Chestlink – Radiology Automation

ChestLink is the first fully autonomous AI medical imaging product with a CE mark. ChestLink identifies CXRs with no abnormality and produces finalized patient reports without any intervention from the radiologist, reducing radiologist workload and enabling them to focus on cases with pathologies.

Healthy Patient Report Automation

AI autonomy in medical imaging is not driven by the technology, but by the current systematic healthcare shortcomings the platforms aim to address. It is safe to say that in developed countries the radiology departments are understaffed by 1/3. According to the World Health Organization, 2/3 of the world population does not have access to diagnostic medical imaging

of world population does not have access to radiology services
Demand for medical imaging examinations grows at a steady annual
It takes
years to train a radiologist
Depending on the type of medical institution, up to
of CXRs may feature no abnormalities

By autonomously reporting on CXRs with no abnormalities where it is highly certain of the results, ChestLink may automate from 15% to 40% of daily reporting, freeing up radiologists to report on cases that feature pathologies.

Key ChestLink features

High confidence reporting

ChestLink will only produce automated reports for chest X-rays, where it is highly confident that the images feature no abnormalities. This allows the sensitivity metric to be higher than 99%.

Accountability of operations

ChestLink analytical dashboard is an integral part of autonomous AI operations. It allows stakeholders to trace back and evaluate every case reported by the AI.

Fully GDPR Compliant

ChestLink adheres to strict privacy regulations. All identifiable data is anonymized and the platform operates onsite.

Built upon ChestEye Imaging Suite

ChestEye Quality builds upon the vanguard capabilities of the ChestEye imaging suite, which supports 75 most common radiological findings covering 90% of pathologies encountered at a medical institution on a daily basis.

Supported Findings

  1. Abnormal Rib
  2. Aortic Sclerosis
  3. Artificial Heart Valve
  4. Azygos Lobe
  5. Barium Swallow
  6. Bowel Gas
  7. Bullous Emphysema
  8. Catheter Malposition
  9. Chest Tube
  10. Congestion
  11. Consolidation
  12. CV Catheter RA Placement
  13. CV Catheter SVC Placement
  14. Cyst
  15. Dislocated Mediastinum
  16. Edema
  17. Elevated Diaphragm
  18. Endovascular Stent
  19. Enlarged Aorta
  20. Enlarged Heart
  21. Esophageal Stent
  22. Fibrosis
  23. Fissural Thickening
  24. Gastric Bubble
  25. Goitre
  26. Granuloma
  27. HD Catheter RA Placement
  28. HD Catheter SVC Placement
  29. Hernia
  30. Hilar Prominence
  31. Hypertension
  32. Hypoventilation
  33. Interstitial Markings
  34. Intra Aortic Balloon
  35. Intubation
  36. Intubation Malposition
  37. Kyphosis
  38. Ligament Ossification
  39. Linear Atelectasis
  40. Lobar Collapse
  41. Loculated Effusion
  42. Lymph Node Calcification
  43. Lymphadenopathy
  44. Mass
  45. Nasogastric Tube
  46. Osteoporosis
  47. Pacemaker
  48. Pericardial Effusion
  49. Pleural Adhesion
  50. Pleural Effusion
  51. Pleural Plaque
  52. Pleural Thickening
  53. Pneumomediastinum
  54. Pneumoperitoneum
  55. Pneumothorax
  56. Pulmonary Cavity
  57. Pulmonary Emphysema
  58. Removed Lung
  59. Respiratory Distress Syndrome
  60. Retrosternal Airspace Obliteration
  61. Rib Resection
  62. Sarcoidosis
  63. Scoliosis
  64. Spinal Compression Fracture
  65. Spinal Degenerative Changes
  66. Spinal Enthesopathy
  67. Spinal Implant
  68. Spondylosis
  69. Sternal Wires
  70. Subcutaneous Emphysema
  71. Thymus
  72. Tracheal Stent
  73. Tuberculosis
  74. Ventricular Assist Device
  75. Widened Mediastinum