Computer Aided Diagnosis of Multiple Eye Fundus Diseases From Color Fundus Photograph
Study Details
Study Description
Brief Summary
Blindness can be caused by many ocular diseases, such as diabetic retinopathy, retinal vein occlusion, age-related macular degeneration, pathologic myopia and glaucoma. Without timely diagnosis and adequate medical intervention, the visual impairment can become a great burden on individuals as well as the society. It is estimated that China has 110 million patients under the attack of diabetes, 180 million patients with hypertension, 120 million patients suffering from high myopia and 200 million people over 60 years old, which suggest a huge population at the risk of blindness. Despite of this crisis in public health, our society has no more than 3,000 ophthalmologists majoring in fundus oculi disease currently. As most of them assembling in metropolitan cities, health system in this field is frail in primary hospitals. Owing to this unreasonable distribution of medical resources, providing medical service to hundreds of millions of potential patients threatened with blindness is almost impossible.
To solve this problem, this software (MCS) was developed as a computer-aided diagnosis to help junior ophthalmologists to detect 13 major retina diseases from color fundus photographs. This study has been designed to validate the safety and efficiency of this device.
| Condition or Disease | Intervention/Treatment | Phase |
|---|---|---|
|
|
Detailed Description
As a prospective clinical trial, This study enjoys multicentric, blind film reading, self-control and superiority test design. In total, 1,500 retinal fundus images from 750 individuals in need of fundus examination (one image for every single eye) were selected. Then a test group, along with a control group was set up in our study. For the test group, ophthalmologists read images with the aid of the assistant software(MCS). In contrast, the same work in the control group was finished by ophthalmologists independently. Meanwhile, the gold standard were obtained from the cooperation of senior ophthalmologists. Diagnoses of both groups were compared with those of the gold standard, thus the investigators could evaluated the safety and effectiveness of this assistant software in diagnosis.
The primary endpoint of this study is the superiority of the consistency rate of the test group. A diagnosis for an image is consistent if it gives the same negative result as the reference standard, or reveals any one condition indicated by the reference standard. The consistency rate is the rate of consistent diagnoses for all the involved images. One control group is designed, where each doctor reads and diagnoses, and give at most 3 possible conditions for each image. In the test group, doctors do the same thing with the help of this software. The investigators in the test group and control group are the same and they are chosen from ophthalmologists with 1~3 years experience. The reference standard of each fundus image is collaboratively given by retinal specialists/fellows from 5 centers. The investigator of XieHe center is the arbitrator if full consensus cannot be reached for any image during the building of reference standard.
Study Design
Arms and Interventions
| Arm | Intervention/Treatment |
|---|---|
| Test Group ophthalmologists read images applying the assistant software |
Diagnostic Test: Software assisted imaging diagnosis
In the test group, diagnoses are given with the help of the software.
|
| Control Group ophthalmologists read images independently |
Outcome Measures
Primary Outcome Measures
- consistent rate of diagnoses [through study completion, an average of 1 year]
Formula for calculation: consistent rate of diagnoses=number of images with consistent diagnosis/ total number of images × 100%. Method: the diagnoses from the test group and the control group were compared with diagnoses from the gold standard. For each image, if one or more diagnoses were consistent with those of the gold standard, which means at least one label existed in the intersection of diagnoses from the test group(or the control group)and those from the gold standard, it would be classified as "image with consistent diagnosis". Otherwise, it would be classified as "image without consistent diagnosis". After above-mentioned steps, the investigators had obtained the number of images with consistent diagnosis in each group. As images with 1-2 labels account for the majority in actual work, the investigators stipulated that each image in both groups could be marked with 3 labels at most in case of invalid improvement in consistent rate owing to multiple selections.
Secondary Outcome Measures
- sensitivity and specificity of software's diagnoses for each diseases [through study completion, an average of 1 year]
sensitivity and specificity of software's diagnoses for each diseases
- PPV and NPV of software's diagnoses for each diseases [through study completion, an average of 1 year]
PPV(Positive Predictive Value) and NPV(Negative Predictive Value) of software's diagnoses for each diseases
- full coincidence rate of software's diagnoses [through study completion, an average of 1 year]
The full consistency rate is the rate of fully consistent diagnoses in the set. A diagnosis is fully consistent it is exactly the same as the reference standard.
Eligibility Criteria
Criteria
Inclusion Criteria:
-
Age between 18 and 75.
-
Anyone need to take fundus photograph in clinical.
-
Understand the study and volunteer to sign the informed consent.
-
For fundus images of participants, the optic disc, fovea, the upper and lower vessel bow should be included in the fundus field.
Exclusion Criteria:
-
Participants has any eye that cannot take fundus photos.
-
Participants have joined or is participating in other clinical trial within one month.
-
Participants who have any other issue that cannot be enrolled.
-
Participants with cloudy refractive media that cannot take fundus photos or get clouding fundus photos.
-
Participants with low quality fundus photos like incompetent vision field, overexposed/underexposed, out of focus, too many shadow or dirties and so on.
Contacts and Locations
Locations
| Site | City | State | Country | Postal Code | |
|---|---|---|---|---|---|
| 1 | Peking Union Medical College Hospital, Chinese Academy of Medical Sciences | BeiJing | Beijing | China | 100730 |
| 2 | The Second Hospital of Hebei Medical University | Shijia Zhuang | Hebei | China | |
| 3 | West China Hospital of Sichuan University | Chengdu | Sichuan | China | |
| 4 | Tianjin Medical University Eye Hospital | Tianjin | Tianjin | China | |
| 5 | Eye Hospital, WMU Zhejiang Eye Hospital | Wenzhou | Zhejiang | China |
Sponsors and Collaborators
- Visionary Intelligence Ltd.
- Peking University First Hospital
- Beijing Municipal Science & Technology Commission
Investigators
- Study Chair: You xin Chen, PHD, Peking Union Medical College
Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- BLG-20200101