INTRODUCTION: Many institutions still perform routine chest radiography (CXR) after tube thoracostomies despite current guidelines suggesting that this is not necessary for simple cases. We aimed to evaluate the usefulness of routine CXR following ultrasonography-guided catheter thoracostomies for the detection of complications of symptomatic pleural effusions in hospitalised patients. METHODS: This was a retrospective review of 2,032 ultrasonography-guided thoracostomies on hospitalised patients with symptomatic effusions at a single institution from April 2012 to May 2015. The aetiology of effusions was not systemically registered, but patient demographics, procedural details and clinical outcomes were collected. Data was analysed using descriptive statistics and chi-square test. Generalised estimating equation analysis was performed to assess the relationship between CXR findings and complications while controlling for age. RESULTS: Out of 2,032 CXRs, 92.96% (n = 1,889) were normal, 5.81% (n = 118) showed pneumothorax and 1.23% (n = 25) showed catheter kinking. 99 pneumothoraces and 24 kinked catheters were detected in the first hour post procedure. 97.40% (n = 115) of patients with pneumothorax were stable or had minor complications, such as a vasovagal event. 0.20% (n = 4) of the cases had a serious complication following chest drain insertion, resulting in cardiovascular collapse. There was no significant relationship between CXR results and occurrence of complications (p = 0.244). Amount of fluid drained or side of insertion did not affect the clinical outcome. CONCLUSION Routine use of CXR after tube thoracostomy did not significantly change patient management, which was concordant with recent guidelines. Instead, adverse clinical outcomes or procedural factors should guide investigations.

A 60-year-old man presented with abdominal pain. He was later diagnosed on imaging to have high-grade small bowel obstruction. The patient underwent surgery, and a hard, rounded bezoar resembling the endosperm of Nypa fruticans, colloquially known as attap chee, was found at the point of obstruction. Small bowel obstruction is a common acute surgical condition with multiple causes, including bezoars. We discuss the typical imaging features of bezoars causing small bowel obstruction as well as potential pitfalls that can mimic the appearance of a bezoar.

INTRODUCTION: We aimed to assess the attitudes and learner needs of radiology residents and faculty radiologists regarding artificial intelligence (AI) and machine learning (ML) in radiology. METHODS: A web-based questionnaire, designed using SurveyMonkey, was sent out to residents and faculty radiologists in all three radiology residency programmes in Singapore. The questionnaire comprised four sections and aimed to evaluate respondents' current experience, attempts at self-learning, perceptions of career prospects and expectations of an AI/ML curriculum in their residency programme. Respondents' anonymity was ensured. RESULTS: A total of 125 respondents (86 male, 39 female; 70 residents, 55 faculty radiologists) completed the questionnaire. The majority agreed that AI/ML will drastically change radiology practice (88.8%) and makes radiology more exciting (76.0%), and most would still choose to specialise in radiology if given a choice (80.0%). 64.8% viewed themselves as novices in their understanding of AI/ML, 76.0% planned to further advance their AI/ML knowledge and 67.2% were keen to get involved in an AI/ML research project. An overwhelming majority (84.8%) believed that AI/ML knowledge should be taught during residency, and most opined that this was as important as imaging physics and clinical skills/knowledge curricula (80.0% and 72.8%, respectively). More than half thought that their residency programme had not adequately implemented AI/ML teaching (59.2%). In subgroup analyses, male and tech-savvy respondents were more involved in AI/ML activities, leading to better technical understanding. CONCLUSION A growing optimism towards radiology undergoing technological transformation and AI/ML implementation has led to a strong demand for an AI/ML curriculum in residency education.