Treatment of spontaneously ruptured hepatocellular carcinoma: use of laparoscopic microwave ablation and washout.

BACKGROUND: Ruptured, or bleeding, hepatocellular carcinoma (rHCC) is a relatively rare disease presentation associated with high acute mortality rates. This study sought to evaluate outcomes following laparoscopic microwave ablation (MWA) and washout in rHCC. METHODS: A retrospective single-center review was performed to identify patients with rHCC (2008-2018). The treatment algorithm consisted of transarterial embolization (TAE) or trans-arterial chemoembolization (TACE) followed by laparoscopic MWA and washout. RESULTS: Fifteen patients with rHCC were identified (n = 5 single lesion, n = 5 multifocal disease, n = 5 extrahepatic metastatic disease). Median tumor size was 83 mm (range 5-228 mm), and 10 of 15 underwent TAE or TACE followed by laparoscopic MWA/washout. One patient required additional treatment for bleeding after MWA with repeat TAE. Thirty-day mortality was 6/15. For those patients discharged (n = 9), additional treatments included chemotherapy (n = 5), TACE (n = 3), and/or partial lobectomy (n = 2). Median follow-up was 18.2 months and median survival was 431 days (range 103-832) (one-year survival n = 7; two-year survival n = 4; three-year survival n = 3). Six patients had post-operative imaging from which one patient demonstrated recurrence. CONCLUSION: Using laparoscopic MWA with washout may offer advantage in the treatment of ruptured HCC. It not only achieves hemostasis but also could have oncologic benefit by targeting local tumor and decreasing peritoneal carcinomatosis risk.

Use of Artificial Intelligence Deep Learning to Determine the Malignant Potential of Pancreatic Cystic Neoplasms With Preoperative Computed Tomography Imaging.

BACKGROUND: Society consensus guidelines are commonly used to guide management of pancreatic cystic neoplasms (PCNs). However, downsides of these guidelines include unnecessary surgery and missed malignancy. The aim of this study was to use computed tomography (CT)-guided deep learning techniques to predict malignancy of PCNs. MATERIALS AND METHODS: Patients with PCNs who underwent resection were retrospectively reviewed. Axial images of the mucinous cystic neoplasms were collected and based on final pathology were assigned a binary outcome of advanced neoplasia or benign. Advanced neoplasia was defined as adenocarcinoma or intraductal papillary mucinous neoplasm with high-grade dysplasia. A convolutional neural network (CNN) deep learning model was trained on 66% of images, and this trained model was used to test 33% of images. Predictions from the deep learning model were compared to Fukuoka guidelines. RESULTS: Twenty-seven patients met the inclusion criteria, with 18 used for training and 9 for model testing. The trained deep learning model correctly predicted 3 of 3 malignant lesions and 5 of 6 benign lesions. Fukuoka guidelines correctly classified 2 of 3 malignant lesions as high risk and 4 of 6 benign lesions as worrisome. Following deep learning model predictions would have avoided 1 missed malignancy and 1 unnecessary operation. DISCUSSION: In this pilot study, a deep learning model correctly classified 8 of 9 PCNs and performed better than consensus guidelines. Deep learning can be used to predict malignancy of PCNs; however, further model improvements are necessary before clinical use.