Using neural networks to autonomously assess adequacy in intraoperative cholangiograms.

BACKGROUND: Intraoperative cholangiography (IOC) is a contrast-enhanced X-ray acquired during laparoscopic cholecystectomy. IOC images the biliary tree whereby filling defects, anatomical anomalies and duct injuries can be identified. In Australia, IOC are performed in over 81% of cholecystectomies compared with 20 to 30% internationally (Welfare AIoHa in Australian Atlas of Healthcare Variation, 2017). In this study, we aim to train artificial intelligence (AI) algorithms to interpret anatomy and recognise abnormalities in IOC images. This has potential utility in (a) intraoperative safety mechanisms to limit the risk of missed ductal injury or stone, (b) surgical training and coaching, and (c) auditing of cholangiogram quality. METHODOLOGY: Semantic segmentation masks were applied to a dataset of 1000 cholangiograms with 10 classes. Classes corresponded to anatomy, filling defects and the cholangiogram catheter instrument. Segmentation masks were applied by a surgical trainee and reviewed by a radiologist. Two convolutional neural networks (CNNs), DeeplabV3+ and U-Net, were trained and validated using 900 (90%) labelled frames. Testing was conducted on 100 (10%) hold-out frames. CNN generated segmentation class masks were compared with ground truth segmentation masks to evaluate performance according to a pixel-wise comparison. RESULTS: The trained CNNs recognised all classes.. U-Net and DeeplabV3+ achieved a mean F1 of 0.64 and 0.70 respectively in class segmentation, excluding the background class. The presence of individual classes was correctly recognised in over 80% of cases. Given the limited local dataset, these results provide proof of concept in the development of an accurate and clinically useful tool to aid in the interpretation and quality control of intraoperative cholangiograms. CONCLUSION: Our results demonstrate that a CNN can be trained to identify anatomical structures in IOC images. Future performance can be improved with the use of larger, more diverse training datasets. Implementation of this technology may provide cholangiogram quality control and improve intraoperative detection of ductal injuries or ductal injuries.

Determination of "borderline resectable" pancreatic cancer - A global assessment of 30 shades of grey.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is an aggressive cancer with a poor prognosis. Accurate preoperative assessment using computed tomography (CT) to determine resectability is crucial in ensuring patients are offered the most appropriate therapeutic strategy. Despite the use of classification guidelines, any interobserver variability between reviewing surgeons and radiologists may confound decisions influencing patient treatment pathways. METHODS: In this multicentre observational study, an international group of 96 clinicians (42 hepatopancreatobiliary surgeons and 54 radiologists) were surveyed and asked to report 30 pancreatic CT scans of pancreatic cancer deemed borderline at respective multidisciplinary meetings (MDM). The degree of interobserver agreement in resectability among radiologists and surgeons was assessed and subgroup regression analysis was performed. RESULTS: Interobserver variability between reviewers was high with no unanimous agreement. Overall interobserver agreement was fair with a kappa value of 0.32 with a higher rate of agreement among radiologists over surgeons. CONCLUSION: Interobserver variability among radiologists and surgeons globally is high, calling into question the consistency of clinical decision making for patients with PDAC and suggesting that central review may be required for studies of neoadjuvant or adjuvant approaches in future as well as ongoing quality control initiatives, even amongst experts in the field.

Rethinking gastroesophageal reflux disorder.

Gastroesophageal reflux disease (GERD) is a common clinical condition for which our understanding has evolved over the past decades. It is now considered a cluster of phenotypes with numerous anatomical and physiological abnormalities contributing to its pathophysiology. As such, it is important to first understand the underlying mechanism of the disease process for each patient before embarking on therapeutic interventions. The aim of our paper is to highlight the mechanisms contributing to GERD and review investigations and interpretation of these results. Finally, the paper reviews the available treatment modalities for this condition, ranging from medical intervention, endoscopic options through to surgery and its various techniques.

The role of esophagectomy in the management of Barrett's esophagus with high-grade dysplasia.

Barrett's esophagus (BE) with high-grade dysplasia (HGD) has previously been a routine indication for esophagectomy. Recent advances in endoscopic therapy have resulted in a shift away from surgery. Current international guidelines recommend endoscopic therapy for BE with HGD irrespective of recurrence or progression of dysplasia. Current guidelines do not address the ongoing role of esophagectomy as an adjunct in the setting of failed endoscopic therapy. This review examines the role of esophagectomy as an adjunct to endoscopy in the management of patients with BE and HGD, with a specific focus on patients with persistent, progressive, or recurrent disease, disease resistant to endoscopic therapy, in patients with concomitant esophageal pathology, and in those patients in whom lifelong surveillance may not be possible or desired.

Recent insights into the biology of Barrett's esophagus.

Barrett's esophagus (BE) is the only known precursor to esophageal adenocarcinoma (EAC), an aggressive cancer with a poor prognosis. Our understanding of the pathogenesis and Barrett's metaplasia is incomplete, and this has limited the development of new therapeutic targets and agents, risk stratification ability, and management strategies. This review outlines current insights into the biology of BE and addresses controversies surrounding cell of origin, cellular reprogramming theories, updates on esophageal epithelial barrier function, and the significance of goblet cell metaplasia and its association with malignant change. Further research into the basic biology of BE is vital as it will underpin novel therapies and improve our ability to predict malignant progression and help identify the minority of patients who will develop EAC.

Frailty status as a predictor of 3-month cognitive and functional recovery following spinal surgery: a prospective pilot study.

BACKGROUND CONTEXT: As increasing numbers of elderly Americans undergo spinal surgery, it is important to identify which patients are at highest risk for poor cognitive and functional recovery. Frailty is a geriatric syndrome that has been closely linked to poor outcomes, and short-form screening may be a helpful tool for preoperative identification of at-risk patients. PURPOSE: This study aimed to conduct a pilot study on the usefulness of a short-form screening tool to identify elderly patients at increased risk for prolonged cognitive and functional recovery following elective spine surgery. STUDY DESIGN/SETTING: This is a prospective, comparative cohort study. PATIENT SAMPLE: The sample comprised 100 patients over age 65 who underwent elective spinal surgery (cervical or lumbar) at a single, large academic medical center from 2013 to 2014. OUTCOME MEASURES: Fatigue, Resistance, Ambulation, Illnesses, Loss of Weight (FRAIL) scale, Postoperative Quality of Recovery Scale (PQRS), and instrumental activities of daily living (IADL) scores were the outcome measures. METHODS: Included patients were assessed with the FRAIL scale and stratified as robust, pre-frail, or frail. The PQRS and IADL scores were also obtained. Patients were re-examined at 1 day, 3 days, 1 month, and 3 months after surgery for cognitive recovery at 3 months, and secondarily, functional recovery at 3 months. RESULTS: At 3 months, only 50% of frail patients had recovered to their cognitive baseline compared with 60.7% of pre-frail and 69.2% of robust patients (trend). At 3 months, 66.7% of frail patients had recovered to their functional baseline compared with 57% of pre-frail and 76.9% of robust patients (trend). Using multivariate regression modeling, at 3 months, frail patients were less likely to have recovered to their cognitive baseline compared with pre-frail and robust patients (odds ratio 0.39, confidence interval 0.131-1.161). CONCLUSIONS: This pilot study demonstrates a trend toward poorer cognitive recovery 3 months following elective spinal surgery for frail patients. Frailty screening can help preoperatively identify patients who may experience protracted cognitive and functional recovery.