Software for Image Enhanced Endoscopy (IEE)
Updated:
We design software for medical imaging applications, particularly for endoscopy video processors from Olympus, Pentax and Fujinon. Nowadays technology based on narrow-band imaging, multi-band imaging, image enhancement, image filtering, color processing and virtual chromoendoscopy gives doctors opportunity to do medical diagnostics more informative and more reliable. These image enhancement techniques are intended to assist in diagnosing and further characterizing lesions in the GI tract.
Need raw sensor processing instead? See the GPU ISP for the OmniVision OH02B10 endoscopy sensor. This page is image-enhanced endoscopy (IEE) — narrow-band and multi-band enhancement.
Computed virtual chromoendoscopy enhances the contrast of the mucosal surface without the use of dyes. That imaging approach is based on narrowing the bandwidth of the conventional or HD endoscopic image or video with the aid of digital image processing. Preliminary clinical tests show that computed virtual chromoendoscopy enhances the vascular network as well as the pit pattern. This method might complement high-resolution endoscopy by facilitating the assessment of the nature and extent of gastrointestinal mucosal lesions.
During endoscopic operations the surgeon usually works without direct visual contact with the operation area and operation situs is displayed on a monitor. Currently, only hardware-based image enhancement methods are used and doctor can see either raw or image enhanced video. We have designed a software for real-time endoscopic image enhancement: conventional video endoscopy system was extended by a computer and a second monitor. Thus we show the enhanced and the original image at the same time and doctors can clearly see the results of image enhancement methods (temporal filtering, undistortion and color normalization).
Endoscopy Image Processing
How does GPU image processing help in endoscopy?
Here you can see an example of endoscopy image enhancement method
 before image enhancement |
 after image enhancement |
Software Features
- Data sources
- Pentax EPK-100, EPK-1000, EPK-i, EPK-i5000, EPK-i7000 video processors
- Olympus Evis Exera II, Evis Exera III video processors
- Fujinon EPX 4450 video processor
- DICOM, image and video files from HDD/SSD/RAID
- Input signals from any endoscopy videoprocessor or camera
- analog SD or HD video
- digital video
- video files AVI, MPEG, etc.
- captured images (BMP, TIFF, JPEG) or DICOM files
- Endoscopy image enhancement features
- color correction and normalization
- tone mapping
- noise suppression
- contrast enhancement
- local edge detection and enhancement
- blood vessels segmentation and extraction
- Computed virtual chromoendoscopy
- Software for correction of radial distortion
- RAW to DICOM converter to save uncompressed video in DICOM format
- Ability to do image enhancement in off-line for prerecorded video and DICOM files
- Endoscopy reporting software
- Compatible with Olympus, Fujinon, Pentax, Aohua, Karl Storz, etc.
- Testing software and library for Windows-10 and Linux Ubuntu
We also offer software custom design services for medical image processing applications including video endoscopy, ultrasound, ophthalmology, video nystagmography, eye-tracking, etc.
Medical imaging on GPU
- GPU Image processing for OmniVision OH0TA10, OH0FA10 and OH02B10 image sensors
- Low-latency ISP on CUDA
- Fast processing of DICOM images on CUDA
- Image processing software for retinal surgery (ophthalmology microscope)
About the author
Fyodor Serzhenko, PhD, is the founder and CEO of Fastvideo. He earned his PhD at the Moscow Institute of Physics and Technology (MIPT) in 1993. Since 2009 he has led the development of Fastvideo’s GPU-accelerated image codecs and ISP modules, including the Fastvideo SDK. Connect on LinkedIn.
Why you can trust these results
Fastvideo has built GPU-accelerated image processing software since 2009. Our codecs comply with the standards they implement — JPEG (ITU-T T.81 / ISO IEC 10918) and JPEG2000 (ITU-T T.800 / ISO IEC 15444) — and our tools are open source on GitHub. Every performance figure we publish is reproducible: see our benchmark methodology, download the Fastvideo SDK benchmark report (PDF), and measure it on your own GPU.