Suggestions for processing DICOM images

I have a series of DICOM images that I need to segment. The problem is that they have a lot of despeckle noise and same intensities among different areas of the soft tissue that makes it difficult for any segmentation algorithm to work.

Can you suggest preprocessing methods so images become more contrast, with less noise and easily segmented?

I attach a sample of the images I want to segment.

Waiting for your suggestions.

Answer 1

[Image Analyst]

I'm sure ultrasound noise is a common topic of research.

Go here to find papers on the subject: Vision Bibliography

You should be able to find something there. For example, just a small sampling:

20.12.3 Ultrasound, Ultrasonic, Speckle Removal, Analysis

Chapter Contents (Back)

Speckle Removal. Despeckle. Ultrasound.

Dutt, V., Greenleaf, J.F.,

Adaptive speckle reduction filter for log-compressed B-scan images,

MedImg(15), No. 6, December 1996, pp. 802-813.

IEEE Top Reference. 0203

BibRef

Czerwinski, R.N., Jones, D.L., O'Brien, Jr., W.D.,

Detection of lines and boundaries in speckle images-application to medical ultrasound,

MedImg(18), No. 2, February 1999, pp. 126-136.

IEEE Top Reference. 0110

BibRef

Earlier:

Ultrasound speckle reduction by directional median filtering,

ICIP95(I: 358-361).

IEEE DOI 9510

BibRef

Earlier:

Edge detection in ultrasound speckle noise,

ICIP94(III: 304-308).

IEEE DOI 9411

BibRef