follow-up of 23 ± 22 months.
Logistic regression, Cox regression, Kaplan-Meier curves, log-rank test, area under the receiver operating characteristic curve (AUC)，and decision curve analysis. A P-value <0.05 was considered significant.
The AUC values for DLCS in the external test, TCIA, and prospective test cohorts (0.834, 0.838, 0.819) were superior to clinical model (0.662, 0.685, 0.694). Decision curve analysis showed that the DLCS model provided greater clinical net benefit over the DL and clinical models. Also, the DLCS model was able to risk-stratify patients and assess PFS.
The DLCS exhibited strong capabilities in histological grading and prognosis assessment for STS patients, and may have potential to aid in the formulation of personalized treatment plans.
Stage 2.
传统活检存在风险，可能无法准确反映软组织肉瘤（STS）的异质性。磁共振成像（MRI）提供了一种非侵入性的全面替代方法。
评估将临床影像参数与术前MR图像的深度学习（DL）特征相结合时，STS患者组织学分级和预后的诊断准确性。
回顾性/前瞻性。
来自三家医院和癌症影像存档库（TCIA）的354例经病理证实的STS患者（226例低级别，128例高级别），分为训练组（n = 185）、外部测试组（n = 125）和TCIA队列（n = 44）。12例患者（6例低级别，6例高级别）被纳入前瞻性验证队列。
场强/序列：1.5T和3.0T/未增强T1加权和脂肪抑制T2加权。
使用并行ResNet-18模型从MR图像中提取DL特征以构建DL特征标记。临床影像特征包括年龄、性别、肿瘤-淋巴结-转移分期和MRI语义特征（深度、数量、T1WI/FS-T2WI的异质性、坏死和瘤周水肿）。逻辑回归分析确定临床模型的显著危险因素。通过将DL特征标记与危险因素相结合构建DL临床影像特征标记（DLCS），在回顾性队列中评估其风险分层，并评估无进展生存期（PFS），平均随访23±22个月。
逻辑回归、Cox回归、Kaplan-Meier曲线、对数秩检验、受试者操作特征曲线下面积（AUC）和决策曲线分析。P值<0.05被认为具有统计学意义。
外部测试组、TCIA组和前瞻性测试队列中DLCS的AUC值（0.834、0.838、0.819）优于临床模型（0.662、0.685、0.694）。决策曲线分析表明，DLCS模型比DL模型和临床模型提供了更大的临床净效益。此外，DLCS模型能够对患者进行风险分层并评估PFS。
DLCS在STS患者的组织学分级和预后评估中表现出强大的能力，可能有助于制定个性化治疗方案。
2级。
