Ovarian ultrasound image analysis: follicle segmentation

• Published in: IEEE transactions on medical imaging Vol. 17; no. 6; pp. 935 - 944
• Main Authors: Krivanek, A., Sonka, M.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.12.1998; Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Area measurement; Automatic testing; Biological and medical sciences; Computer errors; Female; Genital system. Mammary gland; Humans; Image analysis; Image Processing, Computer-Assisted - instrumentation; Image Processing, Computer-Assisted - methods; Image Processing, Computer-Assisted - statistics & numerical data; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Linear Models; Medical sciences; Ovarian Follicle - diagnostic imaging; Search methods; Shape measurement; Size measurement; Ultrasonic imaging; Ultrasonic investigative techniques; Ultrasonic variables measurement; Ultrasonography - instrumentation; Ultrasonography - methods; Ultrasonography - statistics & numerical data; Sonography; Human; Prior information; Ovary; Segmentation; Dimensional analysis; Female genital system; Automatic system; Female; Morphometry; Performance; Ovarian follicle
• ISSN: 0278-0062
• DOI: 10.1109/42.746626

Ovarian ultrasound is an effective tool in infertility treatment. Repeated measurements of the size and shape of follicles over several days are the primary means of evaluation by physicians. Currently, follicle wall segmentation is achieved by manual tracing which is time consuming and susceptible to inter-operator variation. An automated method for follicle wall segmentation is reported that uses a four-step process based on watershed segmentation and a knowledge-based graph search algorithm which utilizes a priori information about follicle structure for inner and outer wall detection. The automated technique was tested on 36 ultrasonographic images of women's ovaries. Validation against manually traced borders has shown good correlation of manually defined and computer-determined area measurements (R/sup 2/=0.85-0.96). The border positioning errors were small: 0.63/spl plusmn/0.36 mm for inner border and 0.67/spl plusmn/0.41 mm for outer border detection. The use of watershed segmentation and graph search methods facilitates fast, accurate inner and outer border detection with minimal user-interaction.