Xiaoyang Xie1, Lijuan Yang2, Fengjun Zhao3, Dong Wang4, Hui Zhang4, Xuelei He1, Xin Cao1, Huangjian Yi1, Xiaowei He1, Yuqing Hou5. 1. Xi'an Key Lab of Radiomics and Intelligent Perception, School of Information Science and Technology, Northwest University, Xi'an, 710069, Shaanxi, China. 2. Department of Radiology, Xi'an Fourth Hospital, Xi'an, 710004, Shaanxi, China. ylijuan@126.com. 3. Xi'an Key Lab of Radiomics and Intelligent Perception, School of Information Science and Technology, Northwest University, Xi'an, 710069, Shaanxi, China. fjzhao@nwu.edu.cn. 4. Department of Radiology, Xi'an Fourth Hospital, Xi'an, 710004, Shaanxi, China. 5. Xi'an Key Lab of Radiomics and Intelligent Perception, School of Information Science and Technology, Northwest University, Xi'an, 710069, Shaanxi, China. houyuqin@nwu.edu.cn.
Abstract
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 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.
Authors: Judith A Ferry; Claire Y Fung; Lawrence Zukerberg; Mark J Lucarelli; Robert P Hasserjian; Frederic I Preffer; Nancy L Harris Journal: Am J Surg Pathol Date: 2007-02 Impact factor: 6.394
Authors: Matthew C Sniegowski; Dianna Roberts; Mathieu Bakhoum; Peter Mc Laughlin; Vivian T Yin; Francesco Turturro; Bita Esmaeli Journal: Br J Ophthalmol Date: 2014-04-23 Impact factor: 4.638
Authors: S E Coupland; L Krause; H J Delecluse; I Anagnostopoulos; H D Foss; M Hummel; N Bornfeld; W R Lee; H Stein Journal: Ophthalmology Date: 1998-08 Impact factor: 12.079
Authors: Claire Y Fung; Nancy J Tarbell; Mark J Lucarelli; Saveli I Goldberg; Rita M Linggood; Nancy L Harris; Judith A Ferry Journal: Int J Radiat Oncol Biol Phys Date: 2003-12-01 Impact factor: 7.038