A View LCS

AVIEW LCS is an image processing software designed for comprehensive analysis of thoracic CT scans, utilizing semi-automatic tools, deep-learning segmentation, and CAD integration to detect and characterize lung nodules. The system quantifies nodule attributes including size, volume, density, growth (VDT), assigns Lung-RADS categories, calculates PANCAN malignancy risk, and incorporates CAC scores and LAA analysis for standardized reporting and longitudinal monitoring.

AVIEW LCS is an image processing software designed for the review, analysis, and reporting of thoracic CT images to characterize lung nodules across single or multiple studies. Its core methodology involves semi-automatic nodule measurement and segmentation, volumetric analysis (including major/minor axis, effective diameter, volume, Mean/Min/Max HU, and mass), and characterization of nodule type and location. The system automatically performs these measurements, integrates with Mevis CAD for automatic nodule detection, employs deep-learning algorithms for lung and lobe segmentation, and features automatic large vessel removal. It further calculates Volume Doubling Time (VDT), assigns Lung-RADS classifications, estimates malignancy risk using the PANCAN model, and provides Coronary Artery Calcification (CAC) scores and Low Attenuation Area (LAA) analysis. The software supports comprehensive follow-up through automated nodule matching and comparison, and facilitates remote access via a thin client service compatible with mobile devices and Chrome browsers, supported by a rule-based automatic processing server. AVIEW LCS generates PDF reports and saves data in DICOM format. Performance validation included software verification, unit testing, system testing (confirming no major or moderate defects), and specific performance tests for DICOM compatibility, overall performance, integration, and thin client server compatibility, all of which passed predefined criteria, demonstrating its functional reliability.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the PANCAN risk model's performance in AVIEW LCS, particularly its sensitivity and specificity for predicting malignancy, compare to established clinical risk calculators when applied to diverse patient populations encountered in lung screening programs?; What is the measurable improvement in inter-observer and intra-observer variability for nodule measurements and Lung-RADS classification when using AVIEW LCS's semi-automatic tools and deep-learning segmentation compared to manual assessment?; Can the AVIEW LCS system effectively track and characterize subtle changes in subsolid nodules over time, and how does its VDT calculation for these nodule types correlate with pathological outcomes?; Beyond integration, how does AVIEW LCS optimize or pre-process CT data for the Mevis CAD system to potentially enhance its nodule detection accuracy or reduce false positives, especially in low-dose scans?; What validation studies support the accuracy of the LAA analysis and CAC scoring features within AVIEW LCS, and how are these co-findings intended to be integrated into the overall lung nodule assessment report for clinical decision-making?