Key points are not available for this paper at this time.
Measurement of the ovarian parameters is one of the primary features observed in all gynecological scans. The ovarian parameters, major axis, minor axis are measured manually by the expert and the shape of the ovary is analyzed subjectively. Manual measurement is time consuming and Doctor requires approximately 20–25 minutes for each patient for complete diagnosis. With this constraint the doctor can effectively examine around 20 patients per day. With dearth of experts, it is required to reduce the diagnosis time so that more patients can get consultation. Hence there is a need for computer-assisted diagnostic support system for detection of ovarian features to aid the experts in faster diagnosis 1. In this paper, we propose an improved algorithm (anisotropic diffusion filter, CLAHE enhancement, and global enhancement) for automated computerassisted measurement of ovarian size and shape parameters to help expert to do a quick diagnosis. The algorithm has a preprocessing stage, processing stage followed by ovarian parameter extraction. The proposed algorithm is tested on 50 Transvaginal ultrasound images of ovaries. The experimental results are validated against the manual measurements done by the expert and the results obtained by our algorithm are in good agreement with the experts inputs. The proposed algorithm could achieve an average Error Percentage of 5.27% for Major-Axis length (E M1 ) and average Error Percentage of 6.1% for Minor-Axis length (E M2 ).
Usha et al. (Sun,) studied this question.