Most surgeons are skeptical as to the feasibility of autonomous actions in surgery. Interestingly, many examples of autonomous actions already exist and have been around for years. Since the beginning of this millennium, the field of artificial intelligence (AI) has grown exponentially with the development of machine learning (ML), deep learning (DL), computer vision (CV) and natural language processing (NLP). All of these facets of AI will be fundamental to the development of more autonomous actions in surgery, unfortunately, only a limited number of surgeons have or seek expertise in this rapidly evolving field. As opposed to AI in medicine, AI surgery (AIS) involves autonomous movements. Fortuitously, as the field of robotics in surgery has improved, more surgeons are becoming interested in technology and the potential of autonomous actions in procedures such as interventional radiology, endoscopy and surgery. The lack of haptics, or the sensation of touch, has hindered the wider adoption of robotics by many surgeons; however, now that the true potential of robotics can be comprehended, the embracing of AI by the surgical community is more important than ever before. Although current complete surgical systems are mainly only examples of tele-manipulation, for surgeons to get to more autonomously functioning robots, haptics is perhaps not the most important aspect. If the goal is for robots to ultimately become more and more independent, perhaps research should not focus on the concept of haptics as it is perceived by humans, and the focus should be on haptics as it is perceived by robots/computers. This article will discuss aspects of ML, DL, CV and NLP as they pertain to the modern practice of surgery, with a focus on current AI issues and advances that will enable us to get to more autonomous actions in surgery. Ultimately, there may be a paradigm shift that needs to occur in the surgical community as more surgeons with expertise in AI may be needed to fully unlock the potential of AIS in a safe, efficacious and timely manner.

One of the most applied imaging methods in medicine is endoscopy. A highly specialized image modality has been developed since the first modern endoscope, the “Lichtleiter” of Bozzini was introduced in the early 19th century. Multiple medical disciplines use endoscopy for diagnostics or to visualize and support therapeutic procedures. Therefore, the shapes, functionalities, handling concepts, and the integrated and surrounding technology of endoscopic systems were adapted to meet these dedicated medical application requirements. This survey gives an overview of modern endoscopic technology’s state of the art. Therefore, the portfolio of several manufacturers with commercially available products on the market was screened and summarized. Additionally, some trends for upcoming developments were collected.

This is a review focused on advances and current limitations of computer vision (CV) and how CV can help us obtain to more autonomous actions in surgery. It is a follow-up article to one that we previously published in Sensors entitled, “Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?” As opposed to that article that also discussed issues of machine learning, deep learning and natural language processing, this review will delve deeper into the field of CV. Additionally, non-visual forms of data that can aid computerized robots in the performance of more autonomous actions, such as instrument priors and audio haptics, will also be highlighted. Furthermore, the current existential crisis for surgeons, endoscopists and interventional radiologists regarding more autonomy during procedures will be discussed. In summary, this paper will discuss how to harness the power of CV to keep doctors who do interventions in the loop.

Globally, the death rate of pancreatic ductal adenocarcinoma (PDAC) has doubled over 30 years and is likely to further increase, making PDAC a leading cause of cancer-related death in the coming years. PDAC is typically diagnosed at an advanced stage, and modified FOLFIRINOX or nab-paclitaxel and gemcitabine are the mainstay of systemic therapy. For elderly patients with good performance status, low-dose treatment can preserve quality of life without compromising cancer control or survival. Maintenance therapy should be considered in PDAC patients achieving disease control with systemic therapy. In particular, olaparib has demonstrated a progression-free survival benefit of 3.6 months in a subgroup of PDAC patients with germline BRCA1/2 mutations (ca. 10% of all PDAC). Pancreatic enzyme replacement therapy is often omitted in the treatment of patients with PDAC, with possibly deleterious consequences. Small intestinal bacterial overgrowth is highly prevalent in patients with PDAC and should be considered in the diagnostic algorithm of PDAC patients with bloating and diarrhea. Rivaroxaban has been associated with a reduced risk of thrombosis without an increase in major bleeding events, and its use should be considered in every patient with advanced PDAC undergoing systemic therapy.

Background: One critical step in the therapy of patients with localized pancreatic cancer is the determination of local resectability. The decision between primary surgery versus upfront local or systemic cancer therapy seems especially to differ between pancreatic cancer centers. In our cohort study, we analyzed the independent judgement of resectability of five experienced high volume pancreatic surgeons in 200 consecutive patients with borderline resectable or locally advanced pancreatic cancer. Methods: Pretherapeutic CT or MRI scans of 200 consecutive patients with borderline resectable or locally advanced pancreatic cancer were evaluated by 5 independent pancreatic surgeons. Resectability and the degree of abutment of the tumor to the venous and arterial structures adjacent to the pancreas were reported. Interrater reliability and dispersion indices were compared. Results: One hundred ninety-four CT scans and 6 MRI scans were evaluated and all parameters were evaluated by all surgeons in 133 (66.5%) cases. Low agreement was observed for tumor infiltration of venous structures (κ = 0.265 and κ = 0.285) while good agreement was achieved for the abutment of the tumor to arterial structures (interrater reliability celiac trunk κ = 0.708 P < 0.001). In patients with vascular tumor contact indicating locally advanced disease, surgeons highly agreed on unresectability, but in patients with vascular tumor abutment consistent with borderline resectable disease, the judgement of resectability was less uniform (dispersion index locally advanced vs. borderline resectable p < 0.05). Conclusion: Excellent agreement between surgeons exists in determining the presence of arterial abutment and locally advanced pancreatic cancer. The determination of resectability in borderline resectable patients is influenced by additional subjective factors. Trial registration: EudraCT:2009-014476-21 (2013-02-22) and NCT01827553 (2013-04-09).

Purpose Enhancer of zeste homolog 2 (EZH2) is associated with epigenetic gene silencing and aggressiveness in many tumor types. However, the prognostic impact of high EZH2 expression is controversially discussed for colorectal cancer. For this reason, we immunohistochemically analyzed EZH2 expression in 105 specimens from colon cancer patients separately for tumor center and invasion front. Methods All sections from tissue microarrays were evaluated manually and digitally using Definiens Tissue Studio software (TSS). To mirror-image the EZH2 status at the tumor invasion front, we treated HCT116 colon cancer cells with the EZH2 inhibitor 3-Deazaneplanocin A (DZNep) and studied the growth of in ovo xenografts in the chorioallantoic membrane (CAM) assay. Results We showed a significant decrease in EZH2 expression and the repressive H3K27me3 code at the tumor invasion front as supported by the TSS-constructed heatmaps. Loss of EZH2 at tumor invasion front, but not in tumor center was correlated with unfavorable prognosis and more advanced tumor stages. The observed cell cycle arrest in vitro and in vivo was associated with higher tumor aggressiveness. Xenografts formed by DZNep-treated HCT116 cells showed loosely packed tumor masses, infiltrative growth into the CAM, and high vessel density. Conclusion The differences in EZH2 expression between tumor center and invasion front as well as different scoring and cutoff values can most likely explain controversial literature data concerning the prognostic value of EZH2. Epigenetic therapies using EZH2 inhibitors have to be carefully evaluated for each specific tumor type, since alterations in cell differentiation might lead to unfavorable results.