Arendt Christophe T, Leithner Doris, Mayerhoefer Marius E, Gibbs Peter, Czerny Christian, Arnoldner Christoph, Burck Iris, Leinung Martin, Tanyildizi Yasemin, Lenga Lukas, Martin Simon S, Vogl Thomas J, Schernthaner Ruediger E
Department of Diagnostic and Interventional Radiology, University Hospital Frankfurt, Frankfurt am Main, Germany.
Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Eur Radiol. 2021 Jun;31(6):4071-4078. doi: 10.1007/s00330-020-07564-4. Epub 2020 Dec 4.
To evaluate the performance of radiomic features extracted from high-resolution computed tomography (HRCT) for the differentiation between cholesteatoma and middle ear inflammation (MEI), and to investigate the impact of post-reconstruction harmonization and data resampling.
One hundred patients were included in this retrospective dual-center study: 48 with histology-proven cholesteatoma (center A: 23; center B: 25) and 52 with MEI (A: 27; B: 25). Radiomic features (co-occurrence and run-length matrix, absolute gradient, autoregressive model, Haar wavelet transform) were extracted from manually defined 2D-ROIs. The ten best features for lesion differentiation were selected using probability of error and average correlation coefficients. A multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used for radiomics-based classification, with histopathology serving as the reference standard (70% of cases for training, 30% for validation). The analysis was performed five times each on (a) unmodified data and on data that were (b) resampled to the same matrix size, and (c) corrected for acquisition protocol differences using ComBat harmonization.
Using unmodified data, the MLP-ANN classification yielded an overall median area under the receiver operating characteristic curve (AUC) of 0.78 (0.72-0.84). Using original data from center A and resampled data from center B, an overall median AUC of 0.88 (0.82-0.99) was yielded, while using ComBat harmonized data, an overall median AUC of 0.89 (0.79-0.92) was revealed.
Radiomic features extracted from HRCT differentiate between cholesteatoma and MEI. When using multi-centric data obtained with differences in CT acquisition parameters, data resampling and ComBat post-reconstruction harmonization clearly improve radiomics-based lesion classification.
• Unenhanced high-resolution CT coupled with radiomics analysis may be useful for the differentiation between cholesteatoma and middle ear inflammation. • Pooling of data extracted from inhomogeneous CT datasets does not appear meaningful without further post-processing. • When using multi-centric CT data obtained with differences in acquisition parameters, post-reconstruction harmonization and data resampling clearly improve radiomics-based soft-tissue differentiation.
评估从高分辨率计算机断层扫描（HRCT）中提取的放射组学特征在胆脂瘤与中耳炎症（MEI）鉴别诊断中的性能，并研究重建后归一化和数据重采样的影响。
本回顾性双中心研究纳入了100例患者：48例经组织学证实为胆脂瘤（中心A：23例；中心B：25例），52例为中耳炎症（A：27例；B：25例）。从手动定义的二维感兴趣区域（ROI）中提取放射组学特征（共生矩阵和游程长度矩阵、绝对梯度、自回归模型、哈尔小波变换）。使用错误概率和平均相关系数选择用于病变鉴别诊断的十个最佳特征。采用多层感知器前馈人工神经网络（MLP-ANN）进行基于放射组学的分类，以组织病理学作为参考标准（70%的病例用于训练，30%用于验证）。分析分别在（a）未修改的数据、（b）重采样至相同矩阵大小的数据以及（c）使用ComBat归一化校正采集协议差异的数据上各进行五次。
使用未修改的数据，MLP-ANN分类的受试者操作特征曲线（AUC）下的总体中位数面积为0.78（0.72 - 0.84）。使用中心A的原始数据和中心B的重采样数据，总体中位数AUC为0.88（0.82 - 0.99），而使用ComBat归一化数据时，总体中位数AUC为0.89（0.79 - 0.92）。
从HRCT中提取的放射组学特征可鉴别胆脂瘤和MEI。当使用CT采集参数存在差异的多中心数据时，数据重采样和ComBat重建后归一化可明显改善基于放射组学的病变分类。
• 未增强的高分辨率CT结合放射组学分析可能有助于胆脂瘤与中耳炎症的鉴别诊断。• 未经进一步后处理，汇总从不均匀CT数据集中提取的数据似乎无意义。• 当使用采集参数存在差异的多中心CT数据时，重建后归一化和数据重采样可明显改善基于放射组学的软组织鉴别诊断。
