Search

Malignant peripheral nerve sheath tumors (MPNSTs) are aggressive soft-tissue tumors prevalent in neurofibromatosis type 1 (NF1) patients, posing a significant risk of metastasis and recurrence. Current magnetic resonance imaging (MRI) imaging lacks decisiveness in distinguishing benign peripheral nerve sheath tumors (BPNSTs) and MPNSTs, necessitating invasive biopsies. This study aims to develop a radiomics model using quantitative imaging features and machine learning to distinguish MPNSTs from BPNSTs. Clinical data and MRIs from MPNST and BPNST patients (2000–2019) were collected at a tertiary sarcoma referral center. Lesions were manually and semi-automatically segmented on MRI scans, and radiomics features were extracted using the Workflow for Optimal Radiomics Classification (WORC) algorithm, employing automated machine learning. The evaluation was conducted using a 100× random-split cross-validation. A total of 35 MPNSTs and 74 BPNSTs were included. The T1-weighted (T1w) MRI radiomics model outperformed others with an area under the curve (AUC) of 0.71. The incorporation of additional MRI scans did not enhance performance. Combining T1w MRI with clinical features achieved an AUC of 0.74. Experienced radiologists achieved AUCs of 0.75 and 0.66, respectively. Radiomics based on T1w MRI scans and clinical features show some ability to distinguish MPNSTs from BPNSTs, potentially aiding in the management of these tumors.

Background: While current preoperative and postoperative assessment of the fractured and surgically reconstructed calcaneus relies on computed tomography (CT)-imaging, there are no established methods to quantify calcaneus morphology on CT-images. This study aims to develop a semi-automated method for morphological measurements of the calcaneus on three-dimensional (3D) models derived from CT-imaging. Methods: Using CT data, 3D models were created from healthy, fractured, and surgically reconstructed calcanei. Böhler's angle (BA) and Critical angle of Gissane (CAG) were measured on conventional lateral radiographs and corresponding 3D CT reconstructions using a novel point-based method with semiautomatic landmark placement by three observers. Intraobserver and interobserver reliability scores were calculated using intra-class correlation coefficient (ICC). In addition, consensus among observers was calculated for a maximal allowable discrepancy of 5 and 10 degrees for both methods. Results: Imaging data from 119 feet were obtained (40 healthy, 39 fractured, 40 reconstructed). Semiautomated measurements on 3D models of BA and CAG showed excellent reliability (ICC: 0.87-1.00). The manual measurements on conventional radiographs had a poor-to-excellent reliability (ICC: 0.22-0.96). In addition, the percentage of consensus among observers was much higher for the 3D method when compared to conventional two-dimensional (2D) measurements. Conclusions: The proposed method enables reliable and reproducible quantification of calcaneus morphology in 3D models of healthy, fractured and reconstructed calcanei.

Objectives: As current health technology assessment (HTA) frameworks do not provide specific guidance on the assessment of medical artificial intelligence (AI), this study aimed to propose a conceptual framework for a broad HTA of medical AI. Methods: A systematic literature review and a targeted search of policy documents was conducted to distill the relevant medical AI assessment elements. Three exemplary cases were selected to illustrate various elements: (1) An application supporting radiologists in stroke-care (2) A natural language processing application for clinical data abstraction (3) An ICU-discharge decision-making application. Results: A total of 31 policy documents and 9 academic publications were selected, from which a list of 29 issues was distilled. The issues were grouped by four focus areas: (1) Technology & Performance, (2) Human & Organizational, (3) Legal & Ethical and (4) Transparency & Usability. Each assessment element was extensively discussed in the test, and the elements clinical effectiveness, clinical workflow, workforce, interoperability, fairness and explainability were further highlighted through the exemplary cases. Conclusion: The current methodology of HTA requires extension to make it suitable for a broad evaluation of medical AI technologies. The 29-item assessment list that we propose needs a tailored approach for distinct types of medical AI, since the conceptualisation of the issues differs across applications.

In 3D-analysis of the calcaneus, a consistent coordinate system aligned with the original anatomical directions is crucial for pre- and postoperative analysis. This importance stems from the calcaneus's key role in weight-bearing and biomechanical alignment. However, defining a reliable coordinate system based solely on fractured or surgically reconstructed calcanei presents significant challenges. Given its anatomical prominence and consistent orientation, the talus offers a potential solution to this challenge. Our work explores the feasibility of talus-derived coordinate systems for 3D-modeling of the calcaneus across its various conditions. Four methods were tested on nonfractured, fractured and surgically reconstructed calcanei, utilizing Principal Component Analysis, anatomical landmarks, bounding box, and an atlas-based approach. The methods were compared with a self-defined calcaneus reference coordinate system. Additionally, the impact of deviation of the coordinate system on morphological measurements was investigated. Among methods for constructing nonfractured calcanei coordinate systems, the atlas-based method displayed the lowest Root Mean Square value in comparison with the reference coordinate system. For morphological measures like Böhler's Angle and the Critical angle of Gissane, the atlas talus-based system closely aligned with ground truth, yielding differences of 0.6° and 1.2°, respectively, compared to larger deviations seen in other talus-based coordinate systems. In conclusion, all tested methods were feasible for creating a talus derived coordinate system. A talus derived coordinate system showed potential, offering benefits for morphological measurements and clinical scenarios involving fractured and surgically reconstructed calcanei. Further research is recommended to assess the impact of these coordinate systems on surgical planning and outcomes.

Objectives: To evaluate an artificial intelligence (AI)–assisted double reading system for detecting clinically relevant missed findings on routinely reported chest radiographs. Methods: A retrospective study was performed in two institutions, a secondary care hospital and tertiary referral oncology centre. Commercially available AI software performed a comparative analysis of chest radiographs and radiologists’ authorised reports using a deep learning and natural language processing algorithm, respectively. The AI-detected discrepant findings between images and reports were assessed for clinical relevance by an external radiologist, as part of the commercial service provided by the AI vendor. The selected missed findings were subsequently returned to the institution’s radiologist for final review. Results: In total, 25,104 chest radiographs of 21,039 patients (mean age 61.1 years ± 16.2 [SD]; 10,436 men) were included. The AI software detected discrepancies between imaging and reports in 21.1% (5289 of 25,104). After review by the external radiologist, 0.9% (47 of 5289) of cases were deemed to contain clinically relevant missed findings. The institution’s radiologists confirmed 35 of 47 missed findings (74.5%) as clinically relevant (0.1% of all cases). Missed findings consisted of lung nodules (71.4%, 25 of 35), pneumothoraces (17.1%, 6 of 35) and consolidations (11.4%, 4 of 35). Conclusion: The AI-assisted double reading system was able to identify missed findings on chest radiographs after report authorisation. The approach required an external radiologist to review the AI-detected discrepancies. The number of clinically relevant missed findings by radiologists was very low. Clinical relevance statement: The AI-assisted double reader workflow was shown to detect diagnostic errors and could be applied as a quality assurance tool. Although clinically relevant missed findings were rare

Objective: To provide a comprehensive framework for value assessment of artificial intelligence (AI) in radiology. Methods: This paper presents the RADAR framework, which has been adapted from Fryback and Thornbury’s imaging efficacy framework to facilitate the valuation of radiology AI from conception to local implementation. Local efficacy has been newly introduced to underscore the importance of appraising an AI technology within its local environment. Furthermore, the RADAR framework is illustrated through a myriad of study designs that help assess value. Results: RADAR presents a seven-level hierarchy, providing radiologists, researchers, and policymakers with a structured approach to the comprehensive assessment of value in radiology AI. RADAR is designed to be dynamic and meet the different valuation needs throughout the AI’s lifecycle. Initial phases like technical and diagnostic efficacy (RADAR-1 and RADAR-2) are assessed pre-clinical deployment via in silico clinical trials and cross-sectional studies. Subsequent stages, spanning from diagnostic thinking to patient outcome efficacy (RADAR-3 to RADAR-5), require clinical integration and are explored via randomized controlled trials and cohort studies. Cost-effectiveness efficacy (RADAR-6) takes a societal perspective on financial feasibility, addressed via health-economic evaluations. The final level, RADAR-7, determines how prior valuations translate locally, evaluated through budget impact analysis, multi-criteria decision analyses, and prospective monitoring.Conclusion: The RADAR framework offers a comprehensive framework for valuing radiology AI. Its layered, hierarchical structure, combined with a focus on local relevance, aligns RADAR seamlessly with the principles of value-based radiology. Critical relevance statement: The RADAR framework advances artificial intelligence in radiology by delineating a

Background Artificial intelligence (AI) applications can facilitate detection of cervical spine fractures on CT and reduce time to diagnosis by prioritizing suspected cases. Purpose To assess the effect on time to diagnose cervical spine fractures on CT and diagnostic accuracy of a commercially available AI application. Materials and methods In this study (June 2020 - March 2022) with historic controls and prospective evaluation, we evaluated regulatory-cleared AI-software to prioritize cervical spine fractures on CT. All patients underwent non-contrast CT of the cervical spine. The time between CT acquisition and the moment the scan was first opened (DNT) was compared between the retrospective and prospective cohorts. The reference standard for determining diagnostic accuracy was the radiology report created in routine clinical workflow and adjusted by a senior radiologist. Discrepant cases were reviewed and clinical relevance of missed fractures was determined. Results 2973 (mean age, 55.4 ± 19.7 [standard deviation]; 1857 men) patients were analyzed by AI, including 2036 retrospective and 938 prospective cases. Overall prevalence of cervical spine fractures was 7.6 %. The DNT was 18 % (5 min) shorter in the prospective cohort. In scans positive for cervical spine fracture according to the reference standard, DNT was 46 % (16 min) shorter in the prospective cohort. Overall sensitivity of the AI application was 89.8 % (95 % CI: 84.2–94.0 %), specificity was 95.3 % (95 % CI: 94.2–96.2 %), and diagnostic accuracy was 94.8 % (95 % CI: 93.8–95.8 %). Negative predictive value was 99.1 % (95 % CI: 98.5–99.4 %) and positive predictive value was 63.0 % (95 % CI: 58.0–67.8 %). 22 fractures were missed by AI of which 5 required stabilizing therapy. Conclusion A time gain of 16 min to diagnosis for fractured cases was observed after introducing AI. Although AI-assisted workflow prioritization of cervical spine fractures

Purpose: To evaluate the diagnostic efficacy of artificial intelligence (AI) software in detecting incidental pulmonary embolism (IPE) at CT and shorten the time to diagnosis with use of radiologist reading worklist prioritization. Materials and Methods: In this study with historical controls and prospective evaluation, regulatory-cleared AI software was evaluated to prioritize IPE on routine chest CT scans with intravenous contrast agent in adult oncology patients. Diagnostic accuracy metrics were calculated, and temporal end points, including detection and notification times (DNTs), were assessed during three time periods (April 2019 to September 2020): routine workflow without AI, human triage without AI, and worklist prioritization with AI. Results: In total, 11 736 CT scans in 6447 oncology patients (mean age, 63 years ± 12 [SD]; 3367 men) were included. Prevalence of IPE was 1.3% (51 of 3837 scans), 1.4% (54 of 3920 scans), and 1.0% (38 of 3979 scans) for the respective time periods. The AI software detected 131 true-positive, 12 false-negative, 31 false-positive, and 11 559 true-negative results, achieving 91.6% sensitivity, 99.7% specificity, 99.9% negative predictive value, and 80.9% positive predictive value. During prospective evaluation, AI-based worklist prioritization reduced the median DNT for IPE-positive examinations to 87 minutes (vs routine workflow of 7714 minutes and human triage of 4973 minutes). Radiologists’ missed rate of IPE was significantly reduced from 44.8% (47 of 105 scans) without AI to 2.6% (one of 38 scans) when assisted by the AI tool (P < .001). Conclusion: AI-assisted workflow prioritization of IPE on routine CT scans in oncology patients showed high diagnostic accuracy and significantly shortened the time to diagnosis in a setting with a backlog of examinations. Supplemental material is available for this article.

Background: Sustainable implementation of telemonitoring in health care is challenging, especially if one aims to scale up telemonitoring initiatives nationwide. The National collaborative eHealth program in the Netherlands is supporting the nationwide upscaling of telemonitoring in 3 clinical domains by implementing telemonitoring in all Dutch university medical centers (UMCs). The chosen telemonitoring concepts are (1) telemonitoring solutions in the domain of cardiology, (2) telemonitoring solutions providing care from a distance in obstetrics, and (3) telemonitoring solutions monitoring vital functions in hospital wards. Objective: The aim of this study is to evaluate the upscaling of telemonitoring in Dutch university hospitals in order to gain a better knowledge of the process, methods, and outcomes of nationwide upscaling strategies. Our hypothesis is that by the completion of the Citrien program’s scale-up, telemonitoring will be operational in all UMCs but not normalized in routine care. Methods: A before-and-after study will be conducted to assess upscaling. The theoretical frameworks used are the framework for nonadoption, abandonment, scale-up, spread, and sustainability; the Normalization Process Theory; and a project management tool Project Canvas. The primary outcome of the study is the degree of normalization to which health care providers at UMCs consider telemonitoring a part of their routine practice, measured using the Normalization MeAsurement Development tool (NoMAD). Our secondary outcome is the uptake of telemonitoring at the Dutch UMCs, using management data from UMCs’ business intelligence systems query. Results: Data will be collected between May 2020 and December 2022. Results were retrieved in June 2023. UMCs’ business intelligence systems are queried for data for the secondary outcome measures. There is a risk that the UMCs will not be able to provide this m

Background Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19). Objectives To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity. Methods The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convolutional neural network. For the segmentation task, a UNET-like architecture with a backbone Residual Network (ResNet-34) was selected. Results A total of 2, 802 CT scans were included (2, 667 unique patients, mean [standard deviation] age = 64.6 [16.2] years, male/female ratio 1.3:1). The distribution of classes (COVID-19/Other type of pulmonary infection/No imaging signs of infection) was 1, 490 (53.2%), 402 (14.3%), and 910 (32.5%), respectively. On the external test dataset, the diagnostic multiclassification model yielded high micro-average and macro-average AUC values (0.93 and 0.91, respectively). The model provided the likelihood of COVID-19 vs other cases with a sensitivity of 87% and a specificity of 94%. The segmentation performance was moderate with Dice similarity coefficient (DSC) of 0.59. An imaging analysis pipeline was developed that returned a quantitative report to the user. Conclusion We developed a deep learning-based clinical decision support system that could bec

Objectives: Only few published artificial intelligence (AI) studies for COVID-19 imaging have been externally validated. Assessing the generalizability of developed models is essential, especially when considering clinical implementation. We report the development of the International Consortium for COVID-19 Imaging AI (ICOVAI) model and perform independent external validation. Methods: The ICOVAI model was developed using multicenter data (n = 1286 CT scans) to quantify disease extent and assess COVID-19 likelihood using the COVID-19 Reporting and Data System (CO-RADS). A ResUNet model was modified to automatically delineate lung contours and infectious lung opacities on CT scans, after which a random forest predicted the CO-RADS score. After internal testing, the model was externally validated on a multicenter dataset (n = 400) by independent researchers. CO-RADS classification performance was calculated using linearly weighted Cohen’s kappa and segmentation performance using Dice Similarity Coefficient (DSC). Results: Regarding internal versus external testing, segmentation performance of lung contours was equally excellent (DSC = 0.97 vs. DSC = 0.97, p = 0.97). Lung opacities segmentation performance was adequate internally (DSC = 0.76), but significantly worse on external validation (DSC = 0.59, p < 0.0001). For CO-RADS classification, agreement with radiologists on the internal set was substantial (kappa = 0.78), but significantly lower on the external set (kappa = 0.62, p < 0.0001). Conclusion: In this multicenter study, a model developed for CO-RADS score prediction and quantification of COVID-19 disease extent was found to have a significant reduction in performance on independent external validation versus internal testing. The limited reproducibility of the model restricted its potential for clinical use. The study demonstrates the importance of independent external validation of AI models. Key Points: • The ICOVAI model for prediction of CO-RADS

Objective Although the role of artificial intelligence (AI) in medicine is increasingly studied, most patients do not benefit because the majority of AI models remain in the testing and prototyping environment. The development and implementation trajectory of clinical AI models are complex and a structured overview is missing. We therefore propose a step-by-step overview to enhance clinicians' understanding and to promote quality of medical AI research. Methods We summarised key elements (such as current guidelines, challenges, regulatory documents and good practices) that are needed to develop and safely implement AI in medicine. Conclusion This overview complements other frameworks in a way that it is accessible to stakeholders without prior AI knowledge and as such provides a step-by-step approach incorporating all the key elements and current guidelines that are essential for implementation, and can thereby help to move AI from bytes to bedside.