Yingying Xu

Texture-specific bag of visual words model and spatial cone matching-based method for the retrieval of focal liver lesions using multiphase contrast-enhanced CT images

PurposeThe bag of visual words (BoVW) model is a powerful tool for feature representation that can integrate various handcrafted features like intensity, texture, and spatial information. In this paper, we propose a novel BoVW-based method that incorporates texture and spatial information for the content-based image retrieval to assist radiologists in clinical diagnosis.MethodsThis paper presents a texture-specific BoVW method to represent focal liver lesions (FLLs). Pixels in the region of interest (ROI) are classified into nine texture categories using the rotation-invariant uniform local binary pattern method. The BoVW-based features are calculated for each texture category. In addition, a spatial cone matching (SCM)-based representation strategy is proposed to describe the spatial information of the visual words in the ROI. In a pilot study, eight radiologists with different clinical experience performed diagnoses for 20 cases with and without the top six retrieved results. A total of 132 multiphase computed tomography volumes including five pathological types were collected.ResultsThe texture-specific BoVW was compared to other BoVW-based methods using the constructed dataset of FLLs. The results show that our proposed model outperforms the other three BoVW methods in discriminating different lesions. The SCM method, which adds spatial information to the orderless BoVW model, impacted the retrieval performance. In the pilot trial, the average diagnosis accuracy of the radiologists was improved from 66 to 80% using the retrieval system.ConclusionThe preliminary results indicate that the texture-specific features and the SCM-based BoVW features can effectively characterize various liver lesions. The retrieval system has the potential to improve the diagnostic accuracy and the confidence of the radiologists.

Bag of temporal co-occurrence words for retrieval of focal liver lesions using 3D multiphase contrast-enhanced CT images

Computer-aided diagnosis (CAD) systems have been verified to have the potential to assist radiologists in clinical diagnosis to detect and characterize focal liver lesions (FLLs) based on single- or multiphase contrast-enhanced computed tomography (CT) images. Features extracted from multiphase contrast-enhanced CT images carry more important diagnostic information i.e. enhancement pattern and demonstrate much stronger discriminative ability compared to those of single-phase CT images. In this paper, we propose a new method for multiphase image feature generation called the bag of temporal co-occurrence words (BoTCoW). A temporal co-occurrence image connecting intensity from multiphase images is constructed. Then the bag of visual word (BoVW) model is employed on the temporal co-occurrence images to extract temporal features. The proposed method effectively captures temporal enhancement information and demonstrates the distribution of the evolution patterns. The effectiveness of this method is validated in a retrieval system using 132 FLLs with confirmed pathology type. The preliminary results show that the proposed BoTCoW method outperforms the previously proposed temporal features and multiphase features based on the BoVW model.

Focal Liver Lesion Classification Based on Tensor Sparse Representations of Multi-phase CT Images

The bag-of-visual-words (BoVW) method has been proved to be an effective method for classification tasks in both natural imaging and medical imaging. In this paper, we propose a multilinear extension of the traditional BoVW method for classification of focal liver lesions using multi-phase CT images. In our approach, we form new volumes from the corresponding slices of multi-phase CT images and extract cubes from the volumes as local structures. Regard the high dimensional local structures as tensors, we propose a K-CP (CANDECOMP/PARAFAC) algorithm to learn a tensor dictionary in an iterative way. With the learned tensor dictionary, we can calculate sparse representations of each group of multi-phase CT images. The proposed tensor was evaluated in classification of focal liver lesions and achieved better results than conventional BoVW method.

Computerized Features for LI-RADS Based Computer-Aided Diagnosis of Liver Lesions

Liver Imaging Reporting Data System (LI-RADS) aims to standardize liver lesion imaging findings and diagnostic reports, and it is used as an accurate noninvasive diagnosis and staging method of hepatocellular carcinoma (HCC) nowadays. In this study, we proposed several computerized features for LI-RADS based computer-aided diagnosis of liver lesions. We used several popular machining learning approaches for computerized LI-RADS classification (benign and malignant classification) with our proposed features. The performance of each method was evaluated by using ROC curve and the best AUC score was 0.965 reached by the gradient boosting classifier.