Content-Based Image Retrieval System for Pulmonary Nodules Using Optimal Feature Sets and Class Membership-Based Retrieval

Retrieval of brain MRI with tumor using contrastive loss based similarity on GoogLeNet encodings

An image retrieval system for medical images aids in disease diagnosis by providing similar images from the medical database to a query image. In this article, a content-based medical image retrieval (CBMIR) system is proposed for the retrieval of magnetic resonance imaging (MRI) images of the brain with three types of tumors:- meningioma, glioma and pituitary tumors. The proposed system uses GoogLeNet encodings via transfer learning as image features. A Siamese Neural Network (SNN), is designed, to represent the GoogLeNet encodings in a two-dimensional (2-D) feature space. The SNN is trained using the contrastive loss function to learn the class-specific image features. The similarity, between a query image and the database images, is measured by the Euclidean metric in the lower dimensional feature space. The proposed method achieves state-of-the-art performance for the retrieval of MRI images with brain tumors. The evaluation is done on the openly available Figshare dataset and the performance metrics used are mean average precision (mAP) and precision@10.

A multi-level similarity measure for the retrieval of the common CT imaging signs of lung diseases

The common CT imaging signs of lung diseases (CISLs) which frequently appear in lung CT images are widely used in the diagnosis of lung diseases. Computer-aided diagnosis (CAD) based on the CISLs can improve radiologists' performance in the diagnosis of lung diseases. Since similarity measure is important for CAD, we propose a multi-level method to measure the similarity between the CISLs. The CISLs are characterized in the low-level visual scale, mid-level attribute scale, and high-level semantic scale, for a rich representation. The similarity at multiple levels is calculated and combined in a weighted sum form as the final similarity. The proposed multi-level similarity method is capable of computing the level-specific similarity and optimal cross-level complementary similarity. The effectiveness of the proposed similarity measure method is evaluated on a dataset of 511 lung CT images from clinical patients for CISLs retrieval. It can achieve about 80% precision and take only 3.6 ms for the retrieval process. The extensive comparative evaluations on the same datasets are conducted to validate the advantages on retrieval performance of our multi-level similarity measure over the single-level measure and the two-level similarity methods. The proposed method can have wide applications in radiology and decision support. Graphical abstract.