Features
Nodule detection*
Longitudinal tracking
Volumetric segmentation
Lung-RADS
Open. Review. Confirm. Report. It's that easy.
Automatic detection* of solid, part solid, and ground glass nodules. Our interactive workflow allows the user to add, edit, or delete detections with automatic updates to quantitative information.
*Detection is for Research use only in US
Automatically assess each lesion's evolution over time.
Whether you have one or many studies to compare, Arterys has your back. Automatically track nodules over time with tabular and graphical progression.
Volumetric segmentation of nodules
With the Arterys Lung AI application, precise volumetric segmentation of lung nodules is available automatically for both detected and user found nodules. Deep Learning reduces variability across analyses.
Built-in Lung-RADS calculations
Standardize reporting of screening exams using the integrated Lung-RADS workflow. Share and communicate results effectively with patients and among colleagues. Arterys Lung AI supports Lung-RADS versions 1.0 and 1.1, as well as linear and volumetric measurements.
Arterys Lung AI is your partner in chest CT analysis. We support the tedious, time consuming portions of your workflow with automation so that you can focus on the parts that matter.
Intended Use
Arterys MICA includes an optional Oncology AI module which provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations. It is a tool used to support the oncological workflow by helping the user confirm the absence or presence of lesions, including evaluation, quantification, follow-up, and documentation of any such lesions.
Arterys MICA software is intended to be used as a support tool by trained healthcare professionals to aid in diagnosis. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.
Limitations
The nodule detection and segmentation algorithms are optimized for Low Dose CT. However, the algorithms will process any chest CT DICOM including regular dose CT, CAP and PA series without generating an error.
Information on training data
The lung nodule detection model was trained on 1889 lung CT scans representing >10,000 nodules. To represent an asymptomatic patient population, a blend of primarily low-dose/non-contrast screening exams and minority standard-dose/contrast incidental findings exams was used.
Model performance metrics
Standalone model performance from 240 case lung assessment validation for findings between 4 to 30mm for a 3/4 Ground Truth expert radiologist consensus level:
Sensitivity: **0.93 **_(0.90 - 0.97) _
FP/scan: **1.53 **_(1.24 - 1.84)_
Performance Curves
