Explore the vast range of titles available.

Caries prevention is essential for oral hygiene. A fully automated procedure that reduces human labor and human error is needed. This paper presents a fully automated method that segments tooth regions of interest from a panoramic radiograph to diagnose caries. A patient’s panoramic oral radiograph, which can be taken at any dental facility, is first segmented into several segments of individual teeth. Then, informative features are extracted from the teeth using a pre-trained deep learning network such as VGG, Resnet, or Xception. Each extracted feature is learned by a classification model such as random forest, k-nearest neighbor, or support vector machine. The prediction of each classifier model is considered as an individual opinion that contributes to the final diagnosis, which is decided by a majority voting method. The proposed method achieved an accuracy of 93.58%, a sensitivity of 93.91%, and a specificity of 93.33%, making it promising for widespread implementation. The proposed method, which outperforms existing methods in terms of reliability, and can facilitate dental diagnosis and reduce the need for tedious procedures.

ObjectivesAccurate assessment of knee alignment and leg length discrepancy is currently measured manually from standing long-leg radiographs (LLR), a process that is both time consuming and poorly reproducible. The aim was to assess the performance of a commercial available AI software by comparing its outputs with manually performed measurements.Materials and methodsThe AI was trained on over 15,000 radiographs to measure various clinical angles and lengths from LLRs. We performed a retrospective single-center analysis on 295 LLRs obtained between 2015 and 2020 from male and female patients over 18 years. AI and expert measurements were performed independently. Kellgren-Lawrence score and reading time were assessed. All measurements were compared and non-inferiority, mean-absolute-deviation (sMAD), and intra-class-correlation (ICC) were calculated.ResultsA total of 295 LLRs from 284 patients (mean age, 65 years (18; 90); 97 (34.2%) men) were analyzed. The AI model produces outputs on 98.0% of the LLRs. Manually annotations were considered as 100% accurate. For each measurement, its divergence was calculated, resulting in an overall accuracy of 89.2% when comparing the AI outputs to the manually measured. AI vs. mean observer revealed an sMAD between 0.39 and 2.19° for angles and 1.45–5.00 mm for lengths. AI showed good reliability in all lengths and angles (ICC ≥ 0.87). Non-inferiority comparing AI to the mean observer revealed an equivalence-index (γ) between 0.54 and 3.03° for angles and − 0.70–1.95 mm for lengths. On average, AI was 130 s faster than clinicians.ConclusionAutomated measurements of knee alignment and length measurements produced with an AI tool result in reproducible, accurate measures with a time savings compared to manually acquired measurements.

Suspected fractures are among the most common reasons for patients to visit emergency departments (EDs), and X-ray imaging is the primary diagnostic tool used by clinicians to assess patients for fractures. Missing a fracture in a radiograph often has severe consequences for patients, resulting in delayed treatment and poor recovery of function. Nevertheless, radiographs in emergency settings are often read out of necessity by emergency medicine clinicians who lack subspecialized expertise in orthopedics, and misdiagnosedfractures account forupwardof four of everyfivereported diagnostic errors in certain EDs. In this work, we developed a deep neural network to detect and localize fractures in radiographs. We trained it to accurately emulate the expertise of 18 senior subspecialized orthopedic surgeons by having them annotate 135,409 radiographs. We then ran a controlled experiment with emergency medicine clinicians to evaluate their ability to detect fractures in wrist radiographs with and without the assistance of the deep learning model. The average clinician’s sensitivity was 80.8% (95% CI, 76.7–84.1%) unaided and 91.5% (95% CI, 89.3–92.9%) aided, and specificity was 87.5% (95 CI, 85.3–89.5%) unaided and 93.9% (95% CI, 92.9–94.9%) aided. The average clinician experienced a relative reduction in misinterpretation rate of 47.0% (95% CI, 37.4–53.9%). The significant improvements in diagnostic accuracy that we observed in this study show that deep learning methods are a mechanism by which senior medical specialists can deliver their expertise to generalists on the front lines of medicine, thereby providing substantial improvements to patient care.

In late December, 2019, a cluster of cases of viral pneumonia was linked to a seafood market in Wuhan (Hubei, China), and was later determined to be caused by a novel coronavirus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2; previously known as 2019-nCoV).1 The genome sequence of SARS-CoV-2 is similar to, but distinct from, those of two other coronaviruses responsible for large-scale outbreaks in the past: severe acute respiratory syndrome coronavirus (SARS-CoV; about 79% sequence identity) and Middle East respiratory syndrome coronavirus (MERS-CoV; about 50%).2 CT has been an important imaging modality in assisting in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19) pneumonia, and reports on the radiological appearances of COVID-19 pneumonia are emerging. [...]it is unclear whether the threshold for performing CT evaluation of potential lung changes should be lower when chest radiographs are normal. There is more to be learnt about this novel contagious viral pneumonia; more research is needed into the correlation of CT findings with clinical severity and progression, the predictive value of baseline CT or temporal changes for disease outcome, and the sequelae of acute lung injury induced by COVID-19.

•We proposed an automatic human identification system from PDRs by using CNN.•A total of 15,868 PDRs from 6473 individuals are used to train and evaluate the CNN.•The teeth, maxilla and mandible were all contributed to human identification.•Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for human identification.•Human identification can be achieved from PDRs by CNN with high accuracy and speed. Human identification is an important task in mass disaster and criminal investigations. Although several automatic dental identification systems have been proposed, accurate and fast identification from panoramic dental radiographs (PDRs) remains a challenging issue. In this study, an automatic human identification system (DENT-net) was developed using the customized convolutional neural network (CNN). The DENT-net was trained on 15,369 PDRs from 6300 individuals. The PDRs were preprocessed by affine transformation and histogram equalization. The DENT-net took 128 × 128 × 7 square patches as input, including the whole PDR and six details extracted from the PDR. Using the DENT-net, the feature extraction took around 10 milliseconds per image and the running time for retrieval was 33.03 milliseconds in a 2000-individual database, promising an application on larger databases. The visualization of CNN showed that the teeth, maxilla, and mandible all contributed to human identification. The DENT-net achieved Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for human identification. The present results demonstrated that human identification can be achieved from PDRs by CNN with high accuracy and speed. The present system can be used without any special equipment or knowledge to generate the candidate images. While the final decision should be made by human specialists in practice. It is expected to aid human identification in mass disaster and criminal investigation.

ObjectivesThe natural history of coal workers’ pneumoconiosis (CWP) after cessation of exposure remains poorly understood.MethodsWe characterised the development of and progression to radiographic progressive massive fibrosis (PMF) among former US coal miners who applied for US federal benefits at least two times between 1 January 2000 and 31 December 2013. International Labour Office classifications of chest radiographs (CXRs) were used to determine initial and subsequent disease severity. Multivariable logistic regression models were used to identify major predictors of disease progression.ResultsA total of 3351 former miners applying for benefits without evidence of PMF at the time of their initial evaluation had subsequent CXRs. On average, these miners were 59.7 years of age and had 22 years of coal mine employment. At the time of their first CXR, 46.7% of miners had evidence of simple CWP. At the time of their last CXR, 111 miners (3.3%) had radiographic evidence of PMF. Nearly half of all miners who progressed to PMF did so in 5 years or less. Main predictors of progression included younger age and severity of simple CWP at the time of initial CXR.ConclusionsThis study provides further evidence that radiographic CWP may develop and/or progress absent further exposure, even among miners with no evidence of radiographic pneumoconiosis after leaving the industry. Former miners should undergo regular medical surveillance because of the risk for disease progression.

Purpose To evaluate the influence of time from injury and meniscus tears on the side-to-side difference in anterior tibial translation (SSD-ATT) as measured on lateral monopodal weightbearing radiographs in both primary and secondary ACL deficiencies. Methods Data from 69 patients (43 males/26 females, median age 27—percentile 25–75: 20–37), were retrospectively extracted from their medical records. All had a primary or secondary ACL deficiency as confirmed by MRI and clinical examination, with a bilateral weightbearing radiograph of the knees at 15°–20° flexion available. Meniscal status was assessed on MRI images by a radiologist and an independent orthopaedic surgeon. ATT and posterior tibial slope (PTS) were measured on the lateral monopodal weightbearing radiographs for both the affected and the contralateral healthy side. A paired t-test was used to compare affected/healthy knees. Independent t-tests were used to compare primary/secondary ACL deficiencies, time from injury (TFI) (≤ 4 years/ > 4 years) and meniscal versus no meniscal tear. Results ATT of the affected side was significantly greater than the contralateral side (6.2 ± 4.4 mm vs 3.5 ± 2.8 mm; p  < 0.01). There was moderate correlation between ATT and PTS in both the affected and healthy knees (r = 0.43, p  < 0.01 and r = 0.41, p  < 0.01). SSD-ATT was greater in secondary ACL deficiencies (4.7 ± 3.8 vs 1.9 ± 3.2 mm; p  < 0.01), patients with a TFI greater than 4 years (4.2 ± 3.8 vs 2.0 ± 3.0 mm; p  < 0.01) and with at least one meniscal tear (3.9 ± 3.8 vs 0.7 ± 2.2 mm; p  < 0.01). Linear regression showed that, in primary ACL deficiencies, SSD-ATT was expected to increase (+ 2.7 mm) only if both a meniscal tear and a TFI > 4 years were present. In secondary ACL deficiencies, SSD-ATT was mainly influenced by the presence of meniscal tears regardless of the TFI. Conclusion SSD-ATT was significantly greater in secondary ACL deficiencies, patients with a TFI greater than 4 years and with at least one meniscal tear. These results confirm that SSD-ATT is a time- and meniscal-dependent parameter, supporting the concept of gradual sagittal decompensation in ACL-deficient knees, and point out the importance of the menisci as secondary restraints of the anterior knee laxity. Monopodal weightbearing radiographs may offer an easy and objective method for the follow-up of ACL-injured patients to identify early signs of soft tissue decompensation under loading conditions. Level of evidence Level III.

IntroductionPlain radiographs are a globally ubiquitous means of investigation for injuries to the musculoskeletal system. Despite this, initial interpretation remains a challenge and inaccuracies give rise to adverse sequelae for patients and healthcare providers alike. This study sought to address the limited, existing meta-analytic research on the initial reporting of radiographs for skeletal trauma, with specific regard to diagnostic accuracy of the most commonly injured region of the appendicular skeleton, the lower limb.MethodA prospectively registered, systematic review and meta-analysis was performed using published research from the major clinical-science databases. Studies identified as appropriate for inclusion underwent methodological quality and risk of bias analysis. Meta-analysis was then performed to establish summary rates for specificity and sensitivity of diagnostic accuracy, including covariates by anatomical site, using HSROC and bivariate models.ResultsA total of 3887 articles were screened, with 10 identified as suitable for analysis based on the eligibility criteria. Sensitivity and specificity across the studies were 93.5% and 89.7% respectively. Compared with other anatomical subdivisions, interpretation of ankle radiographs yielded the highest sensitivity and specificity, with values of 98.1% and 94.6% respectively, and a diagnostic odds ratio of 929.97.ConclusionInterpretation of lower limb skeletal radiographs operates at a reasonably high degree of sensitivity and specificity. However, one in twenty true positives is missed on initial radiographic interpretation and safety netting systems need to be established to address this. Virtual fracture clinic reviews and teleradiology services in conjunction with novel technology will likely be crucial in these circumstances.

Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts. Many machine learning-based approaches have been developed for the prognosis and diagnosis of COVID-19 from medical images and this Analysis identifies over 2,200 relevant published papers and preprints in this area. After initial screening, 62 studies are analysed and the authors find they all have methodological flaws standing in the way of clinical utility. The authors have several recommendations to address these issues.

ObjectivesTo give a systematic overview of current diagnostic imaging options for assessment of the distal tibio-fibular syndesmosis.Materials and methodsA systematic literature search across the following sources was performed: PubMed, ScienceDirect, Google Scholar, and SpringerLink. Forty-two articles were included and subdivided into three groups: group one consists of studies using conventional radiographs (22 articles), group two includes studies using computed tomography (CT) scans (15 articles), and group three comprises studies using magnet resonance imaging (MRI, 9 articles).The following data were extracted: imaging modality, measurement method, number of participants and ankles included, average age of participants, sensitivity, specificity, and accuracy of the measurement technique. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool was used to assess the methodological quality.ResultsThe three most common techniques used for assessment of the syndesmosis in conventional radiographs are the tibio-fibular clear space (TFCS), the tibio-fibular overlap (TFO), and the medial clear space (MCS). Regarding CT scans, the tibio-fibular width (axial images) was most commonly used. Most of the MRI studies used direct assessment of syndesmotic integrity. Overall, the included studies show low probability of bias and are applicable in daily practice.ConclusionsConventional radiographs cannot predict syndesmotic injuries reliably. CT scans outperform plain radiographs in detecting syndesmotic mal-reduction. Additionally, the syndesmotic interval can be assessed in greater detail by CT. MRI measurements achieve a sensitivity and specificity of nearly 100%; however, correlating MRI findings with patients’ complaints is difficult, and utility with subtle syndesmotic instability needs further investigation. Overall, the methodological quality of these studies was satisfactory.