Radiografía del abdomen en Urgencias. ¿Una exploración para el recuerdo?

Applying Deep-Learning Algorithm Interpreting Kidney, Ureter, and Bladder (KUB) X-Rays to Detect Colon Cancer

Early screening is crucial in reducing the mortality of colorectal cancer (CRC). Current screening methods, including fecal occult blood tests (FOBT) and colonoscopy, are primarily limited by low patient compliance and the invasive nature of the procedures. Several advanced imaging techniques such as computed tomography (CT) and histological imaging have been integrated with artificial intelligence (AI) to enhance the detection of CRC. There are still limitations because of the challenges associated with image acquisition and the cost. Kidney, ureter, and bladder (KUB) radiograph which is inexpensive and widely used for abdominal assessments in emergency settings and shows potential for detecting CRC when enhanced using advanced techniques. This study aimed to develop a deep learning model (DLM) to detect CRC using KUB radiographs. This retrospective study was conducted using data from the Tri-Service General Hospital (TSGH) between January 2011 and December 2020, including patients with at least one KUB radiograph. Patients were divided into development (n = 28,055), tuning (n = 11,234), and internal validation (n = 16,875) sets. An additional 15,876 patients were collected from a community hospital as the external validation set. A 121-layer DenseNet convolutional network was trained to classify KUB images for CRC detection. The model performance was evaluated using receiver operating characteristic curves, with sensitivity, specificity, and area under the curve (AUC) as metrics. The AUC, sensitivity, and specificity of the DLM in the internal and external validation sets achieved 0.738, 61.3%, and 74.4%, as well as 0.656, 47.7%, and 72.9%, respectively. The model performed better for high-grade CRC, with AUCs of 0.744 and 0.674 in the internal and external sets, respectively. Stratified analysis showed superior performance in females aged 55-64 with high-grade cancers. AI-positive predictions were associated with a higher long-term risk of all-cause mortality in both validation cohorts. AI-enhanced KUB X-ray analysis can enhance CRC screening coverage and effectiveness, providing a cost-effective alternative to traditional methods. Further prospective studies are necessary to validate these findings and fully integrate this technology into clinical practice.

Radiology education for medical students: a qualitative exploration of educational topics, teaching methods and future strategies

BACKGROUND

Imaging techniques play a central role in modern medicine and therefore it would be beneficial for all medical students to incorporate radiology education in medical school curricula. However, a formal undergraduate radiology curriculum with well-defined learning objectives remains lacking in The Netherlands. This study aims to qualitatively ascertain opinions from clinicians (radiologists and non-radiologists) with regard to radiology education in the medical school curricula, including topics, teaching methods and strategies.

METHODS

A qualitative study with in-depth semi-structured interviews was conducted. Inclusion was carried out until saturation was achieved, after which 2 additional interviews were held. Interviews were conducted using open-ended questions, following a predefined topic list. The constant comparative method was applied in order to include new questions when unexpected topics arose during the interviews. All interviews were transcribed verbatim and coded using a thematic analysis approach. Codes were organized into categories and themes by discussion between the researchers.

RESULTS

Forty-four clinicians were interviewed (8 radiologists, 36 non-radiologists). The three main themes that were derived from the interviews were: (1) expectations of indispensable knowledge and skills on radiology, (2) organization of radiology education within the medical curriculum and (3) promising educational innovations for the radiology curriculum. The qualitative study design provides more in-depth knowledge on clinicians' views on educational topics.

CONCLUSIONS

The themes and statements of this study provided new insights into educational methods, timing of radiology education and new topics to teach. More research is needed to gain consensus on these subjects and inclusion of the opinion of medical students with regard to radiology education is needed.

Assessing fecal load with ultrasound in children with colorectal pathology: ReKiSo study

PURPOSE

To evaluate bowel management for children with colorectal pathology by measuring transverse rectal diameter (TRD) and assessing fecal load with transabdominal rectal ultrasound (TRU).

METHODS

Prospective case-control study of children receiving bowel management (BM) between 04/2023 and 04/2024 was done. There was inclusion of patients with Hirschsprung disease (HD), anorectal malformation (ARM) and functional constipation (FC). Patients with other congenital or neurological conditions were excluded. Control group consisted of inpatients and outpatients without abdominal complaints. FC was diagnosed according to ROM-IV-criteria. For HD and ARM, we followed a list of symptoms. To assess fecal load, we visualized the TRD using the Klijn (Klijn et al. in J Urol 172:1986-1988, 2004) method. The bladder was moderately full. The fecal load was assessed retrograde from the rectum. Follow-up was at 1/3/6 months. Secondary data were collected from medical records. Sample size calculated a priori and follow-up group with new gathered data.

RESULTS

p value for TRD in all groups significant with p < 0.05 and in grouped follow-up.

CONCLUSION

Ultrasound is a useful tool for assessing fecal load and helps diagnose constipation and monitor BM. Irrespective of colorectal pathology, a cut-off of 3 cm seems to discriminate between children without constipation/overload symptoms and asymptomatic patients. We present a radiation-free method for monitoring bowel management.

Utilization of abdominal radiography in the emergency department: Appropriateness, interpretation, radiation protection and costs

INTRODUCTION

The use of abdominal radiography (AXR) apparently continues to be widespread despite its limited indications, the potential radiation and unnecessary costs associated. In addition, the interpretation and its report seem variable and not always performed by a radiologist. Our objective is to analyze the use, adequacy and usefulness of AXR in the emergency of a tertiary referral hospital.

MATERIAL AND METHODS

We retrospectively reviewed all the AXR performed in January 2020 in the emergency of our centre, as well as the patient's demographics and medical records, technical quality of the radiographs, indications according to the SERAM (Spanish Society of Radiology) Appropriateness Guidelines, presence of a formal radiology report, and impact on the clinical management of the patient. Of all non-appropriated AXR we calculated the radiation received by the patients and its extra costs.

RESULTS

In January 2020, 429 AXR (9.1% of all radiographies) were performed in the emergency of our centre. The most frequent indication was abdominal pain (40%, n = 176), followed by low back pain (21.4%, n = 92). 12.4% of AXR requested did not include any clinical information. Most of the AXR (79.6%) had sufficient technical quality. 61.3% (n = 263) of the AXR performed were not indicated, assuming an average unjustified radiation dose per patient of 0.50 ± 0.33 mSv, and a total additional cost of 6575;. Only 6% of the inadequate AXRs led to a change in the clinical management of the patient, compared to 29% of the adequate AXR (p < 0.001). Only 3% of the AXR had a formal radiology report.

CONCLUSIONS

AXR is still common in the emergency setting, although most of them might be inadequate according to the SERAM Appropriateness Guidelines. Its use should be optimized to avoid unnecessary radiation and costs. Radiologists must have a more active participation in the management of AXR.

Current abdominal X-rays practice in accident and emergency

INTRODUCTION

Previous literature reviews revealed that abdominal X-rays (AXR) performed for the accident and emergency department (A&E), had low sensitivity, high further imaging and non-alignment rate to the Royal College of Radiologists (RCR) guidelines. A study was performed to investigate the current practice with the aim of making recommendations to improve practice, which can reduce patients' radiation exposures, while can re-routing resources to other priorities.

METHODS

A study was performed in one of the UK's largest A&Es, in accordance with the RCR guidelines. All the AXR requests from A&E, regardless of the patient's age, within a 28-day period, were retrospectively assessed. Non-A&E patients and abandoned examinations due to uncooperative patients were excluded. The total number of AXR requests received by the A&E imaging department was 169, with 28/169 falling into the exclusion criteria.

RESULTS

Of the 141 included requests, five unjustified requests were correctly rejected. The remaining 136 requests were accepted and performed, though only 115/136 (84.6%) of these were justified. The most common justified and unjustified indications were obstruction and renal stones, respectively. Only 4% of reported AXR had pathological abnormalities, while 45/136 patients had further imaging.

CONCLUSIONS

The small proportion of significant findings echoed previous studies, suggesting an AXR overuse. Over 80% of non-compliant requests were performed, and awareness of the justification guidelines can be increased by clinical governance, posters, or an algorithm previously presented. The 32.4% further imaging rate recorded in this study, as opposed to the 73.7% reported in previous literature, merits attention.

IMPLICATIONS TO PRACTICE

Stopping the overuse of AXR can minimise the radiation dose received and relieve the mounting pressure in imaging and reporting, which can serve other patients who would benefit from the services otherwise.

Appropriateness of adult plain abdominal radiograph requesting in a regional Emergency Department

INTRODUCTION

Although commonly ordered, abdominal x-rays are thought to be overused and unhelpful in many emergency department patients. Our objectives were to evaluate the appropriateness of plain abdominal X-ray (AXR) requests in adult patients presenting to a Victorian regional emergency department (ED).

METHODS

A retrospective chart review was performed of all adult patients with a plain AXR requested by ED medical staff members in a regional healthcare centre in Victoria, Australia in 2016. Patient demographics, ED disposition and any further imaging results were extracted from the medical record. Indications for X-ray and clinician seniority were determined from the radiology request slips signed by the treating emergency doctor. Appropriateness of imaging was determined by comparing the indication for abdominal radiograph to local evidence-based guidelines.

RESULTS

One hundred and nine episodes of plain AXR requests met the inclusion criteria. Of these, 40 were considered inappropriate according to clinical guidelines. Overall, 36% (39/109) had normal or non-specific findings and 42% (46/109) demonstrated faecal loading, while 22% (24/109) identified pathology. Thirty-three patients had further imaging, mostly with computed tomography (CT). Junior staff members were responsible for most of the AXR requests.

CONCLUSION

In our regional hospital ED, over one third of AXRs requested for adult patients were inappropriate according to clinical guidelines. AXRs have a low diagnostic yield and frequently do not reduce the need for further imaging. The use of a clinical practice guideline and education of junior medical staff may increase the appropriate use of plain AXRs in the regional ED setting.