(1) Background: Spondylolisthesis, a common disease among older individuals, involves the displacement of vertebrae. The condition may gradually manifest with age, allowing for potential prevention by the research of predictive algorithms. However, one key issue that hinders research in spondylolisthesis prediction algorithms is the need for publicly available spondylolisthesis datasets. (2) Purpose: This paper introduces BUU-LSPINE, a new dataset for the lumbar spine. It includes 3600 patients’ plain film images annotated with vertebral position, spondylolisthesis diagnosis, and lumbosacral transitional vertebrae (LSTV) ground truth. (4) Methods: We established an annotation pipeline to create the BUU-SPINE dataset and evaluated it in three experiments as follows: (1) lumbar vertebrae detection, (2) vertebral corner points extraction, and (3) spondylolisthesis prediction. (5) Results: Lumbar vertebrae detection achieved the highest precision rates of 81.93% on the AP view and 83.45% on the LA view using YOLOv5; vertebral corner point extraction achieved the lowest average error distance of 4.63 mm on the AP view using ResNet152V2 and 4.91 mm on the LA view using DenseNet201. Spondylolisthesis prediction reached the highest accuracy of 95.14% on the AP view and 92.26% on the LA view of a testing set using Support Vector Machine (SVM). (6) Discussions: The results of the three experiments highlight the potential of BUU-LSPINE in developing and evaluating algorithms for lumbar vertebrae detection and spondylolisthesis prediction. These steps are crucial in advancing the creation of a clinical decision support system (CDSS). Additionally, the findings demonstrate the impact of Lumbosacral transitional vertebrae (LSTV) conditions on lumbar detection algorithms.

Plain film X-ray scanners are indispensable for medical diagnostics and clinical procedures. This type of device typically produces two radiographic images of the human spine, including the anteroposterior and lateral views. However, these two photographs presented perspectives that were distinct. The proposed procedure consists of three fundamental steps. For automated cropping, the grayscale lumbar input image was initially projected vertically using its vertical pattern. Then, Delaunay triangulation was performed with the SURF features serving as the triangle nodes. The posture area of the vertebrae was calculated by utilizing the edge density of each node. The proposed method provided an automated estimation of the position of the human lumbar vertebrae, thereby decreasing the radiologist’s workload, computing time, and complexity in a variety of bone-clinical applications. Numerous applications can be supported by the results of the proposed method, including the segmentation of lumbar vertebrae pose, bone mineral density examination, and vertebral pose deformation. The proposed method can estimate the vertebral position with an accuracy of 80.32 percent, a recall rate of 85.37 percent, a precision rate of 82.36%, and a false-negative rate of 15.42 percent.

Artificial intelligence (AI) in radiology is recently a rapidly growing subject. Much literature about AI in radiology has been launched within 5 years, as well as commercial AI companies. This phenomenon makes some old radiologists feel worried about losing their jobs, and junior doctors hesitate to choose radiology as a specialty. Currently, implementations of proprietary AIs in clinical practice are limited, with a default setting for a convenient human overwrite. The AIs in clinical imaging largely remain either investigational as part of clinical/pre-clinical trials or being developed for commercialized purposes. Radiologists have an important role in all AI processes from the beginning to the end and vital in training the machine, as well as to validate its added benefit for outcome prediction/prognostication. This article will discuss the importance for radiologists to develop, implement, and monitor AI in clinical imaging, together with some ethical considerations. We would like to encourage radiologists to use AI as an adjunct tool, to save time and have better performance.

Idiopathic intrahepatic arterioportal shunt rupture

Purpose This study aimed to evaluate the effectiveness of focused teaching in chest radiography for different elective radiology novice doctors. Methods A 30-chest x-ray image test was administered to various novice doctors before and after a focused teaching session on the hidden areas of chest radiography. Novice doctors who pursued a radiology elective course in our institution were enrolled. The effectiveness of teaching was evaluated by the difference between a pretest and posttest scores. The competency among different groups of novice doctors was compared using improvement score. Results A total of 22 novice doctors participated, including 1 extern, 5 emergency physician residents, 10 internist residents, 2 Thai-graduated interns, and 4 foreign-graduated interns (F-INT). There was no significant difference in pretest score across student specialties. However, there was a significant difference in the score for participants before and after X-ray teaching (p < 0.001). Using the differences in pretest and posttest scores as an indicator of improvement, the improvement score differed significantly across the specialties (p = 0.04). Most of the groups showed positive improvement, except for the F-INT group which exhibited negative improvement. Conclusions Focusing on teaching in chest radiography has a positive significant impact on almost all novice doctors except the F-INT group. Different learners have different abilities to learn. Targeted teaching for specific learners would be more effective. Keywords radiology education, medical student, undergraduate, postgraduate, chest x-ray

Objective: Conventional abdominal radiographs (CAR) are often ordered in patients presented with acute abdominal pain. We investigated the appropriate use of CAR and its usefulness in the Emergency Department (ED). Methods: Adult patients who had CAR ordered from ED between 1st September and 31st October 2018 were retrospectively reviewed. Patients' demographics, indications for CAR, CAR results, further imaging, and their results, and final diagnoses were assessed. The appropriate or inappropriate use of CAR was stratified. A comparison between the appropriate group and inappropriate group was made. Results: There were 154 CAR studies, M:F = 57:97, mean age 48.3 years (ranged 15 - 88 years). 33.8% of CAR was considered an appropriate use. Of the 154 examinations, 17 (11%), 73 (47%), and 64 (42%) were reported as positive, negative, and non-diagnostic results by CAR respectively. A comparison between appropriate and inappropriate groups, number of cases, CAR negative results, CAR non-diagnostic result, and negative further imaging results were significantly different. There was no statistical difference in the number of further imaging between both groups. The common findings of positive results that had no further imaging were bowel obstruction (n = 6), followed by bowel perforation (n = 3). 12 out of 73 (16.4%) negative CAR results, and 11 out of 64 (17%) of non-diagnostic results had positive findings from further imaging. Conclusion: The appropriate use of CAR in non-traumatic acute abdomen patient in our institution is only 33.8%. More precise imaging is required to make a decision whether appropriate indication or not. Strict to the protocols, staff education and internal audit should be performed in the hospital.