■喉鳞状细胞癌(LSCC)隐匿性淋巴结转移(LNM)影响患者的治疗和预后。本研究旨在全面比较三维和二维深度学习模型的性能,影像组学模型,以及预测LSCC隐匿性LNM的融合模型。
■在这项回顾性诊断研究中,共553例临床N0期LSCC患者,他们接受了手术治疗,没有远处转移和多原发癌,他们在2016年1月1日至2020年12月30日期间从4个中国医疗中心连续纳入。参与者数据是从医疗记录中手动检索的,影像数据库,和病理报告。研究队列被分为一个训练集(n=300),内部测试集(n=89),和两个外部测试集(n=120和44,分别)。三维深度学习(3DDL)二维深度学习(2DDL),和影像组学模型是使用原发性肿瘤的CT图像开发的。基于临床和放射学特征构建临床模型。使用两种融合策略来开发融合模型:基于特征的DLRad_FB模型和基于决策的DLRad_DB模型。3DDL的判别能力和相关性,对2DDL和影像组学特征进行了全面分析。根据病理诊断评估预测模型的性能。
■与2DDL和影像组学特征相比,3DDL特征具有更高的辨别能力和更低的内部冗余。DLRad_DB模型在所有研究集中实现了最高的AUC(0.89-0.90),显着优于临床模型(AUC=0.73-0.78,P=0.0001-0.042,Delong检验)。与DLRad_DB模型相比,DLRad_FB的AUC值,3DDL,2DDL,和影像组学模型为0.82-0.84(P=0.025-0.46),0.86-0.89(P=0.75-0.97),0.83-0.86(P=0.029-0.66),和0.79-0.82(P=0.0072-0.10),分别在研究集中。此外,DLRad_DB模型在测试组中表现出最佳的敏感性(82-88%)和特异性(79-85%)。
■基于决策的融合模型DLRad_DB,结合了3DDL,2DDL,影像组学,和临床数据,可用于预测LSCC中的隐匿性LNM。这有可能最大程度地减少cN0病患者不必要的淋巴结清扫和预防性放疗。
■国家自然科学基金,山东省自然科学基金.
UNASSIGNED: The occult lymph node metastasis (LNM) of laryngeal squamous cell carcinoma (LSCC) affects the treatment and prognosis of patients. This study aimed to comprehensively compare the performance of the three-dimensional and two-dimensional deep learning models, radiomics model, and the fusion models for predicting occult LNM in LSCC.
UNASSIGNED: In this retrospective diagnostic study, a total of 553 patients with clinical N0 stage LSCC, who underwent surgical treatment without distant metastasis and multiple primary cancers, were consecutively enrolled from four Chinese medical centres between January 01, 2016 and December 30, 2020. The participant data were manually retrieved from medical records, imaging databases, and pathology reports. The study cohort was divided into a training set (n = 300), an internal test set (n = 89), and two external test sets (n = 120 and 44, respectively). The three-dimensional deep learning (3D DL), two-dimensional deep learning (2D DL), and radiomics model were developed using CT images of the primary tumor. The clinical model was constructed based on clinical and radiological features. Two fusion strategies were utilized to develop the fusion model: the feature-based DLRad_FB model and the decision-based DLRad_DB model. The discriminative ability and correlation of 3D DL, 2D DL and radiomics features were analysed comprehensively. The performances of the predictive models were evaluated based on the pathological diagnosis.
UNASSIGNED: The 3D DL features had superior discriminative ability and lower internal redundancy compared to 2D DL and radiomics features. The DLRad_DB model achieved the highest AUC (0.89-0.90) among all the study sets, significantly outperforming the clinical model (AUC = 0.73-0.78, P = 0.0001-0.042, Delong test). Compared to the DLRad_DB model, the AUC values for the DLRad_FB, 3D DL, 2D DL, and radiomics models were 0.82-0.84 (P = 0.025-0.46), 0.86-0.89 (P = 0.75-0.97), 0.83-0.86 (P = 0.029-0.66), and 0.79-0.82 (P = 0.0072-0.10), respectively in the study sets. Additionally, the DLRad_DB model exhibited the best sensitivity (82-88%) and specificity (79-85%) in the test sets.
UNASSIGNED: The decision-based fusion model DLRad_DB, which combines 3D DL, 2D DL, radiomics, and clinical data, can be utilized to predict occult LNM in LSCC. This has the potential to minimize unnecessary lymph node dissection and prophylactic radiotherapy in patients with cN0 disease.
UNASSIGNED: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.