Department of Radiology, Faculty of Medicine, Ankara Yildirim Beyazit University, Ankara City Hospital, Bilkent, Cankaya, 06800, Ankara, Turkey.
Department of Radiology, Nigde Omer Halisdemir University Training and Research Hospital, Nigde, Turkey.
Jpn J Radiol. 2022 Sep;40(9):951-960. doi: 10.1007/s11604-022-01278-x. Epub 2022 Apr 17.
To evaluate the diagnostic capability of radiomics in distinguishing lipoma and Atypic Lipomatous Tumors/Well-Differentiated Liposarcomas (ALT/WDL) with Magnetic Resonance Imaging (MRI).
Patients with a histopathologic diagnosis of lipoma (n = 45) and ALT/WDL (n = 20), who had undergone pre-surgery or pre-biopsy MRI, were enrolled. The MDM2 amplification was accepted as gold-standard test. The T1-weighted turbo spin echo images were used for radiomics analysis. Utility of a predefined standardized imaging protocol and a single type of 1.5 T scanner were sought as inclusion criteria. Radiomics parameters that show a certain level of reproducibility were included in the study and supplied to Support Vector Machine (SVM) as a machine learning method.
No significant difference was found in terms of gender, location and age between the lipoma and ALT/WDL groups. Sixty-five parameters were accepted as reproducible. Fifty-seven parameters were able to distinguish the two groups significantly (AUC range 0.564-0.902). Diagnostic performance of the SVM was one of the highest among literature findings: sensitivity = 96.8% (95% CI 94.03-98.39%), specificity = 93.72% (95% CI 86.36-97.73%) and AUC = 0.987 (95% CI 0.972-0.999).
Although radiomics has been proven to be useful in previous literature regarding discrimination of lipomas and ALT/WDLs, we found that its accuracy could further be improved with utility of standardized hardware, imaging protocols and incorporation of machine learning methods.
利用磁共振成像（MRI）评估影像组学在区分脂肪瘤和非典型性脂肪肿瘤/高分化脂肪肉瘤（ALT/WDL）方面的诊断能力。
本研究纳入了术前或活检前接受 MRI 检查且经组织病理学诊断为脂肪瘤（n=45）和 ALT/WDL（n=20）的患者。以 MDM2 扩增作为金标准检测方法。采用 T1 加权涡轮自旋回波图像进行影像组学分析。作为纳入标准，我们寻求使用预定义的标准化成像方案和单一类型 1.5T 扫描仪。纳入研究的影像组学参数具有一定的可重复性，并作为机器学习方法提供给支持向量机（SVM）。
在性别、位置和年龄方面，脂肪瘤组和 ALT/WDL 组之间无显著差异。有 65 个参数被认为具有可重复性。57 个参数能够显著区分这两组（AUC 范围为 0.564-0.902）。SVM 的诊断性能在文献中发现的结果中是最高的之一：灵敏度为 96.8%（95%CI 94.03-98.39%），特异性为 93.72%（95%CI 86.36-97.73%），AUC 为 0.987（95%CI 0.972-0.999）。
尽管影像组学在区分脂肪瘤和 ALT/WDL 方面的已有文献中已被证明是有用的，但我们发现，通过使用标准化硬件、成像方案和整合机器学习方法，可以进一步提高其准确性。
