Lijuan Yang

Objectives To evaluate the value of deep learning (DL) combining multimodal radiomics and clinical and imaging features for differentiating ocular adnexal lymphoma (OAL) from idiopathic orbital inflammation (IOI). Methods Eighty-nine patients with histopathologically confirmed OAL (n = 39) and IOI (n = 50) were divided into training and validation groups. Convolutional neural networks and multimodal fusion layers were used to extract multimodal radiomics features from the T1-weighted image (T1WI), T2-weighted image, and contrast-enhanced T1WI. These multimodal radiomics features were then combined with clinical and imaging features and used together to differentiate between OAL and IOI. The area under the curve (AUC) was used to evaluate DL models with different features under five-fold cross-validation. The Student t-test, chi-squared, or Fisher exact test was used for comparison of different groups. Results In the validation group, the diagnostic AUC of the DL model using combined features was 0.953 (95% CI, 0.895–1.000), higher than that of the DL model using multimodal radiomics features (0.843, 95% CI, 0.786–0.898, p < 0.01) or clinical and imaging features only (0.882, 95% CI, 0.782–0.982, p = 0.13). The DL model built on multimodal radiomics features outperformed those built on most bimodalities and unimodalities (p < 0.05). In addition, the DL-based analysis with the orbital cone area (covering both the orbital mass and surrounding tissues) was superior to that with the region of interest (ROI) covering only the mass area, although the difference was not significant (p = 0.33). Conclusions DL-based analysis that combines multimodal radiomics features with clinical and imaging features may help to differentiate between OAL and IOI. Key Points • It is difficult to differentiate OAL from IOI due to the overlap in clinical and imaging manifestations. • Radiomics has shown potential for noninvasive diagnosis of different orbital lymphoproliferative disorders. • DL-based analysis combining radiomics and imaging and clinical features may help the differentiation between OAL and IOI.

Objectives To evaluate the effectiveness of bag-of-features (BOF)-based radiomics for differentiating ocular adnexal lymphoma (OAL) and idiopathic orbital inflammation (IOI) from contrast-enhanced MRI (CE-MRI). Methods Fifty-six patients with pathologically confirmed IOI (28 patients) and OAL (28 patients) were randomly divided into training (n = 42) and testing (n = 14) groups. One hundred sixty texture features extracted from the CE-MR image were encoded into the BOF representation with fewer features. The support vector machine (SVM) with a linear kernel was used as the classifier. Data augmented was performed by cropping orbital lesions in different directions to alleviate the over-fitting problem. Student’s t test and the Holm-Bonferroni method were employed to compare the performance of different analysis methods. The chi-square test was used to compare the analysis with MRI and human radiological diagnosis. Results In the independent testing group, the differentiation by the BOF features with augmentation achieved an area under the curve (AUC) of 0.803 (95% CI: 0.725–0.880), which was significantly higher than that of the BOF features without augmentation and that of the texture features (p < 0.05). In addition, the same radiomic analysis with pre-contrast MRI obtained an AUC of 0.618 (95% CI: 0.560–0.677), which was significantly lower than that with CE-MRI. The diagnostic performance of the analysis with CE-MRI was significantly better than the radiology resident (p < 0.05) but had no significant difference with the experienced radiologist, even though there was less consistency between the radiomic analysis and the human visual diagnosis. Conclusions The BOF-based radiomics may be helpful for the differentiation between OAL and IOI. Key Points • It is challenging to differentiate OAL from IOI due to the similar clinical and image features. • Radiomics has great potential for the noninvasive diagnosis of orbital diseases. • The BOF representation from patch to image may help the differentiation of OAL and IOI.