ClariPulmo

Clari Pi
ClariPulmo Model Card
Product Details
Model Identifier
Manufacturer
Clari Pi
Product
ClariPulmo
Version
Unknown
Date Cleared
04/06/2022
FDA Submission No.
Category
MIMPS
Model Characteristics
Inclusion Criteria
Lung CT
Exclusion Criteria
Unknown
Instructions for Use
Not available
Indications for Use
Indication of Use
ClariPulmo is a non-invasive image analysis software for use with CT images which is intended to support the quantification of lung CT images. The software is designed to support the physician in the diagnosis and documentation of pulmonary tissue images (e.g., abnormalities) from the CT thoracic datasets. (The software is not intended for the diagnosis of pneumonia or COVID-19). The software provides automated segmentation of the lungs and quantification of low-attenuation and high-attenuation areas within the segmented lungs by using predefined Hounsfield unit thresholds. The software displays by color the segmented lungs and analysis results. ClariPulmo provides optional denoising and kernel normalization functions for improved quantification of lung CT images in cases when CT images were taken at low-dose conditions or with sharp reconstruction kernels.
Intended User
Physician
Age
Adult
Anatomy
Chest
Modality
CT
Output
? LAA Analysis provides quantitative measurement of pulmonary tissue image with low attenuation areas (LAA). LAA are measured by counting those voxels with low attenuation values under the user-predefined thresholds within the segmented lungs. This feature supports the physician in quantifying lung tissue image with low attenuation area. ? HAA Analysis provides quantitative measurement of pulmonary tissue image with high attenuation areas (HAA). HAA are measured by counting those voxels with high attenuation values using the user-predefined thresholds within the segmented lungs. This feature supports the physician in quantifying lung tissue image with high attenuation area. ? Lungs are automatically segmented using a pre-trained deep learning model. ? The optional Kernel Normalization function provides an image-to-image translation from a sharp kernel image to a smooth kernel image for improved quantification of lung CT images. The Kernel Normalization algorithm was constructed based on the U-Net architecture. ? The optional Denoising function provides an image-to-image translation from a noisy lowdose image to a noise-reduced enhanced quality image of LDCT for improved quantification of lung LDCT images. The Denoising algorithm was constructed based on the U-Net architecture.
Details on Training Data Sets
Details on Training Data Sets
No. of Cases
Unknown
Age Range (Years)
Unknown
Sex (%)
  • Female: Unknown
  • Male: Unknown
  • Unknown: Unknown
Output
Unknown
Race (%)
  • White: Unknown
  • Black or African American: Unknown
  • American Indian or Alaska Native: Unknown
  • Asian: Unknown
  • Native Hawaiian or Other Pacific Islander: Unknown
  • Unknown: Unknown
Ethnicity (%)
  • Hispanic or Latino: Unknown
  • Not Hispanic or Latino: Unknown
  • Unknown: Unknown
Geographic Region (%)
  • USA: Unknown
  • International: Unknown
  • Unknown: Unknown
Scanner Manufacturer(s)
Unknown
Scanner Model(s)
Unknown
Model Performance
Study Type
Performance Testing Type
Stand-Alone Performance
Standalone Model Performance
Reference Standard (Ground Truth)
Unknown
No. of Cases
Unknown
Age Range (Years)
Unknown
Sex (%)
  • Female: Unknown
  • Male: Unknown
  • Unknown: Unknown
Race (%)
  • White: Unknown
  • Black or African American: Unknown
  • American Indian or Alaska Native: Unknown
  • Asian: Unknown
  • Native Hawaiian or Other Pacific Islander: Unknown
  • Unknown: Unknown
Ethnicity (%)
  • Hispanic or Latino: Unknown
  • Not Hispanic or Latino: Unknown
  • Unknown: Unknown
Geographic Region (%)
  • USA: Unknown
  • International: Unknown
  • Unknown: Unknown
Output
Unknown
Scanner Manufacturer(s)
Unknown
Scanner Model(s)
Unknown
No. of Sites
Unknown
Model Accuracy
Unknown
Model Sensitivity
Not provided
Model Specificity
Not provided
Reader Study Performance
No. of Readers
N/A
No. of Cases
N/A
No. of Sites
N/A
Output
N/A
Age Range (Years)
N/A
Sex (%)
  • Female: N/A
  • Male: N/A
  • Unknown: N/A
Race (%)
  • White: N/A
  • Black or African American: N/A
  • American Indian or Alaska Native: N/A
  • Asian: N/A
  • Native Hawaiian or Other Pacific Islander: N/A
  • Unknown: N/A
Ethnicity (%)
  • Hispanic or Latino: N/A
  • Not Hispanic or Latino: N/A
  • Unknown: N/A
Geographic Region (%)
  • USA: N/A
  • International: N/A
  • Unknown: N/A
Scanner Manufacturer(s)
N/A
Scanner Model(s)
N/A
Model Accuracy
N/A
Model Sensitivity
N/A
Model Specificity
N/A
Model Limitations, Warnings, & Precautions
Model Limitations, Warnings, & Precautions
Supported Scanner Manufacturer(s)
All
Slice Thickness
Unknown
Contrast Use
Unknown
MRI Field Strength
Unknown
Reconstruction Kernel Used
Unknown
Alternative Choices
Alternative Choices
Previous Version(s)
Unknown
Contact Information
Contact Information
Point of Contact Name
Unknown
Email
Unknown
Additional Details
Related Use Cases
Unknown
All Products And Platforms from Clari Pi