Interpretation Of Radiographs Research Articles

Applicant Perception and Content Exploration of the 2024 podiatric Residency Interview Process

Considerable resources are dedicated on an annual basis to the podiatric medicine and surgery residency interview by both students and programs. Despite this, relatively little is known about student perception of the process, nor the format and content of interview. The objective of this investigation was to study and organize experiences of fourth-year podiatric medical students following the 2024 Centralized Residency Interview Program (CRIP) process. An anonymous and voluntary survey was developed and made available to fourth year podiatric medical students. It was relatively common for there to be academic, social/personal, case work-up, and rapid-fire academic question components to the interview. It was also very common to be provided with the opportunity to ask programs questions. It was relatively uncommon for there to be ethical/moral questions, personality/psychologic assessments, logic assessments, and hands-on demonstrations. The most common hands-on demonstrations were suturing, hand ties and performance of fixation principles. Relatively high yield academic topics included plain film radiography interpretation, rearfoot/ankle osseous trauma, diabetic foot infection, advanced imaging interpretation, and fixation constructs/principles. When evaluating programs, students placed high value on surgical volume, surgical variety, relative resident autonomy, program location, exposure to outpatient clinics, salary, future connections as a program alumnus, unique off-service rotations, exposure to business management/coding/billing, scope of practice, exposure to inpatient management, resident salary, and who the senior co-residents would be. The results of this investigation provide unique information for both medical students and residency programs with respect to the perception, format and content of the podiatric residency interview process.

Effectiveness of using concept mapping by dental students in the radiographic interpretation of jaw diseases.

Interpretation of dental radiographs is a difficult process, particularly for inexperienced students. This study introduced concept mapping for dental students to help in the radiographic interpretation of common jaw lesions. We aimed to analyze the efficacy of the concept map (CM) in radiographic interpretation, with a discussion of the diagnostic reasoning dilemma. This study included 39 dental students. After a 1-h class for CM guidance and based on three group discussions and one-on-one feedback, the students completed and submitted CMs for three jaw diseases (ameloblastoma, odontogenic keratocyst, and simple bone cyst). All participants underwent a pretest and posttest of knowledge and diagnosis; all students but one completed an open-ended questionnaire regarding the use of CMs. Concept mapping effectively improved diagnostic accuracy. The participants' posttest scores were better than their pretest scores in both knowledge and diagnostic tests. Most of the students attempted radiographic interpretation through analytic reasoning. The time required for the students to draw a CM varied from student to student from 3-5h to 1-3 days. This study shows that CMs can improve the radiographic diagnostic ability of dental students by providing a framework for analytic reasoning. Continuous research is warranted to improve the effectiveness of CM in oral radiographic interpretation in the dental student's class.

Abstract PO1-15-06: Serum thymidine kinase activity as a “real-time” clinical biomarker of tumor response to CDK4/6 inhibition in hormone receptor positive (HR+), HER2 negative (HER2-) metastatic breast cancer

Abstract Background: CDK4/6 inhibitors (CDK4/6i) plus endocrine therapy (ET) are standard first-line (1L) treatment for hormone receptor positive (HR+), HER2-negative (HER2-) metastatic breast cancer (MBC). Despite general improvements in long-term outcome, not all patients benefit equally from these drugs. The average duration of 1L CDK4/6i therapy is ~2 years. However, 10-15% of patients will progress within 6 months of therapy initiation, while others will derive durable clinical benefit of years. Differences in treatment efficacy cannot be easily explained by clinical-pathological features. No predictive biomarkers are currently available to determine tumor sensitivity to CDK4/6i. There is an unmet need for a complementary diagnostic to identify patients that will or will not respond to these treatments in order to better inform therapy management. Thymidine kinase (TK) is an E2F-regulated enzyme that plays a key role in DNA replication during cell division. The expression and activity of TK is strongly linked to the cell cycle. TK is first expressed in late G1, peaks during S-phase, and then is degraded during mitosis. Because of the restricted expression of TK (only during S phase of the cell cycle) combined with the mechanism of action of CDK4/6i, the measurement of TK activity (TKa) may serve as an ideal pharmacodynamic biomarker to assess a tumor’s response to CDK4/6i-based therapy. DiviTum® TKa is an FDA cleared assay that can quantitate TKa from human serum (sTKa) and is intended to be used as a disease progression monitoring tool for patients with HR+, HER2- MBC. TK IMPACT is a prospective, single arm trial designed to assess the impact of incorporation of DiviTum® TKa on the physician’s decision regarding subsequent timing of routine disease monitoring modalities in patients with advanced HR+, HER2- MBC receiving 1L ET plus CDK 4/6i (NCT04968964). As a part of this ongoing study, DiviTum® TKa values are serially assessed relative to imaging findings and other circulating tumor biomarkers, such as CA15-3 and ctDNA. The primary endpoint is any physician-reported intended change in imaging testing interval post TKa by study cohort, within the first 48-week period of study participation, assessments for which are ongoing. Here we report real-world data and examples of the clinical utility of sTKa as a companion diagnostic from patients treated at Washington University Siteman Cancer Center, St. Louis, MO. Methods: Patients with HR+, HER2- MBC receiving 1L ET + any FDA-approved CDK 4/6i (palbociclib, ribociclib, or abemaciclib) had blood serum samples collected at baseline, weeks 2, 4, 6, 8, every 4 weeks up to week 24, and then every 12 weeks thereafter until disease progression. Samples were analyzed for TKa levels in real-time using the DiviTum® TKa assay. Optional repeat TKa within 2-4 wks (+/- 3 days) is permitted in case of rising TKa. Other standard monitoring assessments were carried out according to institutional guidelines and/or treating clinician discretion. Results: Pre-treatment and early on-therapy TKa levels predicted response to CDK4/6i therapy more accurately than a patient’s clinical characteristics. Rising TKa levels also identified patients with clinically occult disease progression ahead of imaging, and in some cases where radiographic interpretation and serum tumor markers such as CA15-3 were ambiguous. Measurement of TKa levels following CDK4/6i dose reduction was able to confirm continued optimal therapy response at the lower dose. A rise in TKa levels aligned with the re-emergence of ESR1 mutation as identified by ctDNA in one patient and may herald molecular progression. Conclusion: sTKa was able to predict tumor sensitivity and resistance (both intrinsic and acquired) to CDK4/6i + ET therapy in patients with HR+, HER2- MBC. We believe these findings help support the role of sTKa as a non-invasive pharmacodynamic biomarker that can assess in real-time a tumor’s response to CDK4/6i based therapy. Citation Format: Nusayba Bagegni, Amy Williams, Isabella Grigsby, Mattias Bergqvist, Katherine Clifton, Cynthia Ma. Serum thymidine kinase activity as a “real-time” clinical biomarker of tumor response to CDK4/6 inhibition in hormone receptor positive (HR+), HER2 negative (HER2-) metastatic breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-15-06.

Artificial intelligence improves resident detection of pediatric and young adult upper extremity fractures.

We wished to evaluate if an open-source artificial intelligence (AI) algorithm ( https://www.childfx.com ) could improve performance of (1) subspecialized musculoskeletal radiologists, (2) radiology residents, and (3) pediatric residents in detecting pediatric and young adult upper extremity fractures. A set of evaluation radiographs drawn from throughout the upper extremity (elbow, hand/finger, humerus/shoulder/clavicle, wrist/forearm, and clavicle) from 240 unique patients at a single hospital was constructed (mean age 11.3years, range 0-22years, 37.9% female). Two fellowship-trained musculoskeletal radiologists, three radiology residents, and two pediatric residents were recruited as readers. Each reader interpreted each case initially without and then subsequently 3-4weeks later with AI assistance and recorded if/where fracture was present. Access to AI significantly improved area under the receiver operator curve (AUC) of radiology residents (0.768 [0.730-0.806] without AI to 0.876 [0.845-0.908] with AI, P < 0.001) and pediatric residents (0.706 [0.659-0.753] without AI to 0.844 [0.805-0.883] with AI, P < 0.001) in identifying fracture, respectively. There was no evidence of improvement for subspecialized musculoskeletal radiology attendings in identifying fracture (AUC 0.867 [0.832-0.902] to 0.890 [0.856-0.924], P = 0.093). There was no evidence of difference between overall resident AUC with AI and subspecialist AUC without AI (resident with AI 0.863, attending without AI AUC 0.867, P = 0.856). Overall physician radiograph interpretation time was significantly lower with AI (38.9s with AI vs. 52.1s without AI, P = 0.030). An openly accessible AI model significantly improved radiology and pediatric resident accuracy in detecting pediatric upper extremity fractures.

Artificial Intelligence for Detecting Periodontitis: Systematic Literature Review

Background The determination of the diagnosis of inflammatory periodontitis is generally based on clinical examination, which is then strengthened by radiographic examination. Still, the inequality of assessment of clinical conditions, along with limitations of radiographic interpretation, makes determining the diagnosis of the periodontal disease difficult. The use of artificial intelligence as a digital system approach is believed to reduce costs, time, the need for medical services, and medical errors that may occur due to human factors. Objective This systematic review study is to analyze the use of dental and panoramic radiographs combined with the use of artificial intelligence in establishing the diagnosis of periodontitis based on the parameters of periodontal disease severity according to the 2017 American Academy of Periodontology/European Federation of Periodontology Workshop (pocket depth, clinical attachment loss (CAL) and the pattern and level of alveolar bone damage that occurs). Methods Journal searches for articles published in English were carried out through the PubMed and Scopus databases in the 2011-2021 period, using the search terms periodontitis, periodontal disease, food impaction, trauma occlusion, periapical radiograph, panoramic, machine learning, artificial intelligence, and periodontal bone loss, after going through article selection, two suitable articles were obtained. Results Two studies fell into the analyzed category. Both list periodontal bone loss as a parameter that marks periodontitis, and the use of panoramic photos in detecting this parameter assisted by Convolutional Neural Networks as artificial intelligence. Conclusion The use of panoramic radiographs and Convolutional Neural Networks as artificial intelligence that serves as a tool to detect periodontal bone damage has almost the same results as experienced clinicians In order for this method to be developed in the future to help clinicians establish the diagnosis, more clinical and image data will be required.

Interpretation time efficiency with radiographs: a comparison study between standard 6 and 12 MP high-resolution display monitors.

The purpose of this study is to compare interpretation efficiency of radiologists reading radiographs on 6 megapixel (MP) versus 12MP monitors. Our method compares two sets of monitors in two phases: in phase I, radiologists interpreted using a 6 MP, 30.4 in. (Barco Coronis Fusion) and in phase II, a 12MP, 30.9 in. (Barco Nio Fusion). Nine chest and three musculoskeletal radiologists each batch interpreted an average of 115 radiographs in phase I and 115 radiographs in phase II as a part of routine clinical work. Radiologists were blinded to monitor resolution. Interpretation times per radiograph were noted from dictation logs. Interpretation time was significantly decreased utilizing a 12 MP monitor by 6.88s ( ) and 6.76s (8.7%) ( ) for chest radiographs only and combined chest and musculoskeletal radiographs, respectively. When evaluating musculoskeletal radiographs alone, the improvement in reading times with 12 MP monitor was 6.76s, however, this difference was not statistically significant ( ). Interpretation of radiographs on 12MP monitors was 8.7% faster than on 6 MP monitors. Higher resolution diagnostic displays can enable radiologists to interpret radiographs more efficiently.

Enhancing AI-assisted Interpretation of Chest Radiographs: A Critical Analysis of Methods and Applicability.

Enhancing AI-assisted Interpretation of Chest Radiographs: A Critical Analysis of Methods and Applicability.

Perceptiveness and Attitude on the use of Artificial Intelligence (AI) in Dentistry among Dentists and Non-Dentists - A Regional Survey

ABSTRACT Artificial intelligence (AI) is an emerging tool in modern medicine and the digital world. AI can help dentists diagnose oral diseases, design treatment plans, monitor patient progress and automate administrative tasks. The aim of this study is to evaluate the perception and attitude on use of artificial intelligence in dentistry for diagnosis and treatment planning among dentists and non-dentists’ population of south Tamil Nadu region in India. Materials and Methods: A cross sectional online survey conducted using 20 close ended questionnaire google forms which were circulated among the dentists and non -dentists population of south Tamil Nadu region in India. The data collected from 264 participants (dentists -158, non-dentists -106) within a limited time frame were subjected to descriptive statistical analysis. Results: 70.9% of dentists are aware of artificial intelligence in dentistry. 40.5% participants were not aware of AI in caries detection but aware of its use in interpretation of radiographs (43.9%) and in planning of orthognathic surgery (42.4%) which are statistically significant P &lt; 0.05.44.7% support clinical experience of a human doctor better than AI diagnosis. Dentists of 54.4% agree to support AI use in dentistry. Conclusion: The study concluded AI use in dentistry knowledge is more with dentists and perception of AI in dentistry is optimistic among dentists than non -dentists, majority of participants support AI in dentistry as an adjunct tool to diagnosis and treatment planning.

The effects of gaze-display feedback on medical students’ self-monitoring and learning in radiology

Self-monitoring is essential for effectively regulating learning, but difficult in visual diagnostic tasks such as radiograph interpretation. Eye-tracking technology can visualize viewing behavior in gaze displays, thereby providing information about visual search and decision-making. We hypothesized that individually adaptive gaze-display feedback improves posttest performance and self-monitoring of medical students who learn to detect nodules in radiographs. We investigated the effects of: (1) Search displays, showing which part of the image was searched by the participant; and (2) Decision displays, showing which parts of the image received prolonged attention in 78 medical students. After a pretest and instruction, participants practiced identifying nodules in 16 cases under search-display, decision-display, or no feedback conditions (n = 26 per condition). A 10-case posttest, without feedback, was administered to assess learning outcomes. After each case, participants provided self-monitoring and confidence judgments. Afterward, participants reported on self-efficacy, perceived competence, feedback use, and perceived usefulness of the feedback. Bayesian analyses showed no benefits of gaze displays for post-test performance, monitoring accuracy (absolute difference between participants’ estimated and their actual test performance), completeness of viewing behavior, self-efficacy, and perceived competence. Participants receiving search-displays reported greater feedback utilization than participants receiving decision-displays, and also found the feedback more useful when the gaze data displayed was precise and accurate. As the completeness of search was not related to posttest performance, search displays might not have been sufficiently informative to improve self-monitoring. Information from decision displays was rarely used to inform self-monitoring. Further research should address if and when gaze displays can support learning.

NAVIGATING DENTISTRY’S AI REVOLUTION: OPPORTUNITIES IN PAKISTAN

The convergence of Artificial Intelligence (AI) and dentistry marks a profound shift in the way oral healthcare is delivered and managed. In Pakistan, where healthcare resources may be constrained, the integration of AI presents unique opportunities to enhance access, efficiency, and precision in dental practice. AI-powered tele-dentistry platforms offer remote consultations and diagnostics, bridging geographical gaps in access to specialized care. This empowers patients across Pakistan, ensuring timely interventions and expert opinions regardless of location.AI algorithms excel in radiographic interpretation, aiding in early detection of oral pathologies like caries and oral cancers. By augmenting diagnostic accuracy, AI mitigates the burden of oral diseases in Pakistan, optimizing resource allocation and improving patient outcomes. Additionally, AI-driven treatment planning streamlines workflows and enhances precision in dental procedures. From predictive modeling for orthodontic outcomes to computer-aided design of dental prosthetics, AI optimizes treatment efficacy and patient satisfaction. Embracing AI as a complementary tool, Pakistani dental professionals can unlock new horizons in care delivery. By integrating AI with traditional methodologies, dentists can navigate this transformative landscape, fostering innovation and excellence in oral healthcare nationwide.

Osteoarthritis of the temporomandibularjoint

Osteoarthritis (OA) is a degenerativejoint disease marked by progressive lossof articular cartilage and damage of bony components. The clinical features include;joint pain, crepitus and limitation of movement. The exact cause of OA is unknownhowever some authors consider it as a multifaetorial disease. The age and over usageare the most common tactors, in addition to race and sex. ln case oftemporomandibular joint(TMJ), traumatic occlusion, and over load caused byparafunctions are additional factors. The purpose ofthis investigation was to study theTMJ) arthropathy among a group of Iraqi patients previously diagnosed as having(.OAOne hundred patients with OA are used in this study. They were examined.clinically and radiographically for effects of systemic OA on TMJResults of the study revealed that 39% of patients with OA have TMJ lesions ofdifferent degrees ranged between osteophytes, diminusion of joint space and bone.distruction ofglenoid fossa and head of condyleDental management of temporomandibular joints affected with OA usuallyaim to suppress the active disease, preserve functions, prevent deformity and relievepain. Early detection of the disease and early commencement of management greatly ireduce joint destruction and improve prognosis. Results of this study indicated thatl1% of patients had only TMJ lesions, with no other joints lesions. Because ofdifficulty of interpretation of TMJ radiographs we suggest criteria for radiographicdiagnosis of osteoarthritis ofthe TMJ&#x0D;

Plain Radiography: A Unique Component of Spinal Assessment and Predictive Health.

While some research supports utilizing plain radiography for measuring biomechanical alignment of the spine for prognosis and treatment, there are contrasting viewpoints regarding both the value and utilization of these procedures in conservative care. Evaluation of both conservative and non-conservative approaches to spinal care revealed vast differences in radiographic utilization and interpretation between orthopedic surgeons, primary care physicians, chiropractic physicians, and physical therapists, which may account for the different viewpoints and rationales in the literature. A research summary is provided to explore any unique biomechanical parameters identified with plain radiography of the spine (PROTS) and how these measurements may relate to patient health. Understanding any unique value provided through biomechanical assessment utilizing PROTS may help chiropractic physicians determine the appropriate use of radiographic procedures in clinical practice and how to coordinate efforts with other conservative and non-conservative spinal healthcare professions to improve patient health.

Developing New Fully Connected Layers for Convolutional Neural Networks with Hyperparameter Optimization for Improved Multi-Label Image Classification

Chest X-ray evaluation is challenging due to its high demand and the complexity of diagnoses. In this study, we propose an optimized deep learning model for the multi-label classification of chest X-ray images. We leverage pretrained convolutional neural networks (CNNs) such as VGG16, ResNet 50, and DenseNet 121, modifying their output layers and fine-tuning the models. We employ a novel optimization strategy using the Hyperband algorithm to efficiently search the hyperparameter space while adjusting the fully connected layers of the CNNs. The effectiveness of our approach is evaluated on the basis of the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metric. Our proposed methodology could assist in automated chest radiograph interpretation, offering a valuable tool that can be used by clinicians in the future.

Needs assessment of a pythiosis continuing professional development program.

Pythiosis is a rare disease with high mortality, with over 94% of cases reported from Thailand and India. Prompt diagnosis and surgery improves patient outcomes. Therefore, continuing professional development (CPD) is essential for early recognition. However, a needs assessment related to a pythiosis CPD program has not been performed. We conducted a needs assessment to develop a pythiosis CPD program. We conducted a survey study with 267 King Chulalongkorn Memorial Hospital residents (141 internal medicine (IM) residents and 126 surgery residents). A 30-item survey consisting of a knowledge assessment, demographic section, and an attitudes portion was distributed both electronically and via paper. The data was analyzed with descriptive and inferential statistics. Sixty-seven percent completed the survey (110/141 IM residents, 70/126 surgery residents). The mean score [95% confidence interval] on the knowledge assessment was 41.67% [39.64%-43.69%] across all objectives. The three domains with the highest scores were pythiosis risk factors (67.22% correct), microbiologic characteristics (50.83%), and radiographic interpretation (50.56%). The three domains with the lowest scores were laboratory investigation (15.00%), epidemiology (29.17%), and symptomatology (30.83%). Most participants noted that the program should be online with both synchronous and asynchronous sessions, with a preferred length of 60-90 minutes per session. The pythiosis CPD program should emphasize education regarding symptomatology, laboratory investigation, and epidemiology, all of which are critical for the early detection of pythiosis to decrease mortality from this devastating disease. Most respondents felt this program was necessary and should be implemented in a virtual blended format.

Formal Radiologist Interpretations of Intraoperative Spine Radiographs Have Low Clinical Value.

Retrospective cohort. To evaluate the clinical relevance, usefulness, and financial implications of intraoperative radiograph interpretation by radiologists in spine surgery. Due to rising healthcare costs, spine surgery is under scrutiny to maximize value-based care. Formal radiographic analysis remains a potential source of unnecessary healthcare costs, especially for intra-operative radiographs. A retrospective cohort analysis was performed on all adult elective spine surgeries at a single institution between July 2020 and July 2021. Demographic and radiographic data was collected, including intraoperative localization and post-instrumentation radiographs. Financial data was obtained through the institution's price estimator. Radiographic characteristics included time from radiographic imaging to completion of radiologist interpretation report, completion of radiologist interpretation report prior to the conclusion of surgical procedure, clinical relevance, and clinical usefulness. Reports were considered clinically relevant if spinal level of the procedure was described and clinically useful if completed prior to conclusion of the procedure and deemed clinically relevant. 481 intraoperative localization and post-instrumentation radiographs from 360 patients revealed a median delay of 128 minutes between imaging and completion of interpretive report. Only 38.9% of reports were completed before conclusion of surgery. There were 79.4% deemed clinically relevant and only 33.5% were clinically useful. Localization reports were completed more frequently before conclusion of surgery (67.2% vs. 34.4%), but with lower clinical relevance (90.1% vs. 98.5%) and clinical usefulness (60.3% vs. 33.6%) than post-instrumentation reports. Each patient was charged $32-$34 for interpretation fee, cumulating a minimum total cost of $15,392. Formal radiographic interpretation of intraoperative spine radiographs was of low clinical utility for spine surgeons. Institutions should consider optimizing radiology workflows to improve timeliness and clinical relevance or evaluate the necessity of reflexive consultation to radiology for intraoperative imaging interpretation to ensure that value-based care is maximized during spine surgeries. 3.

Deep learning model performance for identifying pediatric acute respiratory distress syndrome on chest radiographs

PurposePediatric acute respiratory distress syndrome (PARDS) is underrecognized in the pediatric intensive care unit and the interpretation of chest radiographs is a key step in identification. We sought to test the performance of a machine learning model to detect PARDS in a cohort of children with respiratory failure.Materials and methodsA convolutional neural network (CNN) model previously developed to detect ARDS on adult chest radiographs was applied to a cohort of children age 7 days to 18 years, admitted to the PICU, and mechanically ventilated through a tracheostomy, endotracheal tube or full-face non-invasive positive pressure mask between May 2016 and January 2017. Two pediatric critical care physicians and a pediatric radiologist reviewed chest radiographs to evaluate if the chest radiographs were consistent with ARDS (bilateral airspace disease) and PARDS (any airspace disease) and the CNN model was tested against clinicians.ResultsA total of 328 chest radiographs were evaluated from 66 patients. Clinicians identified 84% (276/328) of the radiographs as potentially consistent with PARDS. Inter-rater reliability between individual clinicians and between the model and clinicians was similar (Cohen’s kappa 0.48 [95% CI 0.37–0.59] and 0.45 [95% CI 0.33–0.57], respectively). The model was better at identifying PARDS (AUC 0.882, F1 0.897) than ARDS (AUC 0.842, F1 0.742) and had equivalent or better performance to individual clinicians.ConclusionsAn ARDS detection model trained on adults performed well in detecting PARDS in children. Computer-assisted identification of PARDS on chest radiographs could improve the diagnosis of PARDS for enrollment in clinical trials and application of PARDS guidelines through improved diagnosis.

Evaluation of the Success Rate of Immediate Implant Using Clinical and Radiographic Interpretation Methods—A Prospective Study

Evaluation of the Success Rate of Immediate Implant Using Clinical and Radiographic Interpretation Methods—A Prospective Study

Detection of periodontal bone loss patterns and furcation defects from panoramic radiographs using deep learning algorithm: a retrospective study

BackgroundThis retrospective study aimed to develop a deep learning algorithm for the interpretation of panoramic radiographs and to examine the performance of this algorithm in the detection of periodontal bone losses and bone loss patterns.MethodsA total of 1121 panoramic radiographs were used in this study. Bone losses in the maxilla and mandibula (total alveolar bone loss) (n = 2251), interdental bone losses (n = 25303), and furcation defects (n = 2815) were labeled using the segmentation method. In addition, interdental bone losses were divided into horizontal (n = 21839) and vertical (n = 3464) bone losses according to the defect patterns. A Convolutional Neural Network (CNN)-based artificial intelligence (AI) system was developed using U-Net architecture. The performance of the deep learning algorithm was statistically evaluated by the confusion matrix and ROC curve analysis.ResultsThe system showed the highest diagnostic performance in the detection of total alveolar bone losses (AUC = 0.951) and the lowest in the detection of vertical bone losses (AUC = 0.733). The sensitivity, precision, F1 score, accuracy, and AUC values were found as 1, 0.995, 0.997, 0.994, 0.951 for total alveolar bone loss; found as 0.947, 0.939, 0.943, 0.892, 0.910 for horizontal bone losses; found as 0.558, 0.846, 0.673, 0.506, 0.733 for vertical bone losses and found as 0.892, 0.933, 0.912, 0.837, 0.868 for furcation defects (respectively).ConclusionsAI systems offer promising results in determining periodontal bone loss patterns and furcation defects from dental radiographs. This suggests that CNN algorithms can also be used to provide more detailed information such as automatic determination of periodontal disease severity and treatment planning in various dental radiographs.

Nonradiology Health Care Professionals Significantly Benefit From AI Assistance in Emergency-Related Chest Radiography Interpretation

BackgroundChest radiography (CXR) is still of crucial importance in primary diagnostics, but interpretation poses difficulties at times. Research QuestionCan a convolutional neural network (CNN)-based AI system that interprets CXRs add value in an emergency unit (EU) setting? Study Design and MethodsA total of 563 CXRs acquired in the EU of a major university hospital were retrospectively assessed twice by three board-certified radiologists (BCRs), three radiology residents (RRs), and three EU-experienced non-radiology residents (NRRs) employing a two-step reading process: (1) without AI support (woAI), (2) with AI support providing additional images with AI overlays (wAI). Suspicion of four suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, nodules) was reported on a 5-point confidence scale. BCRs’ confidence scores were converted into four binary reference standards (RFS I-IV) of different sensitivities. RRs' and NRRs' performances woAI/wAI were statistically compared using receiver operating characteristics (ROCs), Youden statistics and operating point metrics derived from fitted ROC curves. ResultsNRRs could significantly improve performance, sensitivity and accuracy wAI in all four pathologies tested. E.g., in the most sensitive RFS IV, NRR consensus improved the AUC (mean, 95%-confidence-interval) in the detection of the time-critical pathology pneumothorax from 0.846 (0.785-0.907) woAI to 0.974 (0.947-1.000) wAI [p<0.001], which represented a gain of 30% in sensitivity and 2% in accuracy (while maintaining an optimized specificity). The most pronounced effect was observed in nodule detection, with NRR wAI improving sensitivity by 53% and accuracy by 7% (AUC woAI: 0.723 [0.661-0.785], wAI: 0.890 [0.848-0.931], p<0.001). The RR consensus wAI showed smaller, mostly non-significant gains in performance, sensitivity and accuracy. InterpretationIn an EU setting without 24/7 radiology coverage, the presented AI solution features an excellent clinical support tool to non-radiologists, similar to a second reader, and allows for a more accurate primary diagnosis and thus earlier therapy initiation.

Demystifying the Radiography of Age Estimation in Criminal Jurisprudence: A Pictorial Review.

Skeletal radiographs along with dental examination are frequently used for age estimation in medicolegal cases where documentary evidence pertaining to age is not available. Wrist and hand radiographs are the most common skeletal radiograph considered for age estimation. Other parts imaged are elbow, shoulder, knee, and hip according to suspected age categories. Age estimation by wrist radiographs is usually done by the Tanner-Whitehouse method where the maturity level of each bone is categorized into stages and a final total score is calculated that is then transformed into the bone age. Careful assessment and interpretation at multiple joints are needed to minimize the error and categorize into age-group. In this article, we aimed to summarize a suitable radiographic examination and interpretation for bone age estimation in living children, adolescents, young adults, and adults for medicolegal purposes.