ABSTRACT
BACKGROUND: The precise recognition of liver vessels during liver parenchymal dissection is the crucial technique for laparoscopic liver resection (LLR). This retrospective feasibility study aimed to develop artificial intelligence (AI) models to recognize liver vessels in LLR, and to evaluate their accuracy and real-time performance. METHODS: Images from LLR videos were extracted, and the hepatic veins and Glissonean pedicles were labeled separately. Two AI models were developed to recognize liver vessels: the "2-class model" which recognized both hepatic veins and Glissonean pedicles as equivalent vessels and distinguished them from the background class, and the "3-class model" which recognized them all separately. The Feature Pyramid Network was used as a neural network architecture for both models in their semantic segmentation tasks. The models were evaluated using fivefold cross-validation tests, and the Dice coefficient (DC) was used as an evaluation metric. Ten gastroenterological surgeons also evaluated the models qualitatively through rubric. RESULTS: In total, 2421 frames from 48 video clips were extracted. The mean DC value of the 2-class model was 0.789, with a processing speed of 0.094 s. The mean DC values for the hepatic vein and the Glissonean pedicle in the 3-class model were 0.631 and 0.482, respectively. The average processing time for the 3-class model was 0.097 s. Qualitative evaluation by surgeons revealed that false-negative and false-positive ratings in the 2-class model averaged 4.40 and 3.46, respectively, on a five-point scale, while the false-negative, false-positive, and vessel differentiation ratings in the 3-class model averaged 4.36, 3.44, and 3.28, respectively, on a five-point scale. CONCLUSION: We successfully developed deep-learning models that recognize liver vessels in LLR with high accuracy and sufficient processing speed. These findings suggest the potential of a new real-time automated navigation system for LLR.
Subject(s)
Artificial Intelligence , Laparoscopy , Humans , Retrospective Studies , Liver/diagnostic imaging , Liver/surgery , Liver/blood supply , Hepatectomy/methods , Laparoscopy/methodsABSTRACT
INTRODUCTION AND IMPORTANCE: Diaphragmatic tumor is a rare neoplastic disease. Only three reports have revealed diaphragmatic primary clear cell carcinoma. On the other hand, secondary membranous nephropathy is sometimes triggered by the carcinoma. We describe a case of primary diaphragmatic clear cell carcinoma without relation to endometriosis or ovarian malignancies, and secondary membranous nephropathy was triggered by diaphragmatic primary clear cell carcinoma. CASE PRESENTATION: A 67-year-old woman was found to have membranous nephropathy due to examination for renal dysfunction. A rare diaphragmatic tumor was identified on CT scan for rule out secondary membranous nephropathy. She had underwent resection of the right diaphragm tumor and reconstruction with expanded polyterafluoroethylene (e-PTFE). CLINICAL DISCUSSION: Pathological examination revealed the presence of clear cells with papillary arrangement and no findings of the endometriosis. Immunohistochemistry revealed that the tumor was positive for CK7, p53, and HNF-1-beta. And there had been no evidence of ovarian malignancies. A diagnosed of clear cell carcinoma of the right diaphragm without relation to endometriosis or ovarian malignancies was made. After resection of the tumor, it was revealed that her renal function was improvement. CONCLUSION: This is the first report of diaphragmatic clear cell carcinoma without relation to endometriosis or ovarian malignancies that caused secondary membranous nephropathy. One year after the resection of the tumor, she is being followed up and has shown no signs of recurrence.
ABSTRACT
BACKGROUND: Ischemic bowel injuries are generally caused by arteriosclerosis, thromboembolism, or vasculitis. Ischemic enteritis is less common than ischemic colitis because of the rich collateral arteries of the small intestine. In the present case, smooth muscle degeneration of the mesenteric to the submucosal veins caused ischemic enteritis and small bowel obstruction. CASE PRESENTATION: An 85-year-old woman with recurrent enteritis eventually developed small bowel obstruction. We performed laparoscopic partial resection of the small intestine. The pathological findings revealed smooth muscle degeneration of the mesenteric veins that caused ischemic enteritis. Venous changes were detected not only in the injured region, but also in a part of the normal region of the resected specimen. She continued to experience some minor symptoms postoperatively; however, these symptoms subsided in a short period with medicine discontinuation. CONCLUSION: This report shows the possibility that a disease causes ischemic enteritis with unique venous pathological changes and may recur postoperatively.
ABSTRACT
Preoperative diagnosis of cholecystocolonic fistula (CCF) is difficult and the contribution of gallbladder cancer or colon cancer is unclear when there is associated malignancy. We present a case that was diagnosed with acute cholecystitis associated with CCF by multidetector computed tomography (MDCT) preoperatively and malignant neoplasm during emergency surgery. She was finally diagnosed with gallbladder cancer after the operation and underwent a two-stage surgery for regional lymph node dissection. Gallbladder cancer can be a primary malignant cancer causing CCF, whereas MDCT is useful for preoperative diagnosis of CCF. A treatment plan in consideration of gallbladder cancer is advisable for CCF associated with malignant tumor.
