Automatic Generation of Liver Virtual Models With Artificial Intelligence: Application to Liver Resection Complexity
Omar Ali1,2,3,4, Alexandre Bône1, Caterina Accardo5,6
1Guerbet Research, Villepinte, France.
Objective:
The clinical aim of this work is to predict intraoperative LRC from preoperative CT scans only.
Background:
Liver resection (LR) is the most prevalent curative treatment for primary liver cancer, yet overall mortality/morbidity rates remain elevated. The conventional definition and classification of LR complexity (LRC) lack the inclusion of the disease-induced 3D anatomic surgery complexity.
Methods:
3D models of the organ, tumors, and blood vessels were generated from deep learning models trained on patients' CT scans. The surgeons' expertise on which anatomic factors lead to LRC was translated into a new anatomic frame of reference around the Hepatic Central Zone (HCZ). A fully automatic pipeline to generate the HCZ and quantify the tumor position relative to it was assessed. An AI model was then trained to predict LRC from a patient cohort for whom LRC was annotated at the end of each surgery. The AI prediction was finally compared to the prediction of surgeons who only saw the patient's preoperative CT scan.
Results:
The 3D reconstructions are successfully evaluated on benchmark data sets. The HCZ is accurately generated for a variety of atypical vascular anatomies (dice score 82±4.6%). The automatic pipeline is successfully run on a 145 HCC patient cohort. The predicted LRC outperforms the surgeons' individual and combined anticipated complexities (accuracy and AUC scores: 79.4±3.4% and 85.1±3.2%, respectively).
Conclusions:
This automatic digital tool accurately predicts intraoperative LRC and paves the way for an innovative oncology surgery planning. This tool could help orient patients toward appropriate medical centers depending on the predicted LRC level.
