Page 21 - Read Online

O’Reilly et al. Art Int Surg 2022;2:173-6 https://dx.doi.org/10.20517/ais.2022.26 Page 175

Gastrointestinal and Endoscopic Surgeons (SAGES) consensus conference on prevention of bile duct injury
(BDI) during cholecystectomy identified that its incidence still occurs at a frequency higher than the 0.1%-
[9]
0.2% rate reported in the open cholecystectomy era . This situation exists despite advances in
instrumentation, imaging, surgical techniques, as well as the considerable educational efforts by SAGES and
other organisations. Given the devastating nature of this complication for the patient (and the surgeon), can
AI offer any solutions to this persisting problem?

Madani and colleagues have explored the ability of deep learning models to identify anatomical landmarks,
as well as safe and dangerous zones of dissection during LC and to assess their performance compared to
expert annotations . Videos of LC were used to train deep neural networks to identify the safe zone of
[10]
dissection (Go zone) and the dangerous zone of dissection (No-Go zone). The deep learning models
produced a consistent yet dynamic video overlay to distinguish these zones. Such an intra-operative overlay
tool could provide augmented reality feedback to surgeons to provide real-time guidance. Remarkably,
already a number of commercially available ML-driven platforms are available, whose utility during LC are
being assessed . This work is at an early stage of development and the ultimate measure of its success will
[11]
be safer surgery and specifically, reduced BDI during LC.

Early prediction of morbidity with detailed attention and thorough postoperative management of
complications can positively impact the overall outcomes of complex HPB procedures. Can AI do this
better than existing tools? Early experience with machine learning suggests that it may. When a machine
learning technique was applied to a dataset of 15,657 HPB and colorectal surgery patients, it had a better
predictive ability (C-statistic) than other established methods, like the American College of Surgery risk
calculator or that of the American Society of Anaesthesiologists .
[12]

The role of radiomics in the field of hepatobiliary oncology is based on the expectation that a radiologic
phenotype, extracted and analysed from computed tomography, positron emission tomography or magnetic
resonance imaging, can imitate a cancer’s genetic variations and help determine the expected tumour
behaviour. Radiomic models have already shown promise in the accurate prediction of early recurrence for
hepatocellular and pancreatic cancer [13,14] . Similarly, AI evaluation of histologic pathology specimens as well
as the proteins and metabolites within the liver, pancreas and adjacent tumors will advance our ability to
precisely diagnose and treat HPB disease. These models have the potential to inform clinical decision
making, especially in the use of precision oncology.

WHY WE SET UP THIS SPECIAL HPB ISSUE OF ARTIFICIAL INTELLIGENCE SURGERY
Over the past decade, enhanced preoperative imaging and visualization, improved delineation of the
complex anatomical structures of the hepatobiliary system and pancreas, and intra-operative technological
advances have helped deliver HPB surgery with increased safety and better postoperative outcomes. AI has a
major role to play in 3D visualization, virtual simulation and augmented reality that will help in the training
of surgeons and the future delivery of conventional and robotic HPB surgery. Artificial neural networks and
machine learning have the potential to revolutionise individualised patient care during the preoperative
[15]
imaging and postoperative surveillance phases .

Artificial Intelligence Surgery has launched a special issue, called “Role of Artificial Intelligence in HPB
Surgery”. The goal is to provide up-to-date, evidence-based literature, as well as expert-guided practice to
understand the current status of artificial intelligence application in HPB surgery and the prospects for
future developments in this field. Ultimately, we hope to help realise the promise of AI, to solve the urgent
problems inherent to our specialty and make our lives, and patients’ lives, “easier and better”.