Background and Aims
Magnifying narrow-band imaging (M-NBI) is important in the diagnosis of early gastric
cancers (EGCs) but requires expertise to master. We developed a computer-aided diagnosis
(CADx) system to assist endoscopists in identifying and delineating EGCs.
Methods
We retrospectively collected and randomly selected 66 EGC M-NBI images and 60 non-cancer
M-NBI images into a training set and 61 EGC M-NBI images and 20 non-cancer M-NBI images
into a test set. After preprocessing and partition, we determined 8 gray-level co-occurrence
matrix (GLCM) features for each partitioned 40 × 40 pixel block and calculated a coefficient
of variation of 8 GLCM feature vectors. We then trained a support vector machine (SVMLv1) based on variation vectors from the training set and examined in the test set. Furthermore,
we collected 2 determined P and Q GLCM feature vectors from cancerous image blocks
containing irregular microvessels from the training set, and we trained another SVM
(SVMLv2) to delineate cancerous blocks, which were compared with expert-delineated areas
for area concordance.
Results
The diagnostic performance revealed accuracy of 96.3%, precision (positive predictive
value [PPV]) of 98.3%, recall (sensitivity) of 96.7%, and specificity of 95%, at a
rate of 0.41 ± 0.01 seconds per image. The performance of area concordance, on a block
basis, demonstrated accuracy of 73.8% ± 10.9%, precision (PPV) of 75.3% ± 20.9%, recall
(sensitivity) of 65.5% ± 19.9%, and specificity of 80.8% ± 17.1%, at a rate of 0.49
± 0.04 seconds per image.
Conclusions
This pilot study demonstrates that our CADx system has great potential in real-time
diagnosis and delineation of EGCs in M-NBI images.
Abbreviations:
CADx (computer-aided diagnosis), EGC (early gastric cancer), ESD (endoscopic submucosal dissection), GLCM (gray-level co-occurrence matrix), M-NBI (magnifying narrow-band imaging), NBI (narrow-band imaging), PPV (positive predictive value), SVM (support vector machine), SVMLv1 (level-1 SVM), SVMLv2 (level-2 SVM)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Gastrointestinal EndoscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Guidelines for the management of oesophageal and gastric cancer.Gut. 2011; 60: 1449-1472
- The diagnosis and management of gastric cancer.BMJ. 2013; 347: f6367
- Magnifying endoscopy for diagnosing and delineating early gastric cancer.Endoscopy. 2009; 41: 462-467
- Magnifying narrowband imaging is more accurate than conventional white-light imaging in diagnosis of gastric mucosal cancer.Gastroenterology. 2011; 141: 2017-2025
- Observer variability in gastric neoplasm assessment using the vessel plus surface classification for magnifying endoscopy with narrow band imaging.Clin Endosc. 2014; 47: 74-78
- Single reading with computer-aided detection for screening mammography.N Engl J Med. 2008; 359: 1675-1684
- Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy.Gastrointest Endosc. 2015; 81: 621-629
Misawa M, Kudo SE, Mori Y, et al. Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts. Int J Comput Assist Radiol Surg. Epub 2017 Feb 28.
- Computer-aided diagnosis of colorectal polyp histology by using a real-time recognition system and narrow-band imaging magnifying colonoscopy.Gastrointest Endosc. 2016; 83: 643-649
- A computer system to be used with laser-based endoscopy for quantitative diagnosis of early gastric cancer.J Clin Gastroenterol. 2015; 49: 108-115
- Hue-texture-embedded region-based model for magnifying endoscopy with narrow-band image segmentation based on visual features.Comput Methods Programs Biomed. 2017; 145: 53-66
- Towards complete and accurate reporting of studies of diagnostic accuracy: the STARD initiative.BMJ. 2003; 326: 41-44
- Japanese gastric cancer treatment guidelines 2014 (ver. 4).Gastric Cancer. 2017; 20: 1-19
- Magnifying endoscopy simple diagnostic algorithm for early gastric cancer (MESDA-G).Dig Endosc. 2016; 28: 379-393
- An investigation of the textural characteristics associated with gray level co-occurrence matrix statistical parameters.IEEE Trans Geosci Remote Sensing. 1995; 33: 293-304
- Automatic labeling of abnormal microvessels on early gastric cancer: magnifying narrow-band imaging using gray-level co-occurrence matrix and vector quantization techniques.United European Gastroenterol J. 2016; 3: A385
- Agreement, the F-measure, and reliability in information retrieval.J Am Med Inform Assoc. 2005; 12: 296-298
- Computer aided diagnosis system for automatic classification of gastric cancerous lesions in magnifying narrow-band imaging endoscopy.J Gastroenterol Hepatol. 2016; 31: 288
Lee TC, Lin YH, Uedo N, et al. Computer-aided diagnosis in endoscopy: a novel application toward automatic detection of abnormal lesions on magnifying narrow-band imaging endoscopy in the stomach. Conference Proceedings of IEEE Engineering in Medicine and Biology Society (EMBC), July 3-7, 2013:4430-3.
- Endoscopic submucosal dissection for early gastric cancer: a large-scale feasibility study.Gut. 2009; 58: 331-336
- Scheduled endoscopic surveillance controls secondary cancer after curative endoscopic resection for early gastric cancer: a multicentre retrospective cohort study by Osaka University ESD study group.Gut. 2013; 62: 1425-1432
- Diagnostic performance and limitations of magnifying narrow-band imaging in screening endoscopy of early gastric cancer: a prospective multicenter feasibility study.Gastric Cancer. 2014; 17: 669-679
- Magnifying endoscopy with narrow-band imaging is more accurate for determination of horizontal extent of early gastric cancers than chromoendoscopy.Endosc Int Open. 2016; 4: E690-E698
- Incidence of lymph node metastasis and the feasibility of endoscopic resection for undifferentiated-type early gastric cancer.Gastric Cancer. 2009; 12: 148-152
Article info
Publication history
Published online: December 07, 2017
Accepted:
November 15,
2017
Received:
June 22,
2017
Footnotes
DISCLOSURE: All authors disclosed no financial relationships relevant to this publication.
If you would like to chat with an author of this publication, you may contact Dr Uedo at [email protected]
Identification
Copyright
© 2018 by the American Society for Gastrointestinal Endoscopy
ScienceDirect
Access this article on ScienceDirectLinked Article
- Deep learning–based endoscopic image recognition for detection of early gastric cancer: a Chinese perspectiveGastrointestinal EndoscopyVol. 88Issue 1
- PreviewWe read with great interest the recent article in which Kanesaka et al1 reported a computer-aided system for identifying early gastric cancers (EGC). The diagnostic performance (accuracy of 96.3%) suggests the great potential of computer-aided diagnosis for EGC. This is especially true in countries such as China that have a high incidence of gastric cancer but a low EGC detection rate.2 Recent reports3 have estimated that about 679,100 new cases of gastric cancer were confirmed in China each year and that more than 80% of patients received their diagnoses at an advanced stage with poor prognosis.
- Full-Text
- Preview
