AUTHOR=Cui Fengzhi , Khodrog Osama A. , Liu Wei , Liu Jianhua , Yuan Qinghai TITLE=Clinical application of CT-based radiomics model in differentiation between laryngeal squamous cell carcinoma and squamous cell hyperplasia JOURNAL=Frontiers in Medicine VOLUME=Volume 10 - 2023 YEAR=2024 URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1337723 DOI=10.3389/fmed.2023.1337723 ISSN=2296-858X ABSTRACT=To evaluate the clinical application valuation of CT-based radiomics prediction model for discriminating SCC and SCH.METHODS: A total of 254 clinical samples were selected from 291 patients with larynx occupying lesion which underwent primary surgery and all lesions were validated via histopathological examination at the Second Hospital of Jilin University between June 2004 and December 2019. All patients were randomly allocated into the training (n = 177) and validation (n = 77) cohorts. After the acquisition of CT images, manual 3D tumor segmentation was performed from the CT images of the arterial, venous, and non-contrast phases via ITK-SNAP software, and then radiomics features are extracted by A.K. software. Based on the above features, three different diagnostic models(CTN, CTA+CTV, and CTN+CTA+CTV) were constructed to classify SCC and SCH. Additionally, ROC and DCA analysis were measured to evaluate the diagnostic characteristic and clinical safety of the proposed three prognostic models.In radiomic prediction Model 1(CTN), the AUC, accuracy, sensitivity, specificity, PPV and NPV of the training cohorts in differentiating SCC and SCH were 0.883, 0.785, 0.645, 1.000, 1.000 and 0.648, while in the testing cohorts were 0.852, 0.792, 0.66, 1.000, 1.000 and 0.652. In radiomic prediction Model 2(CTA+CTV), the measured values of training cohorts were 0.965, 0.91, 0.916, 0.9, 0.933 and 0.875, while in the testing cohorts were 0.902, 0.805, 0.851, 0.733, 0.833 and 0.759. In radiomic prediction Model 3(CTN+CTA+CTV), the measured values of training cohorts were 0.985, 0.944, 0.953, 0.929, 0.953 and 0.929, while in the testing cohorts were 0.965, 0.857, 0.894, 0.8, 0.875 and 0.828, respectively.The radiomic prediction Model 3 based on arterial-venous-plain combined scan phase of CT achieved promising diagnostic performance, expected to be regarded as a preoperative imaging tool in classifying SCC and SCH to guide clinicians to develop individualized treatment programs.