Lunit Logo

Product

Explore our Products

흉부 X선 영상 분석 AI

Insight CXR

유방촬영술 영상 분석 AI

Insight MMG

조직 슬라이드 영상 분석 AI

Insight SCOPE
CE Mark
Lunit INSIGHT CXR3 logo

For 10 Radiologic Findings

Atelectasis, Calcification, Cardiomegaly, Consolidation, Fibrosis, Mediastinal Widening, Nodule, Pleural Effusion, Pneumoperitoneum, Pneumothorax

Lunit INSIGHT CXR3 capture

Background

Chest radiography is one of the most basic and fundamental diagnostic tests used in medicine, accounting for 25% of the annual total numbers of diagnostic imaging procedures.1 It has been shown that radiologic information changed clinical practice in more than 60% of those who received chest radiography.2,3 Unfortunately, miss rates for proper interpretation of chest radiographs go as high as 30% even for experts,4,5 leading to increased mortality from treatable diseases.6 Moreover, the interpretive performance of chest radiographs differ significantly between specialists and non-specialists, up to 30%.7-9 Additionally, 10% of chest radiographs are reported to be held back for 30 days until the final report is issued, and only 60% of radiographs are reported by radiologists due to overflowing number of cases to interpret.10 Improvement in the radiology workflow and efficiency can greatly alleviate the burden.

Product description

Developed using Lunit’s cutting-edge deep learning technology,11-14 which has been validated through publications in numerous major publications such as Radiology,15-16 Scientific Reports,17 Clinical Infectious Diseases18 and more, Lunit INSIGHT CXR 3 accurately detects 10 of the most common findings in a chest x-ray, which includes atelectasis, calcification, cardiomegaly, consolidation, fibrosis, mediastinal widening, nodule, pleural effusion, pneumoperitoneum, and pneumothorax. The AI solution generates (1) location information of detected lesions in the form of heatmaps, (2) abnormality scores reflecting the probability that the detected lesion is abnormal, and (3) an AI “case report” that summarizes the analysis result by each finding. The solution is indicated to be directly involved in the primary interpretation process of radiologists or clinicians.

Primary value proposition

  • Prevent difficult cases of chest abnormalities from being missed upon reading chest radiographs.
  • Help physicians make early diagnosis of chest abnormalities in chest radiographs.
  • Increases workflow efficiency in interpretation through decreasing reading time by 34%.
  • Trained to individually detect and locate 10 different radiologic findings
  • The user can customize detectable findings and its visualization method according to user clinical environment
  • Automatically generates case report which includes analysis of each radiologic findings and its location information
  • Provides TB screening AI score to identify tuberculosis on the chest radiograph

Training & Validation

  • Trained with a large-scale (>200,000 cases), high-quality (clinically/CT-proven cases) training set.
  • Demonstrated to perform at a standalone accuracy of 97-99% in ROC AUC.19
  • Certified with CE Mark and approved by Korea MFDS.
  • Currently in preparation for regulatory approval in various markets worldwide, including FDA.

Example cases

example case1example case1example case1

Case 1 : Subtle consolidation, diagnosed as pneumonia, is properly detected in the right lower zone, with an abnormality score of 29%.

example case2example case2example case2

Case 2 : Multiple subsegmental atelectasis is in both lungs with pleural effusion.

example case3example case3example case3

Case 3 : Free air is present under the right diaphragm, pneumoperitoneum.

Journals & Conference
Abstracts

  • Hwang EJ, Nam JG, et al. Deep Learning for Chest Radiograph Diagnosis in the Emergency Department, Radiology 2019
  • Hwang EJ, Park SG, et al. Development and Validation of a Deep Learning–Based Automated Detection Algorithm for Major Thoracic Diseases on Chest Radiographs, JAMA Network Open 2019
  • Hwang EJ, Park SG, et al. Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs, Clinical Infectious Diseases 2019
  • Nam JG, Park SG, et al. Development and Validation of Deep Learning-Based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs, Radiology 2018 (in press)
  • Development and Validation of a Deep Learning-Based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs, RSNA 2018
  • Multi-Stage Deep Disassembling Networks for Generating Bone-Only and Tissue-Only Images from Chest Radiographs Performance Validation of a Deep Learning-Based Automatic, RSNA 2018
  • Detection Algorithm for Major Thoracic Abnormalities on Chest Radiographs, RSNA 2018
  • Deep Learning-Based Automatic Detection Algorithm for the Detection of Major Thoracic Abnormalities on Chest Radiographs, RSNA 2018
  • Automatic Detection of Malignant Pulmonary Nodules on Chest Radiographs Using a Deep Convolutional Neural Network: Detection Performance and Comparison with Human Experts, RSNA 2017
  • Deep Learning-based Automatic Detection Algorithm for the Detection of Malignant Pulmonary Nodules on Chest Radiographs, RSNA 2017

References

1Radiation UNSCotEoA. Sources and effects of ionizing radiation: sources: United Nations Publications; 2000.

2 Geijer M, Ivarsson L, Göthlin JH. A retrospective analysis of the clinical impact of 939 chest radiographs using the medical records. Radiol Res Pract 2012;2012.

3 Speets AM, van der Graaf Y, Hoes AW, et al. Chest radiography in general practice: indications, diagnostic yield and consequences for patient management. Br J Gen Pract 2006;56:574-8.

4 Quekel LG, Kessels AG, Goei R, van Engelshoven JM. Miss rate of lung cancer on the chest radiograph in clinical practice. Chest 1999;115:720-4.

5 Forrest JV, Friedman PJ. Radiologic errors in patients with lung cancer. Wes J Med 1981;134:485.

6 Kesselman A, Soroosh G, Mollura DJ, et al. 2015 RAD-AID Conference on International Radiology for Developing Countries: the evolving global radiology landscape. J Am Coll Radiol 2016;13:1139-44.

7 Monnier-Cholley L, Carrat F, Cholley BP, Tubiana J-M, Arrivé L. Detection of lung cancer on radiographs: receiver operating characteristic analyses of radiologists’, pulmonologists’, and anesthesiologists’ performance. Radiology 2004;233:799-805.

8 Eng J, Mysko WK, Weller GE, et al. Interpretation of emergency department radiographs: a comparison of emergency medicine physicians with radiologists, residents with faculty, and film with digital display. Am J Roentgenol 2000;175:1233-8.

9 Potchen EJ, Cooper TG, Sierra AE, et al. Measuring performance in chest radiography. Radiology 2000;217:456-9.

10 Milner RC, Culpan G, Snaith B.Radiographer reporting in the UK: is the current scope of practice limiting plain-film reporting capacity? Br J Radiol. 2016 Sep;89(1065):20160228. doi:

11 Lunit’s high-end deep learning technology has been demonstrated in various international competitions - won World #1 in MICCAI TUPAC 2016, and CAMELYON 2017; Recognized as one of the world's top 100 AI startups by CB Insights in 2017 & 150 Digital Health companies in 2019

12 D.G. Yoo et al. Learning Loss for Active Learning. CVPR 2019

13 H.J. Lee et al. SRM: A Style-based Recalibration Module for Convolutional Neural Networks. ICCV 2019

14 H.S. Nam et al. Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks. NIPS 2018

15 E.J. Hwang et al. Deep Learning for Chest Radiograph Diagnosis in the Emergency Department, Radiology 2019; 00:1–8

16 Nam JG, Park SG, et al. Development and Validation of Deep Learning-Based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs, Radiology 2018

17 E.J. Hwang et al. Kim, E., Kim, H., Han, K. et al. Applying Data-driven Imaging Biomarker in Mammography for Breast Cancer Screening: Preliminary Study. Sci Rep 8, 2762 (2018)

18 E.J. Hwang et al. Development and Validation of a Deep Learning–based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs. Clinical Infectious Diseases, Volume 69, Issue 5, 1 September 2019, Pages 739–747

19 ROC AUC Area Under the Receiver Operating Characteristic Curve