Aims:
Computer-aided diagnosis (CAD) is becoming a next-generation tool for the diagnosis
of human disease. CAD for colon polyps has been suggested as a particularly useful
tool for trainee colonoscopists, as the use of a CAD system avoids the complications
associated with unnecessary endoscopic resections. In addition to conventional CAD,
a convolutional neural network (CNN) system utilizing artificial intelligence (AI)
has been developing rapidly over the past 5 years. We firstly reported to generate
a unique CNN-CAD system with an AI function that studied endoscopic images extracted
from movies obtained with colonoscopes used in routine examinations (Komeda Y, Handa
H et al Oncology 2017). Here, we attempted a pilot study of this novel CNN-CAD system
for the diagnosis of colon polyps.
Methods:
A total of 92,571 images from cases of colonoscopy performed between January 2010
and December 2017 at Kindai University Hospital were used. These images were extracted
from the video of actual endoscopic examinations. They were simply diagnosed as either
an adenomatous or non-adenomatous polyp (hyperplastic polyp). The gold standard of
endoscopic diagnosis is the pathological results. The number of images used by AI
to learn to distinguish adenomatous polyp from non-adenomatous polyp (hyperplastic
polyp) was 29,572: 62,999. The size of each image was adjusted to 256 × 256 pixels.
A 10-hold cross-validation was carried out. We carried out a pilot study evaluating
the 60 cases of colonic polyp that were not learned on AI function.
Results:
The rate of diagnosis of adenomatous polyps through white-light, NBI and chromoendoscopy
observation were 97.5%, 94.8% and 90.1%, respectively. The rate of diagnosis of non-adenomatous
polyp (hyperplastic polyps) through white light, NBI and chromoendoscopy observation
were 97.9%, 96.5% and 99.5%, respectively.
Conclusions:
A CNN-CAD system using routine colonoscopy might be useful for the rapid diagnosis
of colorectal polyp classification.
