Nano-x Imaging Ltd · NASDAQ:NNOX
Nano-x Imaging — Technical Presentation (February 2025)
22 slides from Nano-x Imaging's technical presentation, February 2025
Slide 1: Leveraging AI for Opportunistic Screening: Identifying Coronary Artery Calcification
Leveraging AI for Opportunistic Screening: Identifying Coronary Artery Calcification on Non-ECG Gated Lung Cancer Screening Chest CT Kevin Pham DO, Akash Dadlani MD, Ava Wexler MD, Devon Klein MD MPH
Slide 2: Disclosures
Disclosures Nanox AI provided software free of charge for the purposes of conducting this study.
Slide 3: Background
Background • Atherosclerotic cardiovascular disease (ASCVD) is prevalent in the general population and remains one of the leading causes of morbidity and mortality in the United States • Coronary artery calcium (CAC) is a highly specific feature of coronary atherosclerosis which has been shown to pr
Slide 4: Purpose
Purpose • Asymptomatic adults with intermediate to high ASCVD risk are typically screened for CAC with dedicated ECG-gated chest CT examinations • CAC can be detected incidentally on non-ECG gated chest CT studies performed for other reasons including trauma, dyspnea, and lung cancer screening • Eva
Slide 5: Current State of Risk Assessment on Non-Dedicated Exams
Current State of Risk Assessment on Non-Dedicated Exams Presence of coronary calcification may not be reported Binary reporting of presence or When reported, there is no absence standard assessment Subjective “eyeball” estimation of mild-moderate-severe
Slide 6: Examinations Across Atlantic Health System
Examinations Across Atlantic Health System Approximately 10,000 outpatient non-contrast chest CTs were performed within our health system in 2023 Of these, 3200 were low-dose chest CTs performed for lung cancer screening Utilizing Nanox AI, we can identify and report on the presence and severity of
Slide 7: Nanox AI Cardiac Solution
Nanox AI Cardiac Solution Analyzes non-contrast, non-ECG gated chest CTs Automatically measures calcified plaque • Quantifies by Agatston score • Agatston risk stratification based on total calcium score • Zero • Minimal (1-10) • Mild (11-100) • Moderate (101-400) • Severe (>400) Outputs key images
Slide 8: Nanox AI Workflow
Nanox AI Workflow Analysis Review Report Treatment Non-contrast chest CT Suspected findings is analyzed by the are presented to and Findings are Patients are directed Nanox AI algorithm reviewed by the automatically added to the appropriate interpreting to the report treatment pathway radiologist
Slide 9: Nanox AI Examination Criteria
Nanox AI Examination Criteria Inclusion Criteria Exclusion Criteria • Modality: CT • Any CT not including the entire heart • Gender: All • ECG-gated CTs • Orientation: Axial • Number of slices: <20 • Age: 30 years old and older • Series: CT Attenuation Correction, PET • Slice thickness 0.1 mm – 3.1
Slide 10: Nanox AI Sample Image
Nanox AI Sample Image Segmentation of coronary artery indicated in yellow Index bar indicates CAC quantification
Slide 11: Objective Coronary Calcium Scoring
Objective Coronary Calcium Scoring
Slide 12: Two Phase Pilot at Atlantic Health System
Two Phase Pilot at Atlantic Health System • Phase 1 – Validation Does the AI work with our population and technology? How user friendly is it? Do our results match published data? • Phase 2 – Experimental Phase Is it reproducible if we apply it to a subset of our population? What can we le
Slide 13: Phase 1: Validation
Phase 1: Validation •497 adult non-contrast, non-ECG gated chest CTs were retrospectively submitted to Nanox AI for analysis •Of these, 382 (77%) studies were successfully analyzed by the AI algorithm •In 41.6% of cases (159/382), moderate to severe disease was discovered 30.1% with CAC Score > 40
Slide 14: Phase 2: Experimental
Phase 2: Experimental •492 lung cancer screening studies were submitted for analysis by Nanox AI •87.6% (431/492) were successfully analyzed •39.7% (171/431) of patients were found to have moderate to severe disease 23.4% (101) with CAC Score > 400 (Severe) 16.2% (70) with CAC Score of 100-400 (Mo
Slide 15: Study Population Demographics
Study Population Demographics • Mean patient age = Gender Frequency Percentage 67 (SD = 5.8) Male 120 70 51 30 • Age range = 52 – 78 Female 171 100 Total
Slide 16: Chart Review
Chart Review • AI detected moderate to severe CAC burden in 39.7% (171) patients undergoing lung cancer screening with low-dose chest CT • Upon chart review, 31.0% (53) of these patients did not have a known diagnosis of coronary artery disease at the time of imaging • Known/existing coronary artery
Slide 17: Lung-RADS Score vs Known/Existing CAD at Imaging
Lung-RADS Score vs Known/Existing CAD at Imaging Known/Existing CAD at Imaging? Lung RADS No Yes Total 3 7 10 3 30% 70% 100% 2 1 3 3S 67% 33% 100% 1 5 6 4A 17% 83% 100% 2 0 2 4B 100% 0% 100% 1 0 1 4X 100% 0% 100% 9 13 22 Total 41% 59% 100%
Slide 18: Correlation Between Lung-RADS Score and Moderate-Severe CAC
Correlation Between Lung-RADS Score and Moderate-Severe CAC Lung RADS Frequency Percentage 1 31 18.1 1S 4 2.3 2 97 56.7 2S 17 9.9 3 10 5.8 3S 3 1.8 4A 6 3.5 4B 2 1.2 4X 1 0.6 Total 171 100 A Lung-RADS score of 3 or higher is considered significant 13% (22/171) of patients with moderate to severe CAC
Slide 19: Correlation Between Lung-RADS Score and Moderate-Severe CAC
Correlation Between Lung-RADS Score and Moderate-Severe CAC AI Result of Disease Lung RADS Moderate Severe Total 61 88 149 Less than 3 41% 59% 100% Greater than or 9 13 22 equal to 3 41% 59% 100% 70 101 171 Total 41% 59% 100% No significant relationship was seen between Lung-RADS Score and the prese
Slide 20: Relationship Between Gender and AI Results
Relationship Between Gender and AI Results AI Result of Disease Gender Moderate Severe Total 26 25 51 Female 51% 49% 100% 44 76 120 Male 37% 63% 100% 70 101 171 Total 41% 59% 100% Male patients undergoing lung cancer screening were found to have a higher incidence of severe CAC burden compared to fe
Slide 21: Conclusion
Conclusion • Using a commercially available AI solution, we were able to successfully identify the presence of CAD in a significant number of patients within our health system who did not previously have a known or existing CAD • Moderate to severe CAC burden was detected by AI in 41.6% and 39.7% of
Slide 22: References
References • Agatston AS, Janowitz WR, Hildner FJ, Zusmer NR, Viamonte M, Detrano R. Quantification of coronary artery calcium using ultrafast computed tomography. Journal of the American College of Cardiology. 1990;15(4):827-832. doi:10.1016/0735- 1097(90)90282-t • Greenland P, Blaha MJ, Budoff MJ,
Nano-X Imaging — Technical Presentation (February 2025) on 6ix