Share Email Print
cover

Proceedings Paper

Automatic detection and measurement of femur length from fetal ultrasonography
Author(s): Prateep Mukherjee; Gokul Swamy; Madhumita Gupta; Uday Patil; Kajoli Banerjee Krishnan
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Femur bone length is used in the assessment of fetal development and in the prediction of gestational age (GA). In this paper, we present a completely automated two-step method for identifying fetal femur and measuring its length from 2D ultrasound images. The detection algorithm uses a normalized score premised on the distribution of anatomical shape, size and presentation of the femur bone in clinically acceptable scans. The measurement process utilizes a polynomial curve fitting technique to determine the end-points of the bone from a 1D profile that is most distal from the transducer surface. The method has been tested with manual measurements made on 90 third trimester femur images by two radiologists. The measurements made by the experts are strongly correlated (Pearson's coefficient = 0.95). Likewise, the algorithm estimate is strongly correlated with expert measurements (Pearson's coefficient = 0.92 and 0.94). Based on GA estimates and their bounds specified in Standard Obstetric Tables, the GA predictions from automated measurements are found to be within ±2SD of GA estimates from both manual measurements in 89/90 cases and within ±3SD in all 90 cases. The method presented in this paper can be adapted to perform automatic measurement of other fetal limbs.

Paper Details

Date Published: 12 March 2010
PDF: 9 pages
Proc. SPIE 7629, Medical Imaging 2010: Ultrasonic Imaging, Tomography, and Therapy, 762909 (12 March 2010); doi: 10.1117/12.844340
Show Author Affiliations
Prateep Mukherjee, International Institute of Information Technology (India)
Gokul Swamy, GE Global Research (India)
Madhumita Gupta, GE Healthcare (India)
Uday Patil, GE Global Research (India)
Kajoli Banerjee Krishnan, GE Global Research (India)


Published in SPIE Proceedings Vol. 7629:
Medical Imaging 2010: Ultrasonic Imaging, Tomography, and Therapy
Jan D'hooge; Stephen A. McAleavey, Editor(s)

© SPIE. Terms of Use
Back to Top