Artificial intelligence-assisted decision making: Prediction of optimal level of distal mesorectal margin during transanal total mesorectal excision (taTME) using deep neural network modeling

Abstract

Background: With steep posterior anorectal angulation, transanal total mesorectal excision (taTME) may have a risk of dissection in the wrong plane or starting higher up, resulting in leaving distal mesorectum behind. Although the distal mesorectal margin can be assessed by preoperative MRI, it needs skilled radiologist and high-definition image for accurate evaluation. This study developed a deep neural network (DNN) to predict the optimal level of distal mesorectal margin.

Methods: A total of 182 pelvic MRI images extracted from the cancer image archive (TCIA) database were included. A DNN was developed using gender, the degree of anterior and posterior anorectal angles as input variables while the difference between anterior and posterior mesorectal distances from anal verge was selected as a target. The predictability power was assessed by regression values (R) which is the correlation between the predicted outputs and actual targets.

Results: The anterior angle was an obtuse angle while the posterior angle varied from acute to obtuse with mean angle difference 35.5°±14.6. The mean difference between the anterior and posterior mesorectal end distances was 18.6±6.6mm. The developed DNN had a very close correlation with the target during training, validation, and testing (R=0.99, 0.81, and 0.89, P<0.001). The predicted level of distal mesorectal margin was closely correlated with the actual optimal level (R=0.91, P<0.001).

Conclusions: Artificial intelligence can assist in either making or confirming the preoperative decisions. Furthermore, the developed model can alert the surgeons for this potential risk and the necessity of re-positioning the proctectomy incision.

Keywords: Artificial intelligence; Deep learning; TAMIS; Transanal total mesorectal excision; taTME.