Machine learning models to predict success of endoscopic sleeve gastroplasty using total and excess weight loss percent achievement: a multicentre study.

BACKGROUND: The large amount of heterogeneous data collected in surgical/endoscopic practice calls for data-driven approaches as machine learning (ML) models. The aim of this study was to develop ML models to predict endoscopic sleeve gastroplasty (ESG) efficacy at 12 months defined by total weight loss (TWL) % and excess weight loss (EWL) % achievement. Multicentre data were used to enhance generalizability: evaluate consistency among different center of ESG practice and assess reproducibility of the models and possible clinical application. Models were designed to be dynamic and integrate follow-up clinical data into more accurate predictions, possibly assisting management and decision-making. METHODS: ML models were developed using data of 404 ESG procedures performed at 12 centers across Europe. Collected data included clinical and demographic variables at the time of ESG and at follow-up. Multicentre/external and single center/internal and temporal validation were performed. Training and evaluation of the models were performed on Python's scikit-learn library. Performance of models was quantified as receiver operator curve (ROC-AUC), sensitivity, specificity, and calibration plots. RESULTS: Multicenter external validation: ML models using preoperative data show poor performance. Best performances were reached by linear regression (LR) and support vector machine models for TWL% and EWL%, respectively, (ROC-AUC: TWL% 0.87, EWL% 0.86) with the addition of 6-month follow-up data. Single-center internal validation: Preoperative data only ML models show suboptimal performance. Early, i.e., 3-month follow-up data addition lead to ROC-AUC of 0.79 (random forest classifiers model) and 0.81 (LR models) for TWL% and EWL% achievement prediction, respectively. Single-center temporal validation shows similar results. CONCLUSIONS: Although preoperative data only may not be sufficient for accurate postoperative predictions, the ability of ML models to adapt and evolve with the patients changes could assist in providing an effective and personalized postoperative care. ML models predictive capacity improvement with follow-up data is encouraging and may become a valuable support in patient management and decision-making.

Surgical optomics: hyperspectral imaging and deep learning towards precision intraoperative automatic tissue recognition-results from the EX-MACHYNA trial.

BACKGROUND: Hyperspectral imaging (HSI), combined with machine learning, can help to identify characteristic tissue signatures enabling automatic tissue recognition during surgery. This study aims to develop the first HSI-based automatic abdominal tissue recognition with human data in a prospective bi-center setting. METHODS: Data were collected from patients undergoing elective open abdominal surgery at two international tertiary referral hospitals from September 2020 to June 2021. HS images were captured at various time points throughout the surgical procedure. Resulting RGB images were annotated with 13 distinct organ labels. Convolutional Neural Networks (CNNs) were employed for the analysis, with both external and internal validation settings utilized. RESULTS: A total of 169 patients were included, 73 (43.2%) from Strasbourg and 96 (56.8%) from Verona. The internal validation within centers combined patients from both centers into a single cohort, randomly allocated to the training (127 patients, 75.1%, 585 images) and test sets (42 patients, 24.9%, 181 images). This validation setting showed the best performance. The highest true positive rate was achieved for the skin (100%) and the liver (97%). Misclassifications included tissues with a similar embryological origin (omentum and mesentery: 32%) or with overlaying boundaries (liver and hepatic ligament: 22%). The median DICE score for ten tissue classes exceeded 80%. CONCLUSION: To improve automatic surgical scene segmentation and to drive clinical translation, multicenter accurate HSI datasets are essential, but further work is needed to quantify the clinical value of HSI. HSI might be included in a new omics science, namely surgical optomics, which uses light to extract quantifiable tissue features during surgery.

Towards automatic verification of the critical view of the myopectineal orifice with artificial intelligence.

BACKGROUND: Visualization of key anatomical landmarks is required during surgical Trans Abdominal Pre Peritoneal repair (TAPP) of inguinal hernia. The Critical View of the MyoPectineal Orifice (CVMPO) was proposed to ensure correct dissection. An artificial intelligence (AI) system that automatically validates the presence of key and marks during the procedure is a critical step towards automatic dissection quality assessment and video-based competency evaluation. The aim of this study was to develop an AI system that automatically recognizes the TAPP key CVMPO landmarks in hernia repair videos. METHODS: Surgical videos of 160 TAPP procedures were used in this single-center study. A deep neural network-based object detector was developed to automatically recognize the pubic symphysis, direct hernia orifice, Cooper's ligament, the iliac vein, triangle of Doom, deep inguinal ring, and iliopsoas muscle. The system was trained using 130 videos, annotated and verified by two board-certified surgeons. Performance was evaluated in 30 videos of new patients excluded from the training data. RESULTS: Performance was validated in 2 ways: first, single-image validation where the AI model detected landmarks in a single laparoscopic image (mean average precision (MAP) of 51.2%). The second validation is video evaluation where the model detected landmarks throughout the myopectineal orifice visual inspection phase (mean accuracy and F-score of 77.1 and 75.4% respectively). Annotation objectivity was assessed between 2 surgeons in video evaluation, showing a high agreement of 88.3%. CONCLUSION: This study establishes the first AI-based automated recognition of critical structures in TAPP surgical videos, and a major step towards automatic CVMPO validation with AI. Strong performance was achieved in the video evaluation. The high inter-rater agreement confirms annotation quality and task objectivity.

Mice with endogenous TDP-43 mutations exhibit gain of splicing function and characteristics of amyotrophic lateral sclerosis.

TDP-43 (encoded by the gene TARDBP) is an RNA binding protein central to the pathogenesis of amyotrophic lateral sclerosis (ALS). However, how TARDBP mutations trigger pathogenesis remains unknown. Here, we use novel mouse mutants carrying point mutations in endogenous Tardbp to dissect TDP-43 function at physiological levels both in vitro and in vivo Interestingly, we find that mutations within the C-terminal domain of TDP-43 lead to a gain of splicing function. Using two different strains, we are able to separate TDP-43 loss- and gain-of-function effects. TDP-43 gain-of-function effects in these mice reveal a novel category of splicing events controlled by TDP-43, referred to as "skiptic" exons, in which skipping of constitutive exons causes changes in gene expression. In vivo, this gain-of-function mutation in endogenous Tardbp causes an adult-onset neuromuscular phenotype accompanied by motor neuron loss and neurodegenerative changes. Furthermore, we have validated the splicing gain-of-function and skiptic exons in ALS patient-derived cells. Our findings provide a novel pathogenic mechanism and highlight how TDP-43 gain of function and loss of function affect RNA processing differently, suggesting they may act at different disease stages.

Automatic optical biopsy for colorectal cancer using hyperspectral imaging and artificial neural networks.

BACKGROUND: Intraoperative identification of cancerous tissue is fundamental during oncological surgical or endoscopic procedures. This relies on visual assessment supported by histopathological evaluation, implying a longer operative time. Hyperspectral imaging (HSI), a contrast-free and contactless imaging technology, provides spatially resolved spectroscopic analysis, with the potential to differentiate tissue at a cellular level. However, HSI produces "big data", which is impossible to directly interpret by clinicians. We hypothesize that advanced machine learning algorithms (convolutional neural networks-CNNs) can accurately detect colorectal cancer in HSI data. METHODS: In 34 patients undergoing colorectal resections for cancer, immediately after extraction, the specimen was opened, the tumor-bearing section was exposed and imaged using HSI. Cancer and normal mucosa were categorized from histopathology. A state-of-the-art CNN was developed to automatically detect regions of colorectal cancer in a hyperspectral image. Accuracy was validated with three levels of cross-validation (twofold, fivefold, and 15-fold). RESULTS: 32 patients had colorectal adenocarcinomas confirmed by histopathology (9 left, 11 right, 4 transverse colon, and 9 rectum). 6 patients had a local initial stage (T1-2) and 26 had a local advanced stage (T3-4). The cancer detection performance of the CNN using 15-fold cross-validation showed high sensitivity and specificity (87% and 90%, respectively) and a ROC-AUC score of 0.95 (considered outstanding). In the T1-2 group, the sensitivity and specificity were 89% and 90%, respectively, and in the T3-4 group, the sensitivity and specificity were 81% and 93%, respectively. CONCLUSIONS: Automatic colorectal cancer detection on fresh specimens using HSI, using a properly trained CNN is feasible and accurate, even with small datasets, regardless of the local tumor extension. In the near future, this approach may become a useful intraoperative tool during oncological endoscopic and surgical procedures, and may result in precise and non-destructive optical biopsies to support objective and consistent tumor-free resection margins.

A novel knockout mouse for the small EDRK-rich factor 2 (Serf2) showing developmental and other deficits.

The small EDRK-rich factor 2 (SERF2) is a highly conserved protein that modifies amyloid fibre assembly in vitro and promotes protein misfolding. However, the role of SERF2 in regulating age-related proteotoxicity remains largely unexplored due to a lack of in vivo models. Here, we report the generation of Serf2 knockout mice using an ES cell targeting approach, with Serf2 knockout alleles being bred onto different defined genetic backgrounds. We highlight phenotyping data from heterozygous Serf2+/- mice, including unexpected male-specific phenotypes in startle response and pre-pulse inhibition. We report embryonic lethality in Serf2-/- null animals when bred onto a C57BL/6 N background. However, homozygous null animals were viable on a mixed genetic background and, remarkably, developed without obvious abnormalities. The Serf2 knockout mice provide a powerful tool to further investigate the role of SERF2 protein in previously unexplored pathophysiological pathways in the context of a whole organism.

Prediction of In Vivo Laser-Induced Thermal Damage with Hyperspectral Imaging Using Deep Learning.

Thermal ablation is an acceptable alternative treatment for primary liver cancer, of which laser ablation (LA) is one of the least invasive approaches, especially for tumors in high-risk locations. Precise control of the LA effect is required to safely destroy the tumor. Although temperature imaging techniques provide an indirect measurement of the thermal damage, a degree of uncertainty remains about the treatment effect. Optical techniques are currently emerging as tools to directly assess tissue thermal damage. Among them, hyperspectral imaging (HSI) has shown promising results in image-guided surgery and in the thermal ablation field. The highly informative data provided by HSI, associated with deep learning, enable the implementation of non-invasive prediction models to be used intraoperatively. Here we show a novel paradigm "peak temperature prediction model" (PTPM), convolutional neural network (CNN)-based, trained with HSI and infrared imaging to predict LA-induced damage in the liver. The PTPM demonstrated an optimal agreement with tissue damage classification providing a consistent threshold (50.6 ± 1.5 °C) for the damage margins with high accuracy (~0.90). The high correlation with the histology score (r = 0.9085) and the comparison with the measured peak temperature confirmed that PTPM preserves temperature information accordingly with the histopathological assessment.

Trisomy of human chromosome 21 enhances amyloid-ß deposition independently of an extra copy of APP.

Down syndrome, caused by trisomy of chromosome 21, is the single most common risk factor for early-onset Alzheimer's disease. Worldwide approximately 6 million people have Down syndrome, and all these individuals will develop the hallmark amyloid plaques and neurofibrillary tangles of Alzheimer's disease by the age of 40 and the vast majority will go on to develop dementia. Triplication of APP, a gene on chromosome 21, is sufficient to cause early-onset Alzheimer's disease in the absence of Down syndrome. However, whether triplication of other chromosome 21 genes influences disease pathogenesis in the context of Down syndrome is unclear. Here we show, in a mouse model, that triplication of chromosome 21 genes other than APP increases amyloid-ß aggregation, deposition of amyloid-ß plaques and worsens associated cognitive deficits. This indicates that triplication of chromosome 21 genes other than APP is likely to have an important role to play in Alzheimer's disease pathogenesis in individuals who have Down syndrome. We go on to show that the effect of trisomy of chromosome 21 on amyloid-ß aggregation correlates with an unexpected shift in soluble amyloid-ß 40/42 ratio. This alteration in amyloid-ß isoform ratio occurs independently of a change in the carboxypeptidase activity of the γ-secretase complex, which cleaves the peptide from APP, or the rate of extracellular clearance of amyloid-ß. These new mechanistic insights into the role of triplication of genes on chromosome 21, other than APP, in the development of Alzheimer's disease in individuals who have Down syndrome may have implications for the treatment of this common cause of neurodegeneration.

Augmented reality in a tumor resection model.

BACKGROUND: Augmented Reality (AR) guidance is a technology that allows a surgeon to see sub-surface structures, by overlaying pre-operative imaging data on a live laparoscopic video. Our objectives were to evaluate a state-of-the-art AR guidance system in a tumor surgical resection model, comparing the accuracy of the resection with and without the system. Our system has three phases. Phase 1: using the MRI images, the kidney's and pseudotumor's surfaces are segmented to construct a 3D model. Phase 2: the intra-operative 3D model of the kidney is computed. Phase 3: the pre-operative and intra-operative models are registered, and the laparoscopic view is augmented with the pre-operative data. METHODS: We performed a prospective experimental study on ex vivo porcine kidneys. Alginate was injected into the parenchyma to create pseudotumors measuring 4-10 mm. The kidneys were then analyzed by MRI. Next, the kidneys were placed into pelvictrainers, and the pseudotumors were laparoscopically resected. The AR guidance system allows the surgeon to see tumors and margins using classical laparoscopic instruments, and a classical screen. The resection margins were measured microscopically to evaluate the accuracy of resection. RESULTS: Ninety tumors were segmented: 28 were used to optimize the AR software, and 62 were used to randomly compare surgical resection: 29 tumors were resected using AR and 33 without AR. The analysis of our pathological results showed 4 failures (tumor with positive margins) (13.8%) in the AR group, and 10 (30.3%) in the Non-AR group. There was no complete miss in the AR group, while there were 4 complete misses in the non-AR group. In total, 14 (42.4%) tumors were completely missed or had a positive margin in the non-AR group. CONCLUSIONS: Our AR system enhances the accuracy of surgical resection, particularly for small tumors. Crucial information such as resection margins and vascularization could also be displayed.

Differential Contribution of Subunit Interfaces to α9α10 Nicotinic Acetylcholine Receptor Function.

Nicotinic acetylcholine receptors can be assembled from either homomeric or heteromeric pentameric subunit combinations. At the interface of the extracellular domains of adjacent subunits lies the acetylcholine binding site, composed of a principal component provided by one subunit and a complementary component of the adjacent subunit. Compared with neuronal nicotinic acetylcholine cholinergic receptors (nAChRs) assembled from α and ß subunits, the α9α10 receptor is an atypical member of the family. It is a heteromeric receptor composed only of α subunits. Whereas mammalian α9 subunits can form functional homomeric α9 receptors, α10 subunits do not generate functional channels when expressed heterologously. Hence, it has been proposed that α10 might serve as a structural subunit, much like a ß subunit of heteromeric nAChRs, providing only complementary components to the agonist binding site. Here, we have made use of site-directed mutagenesis to examine the contribution of subunit interface domains to α9α10 receptors by a combination of electrophysiological and radioligand binding studies. Characterization of receptors containing Y190T mutations revealed unexpectedly that both α9 and α10 subunits equally contribute to the principal components of the α9α10 nAChR. In addition, we have shown that the introduction of a W55T mutation impairs receptor binding and function in the rat α9 subunit but not in the α10 subunit, indicating that the contribution of α9 and α10 subunits to complementary components of the ligand-binding site is nonequivalent. We conclude that this asymmetry, which is supported by molecular docking studies, results from adaptive amino acid changes acquired only during the evolution of mammalian α10 subunits.

Augmented reality in gynecologic surgery: evaluation of potential benefits for myomectomy in an experimental uterine model.

BACKGROUND: Augmented Reality (AR) is a technology that can allow a surgeon to see subsurface structures. This works by overlaying information from another modality, such as MRI and fusing it in real time with the endoscopic images. AR has never been developed for a very mobile organ like the uterus and has never been performed for gynecology. Myomas are not always easy to localize in laparoscopic surgery when they do not significantly change the surface of the uterus, or are at multiple locations. OBJECTIVE: To study the accuracy of myoma localization using a new AR system compared to MRI-only localization. METHODS: Ten residents were asked to localize six myomas (on a uterine model into a laparoscopic box) when either using AR or in conditions that simulate a standard method (only the MRI was available). Myomas were randomly divided in two groups: the control group (MRI only, AR not activated) and the AR group (AR activated). Software was used to automatically measure the distance between the point of contact on the uterine surface and the myoma. We compared these distances to the true shortest distance to obtain accuracy measures. The time taken to perform the task was measured, and an assessment of the complexity was performed. RESULTS: The mean accuracy in the control group was 16.80 mm [0.1-52.2] versus 0.64 mm [0.01-4.71] with AR. In the control group, the mean time to perform the task was 18.68 [6.4-47.1] s compared to 19.6 [3.9-77.5] s with AR. The mean score of difficulty (evaluated for each myoma) was 2.36 [1-4] versus 0.87 [0-4], respectively, for the control and the AR group. DISCUSSION: We developed an AR system for a very mobile organ. This is the first user study to quantitatively evaluate an AR system for improving a surgical task. In our model, AR improves localization accuracy.

Profilin1 E117G is a moderate risk factor for amyotrophic lateral sclerosis.

BACKGROUND: Amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD) are progressive neurodegenerative disorders that share significant clinical, pathological and genetic overlap and are considered to represent different ends of a common disease spectrum. Mutations in Profilin1 have recently been described as a rare cause of familial ALS. The PFN1 E117G missense variant has been described in familial and sporadic cases, and also found in controls, casting doubt on its pathogenicity. Interpretation of such variants represents a significant clinical-genetics challenge. OBJECTIVE AND RESULTS: Here, we combine a screen of a new cohort of 383 ALS patients with multiple-sequence datasets to refine estimates of the ALS and FTD risk associated with PFN1 E117G. Together, our cohorts add up to 5118 ALS and FTD cases and 13 089 controls. We estimate a frequency of E117G of 0.11% in controls and 0.25% in cases. Estimated odds after population stratification is 2.44 (95% CI 1.048 to ∞, Mantel-Haenszel test p=0.036). CONCLUSIONS: Our results show an association between E117G and ALS, with a moderate effect size.

A nicotinic acetylcholine receptor transmembrane point mutation (G275E) associated with resistance to spinosad in Frankliniella occidentalis.

High levels of resistance to spinosad, a macrocyclic lactone insecticide, have been reported previously in western flower thrips, Frankliniella occidentalis, an economically important insect pest of vegetables, fruit and ornamental crops. We have cloned the nicotinic acetylcholine receptor (nAChR) α6 subunit from F. occidentalis (Foα6) and compared the nucleotide sequence of Foα6 from susceptible and spinosad-resistant insect populations (MLFOM and R1S respectively). A single nucleotide change has been identified in Foα6, resulting in the replacement of a glycine (G) residue in susceptible insects with a glutamic acid (E) in resistant insects. The resistance-associated mutation (G275E) is predicted to lie at the top of the third α-helical transmembrane domain of Foα6. Although there is no direct evidence identifying the location of the spinosad binding site, the analogous amino acid in the C. elegans glutamate-gated chloride channel lies in close proximity (4.4 Å) to the known binding site of ivermectin, another macrocyclic lactone pesticide. The functional consequences of the resistance-associated mutation have been examined in the human nAChR α7 subunit. Introduction of an analogous (A272E) mutation in α7 abolishes the modulatory effects of spinosad whilst having no significant effect upon activation by acetylcholine, consistent with spinosad having an allosteric mechanism of action.

Partial Hepatic Vein Occlusion and Venous Congestion in Liver Exploration Using a Hyperspectral Camera: A Proposal for Monitoring Intraoperative Liver Perfusion.

INTRODUCTION: The changes occurring in the liver in cases of outflow deprivation have rarely been investigated, and no measurements of this phenomenon are available. This investigation explored outflow occlusion in a pig model using a hyperspectral camera. METHODS: Six pigs were enrolled. The right hepatic vein was clamped for 30 min. The oxygen saturation (StO2%), deoxygenated hemoglobin level (de-Hb), near-infrared perfusion (NIR), and total hemoglobin index (THI) were investigated at different time points in four perfused lobes using a hyperspectral camera measuring light absorbance between 500 nm and 995 nm. Differences among lobes at different time points were estimated by mixed-effect linear regression. RESULTS: StO2% decreased over time in the right lateral lobe (RLL, totally occluded) when compared to the left lateral (LLL, outflow preserved) and the right medial (RML, partially occluded) lobes (p < 0.05). De-Hb significantly increased after clamping in RLL when compared to RML and LLL (p < 0.05). RML was further analyzed considering the right portion (totally occluded) and the left portion of the lobe (with an autonomous draining vein). StO2% decreased and de-Hb increased more smoothly when compared to the totally occluded RLL (p < 0.05). CONCLUSIONS: The variations of StO2% and deoxy-Hb could be considered good markers of venous liver congestion.

The Drosophila nicotinic acetylcholine receptor subunits Dα5 and Dα7 form functional homomeric and heteromeric ion channels.

BACKGROUND: Nicotinic acetylcholine receptors (nAChRs) play an important role as excitatory neurotransmitters in vertebrate and invertebrate species. In insects, nAChRs are the site of action of commercially important insecticides and, as a consequence, there is considerable interest in examining their functional properties. However, problems have been encountered in the successful functional expression of insect nAChRs, although a number of strategies have been developed in an attempt to overcome such difficulties. Ten nAChR subunits have been identified in the model insect Drosophila melanogaster (Dα1-Dα7 and Dß1-Dß3) and a similar number have been identified in other insect species. The focus of the present study is the Dα5, Dα6 and Dα7 subunits, which are distinguished by their sequence similarity to one another and also by their close similarity to the vertebrate α7 nAChR subunit. RESULTS: A full-length cDNA clone encoding the Drosophila nAChR Dα5 subunit has been isolated and the properties of Dα5-, Dα6- and Dα7-containing nAChRs examined in a variety of cell expression systems. We have demonstrated the functional expression, as homomeric nAChRs, of the Dα5 and Dα7 subunits in Xenopus oocytes by their co-expression with the molecular chaperone RIC-3. Also, using a similar approach, we have demonstrated the functional expression of a heteromeric 'triplet' nAChR (Dα5 + Dα6 + Dα7) with substantially higher apparent affinity for acetylcholine than is seen with other subunit combinations. In addition, specific cell-surface binding of [125I]-α-bungarotoxin was detected in both Drosophila and mammalian cell lines when Dα5 was co-expressed with Dα6 and RIC-3. In contrast, co-expression of additional subunits (including Dα7) with Dα5 and Dα6 prevented specific binding of [125I]-α-bungarotoxin in cell lines, suggesting that co-assembly with other nAChR subunits can block maturation of correctly folded nAChRs in some cellular environments. CONCLUSION: Data are presented demonstrating the ability of the Drosophila Dα5 and Dα7 subunits to generate functional homomeric and also heteromeric nAChRs.

StaSiS-Net: A stacked and siamese disparity estimation network for depth reconstruction in modern 3D laparoscopy.

Developing accurate and real-time algorithms for a non-invasive three-dimensional representation and reconstruction of internal patient structures is one of the main research fields in computer-assisted surgery and endoscopy. Mono and stereo endoscopic images of soft tissues are converted into a three-dimensional representation by the estimation of depth maps. However, automatic, detailed, accurate and robust depth map estimation is a challenging problem that, in the stereo setting, is strictly dependent on a robust estimate of the disparity map. Many traditional algorithms are often inefficient or not accurate. In this work, novel self-supervised stacked and Siamese encoder/decoder neural networks are proposed to compute accurate disparity maps for 3D laparoscopy depth estimation. These networks run in real-time on standard GPU-equipped desktop computers and the outputs may be used for depth map estimation using the a known camera calibration. We compare performance on three different public datasets and on a new challenging simulated dataset and our solutions outperform state-of-the-art mono and stereo depth estimation methods. Extensive robustness and sensitivity analyses on more than 30000 frames has been performed. This work leads to important improvements in mono and stereo real-time depth map estimation of soft tissues and organs with a very low average mean absolute disparity reconstruction error with respect to ground truth.

Computer-Assisted Differentiation between Colon-Mesocolon and Retroperitoneum Using Hyperspectral Imaging (HSI) Technology.

Complete mesocolic excision (CME), which involves the adequate resection of the tumor-bearing colonic segment with "en bloc" removal of its mesocolon along embryological fascial planes is associated with superior oncological outcomes. However, CME presents a higher complication rate compared to non-CME resections due to a higher risk of vascular injury. Hyperspectral imaging (HSI) is a contrast-free optical imaging technology, which facilitates the quantitative imaging of physiological tissue parameters and the visualization of anatomical structures. This study evaluates the accuracy of HSI combined with deep learning (DL) to differentiate the colon and its mesenteric tissue from retroperitoneal tissue. In an animal study including 20 pig models, intraoperative hyperspectral images of the sigmoid colon, sigmoid mesentery, and retroperitoneum were recorded. A convolutional neural network (CNN) was trained to distinguish the two tissue classes using HSI data, validated with a leave-one-out cross-validation process. The overall recognition sensitivity of the tissues to be preserved (retroperitoneum) and the tissues to be resected (colon and mesentery) was 79.0 ± 21.0% and 86.0 ± 16.0%, respectively. Automatic classification based on HSI and CNNs is a promising tool to automatically, non-invasively, and objectively differentiate the colon and its mesentery from retroperitoneal tissue.

Hyperspectral Imaging in Major Hepatectomies: Preliminary Results from the Ex-Machyna Trial.

Ischemia-reperfusion injury during major hepatic resections is associated with high rates of post-operative complications and liver failure. Real-time intra-operative detection of liver dysfunction could provide great insight into clinical outcomes. In the present study, we demonstrate the intra-operative application of a novel optical technology, hyperspectral imaging (HSI), to predict short-term post-operative outcomes after major hepatectomy. We considered fifteen consecutive patients undergoing major hepatic resection for malignant liver lesions from January 2020 to June 2021. HSI measures included tissue water index (TWI), organ hemoglobin index (OHI), tissue oxygenation (StO2%), and near infrared (NIR). Pre-operative, intra-operative, and post-operative serum and clinical outcomes were collected. NIR values were higher in unhealthy liver tissue (p = 0.003). StO2% negatively correlated with post-operative serum ALT values (r = -0.602), while ΔStO2% positively correlated with ALP (r = 0.594). TWI significantly correlated with post-operative reintervention and OHI with post-operative sepsis and liver failure. In conclusion, the HSI imaging system is accurate and precise in translating from pre-clinical to human studies in this first clinical trial. HSI indices are related to serum and outcome metrics. Further experimental and clinical studies are necessary to determine clinical value of this technology.

Knowledge, attitude, and practice of artificial intelligence in emergency and trauma surgery, the ARIES project: an international web-based survey.

AIM: We aimed to evaluate the knowledge, attitude, and practices in the application of AI in the emergency setting among international acute care and emergency surgeons. METHODS: An online questionnaire composed of 30 multiple choice and open-ended questions was sent to the members of the World Society of Emergency Surgery between 29th May and 28th August 2021. The questionnaire was developed by a panel of 11 international experts and approved by the WSES steering committee. RESULTS: 200 participants answered the survey, 32 were females (16%). 172 (86%) surgeons thought that AI will improve acute care surgery. Fifty surgeons (25%) were trained, robotic surgeons and can perform it. Only 19 (9.5%) were currently performing it. 126 (63%) surgeons do not have a robotic system in their institution, and for those who have it, it was mainly used for elective surgery. Only 100 surgeons (50%) were able to define different AI terminology. Participants thought that AI is useful to support training and education (61.5%), perioperative decision making (59.5%), and surgical vision (53%) in emergency surgery. There was no statistically significant difference between males and females in ability, interest in training or expectations of AI (p values 0.91, 0.82, and 0.28, respectively, Mann-Whitney U test). Ability was significantly correlated with interest and expectations (p < 0.0001 Pearson rank correlation, rho 0.42 and 0.47, respectively) but not with experience (p = 0.9, rho - 0.01). CONCLUSIONS: The implementation of artificial intelligence in the emergency and trauma setting is still in an early phase. The support of emergency and trauma surgeons is essential for the progress of AI in their setting which can be augmented by proper research and training programs in this area.

Surgical data science - from concepts toward clinical translation.

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.