Method and system for the automated temporal subtraction of medical images

Abstract

Method and system for the detection of interval change in medical images. Three dimensional images, such as previous and current section images in CT scans, are obtained. An anatomic feature, such as the lungs, is used to select sections containing lung by a gray-level thresholding technique. The section correspondence between the current and previous scans is determined automatically. The initial registration of the corresponding sections in the two scans is achieved by a rotation correction and a cross-correlation technique. A more accurate registration between the corresponding current and previous section images is achieved by local matching. A nonlinear warping process which is also based on the cross-correlation technique is applied to the previous image to yield a warped image after the matching. The final subtracted section images were derived by subtracting of the previous section images from the corresponding current section images. Interval changes such as a change in tumor size and a newly developed pleural effusion are enhanced significantly.

Description

[0001] 1. Field of the Invention[0002] The present invention is related to temporal analysis of medical images and, in particular, to the analysis of computed tomographic images using automated temporal subtraction.[0003] 2. Discussion of the Background[0004] The application of a temporal subtraction technique to radiographic images such as chest images can significantly enhance some subtle interval changes existing in sequentially obtained images which might be missed by radiologists. These interval changes may be very important in enabling radiologists to detect some diseases, such as early lung cancer, or to assess the effects of treatment on known lesions. Difazio et al., in Digital chest radiography: Effect of temporal subtraction images on detection accuracy, Radiology, 202:447-452 (1997) reported that the use of the temporal subtraction technique for sequential chest images can significantly increase radiologists' diagnostic accuracy in identifying interval changes.[0005] Whe...

AI Technical Summary

Benefits of technology

[0009] A second object of the invention is to enhance interval changes in images.

[0013] These and other objects of the invention are achieved by a method, system and computer program product for detecting interval change in images. In the method according to the invention, first and second three-dimensional images of a subject are obtained. The first and second images are typically current and previous images of a subject. The first and second images are matched. The first image is non-linearly warped to produce a warped image and the warped image is subtracted from the second image. The subtraction can produce and / or enhance interval changes in the first and second images.

Problems solved by technology

However, it is difficult and time-consuming for radiologists to compare current and previous (temporally sequential) thoracic CT scans to identify new findings or to assess the effects of treatments on known lesions, because this requires a systematic visual search and correlation of a large number of images (sections) in both current and previous scans.

Viewing several images can be difficult because of variations in the images.

However, it is very difficult to keep these positions unchanged in a clinical environment.

However, the difference in lung orientations could be very large for sections from different scans.

The local matching technique is again based on the cross-correlation technique, which results in nonlinear warping of the previous section image.

Images