This paper aims to provide a review of the basis for application of AI in radiology, to discuss the immediate ethical and professional impact in radiology, and to consider possible future evolution.
Even if AI does add significant value to image interpretation, there are implications outside the traditional radiology activities of lesion detection and characterisation. In radiomics, AI can foster the analysis of the features and help in the correlation with other omics data. Imaging biobanks would become a necessary infrastructure to organise and share the image data from which AI models can be trained. AI can be used as an optimising tool to assist the technologist and radiologist in choosing a personalised patient’s protocol, tracking the patient’s dose parameters, providing an estimate of the radiation risks. AI can also aid the reporting workflow and help the linking between words, images, and quantitative data. Finally, AI coupled with CDS can improve the decision process and thereby optimise clinical and radiological workflow.
Ultrasound-guided surgical cholecystostomy with local infiltration anesthesia was combined with radiologic removal of gallstones in 36 elderly patients with acute calculous gallbladder disease who were considered to be at high risk due to multiple coexisting diseases. At cholecystostomy, the fundus of the gallbladder was sutured to the anterior abdominal wall resulting in a short surgical track to the gallbladder. This permitted early percutaneous stone removal through the cholecystostomy track under fluoroscopic guidance. All gallstones were removed in 31 of 36 patients, for an overall success rate of 86%. The success rate was 97% for gallbladder stones, 86% for cystic duct stones, and 63% for common bile duct stones that were removed by traversing the cystic duct. The treatment in the five patients in whom radiologic stone removal was incomplete or unsuccessful consisted of elective cholecystectomy in three, with common bile duct exploration in two of these; endoscopic sphincterotomy and stone extraction in one; and expectant management in one. There were no deaths or serious complications. This technique has thus proved safe and effective in these 36 high-risk patients.
In a patient with choledocholithiasis, a duodenal diverticulum precluded endoscopic retrograde bile duct cannulation. A transhepatic catheter was used to opacify the bile ducts and to guide the endoscopic sphincterotome into the major duodenal papilla. Because limited sphincterotomy did not allow extraction or spontaneous passage of the common duct stones, extracorporeal lithotripsy was performed. Following fragmentation, the stones passed spontaneously and without complications.
The accepted technique for diagnosing choledocholithiasis at the time of cholecystectomy is operative cholangiography. Reports in the surgical literature suggest that intraoperative ultrasound can replace operative cholangiography in the accurate detection of common duct stones. This prospective study was performed jointly by radiologists and surgeons together in the operating room. Twenty-one patients underwent intraoperative ultrasonography and operative cholangiography at the time of cholecystectomy. In the 16 cases in which both studies were adequate, there were 11 in which no stones were seen on either; three in which stones were seen on both; and two in which stones were diagnosed by sonography alone. In one of these latter cases, the stones were confirmed, making the cholangiogram falsely negative. In the other case, no stones were found so we presume that sonography was falsely positive. Although this technique can be accurate and useful, it is technically demanding, even for an experienced sonologist. We feel that this technique is likely to be of benefit only to the surgeon with considerable ultrasound training, expertise, and motivation.
Routine pre- and postlithotripsy chest radiographs are usually obtained on patients undergoing biliary extracorporeal shock-wave lithotripsy. To evaluate the need for this procedure, we reviewed posteroanterior and lateral chest radiographs obtained before and after 107 lithotripsy sessions in 75 patients. In each case, posteroanterior and lateral chest radiographs were obtained as a routine baseline (not to detect incidental abnormalities) before the patient was scheduled for lithotripsy. Posteroanterior and lateral chest radiographs were obtained routinely after each lithotripsy session. Seventy-five patients had 107 lithotripsy sessions on a second-generation lithotripter. Sixty had gallbladder stones, five had cystic duct stones, and 10 had common duct stones. All chest radiographs were reviewed by a chest radiologist. No pulmonary or pleural changes occurred after lithotripsy. We conclude that routine pre- and postlithotripsy chest radiographs are not warranted in patients undergoing biliary lithotripsy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.