Abstract
This study aims to develop content-based image retrieval (CBIR) system for the retrieval of T1-weighted contrast-enhanced MR (CE-MR) images of brain tumors. When a tumor region is fed to the CBIR system as a query, the system attempts to retrieve tumors of the same pathological category. The bag-of-visual-words (BoVW) model with partition learning is incorporated into the system to extract informative features for representing the image contents. Furthermore, a distance metric learning algorithm called the Rank Error-based Metric Learning (REML) is proposed to reduce the semantic gap between low-level visual features and high-level semantic concepts. The effectiveness of the proposed method is evaluated on a brain T1-weighted CE-MR dataset with three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor). Using the BoVW model with partition learning, the mean average precision (mAP) of retrieval increases beyond 4.6% with the learned distance metrics compared with the spatial pyramid BoVW method. The distance metric learned by REML significantly outperforms three other existing distance metric learning methods in terms of mAP. The mAP of the CBIR system is as high as 91.8% using the proposed method, and the precision can reach 93.1% when the top 10 images are returned by the system. These preliminary results demonstrate that the proposed method is effective and feasible for the retrieval of brain tumors in T1-weighted CE-MR Images.
Highlights
In the medical field, digital images are produced every day and are used by radiologists to make diagnoses
Content-based image retrieval (CBIR) mainly serves for two types of application: retrieval of the same anatomic regions [2,3,4] and retrieval of clinically relevant lesions [5,6,7,8]
The current study aims to develop a CBIR system for retrieving T1-weighted contrast-enhanced MR (CE-MR) images that contain brain tumors of the same pathological category
Summary
Digital images are produced every day and are used by radiologists to make diagnoses. Searching for images with the same anatomic regions or similar-appearing lesions according to their visual contents in a large image dataset is difficult. CBIR mainly serves for two types of application: retrieval of the same anatomic regions [2,3,4] and retrieval of clinically relevant lesions (e.g., lesions of the same pathological category) [5,6,7,8]. The current study aims to develop a CBIR system for retrieving T1-weighted contrast-enhanced MR (CE-MR) images that contain brain tumors of the same pathological category. The most similar tumors with the same pathological category in the dataset are returned when a tumor is sent to the system as a query. This study focuses on three types of brain tumors with high incidence rates in clinics: gliomas, meningiomas, and pituitary tumors, percentages of which are about 45%, 15%, and 15% of all brain tumors, respectively
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have