Want to learn more about Lunit AI Solutions? Let’s connect! Contact Us

logo-cxr

AI Solution for Chest X-ray

ce_white

Proven accuracy leading to complete efficiency

cxt-icon

Want an interactive way
to try our AI?

Test yourself with our
INSIGHT Challenge!

97-99% AUC

Lunit INSIGHT CXR detects 11 abnormal radiologic findings (also supports tuberculosis screening), enabling identification of 45 different diagnoses.

Nodule
Consolidation
Pneumothorax
Pleural effusion
Atelectasis
Pneumoperitoneum
Cardiomegaly
Mediastinal widening
Calcification
Fibrosis
Supports tuberculosis screening
[New] Acute bone fracture*

* Available for Lunit INSIGHT CXR4 version.

slide

Global partnership

fujifilm_fit

[New] Launching Lunit INSIGHT CXR 4
powered by DualScan System

Lunit INSIGHT CXR 4 is a first-in-class chest X-ray solution built on proprietary DualScan System. It supports faster and more accurate
diagnosis, workload, and helps prevent burnout, especially critical in today's overburdened radiology environments.

DualScan System : An advanced AI architecture that combines two engines, one for detecting clinically relevant abnormalities and
another for flagging normal cases
, to deliver unparalleled accuracy and workflow efficiency.

Normal
flagging

uihc-img-1

Save time and optimize efficiency with normal flagging and automated normal report generation, allowing you to focus on timely reporting of more complex cases.

Acute bone
fracture

uihc-img-2

Improve diagnostic confidence with AI support for detecting subtle, easily overlooked fractures in the ribs, clavicle, scapula, and humerus.

Current-prior
comparison

uihc-img-3

Quickly detect changes by comparing current and prior CXRs, now with automated nodule progression tracking.
(Currently available for pneumothorax, pleural effusion, nodule, and consolidation.)

Lunit INSIGHT CXR
user testimonial

Features

Workload reduction

Lunit AI identifies normal CXRs with high accuracy, enabling radiologists to focus on more complex cases.

Lunit INSIGHT CXR leads to a 36.2% reduction in workload by correctly identifying about 92.3% of normal CXRs, while also detecting about 95% of urgent/critical findings.¹

* This study was conducted based on CXR3.


1. Schalekamp et al,. Performance of AI to Exclude Normal Chest Radiographs to
Reduce Radiologists’ Workload. Published in European Radiology, 2024.

Improved performance across specialties

Lunit INSIGHT CXR supports both radiologists and non-radiologists in achieving more accurate, efficient interpretations.²

<AUC comparison without and with Lunit AI, stratified by specialty and pathology>

Read clinical evidence

2. Shah et al,. Does AI Assistance Improve Clinician Interpretation of Inpatient and Emergency Department Chest X-Rays?. abstract presented at RSNA 2024

50% of lung cancer patients can be diagnosed earlier

Lunit INSIGHT CXR successfully analyzed the chest X-ray image of a 54-year-old male partient, detecting lung cancer 3 years prior to when it was diagnosed

  • 2013
  • 2014
  • 2015
  • 2016

Seamless integration

Regardless of your system, location, or environment, Lunit INSIGHT CXR will be seamlessly integrated into your existing workflow, transforming your reading experience.

chart-c-en-xl

Publication

  1. Ju Gang Nam, Minchul Kim, et al. Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs. European Respiratory Journal. 2020
  2. Sowon Jang, Hwayoung Song, et al. Deep learning–based automatic detection algorithm for reducing overlooked lung cancers on chest radiographs. Radiology. 2020
Product manual download

Only verified users can access the product manual

Publications featuring

The publications listed below are not subject to the review of medical device advertising and are intended to showcase Lunit’s technology.

No Data

Learn more about Lunit INSIGHT CXR

What do the medical journals say about AI-powered chest x-ray?

Watch the animated video about Lunit INSIGHT CXR featured in peer-reviewed journals

Lunit INSIGHT MMG

Computer-Aided Detection / Diagnosis Software for Mammography

Publication

Making data-driven medicine a reality