From the Department of Radiology (Khodrog, Cui, Xu, Han, Liu, Gong, Yuan), the Second Hospital of Jilin University, Changchun, China and from the Department of Medical Imaging (Khodrog), Faculty of Applied Medical Health, Palestine Ahliya University, Bethlehem, Palestine.
Saudi Med J. 2021 Mar;42(3):284-292. doi: 10.15537/smj.2021.42.3.20200617.
To differentiate squamous cell hyperplasia (SCH) (benign) from squamous cell carcinoma (SCC) malignant) using textural features extracted from CT images and thereby, facilitate the preoperative medical diagnosis and treatment of throat cancers without the need for sample biopsies.
In total, 100 throat cancer patients were selected for this retrospective study. The cases were collected from the Second Hospital of Jilin University, Changchun, China, from June 2017 to January 2019. The patients were separated into a training and validation cohort consisting of 70 and 30 cases, respectively. The Artificial Intelligence Kit software (A.K. software) was used to extract the radiomics features from the CT images. These features were further processed using the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) methods to obtain a subset of optimal features. The radiomics model was validated based on area-under-the-curve (AUC) values, accuracy, specificity, and sensitivity using the R-studio software.
The diagnostic accuracy, specificity, PPV, NPV, and AUC values obtained for the training cohort was 0.91, 0.9, 0.93, 0.9, and 0.96 CT angiography (CTA), 0.93, 0.93, 0.95, 0.90, and 0.96 computed tomography normal (CTN), and 0.92, 0.87, 0.91, 0.96, and 0.96 CT venogram (CTV). These values were subsequently confirmed in the validation cohort.
The radiomics-based prediction model proposed in this study successfully differentiated between SCH and SCC throat cancers using CT imaging, thereby facilitating the development of accurate preoperative diagnosis based on specific biomarkers and cancer phenotypes.
利用 CT 图像提取的纹理特征区分鳞状细胞增生（SCH）（良性）和鳞状细胞癌（SCC）（恶性），从而在无需样本活检的情况下，辅助术前对咽喉癌进行医学诊断和治疗。
本回顾性研究共纳入 100 例咽喉癌患者。这些病例来自中国长春吉林大学第二医院，时间为 2017 年 6 月至 2019 年 1 月。患者被分为训练队列和验证队列，分别包含 70 例和 30 例患者。人工智能套件软件（A.K.软件）用于从 CT 图像中提取放射组学特征。使用最小冗余最大相关性（mRMR）和最小绝对收缩和选择算子（LASSO）方法对这些特征进行进一步处理，以获得最佳特征的子集。使用 R-studio 软件基于曲线下面积（AUC）值、准确性、特异性和敏感性验证放射组学模型。
训练队列的诊断准确性、特异性、PPV、NPV 和 AUC 值分别为 0.91、0.9、0.93、0.9 及 0.96 （CTA）、0.93、0.93、0.95、0.9 及 0.96（CTN）和 0.92、0.87、0.91、0.96 及 0.96（CTV）。这些值随后在验证队列中得到了验证。
本研究提出的基于放射组学的预测模型成功地利用 CT 成像区分了 SCH 和 SCC 咽喉癌，从而有助于基于特定生物标志物和癌症表型制定准确的术前诊断。
