Lunit INSIGHT CXR

Lunit
Lunit INSIGHT CXR is deep learning based software that assists radiologists or clinicians in the interpretation of chest x-ray (PA/AP). The AI solution automatically detects 10 radiologic findings including atelectasis, calcification, cardiomegaly, consolidation, fibrosis, mediastinal widening, nodule, pleural effusion, pneumoperitoneum, and pneumothorax, and also supports tuberculosis screening. The analysis result contains (1) localization of suspicious areas in color or outline, (2) abnormality scores reflecting the probability that the detected lesion is abnormal, and (3) text interpretation for the analysis result by each finding.
Information source: Vendor
Last updated: Jan. 15, 2024

General Information

General
Product name Lunit INSIGHT CXR
Company Lunit
Subspeciality Chest
Modality X-ray
Disease targeted Atelectasis, calcification, cardiomegaly, consolidation, fibrosis, mediastinal widening, nodule, pleural effusion, pneumothorax, pneumoperitoneum, tuberculosis
Key-features Radiologic finding detection, abnormality score, text interpretation
Suggested use Before: adapting worklist order, flagging acute findings
During: perception aid (prompting all abnormalities/results/heatmaps), report suggestion

Technical Specifications

Data characteristics
Population Patients aged 14 years or older
Input chest PA(posterior-anterior view), chest AP(anterior-posterior view)
Input format DICOM
Output Localization (color map, grayscale map, combined map, single colormap), abnormality score for each lesion/case, binary assessment of abnormality, worklist order, draft radiology report generation
Output format DICOM Secondary Capture, DICOM GSPS (Grayscale Softcopy Presentation State), Prepopulated Report (API integration only), HL7
Technology
Integration Integration in standard reading environment (PACS), Integration via AI marketplace or distribution platform, Stand-alone third party application, Stand-alone webbased
Deployment Locally on dedicated hardware, Locally virtualized (virtual machine, docker), Cloud-based
Trigger for analysis Automatically, right after the image acquisition
Processing time 3 - 10 seconds

Regulatory

Certification
CE
Certified, Class IIa , MDR
FDA 510(k) cleared , Class II
Intended Use Statements
Intended use (according to CE)

Market

Market presence
On market since 11-2019
Distribution channels GE Healthcare (Thoracic Care Suite), Philips Healthcare, INFINITT AI Platform, FujiFilm, Agfa, CARPL.ai, Osimis, Blackford
Countries present (clinical, non-research use)
Paying clinical customers (institutes)
Research/test users (institutes)
Pricing
Pricing model
Based on

Evidence

Evidence
Peer reviewed papers on performance

  • Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction (read)

  • Effects of Implementing Artificial Intelligence-Based Computer-Aided Detection for Chest Radiographs in Daily Practice on the Rate of Referral to Chest Computed Tomography in Pulmonology Outpatient Clinic (read)

  • The impact of artificial intelligence on the reading times of radiologists for chest radiographs (read)

  • Incidentally found resectable lung cancer with the usage of artificial intelligence on chest radiographs (read)

  • AI Improves Nodule Detection on Chest Radiographs in a Health Screening Population : A Randomized Controlled Trial (read)

  • Multicentre external validation of a commercial artificial intelligence software to analyse chest radiographs in health screening environments with low disease prevalence (read)

  • Validation study of machine-learning chest radiograph software in primary and emergency medicine (read)

  • Association of Artificial Intelligence–Aided Chest Radiograph Interpretation With Reader Performance and Efficiency (read)

  • Successful Implementation of an Artificial Intelligence-Based Computer-Aided Detection System for Chest Radiography in Daily Clinical Practice (read)

  • Diagnostic performance of artifcial intelligence approved for adults for the interpretation of pediatric chest radiographs (read)

  • Deep Learning for Detecting Pneumothorax on Chest Radiographs after Needle Biopsy: Clinical Implementation (read)

  • Effect of deep learning-based assistive technology use on chest radiograph interpretation by emergency department physicians: a prospective interventional simulation-based study (read)

  • Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms (read)

  • Development and Validation of Deep Learning–based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs (read)

  • Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs (read)

  • Development and Validation of a Deep Learning–Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs (read)

  • Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems (read)

  • Deep Learning for Chest Radiograph Diagnosis in the Emergency Department (read)

  • Test-retest reproducibility of a deep learning–based automatic detection algorithm for the chest radiograph (read)

Non-peer reviewed papers on performance H Yoo, et al. Deep learning to increase lung cancer detection in chest x-rays: a retrospective cohort analysis of national lung screening trial participants. ECR. 2020
S Na, et al. On the robustness of a deep learning-based algorithm for detecting abnormalities in chest radiographs across different devices and view positions: a retrospective case-control study. ECR. 2020
JH Lee, et al. RSNA. Deep-Learning based Automated Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs: Diagnostic Performance in Systematic Screening of Asymptomatic Individuals. 2019
EJ Hwang, et al. Deep Learning Algorithm for Surveillance of Pneumothorax after Percutaneous Transthoracic Lung Biopsy: Validation in Multi-Center, Consecutive Cohorts. RSNA. 2019
M Kim, et al. Development of a Deep Learning-Based Algorithm for Independent Detection of Chest Abnormalities on Chest Radiographs. RSNA. 2019
S Park, et al. Deep Learning-Based Automatic Detection Algorithm for the Detection of Major Thoracic Abnormalities on Chest Radiographs. RSNA. 2018
EJ Hwang, et al. Performance Validation of a Deep Learning-Based Automatic Detection Algorithm for Major Thoracic Abnormalities on Chest Radiographs. RSNA. 2018
J Aum, et al. Multi-Stage Deep Disassembling Networks for Generating Bone-Only and Tissue-Only Images from Chest Radiographs. RSNA. 2018
EJ Hwang, et al. Development and Validation of a Deep Learning-Based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. RSNA. 2018
JG Nam, et al. Automatic Detection of Malignant Pulmonary Nodules on Chest Radiographs Using a Deep Convolutional Neural Network: Detection Performance and Comparison with Human Experts. RSNA. 2017
S Park, et al. Deep Learning-based Automatic Detection Algorithm for the Detection of Malignant Pulmonary Nodules on Chest Radiographs. RSNA. 2017
HJ Kim, et al. Performance Assessment of Data-driven Imaging Biomarker for Screening Pulmonary Tuberculosis on Chest Radiographs. RSNA. 2016
CM Park, et al. Deep Convolutional Neural Network Approaches in Making a Diagnosis with Chest Radiographs: Initial Experience. RSNA. 2016
Other relevant papers

  • Early user perspectives on using computer-aided detection software for interpreting chest X-ray images to enhance access and quality of care for persons with tuberculosis (read)

  • Artificial Intelligence for Assessment of Endotracheal Tube Position on Chest Radiographs: Validation in Patients From Two Institutions (read)

  • Hospital-wide survey of clinical experience with artificial intelligence applied to daily chest radiographs (read)