Applying a statistical method in transvaginal ultrasound training: lessons from the learning curve cumulative summation test (LC-CUSUM) for endometriosis mapping

Abstract

Background: Methods available for assessing the learning curve, such as a predefined number of procedures or direct mentoring are lacking. Our aim was to describe the use of a statistical method to identify the minimal training length of an experienced sonographer, newly trained in deep infiltrating endometriosis (DIE) mapping by evaluating the learning curve of transvaginal ultrasound (TVUS) in the preoperative assessment of endometriosis.

Methods: A retrospective study in a tertiary referral center for endometriosis. Reports and stored data from TVUS scans performed by one operator with training in general gynecological ultrasound, but not in endometriosis mapping, were analyzed retrospectively for patients who subsequently underwent laparoscopy, which served as a reference standard. The performance of TVUS was assessed for the following sites: endometriomas, bladder, vagina, pouch of Douglas, bowel and uterosacral ligaments, and correlated with laparoscopic findings. Sensitivity, specificity, PPV, NPV, and accuracy were calculated, and the operator's diagnostic performance was assessed using the learning curve cumulative summation test (LC-CUSUM).

Results: Data from 94 women were available for analysis. The learning curve using the LC-CUSUM graph showed that the sonographer reached the predefined level of proficiency in detecting endometriosis lesions after 20, 26, 32, 31, 38, and 44 examinations for endometriomas, bladder nodules, vaginal nodules, pouch of Douglas obliteration, bowel nodules, and uterosacral ligament nodules, respectively.

Conclusions: LC-CUSUM allows monitoring of individual performance during the learning process of new methodologies. This study shows that a sonographer trained in general gynecologic ultrasonography, who devotes time to learn TVUS for DIE mapping, can achieve proficiency for diagnosing the major types of endometriotic lesions after examining less than 50 patients who subsequently undergo surgery in a training setting.

Keywords: Deep infiltrative endometriosis; Endometriomas; Individualized assessment; LC-CUSUM; Learning curve; Transvaginal ultrasound.

Fig. 1

Cumulative summation test for the learning curve (LC-CUSUM) graphs for TVUS for endometriomas and deep infiltrative endometriosis. The vertical axis shows the CUSUM values, the horizontal axis shows the case number. Dotted horizontal lines show acceptable/unacceptable boundary lines of the CUSUM score. As long as the score remains over the limit h (dotted line), the operator is not considered as proficient, whereas when the LC-CUSUM score crosses this limit, he is considered to have become proficient. As long as the score remains under the limit, the operator is considered to maintain an acceptable performance. Performance was reached after 20 exams for endometriomas (red line), 26 exams for bladder nodules (blue), 32 exams for vaginal nodules (green), 31 exams for pouch of Douglas obliteration (turquoise), 38 exams for bowel nodules (purple), and 44 exams for uterosacral ligament nodules (dark red)

Fig. 2

Multiplanar 3D image of TVUS of bladder detrusor endometriosis penetrating from the anterior uterine wall. See hourglass appearance of nodule penetration (arrow). The uterus is affected by adenomyosis

Fig. 3

TVUS of a large vaginal nodule extending to the rectosigmoid. The sonographer interpreted this lesion as a rectosigmoid bowel lesion while the surgeon described it as a vaginal lesion. Arrows show extent of lesion

Fig. 4

Multiplanar 3D image of TVUS of a bowel nodule behind the cervix. Nodule is shown in arrows