pulmoinsight™️ -最新凯时注册

ai-aided analysis system based on ct images of pulmonary nodules

disease background

lung cancer ranks first in the number of new cases and the number of deaths

828,000 new cases of lung cancer and 657,000 of deaths from lung cancer^[1].
the 5-year survival rate is above 90% for earlystage lung cancer and less than 10% for late stages.

medical imaging ai is expected to become a powerful assistant in the imaging evaluation of pulmonary nodules

imaging diagnosis talent resources are in short supply.
it takes a long time for radiologists to read images, and the efficiency of reading needs to be improved.
there are errors in traditional qualitative analysis, and many small quantitative changes are difficult to judge with the naked eye.

product advantages

95
%

detectable rate
87.4
%

accuracy
30
s

automatic analysis

identification

accurate detection of pulmonary nodules
monitoring

intelligent and precise tracking, and dynamic follow-up assessment of pulmonary nodule lesions
insight

accurately discriminating between benign and malignant pulmonary nodules
algorithm

accurate, automatic and quantitative analysis of image indicators (size, density, etc.)

professional certification

large-scale sample size for modeling and validation; excellent performance in assessment of pulmonary nodules

training and validation of model based on preoperative ct images data of pulmonary nodule from more than 20,000 of pathologically confirmed cases. accurately outline the lesion in seconds, and the volume calculation is accurate to 0.001 mm³.

target users

patients with pulmonary nodules
people at a high risk of lung cancer who undergo ldct/ct screening

sample collection and service process

sample collection

ct-dicom data

service process

test
counseling
ct-dicom
data upload
testing
and analysis
report
issuance
report
interpretation

references

[1] report of cancer epidemiology in china, 2015. chinese journal of oncology, 2019;41(1).