Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Three-dimensional analysis of the change in the curvature of the smiling line following orthodontic treatment in incisor class II division 1 malocclusion.

OBJECTIVES: To investigate the different effects of changes in the occlusal plane, incisors inclination, and maxillary intercanine width on the curvature of the smiling line. MATERIALS: Records of 46 subjects (28 females and 18 males, mean age 16.6 ± 4.2 years) with incisor class II division 1 malocclusions were selected. All subjects had four premolar extractions and were treated with preadjusted edgewise appliances. METHODS: Pre- and post-treatment maxillary dental digital models were virtually aligned via corresponding landmarks to the respective lateral cephalograms. Subsequent two-dimensional superimposition of the aligned cephalograms facilitated the three-dimensional superimposition of the pre- and post-treatment models. This process allowed the quantification of the curvature from a frontal perspective of the models. The change in curvature was then correlated with changes in the cephalometric inclination of the anterior occlusal plane (AOP), functional occlusal plane (FOP), maxillary central incisor (U1), and the intercanine width. RESULTS: Orthodontic correction in this sample resulted in the clockwise rotation of the anterior occlusal plane (5.84 degrees), reduction in proclination of the incisors (-14.39 degrees), increase in intercanine width (2.48mm), and a corresponding increase in the curvature of the smiling line (6.83 degrees). CONCLUSIONS: The change in curvature of the smiling line in these subjects was found to be related more significantly to the magnitude of difference in the inclination between the pre-treatment AOP and FOP than to the change in the inclination of the maxillary incisors. With orthodontic treatment, the smiling line can be correlated with cephalometric data to improve or maintain the curvature.

Surgical Management of Pericaecal Hernia in a Virgin Abdomen.

Internal hernia is an uncommon cause of mechanical small bowel obstruction. This case report details a 66-year-old Chinese male with no prior abdominal surgeries who presented with colicky abdominal pain, abdominal distension, and vomiting. Initial investigations were unyielding, but escalating symptoms prompted a diagnostic laparoscopy. Laparotomy then revealed a closed-loop obstruction through a lateral type pericecal hernia, with a segment of ischemic jejunum. Adhesion bands in the right iliac fossa and a congenital hernia orifice in the mesentery were identified and addressed. The patient recovered well postoperatively. This discussion explores the Meyer's classification of pericecal hernias, potential etiologies, clinical manifestations, diagnostic considerations, and the choice between laparoscopic and open surgeries. This case underscores the importance of a high index of suspicion, prompt surgical intervention, and the diagnostic utility of laparoscopy in managing pericecal hernias.

Applications of Artificial Intelligence and Machine Learning in Spine MRI.

Diagnostic imaging, particularly MRI, plays a key role in the evaluation of many spine pathologies. Recent progress in artificial intelligence and its subset, machine learning, has led to many applications within spine MRI, which we sought to examine in this review. A literature search of the major databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search yielded 1226 results, of which 50 studies were selected for inclusion. Key data from these studies were extracted. Studies were categorized thematically into the following: Image Acquisition and Processing, Segmentation, Diagnosis and Treatment Planning, and Patient Selection and Prognostication. Gaps in the literature and the proposed areas of future research are discussed. Current research demonstrates the ability of artificial intelligence to improve various aspects of this field, from image acquisition to analysis and clinical care. We also acknowledge the limitations of current technology. Future work will require collaborative efforts in order to fully exploit new technologies while addressing the practical challenges of generalizability and implementation. In particular, the use of foundation models and large-language models in spine MRI is a promising area, warranting further research. Studies assessing model performance in real-world clinical settings will also help uncover unintended consequences and maximize the benefits for patient care.

Oncologic Applications of Artificial Intelligence and Deep Learning Methods in CT Spine Imaging-A Systematic Review.

In spinal oncology, integrating deep learning with computed tomography (CT) imaging has shown promise in enhancing diagnostic accuracy, treatment planning, and patient outcomes. This systematic review synthesizes evidence on artificial intelligence (AI) applications in CT imaging for spinal tumors. A PRISMA-guided search identified 33 studies: 12 (36.4%) focused on detecting spinal malignancies, 11 (33.3%) on classification, 6 (18.2%) on prognostication, 3 (9.1%) on treatment planning, and 1 (3.0%) on both detection and classification. Of the classification studies, 7 (21.2%) used machine learning to distinguish between benign and malignant lesions, 3 (9.1%) evaluated tumor stage or grade, and 2 (6.1%) employed radiomics for biomarker classification. Prognostic studies included three (9.1%) that predicted complications such as pathological fractures and three (9.1%) that predicted treatment outcomes. AI's potential for improving workflow efficiency, aiding decision-making, and reducing complications is discussed, along with its limitations in generalizability, interpretability, and clinical integration. Future directions for AI in spinal oncology are also explored. In conclusion, while AI technologies in CT imaging are promising, further research is necessary to validate their clinical effectiveness and optimize their integration into routine practice.

Deep learning model for automated diagnosis of degenerative cervical spondylosis and altered spinal cord signal on MRI.

BACKGROUND CONTEXT: A deep learning (DL) model for degenerative cervical spondylosis on MRI could enhance reporting consistency and efficiency, addressing a significant global health issue. PURPOSE: Create a DL model to detect and classify cervical cord signal abnormalities, spinal canal and neural foraminal stenosis. STUDY DESIGN/SETTING: Retrospective study conducted from January 2013 to July 2021, excluding cases with instrumentation. PATIENT SAMPLE: Overall, 504 MRI cervical spines were analyzed (504 patients, mean=58 years±13.7[SD]; 202 women) with 454 for training (90%) and 50 (10%) for internal testing. In addition, 100 MRI cervical spines were available for external testing (100 patients, mean=60 years±13.0[SD];26 women). OUTCOME MEASURES: Automated detection and classification of spinal canal stenosis, neural foraminal stenosis, and cord signal abnormality using the DL model. Recall(%), inter-rater agreement (Gwet's kappa), sensitivity, and specificity were calculated. METHODS: Utilizing axial T2-weighted gradient echo and sagittal T2-weighted images, a transformer-based DL model was trained on data labeled by an experienced musculoskeletal radiologist (12 years of experience). Internal testing involved data labeled in consensus by two musculoskeletal radiologists (reference standard, both with 12-years-experience), two subspecialist radiologists, and two in-training radiologists. External testing was performed. RESULTS: The DL model exhibited substantial agreement surpassing all readers in all classes for spinal canal (κ=0.78, p<0.001 vs. κ range=0.57-0.70 for readers) and neural foraminal stenosis (κ=0.80, p<0.001 vs. κ range=0.63-0.69 for readers) classification. The DL model's recall for cord signal abnormality (92.3%) was similar to all readers (range: 92.3-100.0%). Nearly perfect agreement was demonstrated for binary classification (normal/mild vs. moderate/severe) (κ=0.95, p<0.001 for spinal canal; κ=0.90, p<0.001 for neural foramina). External testing showed substantial agreement using all classes (κ=0.76, p<0.001 for spinal canal; κ=0.66, p<0.001 for neural foramina) and high recall for cord signal abnormality (91.9%). The DL model demonstrated high sensitivities (range:83.7%-92.4%) and specificities (range:87.8%-98.3%) on both internal and external datasets for spinal canal and neural foramina classification. CONCLUSIONS: Our DL model for degenerative cervical spondylosis on MRI showed good performance, demonstrating substantial agreement with the reference standard. This tool could assist radiologists in improving the efficiency and consistency of MRI cervical spondylosis assessments in clinical practice.

Cardiopulmonary bypass time: every minute counts.

BACKGROUND: This study was conducted to examine the impact of CPB times on postoperative outcomes. We sought to determine the optimum cut-offs of CPB per graft time and cumulative CPB time and their predictive accuracy for mortality in conjunction with EuroSCORE II. METHODS: The de-identified data of 1960 patients who had undergone isolated on-pump CABG from 2009 to 2014 were analyzed. The risk strata of cardiopulmonary bypass (CPB)/graft and cumulative CPB times, identified with a decision tree, were added into an augmented model for predicting short- and intermediate-term postoperative clinical events. RESULTS: Prolonged cumulative CPB time (>180 minutes) was significant in predicting mortality while adjusting for EuroSCORE II, postoperative complications, prolonged ICU stay and prolonged mechanical ventilation. Whereas prolonged CPB/graft time (>56 minutes) was marginally non-significant in terms of its direct effects, its indirect effect on mortality could be manifested through enhanced risks of complications, prolonged ICU stay (>48 hours) and prolonged mechanical ventilation (>24 hours). CONCLUSIONS: Prolonged CPB times could predict postoperative clinical events, in particular mortality. To minimize the occurrence of unfavorable adverse outcomes, it is recommended that the CPB/graft time and cumulative CPB time be kept below 56 minutes and 180 minutes respectively.

Doll therapy for dementia sufferers: A systematic review.

Dementia affects more than 47.5 million people worldwide, and the number is expected to continue to increase as the population ages. Doll therapy is an emerging nonpharmacologic management strategy for patients with advanced dementia, especially in patients with challenging behaviours. A total of 12 published studies (mainly cohort and observational studies) were identified and discussed in this systematic review. In most instances, cognitive, behavioural and emotional symptoms were alleviated and overall wellbeing was improved with doll therapy, and dementia sufferers were found to be able to better relate with their external environment. Despite the relative paucity of empirical data and ethical concerns, we are of the opinion that doll therapy is effective for dementia care, is well-aligned with the ethos of person-centred care and should be applied in the management of dementia patients. Future research should include more robust randomized controlled trials.