Background: One of the ways to reduce the radiation dose in CT is to improve image reconstruction algorithms. The latest offer from scanner manufacturers is Model Iterative Reconstruction (MIR). Aims: To compare the quality of visualization of the structures of the organs of the chest and to prove the effectiveness of the low-dose protocol with iterative model reconstruction. Materials and methods: A calibration phantom with a spatial resolution module and an anthropomorphic phantom of the upper body of an adult with nodules in the lungs was scanned on two CT scanners of different manufacturers using the standard dose protocol (SDCT) with algorithms of hybrid iterative reconstruction (HIR) of images and MIR and low-dose protocol (LDCT) and MIR algorithm. The quality of the obtained images was evaluated by the parameters: noise (SD), the contrast-to-noise ratio (CNR), spatial resolution and visualization of pulmonary nodules. The radiation dose was calculated according to the scanner data, the data of individual dosimeters placed on the anthropomorphic phantom, and using a dosimetric phantom. Results: The average SD was 11.5; 24.4 and 21.6; CNR 85.47; 40.6 and 45.6; spatial resolution 2 mm; 2 mm and 3 mm for SDCT with MIR, SDCT with HIR and LDCT with MIR, respectively. Visualization of pulmonary lesions remained excellent in all cases. The radiation dose in case of SDCT was 2.7, and in case of LDCT - 0.67 mSv. The dose reduction was confirmed by dosimeter data. Similar results were obtained by repeating the experiment on a second scanner. Conclusions: The average SD was 11.5; 24.4 and 21.6; CNR 85.47; 40.6 and 45.6; spatial resolution 2 mm; 2 mm and 3 mm for SDCT with MIR, SDCT with HIR and LDCT with MIR, respectively. Visualization of pulmonary lesions remained excellent in all cases. The radiation dose in case of SDCT was 2.7, and in case of LDCT - 0.67 mSv. The dose reduction was confirmed by dosimeter data. Similar results were obtained by repeating the experiment on a second scanner.
Background: Artificial intelligence (AI) technologies can help solve the significant problem of missed findings in radiology studies. An important issue is assessing the economic benefits of implementing AI. Aim: to evaluate the frequency of missed pathologies detection and the economic potential of AI technology for chest CT, validated by expert radiologists, compared with radiologists without access to AI in a private medical center. Methods: An observational, single-center retrospective study was conducted. The study included chest CTs without IV contrast performed from 01.06.2022 to 31.07.2022 in "Yauza Hospital" LLC, Moscow. The CTs were processed using a complex AI algorithm for ten pathologies: pulmonary infiltrates, typical for viral pneumonia (COVID-19 in pandemic conditions); lung nodules; pleural effusion; pulmonary emphysema; thoracic aortic dilatation; pulmonary trunk dilatation; coronary artery calcification; adrenal hyperplasia; osteoporosis (vertebral body height and density changes). Two experts analyzed CTs and compared results with AI. Further routing was determined according to clinical guidelines for all findings initially detected and missed by radiologists. The lost potential revenue (LPR) was calculated for each patient according to the hospital price list. Results: From the final 160 CTs, the AI identified 90 studies (56%) with pathologies, of which 81 studies (51%) were missing at least one pathology in the report. The "second-stage" LPR for all pathologies from 81 patients was RUB 2,847,760 ($37,251 or CNY 256,218). LPR only for those pathologies missed by radiologists but detected by AI was RUB 2,065,360 ($27,017 or CNY 185,824). Conclusion: Using AI for chest CTs as an "assistant" to the radiologist can significantly reduce the number of missed abnormalities. AI usage can bring 3.6 times more benefits compared to the standard model without AI. The use of complex AI for chest CT can be cost-effective.
Aim: A literature review of the possibilities of applying model iterative reconstruction (MIR) in computed tomography to improve image quality, including in low-dose scanning protocols.Materials and methods. The analysis of publications devoted to the application of MIR to reduce the radiation dose and improve the quality of images in CT diagnostics of lung pathology with an emphasis on the value of the achieved radiation dose was carried out.Results. The use of MIR eliminates digital noise from medical images, improving their quality. This feature can significantly reduce radiation exposure with low-dose protocols without loss of diagnostic quality. On average, application of MIR allows to reduce the radiation dose by 70% compared to a standard protocol, without increasing the noise level of CT images and maintaining the contrast-to-noise ratio. Previous studies have shown positive experience with the use of MIR in lung cancer screening programs and monitoring of cancer patients.Conclusion. The introduction of MIR in clinical practice can optimize the radiation exposure on the population without reducing the quality of CT images, however, the threshold dose to achieve a satisfactory image quality remains unexplored.
Background: Artificial intelligence (AI) technologies can help to solve the problem of missed findings in radiology studies. An important issue is assessing the economic benefits of implementing AI. Aim: to evaluate the incidence of pathologies and the economic potential of AI technology for chest CT, validated by radiologists, compared with radiologists without access to AI in a private medical centre. Methods: An observational, single-center retrospective study was conducted. The study included chest CTs without IV contrast performed from 01.06.2022 to 31.07.2022 in "YAUZA MEDICAL CENTER LLC", Moscow. The CTs were processed using a complex AI algorithm for 10 pathologies: infiltrative changes in the lungs, typical for viral pneumonia (COVID-19 in pandemic conditions); pulmonary nodules; free fluid in pleural cavities; pulmonary emphysema; increased thoracic aortic diameter; increased pulmonary artery trunk diameter; coronary calcinosis; adrenal thickness evaluation; vertebral body height and density. 2 experts analysed CTs and compared results with AI. For all findings detected and not detected by radiologists, further routing was determined, according to clinical guidelines. An under-recovery was calculated for each patient according to the hospital price list. Results: From the final 160 CTs the AI identified 90 (56%) studies with pathology, of which 81 (51%) were missing at least one pathology in the report. The "second-stage" lost profit for all pathologies from 81 patients was 2,847,760 RUB (37250.99$ or 256,217.95 CNY). The "second-stage" profit shortfall only for those pathologies that were missed by radiologists but detected by AI was RUB 2,065,360 ($27,016.57 or CNY 185,824.05). Conclusion: The use of AI for chest CTs as an assistant to the radiologist can significantly reduce the number of missed abnormalities. The use of AI can bring 3.6 times more benefit compared to the standard model without AI. The use of complex AI for chest CT can be cost-effective.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.