2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: A Multi-Center Study

• Published in: IEEE journal of biomedical and health informatics 2021-03, Vol.25 (3), p.755-763
• Main Authors: Meng, Lingwei, Dong, Di, Chen, Xin, Fang, Mengjie, Wang, Rongpin, Li, Jing, Liu, Zaiyi, Tian, Jie
• Format: Article
• Language: English
• Subjects: Annotations; Cancer; Computed tomography; Computed tomography (CT); computer-aided detection (CAD); Confidence intervals; Feature extraction; Gastric cancer; Image analysis; Image processing; Learning algorithms; Lymph nodes; Machine learning; Medical imaging; Metastases; Radiomics; radiomics features; Resampling; Statistical analysis; Three-dimensional displays; Tumors; Two dimensional displays; Two dimensional models
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2020.3002805

Objective: Radiomics, an emerging tool for medical image analysis, is potential towards precisely characterizing gastric cancer (GC). Whether using one-slice 2D annotation or whole-volume 3D annotation remains a long-time debate, especially for heterogeneous GC. We comprehensively compared 2D and 3D radiomic features' representation and discrimination capacity regarding GC, via three tasks ({\boldsymbol{T}^{\boldsymbol{LNM}}}, lymph node metastasis' prediction; {\boldsymbol{T}^{\boldsymbol{LVI}}}, lymphovascular invasion's prediction; {\boldsymbol{T}^{\boldsymbol{pT}}}, pT4 or other pT stages' classification). Methods: Four-center 539 GC patients were retrospectively enrolled and divided into the training and validation cohorts. From 2D or 3D regions of interest (ROIs) annotated by radiologists, radiomic features were extracted respectively. Feature selection and model construction procedures were customed for each combination of two modalities (2D or 3D) and three tasks. Subsequently, six machine learning models (\boldsymbol{Model}_{2\boldsymbol{D}}^{\boldsymbol{LNM}}, \boldsymbol{Model}_{3\boldsymbol{D}}^{\boldsymbol{LNM}}; \boldsymbol{Model}_{2\boldsymbol{D}}^{\boldsymbol{LVI}}, \boldsymbol{Model}_{3\boldsymbol{D}}^{\boldsymbol{LVI}}; \boldsymbol{Model}_{2\boldsymbol{D}}^{\boldsymbol{pT}}, \boldsymbol{Model}_{3\boldsymbol{D}}^{\boldsymbol{pT}}) were derived and evaluated to reflect modalities' performances in characterizing GC. Furthermore, we performed an auxiliary experiment to assess modalities' performances when resampling spacing different. Results: Regarding three tasks, the yielded areas under the curve (AUCs) were: \boldsymbol{Model}_{2\boldsymbol{D}}^{\boldsymbol{LNM}}'s 0.712 (95% confidence interval, 0.613-0.811),