601. Selection of Radiomics Features based on their Reproducibility
- Author
-
Carles Sanchez, Raquel Perez, Katerine Diaz-Chito, Debora Gil, Guillermo Torres, and Marta Ligero
- Subjects
0301 basic medicine ,Reproducibility ,business.industry ,Dimensionality reduction ,Feature extraction ,Reproducibility of Results ,Pattern recognition ,Convolutional neural network ,03 medical and health sciences ,030104 developmental biology ,0302 clinical medicine ,Kernel (image processing) ,Lasso (statistics) ,030220 oncology & carcinogenesis ,Principal component analysis ,Artificial intelligence ,Neural Networks, Computer ,Kernel Fisher discriminant analysis ,business ,Artifacts ,Algorithms - Abstract
Dimensionality reduction is key to alleviate machine learning artifacts in clinical applications with Small Sample Size (SSS) unbalanced datasets. Existing methods rely on either the probabilistic distribution of training data or the discriminant power of the reduced space, disregarding the impact of repeatability and uncertainty in features.In the present study is proposed the use of reproducibility of radiomics features to select features with high inter-class correlation coefficient (ICC). The reproducibility includes the variability introduced in the image acquisition, like medical scans acquisition parameters and convolution kernels, that affects intensity-based features and tumor annotations made by physicians, that influences morphological descriptors of the lesion.For the reproducibility of radiomics features three studies were conducted on cases collected at Vall Hebron Oncology Institute (VHIO) on responders to oncology treatment. The studies focused on the variability due to the convolution kernel, image acquisition parameters, and the inter-observer lesion identification. The features selected were those features with a ICC higher than 0.7 in the three studies.The selected features based on reproducibility were evaluated for lesion malignancy classification using a different database. Results show better performance compared to several state-of-the-art methods including Principal Component Analysis (PCA), Kernel Discriminant Analysis via QR decomposition (KDAQR), LASSO, and an own built Convolutional Neural Network.
- Full Text
- View/download PDF