RESUMO
PURPOSE: Thyroid cancer is one of the most common cancers worldwide, with ultrasound-guided biopsy being the method of choice for its early detection. The accuracy of diagnostics directly depends on the qualifications of the ultrasonographers, whose performance can be enhanced through training with phantoms. The aim of this study is to propose a reproducible methodology for designing a neck phantom for ultrasound training and research from widely available materials and to validate its applicability. METHODS: The phantom was made using polyvinyl chloride mixed with additives to reproduce different levels of brightness on ultrasound screens. 3D printing and casting were used to create the neck model and various structures of the neck, including bones, cartilage, arteries, veins, lymph nodes, thyroid gland, and soft tissues. The small objects, such as tumor and lymph node models, were shaped manually. All the phantom's materials were carefully selected to match the ultrasonic speed and attenuation values of real soft tissues and bones. RESULTS: The thyroid gland contains models of a cancerous and cystic nodule. In the neck, there are models of carotid arteries and jugular veins filled with ultrasound-transparent gel. Additionally, there are replicas of lymph nodes and bone structures such as hyoid bone, thyroid cartilage, trachea, and vertebrae. The resulting phantom covers the entire neck area and has been positively received by practicing ultrasound specialists. CONCLUSIONS: The proposed manufacturing technology offers a reliable and cost-effective approach to produce an anthropomorphic neck phantom for ultrasound diagnosis of the thyroid gland. The realistic simulation provided by the phantom enhances the quality and accuracy of ultrasound examinations, contributing to better training for medical professionals and improved patient care. Subsequent research efforts can concentrate on refining the fabrication process and exploring additional features to enhance the phantom's capabilities.
Assuntos
Pescoço , Imagens de Fantasmas , Neoplasias da Glândula Tireoide , Ultrassonografia , Humanos , Neoplasias da Glândula Tireoide/diagnóstico por imagem , Ultrassonografia/métodos , Pescoço/diagnóstico por imagem , Impressão Tridimensional , Desenho de Equipamento , Glândula Tireoide/diagnóstico por imagemRESUMO
Background: The integration of artificial intelligence (AI) into medicine is growing, with some experts predicting its standalone use soon. However, skepticism remains due to limited positive outcomes from independent validations. This research evaluates AI software's effectiveness in analyzing chest X-rays (CXR) to identify lung nodules, a possible lung cancer indicator. Methods: This retrospective study analyzed 7,670,212 record pairs from radiological exams conducted between 2020 and 2022 during the Moscow Computer Vision Experiment, focusing on CXR and computed tomography (CT) scans. All images were acquired during clinical routine. The final dataset comprised 100 CXR images (50 with lung nodules, 50 without), selected consecutively and based on inclusion and exclusion criteria, to evaluate the performance of all five AI-based solutions, participating in the Moscow Computer Vision Experiment and analyzing CXR. The evaluation was performed in 3 stages. In the first stage, the probability of a nodule in the lung obtained from AI services was compared with the Ground Truth (1-there is a nodule, 0-there is no nodule). In the second stage, 3 radiologists evaluated the segmentation of nodules performed by the AI services (1-nodule correctly segmented, 0-nodule incorrectly segmented or not segmented at all). In the third stage, the same radiologists additionally evaluated the classification of the nodules (1-nodule correctly segmented and classified, 0-all other cases). The results obtained in stages 2 and 3 were compared with Ground Truth, which was common to all three stages. For each stage, diagnostic accuracy metrics were calculated for each AI service. Results: Three software solutions (Celsus, Lunit INSIGHT CXR, and qXR) demonstrated diagnostic metrics that matched or surpassed the vendor specifications, and achieved the highest area under the receiver operating characteristic curve (AUC) of 0.956 [95% confidence interval (CI): 0.918 to 0.994]. However, when evaluated by three radiologists for accurate nodule segmentation and classification, all solutions performed below the vendor-declared metrics, with the highest AUC reaching 0.812 (95% CI: 0.744 to 0.879). Meanwhile, all AI services demonstrated 100% specificity at stages 2 and 3 of the study. Conclusions: To ensure the reliability and applicability of AI-based software, it is crucial to validate performance metrics using high-quality datasets and engage radiologists in the evaluation process. Developers are recommended to improve the accuracy of the underlying models before allowing the standalone use of the software for lung nodule detection. The dataset created during the study may be accessed at https://mosmed.ai/datasets/mosmeddatargogksnalichiemiotsutstviemlegochnihuzlovtipvii/.
RESUMO
We performed a multicenter external evaluation of the practical and clinical efficacy of a commercial AI algorithm for chest X-ray (CXR) analysis (Lunit INSIGHT CXR). A retrospective evaluation was performed with a multi-reader study. For a prospective evaluation, the AI model was run on CXR studies; the results were compared to the reports of 226 radiologists. In the multi-reader study, the area under the curve (AUC), sensitivity, and specificity of the AI were 0.94 (CI95%: 0.87-1.0), 0.9 (CI95%: 0.79-1.0), and 0.89 (CI95%: 0.79-0.98); the AUC, sensitivity, and specificity of the radiologists were 0.97 (CI95%: 0.94-1.0), 0.9 (CI95%: 0.79-1.0), and 0.95 (CI95%: 0.89-1.0). In most regions of the ROC curve, the AI performed a little worse or at the same level as an average human reader. The McNemar test showed no statistically significant differences between AI and radiologists. In the prospective study with 4752 cases, the AUC, sensitivity, and specificity of the AI were 0.84 (CI95%: 0.82-0.86), 0.77 (CI95%: 0.73-0.80), and 0.81 (CI95%: 0.80-0.82). Lower accuracy values obtained during the prospective validation were mainly associated with false-positive findings considered by experts to be clinically insignificant and the false-negative omission of human-reported "opacity", "nodule", and calcification. In a large-scale prospective validation of the commercial AI algorithm in clinical practice, lower sensitivity and specificity values were obtained compared to the prior retrospective evaluation of the data of the same population.
RESUMO
An international reader study was conducted to gauge an average diagnostic accuracy of radiologists interpreting chest X-ray images, including those from fluorography and mammography, and establish requirements for stand-alone radiological artificial intelligence (AI) models. The retrospective studies in the datasets were labelled as containing or not containing target pathological findings based on a consensus of two experienced radiologists, and the results of a laboratory test and follow-up examination, where applicable. A total of 204 radiologists from 11 countries with various experience performed an assessment of the dataset with a 5-point Likert scale via a web platform. Eight commercial radiological AI models analyzed the same dataset. The AI AUROC was 0.87 (95% CI:0.83-0.9) versus 0.96 (95% CI 0.94-0.97) for radiologists. The sensitivity and specificity of AI versus radiologists were 0.71 (95% CI 0.64-0.78) versus 0.91 (95% CI 0.86-0.95) and 0.93 (95% CI 0.89-0.96) versus 0.9 (95% CI 0.85-0.94) for AI. The overall diagnostic accuracy of radiologists was superior to AI for chest X-ray and mammography. However, the accuracy of AI was noninferior to the least experienced radiologists for mammography and fluorography, and to all radiologists for chest X-ray. Therefore, an AI-based first reading could be recommended to reduce the workload burden of radiologists for the most common radiological studies such as chest X-ray and mammography.
RESUMO
PURPOSE: replicability and generalizability of medical AI are the recognized challenges that hinder a broad AI deployment in clinical practice. Pulmonary nodes detection and characterization based on chest CT images is one of the demanded use cases for automatization by means of AI, and multiple AI solutions addressing this task are becoming available. Here, we evaluated and compared the performance of several commercially available radiological AI with the same clinical task on the same external datasets acquired before and during the pandemic of COVID-19. APPROACH: 5 commercially available AI models for pulmonary nodule detection were tested on two external datasets labelled by experts according to the intended clinical task. Dataset1 was acquired before the pandemic and did not contain radiological signs of COVID-19; dataset2 was collected during the pandemic and did contain radiological signs of COVID-19. ROC-analysis was applied separately for the dataset1 and dataset2 to select probability thresholds for each dataset separately. AUROC, sensitivity and specificity metrics were used to assess and compare the results of AI performance. RESULTS: Statistically significant differences in AUROC values were observed between the AI models for the dataset1. Whereas for the dataset2 the differences of AUROC values became statistically insignificant. Sensitivity and specificity differed statistically significantly between the AI models for the dataset1. This difference was insignificant for the dataset2 when we applied the probability threshold initially selected for the dataset1. An update of the probability threshold based on the dataset2 created statistically significant differences of sensitivity and specificity between AI models for the dataset2. For 3 out of 5 AI models, the update of the probability threshold was valuable to compensate for the degradation of AI model performances with the population shift caused by the pandemic. CONCLUSIONS: Population shift in the data is able to deteriorate differences of AI models performance. Update of the probability threshold together with the population shift seems to be valuable to preserve AI models performance without retraining them.
Assuntos
COVID-19 , Radiologia , Humanos , Pandemias , COVID-19/diagnóstico por imagem , COVID-19/epidemiologia , Radiografia , Tomografia Computadorizada por Raios XRESUMO
RATIONALE AND OBJECTIVES: Post-COVID condition (PCC) is associated with long-term neuropsychiatric symptoms. Magnetic resonance imaging (MRI) in PCC examines the brain metabolism, connectivity, and morphometry. Such techniques are not easily available in routine practice. We conducted a scoping review to determine what is known about the routine MRI findings in PCC patients. MATERIALS AND METHODS: The PubMed database was searched up to 11 April 2023. We included cohort, cross-sectional, and before-after studies in English. Articles with only advanced MRI sequences (DTI, fMRI, VBM, PWI, ASL), preprints, and case reports were excluded. The National Heart, Lung, and Blood Institute and PRISMA Extension tools were used for quality assurance. RESULTS: A total of 7 citations out of 167 were included. The total sample size was 451 patients (average age 51 ± 8 years; 67% female). Five studies followed a single recovering cohort, while two studies compared findings between two severity groups. The MRI findings were perivascular spaces (47%), microbleeds (27%) and white matter lesions (10%). All the studies agreed that PCC manifestations are not associated with specific MRI findings. CONCLUSION: The results of the included studies are heterogeneous due to the low agreement on the types of MRI abnormalities in PCC. Our findings indicate that the routine brain MRI protocol has little value for long COVID diagnostics.
RESUMO
In this review, we focused on the applicability of artificial intelligence (AI) for opportunistic abdominal aortic aneurysm (AAA) detection in computed tomography (CT). We used the academic search system PubMed as the primary source for the literature search and Google Scholar as a supplementary source of evidence. We searched through 2 February 2022. All studies on automated AAA detection or segmentation in noncontrast abdominal CT were included. For bias assessment, we developed and used an adapted version of the QUADAS-2 checklist. We included eight studies with 355 cases, of which 273 (77%) contained AAA. The highest risk of bias and level of applicability concerns were observed for the "patient selection" domain, due to the 100% pathology rate in the majority (75%) of the studies. The mean sensitivity value was 95% (95% CI 100-87%), the mean specificity value was 96.6% (95% CI 100-75.7%), and the mean accuracy value was 95.2% (95% CI 100-54.5%). Half of the included studies performed diagnostic accuracy estimation, with only one study having data on all diagnostic accuracy metrics. Therefore, we conducted a narrative synthesis. Our findings indicate high study heterogeneity, requiring further research with balanced noncontrast CT datasets and adherence to reporting standards in order to validate the high sensitivity value obtained.
RESUMO
Patients with advanced malignant tumors, including both jaws, is a challenging task for a head and neck surgeon. Current treatment landscape demonstrates good functional, anatomical, and aesthetic results in patients who could previously receive only palliative care. The extensive tissue defects resulting from oncological resections in the head and neck region require immediate reconstruction due to the exposure of vital structures and their contact with the external environment. A patient was operated using a three-team multidisciplinary approach involving simultaneous work of three specialized teams of maxillofacial and reconstructive microsurgeons, as well as an implantologist and a prosthodontist. This approach allowed simultaneous tumor resection with subsequent reconstruction of the intraoperative defect involving bilateral harvesting of two revascularized free fibular osteomusculocutaneous flaps with dental implantation and simultaneous rehabilitation of dentition with crowns.
RESUMO
Compositions and technology for obtaining a photocatalytic composite material (PCM) by deposition of titanium dioxide particles synthesized by the sol-gel method on a silica support of various types (microsilica, gaize and diatomite) have been developed. The properties (chemical and mineral composition, dispersion, specific surface area, porosity, ζ-potential, acid-base properties, and microstructure) of microsilica, gaize and diatomite were studied to assess the effectiveness of using a photocatalytic agent as a carrier. In terms of specific viscosity (ηsp = 45), the concentration of the precursor (tetrabutoxytitanium-TBT) is set at 22 vol. % in a solvent (ethanol), at which it is possible to obtain the maximum amount of dissolved film oligomer without the formation of an aggregate-like precipitate. Modification of the reaction mixture (precursor: ethanol = 1:3) by replacing part of the solvent with a Span-60 surfactant/TBT = 1-1.1 made it possible to obtain polydisperse titanium dioxide particles with peak sizes of 43 nm and 690 nm according to laser granulometry data. Taking into account the interaction of titanium complexes with the surface of a silica support, a phenomenological model of the processes of structure formation of a photocatalytic composite material is proposed. By the value of the decomposition of rhodamine B, the photocatalytic activity of the developed composite materials was determined: PCM based on diatomite-86%; PCM based on microsilica-85%; PCM based on gaize-57%.
RESUMO
Concrete is the most common building material; therefore, when designing structures, it is obligatory to consider all structural parameters and design characteristics such as acoustic properties. In particular, this is to ensure comfortable living conditions for people in residential premises, including acoustic comfort. Different types of concrete behave differently as a sound conductor; especially dense mixtures are superior sound reflectors, and light ones are sound absorbers. It is found that the level of sound reflection in modified concrete is highly dependent on the type of aggregates, size and distribution of pores, and changes in concrete mix design constituents. The sound absorption of acoustic insulation concrete (AIC) can be improved by forming open pores in concrete matrices by either using a porous aggregate or foam agent. To this end, this article reviews the noise and sound transmission in buildings, types of acoustic insulating materials, and the AIC properties. This literature study also provides a critical review on the type of concretes, the acoustic insulation of buildings and their components, the assessment of sound insulation of structures, as well as synopsizes the research development trends to generate comprehensive insights into the potential applications of AIC as applicable material to mitigate noise pollution for increase productivity, health, and well-being.
RESUMO
The huge demand for concrete is predicted to upsurge due to rapid construction developments. Environmental worries regarding the large amounts of carbon dioxide emanations from cement production have resulted in new ideas to develop supplemental cementing materials, aiming to decrease the cement volume required for making concrete. Palm-oil-fuel-ash (POFA) is an industrial byproduct derived from palm oil waste's incineration in power plants' electricity generation. POFA has high pozzolanic characteristics. It is highly reactive and exhibits satisfactory micro-filling ability and unique properties. POFA is commonly used as a partially-alternated binder to Portland cement materials to make POFA-based eco-efficient concrete to build building using a green material. This paper presents a review of the material source, chemical composition, clean production and short-term properties of POFA. A review of related literature provides comprehensive insights into the potential application of POFA-based eco-efficient concrete in the construction industry today.
RESUMO
Quartz sandstone (QS) is a mine waste; therefore, its use in construction allows for both reducing the cost of the concrete and contributing to the utilization of waste. The scientific originality of this study is the identification of models of the effect of QS aggregate on the physicomechanical, durability characteristics, and eco-safety of greener high-strength concrete. The study used an energy-efficient method of non-thermal effects of electromagnetic pulses on the destruction mechanisms of quartz-containing raw materials. The characteristics of quartzite sandstone aggregates, including the natural activity of radionuclides, were comprehensively studied. The features of concrete hardening, including the formation of an interfacial transition zone between the aggregate and the cement matrix, were studied, taking into account the chemical and morphological features of quartzite sandstone. In addition, the microstructural and morphological properties of concrete were determined after a 28 day curing. In this study, the behaviors of the concrete with QS aggregate were investigated, bearing in mind the provisions of geomimetics science on the affinity of structures. The results obtained showed that the QS aggregate had the activity of natural radionuclides 3-4 times lower compared to traditional aggregates. Efficient greener concrete with a 46.3 MPa compressive strength, water permeability grade W14, and freeze-thaw resistance of 300 cycles were also obtained, demonstrating that the performance of this greener concrete was comparable to that of traditional concrete with more expensive granite or gabbro diabase aggregates.