A CT-based radiomics nomogram involving the cystic fluid area for differentiating appendiceal mucinous neoplasms from appendicitis with intraluminal fluid

• DOI: 10.1007/s00432-024-05695-5
• Publication Date: 2024-03-20T05:09:00Z
• Authors: Xinbin Wang; Na Feng; Yonggang Qiu; Hao Dong; Cuncheng Lou; Junjie Yang; Jieni Yu; Chunyan Jiang; Jianxia Xu; Risheng Yu
• Keywords: Nomogram

Abstract Objective To develop and validate a radiomics nomogram based on computed tomography (CT) to distinguish appendiceal mucinous neoplasms (AMNs) from appendicitis with intraluminal fluid (AWIF). Method A total of 211 patients two medical institutions were retrospectively analysed, which 109 pathologically confirmed as having concomitant CT signs 102 AMN. All randomly assigned training (147 patients) or validation cohort (64 at 7:3 ratio. Radiomics features the cystic area lesions extracted nonenhanced images using 3D Slicer software. Minimum redundancy maximum relevance least absolute shrinkage selection operator regression methods employed screen model. Combined clinical-CT models further developed corresponding selected after multivariate analysis. Lastly, receiver operating characteristic curves, decision curve analysis (DCA) used assess models’ performances in cohorts. Results 851 acquired images. Subsequently, model consisting eight was developed. The combined comprised rad-score, age, mural calcification, while contained age calcification. achieved under curves (AUCs) 0.945 (95% confidence interval [CI]: 0.895, 0.976) 0.933 CI: 0.841, 0.980) cohorts, respectively, larger than those obtained by (training cohort: AUC, 0.915 [95% 0.865, 0.964]; 0.912 0.843, 0.981]) 0.884 0.820, 0.931]; 0.767 0.644, 0.863]). Finally, DCA showed that clinical utility superior models. Conclusion Our constituting radiomics, clinical, exhibited good performance for differentiating AMN AWIF, indicating its potential application decision-making.