Automatic weighing attribute to retrieve similar lung cancer nodules

Abstract

Background: Cancer is a disease characterized as an uncontrolled growth of abnormal cells that invades neighboring tissues and destroys them. Lung cancer is the primary cause of cancer-related deaths in the world, and it diagnosis is a complex task for specialists and it presents some big challenges as medical image interpretation process, pulmonary nodule detection and classification. In order to aid specialists in the early diagnosis of lung cancer, computer assistance must be integrated in the imaging interpretation and pulmonary nodule classification processes. Methods of Content-Based Image Retrieval (CBIR) have been described as one promising technique to computer-aided diagnosis and is expected to aid radiologists on image interpretation with a second opinion. However, CBIR presents some limitations: image feature extraction process and appropriate similarity measure. The efficiency of CBIR systems depends on calculating image features that may be relevant to the case similarity analysis. When specialists classify a nodule, they are supported by information from exams, images, etc. But each information has more or less weight over decision making about nodule malignancy. Thus, finding a way to measure the weight allows improvement of image retrieval process through the assignment of higher weights to that attributes that best characterize the nodules.

Methods: In this context, the aim of this work is to present a method to automatically calculate attribute weights based on local learning to reflect the interpretation on image retrieval process. The process consists of two stages that are performed sequentially and cyclically: Evaluation Stage and Training Stage. At each iteration the weights are adjusted according to retrieved nodules. After some iterations, it is possible reach a set of attribute weights that optimize the recovery of similar nodes.

Results: The results achieved by updated weights were promising because was possible increase precision by 10% to 6% on average to retrieve of benign and malignant nodules, respectively, with recall of 25% compared with tests without weights associated to attributes in similarity metric. The best result, we reaching values over 100% of precision average until thirtieth lung cancer nodule retrieved.

Conclusions: Based on the results, WED applied to the three vectors used attributes (3D TA, 3D MSA and InV), with weights adjusted by the process, always achieved better results than those found with ED. With the weights, the Precision was increased on average by 17.3% compared with using ED.

Keywords: Content-based image retrieval; Decision support; Information retrieval; Lung cancer; Update weighing attributes.

Fig. 1

CT image presenting a pulmonary nodule (red arrow)

Fig. 2

Maximum intensity projection renderings of pulmonary nodules of different sizes [8]. a, b and c are juxtavascular, juxtapleural and isolated nodules, respectively

Fig. 3

Pulmonary nodule sample of a 3-slice volume, with LIDC-IDRI radiologist’s marks

Fig. 4

Manual segmentation of a pulmonary nodule from the LIDC-IDRI [22]

Fig. 5

GLCM calculation over a 3-slice image volume [24]. Between-slices joint relationships have 1 pixel and slice distances in 45° and 90°

Fig. 6

Output images from the 3D margin sharpness analysis

Fig. 7

Workflow of the weighing update process

Fig. 8

Update weighting methodology for the n retrieved nodules. f is the number of attributes used to represent the nodules, Π _f represents the projection of attribute f over nodules retrieved matrix, σ ⁻¹(Π _f) represents the application of inverse of deviation pattern over the resulting sample from projection Π _f, and w _f is the weight of attribute a _f