Tags

Type your tag names separated by a space and hit enter

Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis.
Gastroenterology 2018; 154(3):568-575G

Abstract

BACKGROUND & AIMS

Narrow-band imaging is an image-enhanced form of endoscopy used to observed microstructures and capillaries of the mucosal epithelium which allows for real-time prediction of histologic features of colorectal polyps. However, narrow-band imaging expertise is required to differentiate hyperplastic from neoplastic polyps with high levels of accuracy. We developed and tested a system of computer-aided diagnosis with a deep neural network (DNN-CAD) to analyze narrow-band images of diminutive colorectal polyps.

METHODS

We collected 1476 images of neoplastic polyps and 681 images of hyperplastic polyps, obtained from the picture archiving and communications system database in a tertiary hospital in Taiwan. Histologic findings from the polyps were also collected and used as the reference standard. The images and data were used to train the DNN. A test set of images (96 hyperplastic and 188 neoplastic polyps, smaller than 5 mm), obtained from patients who underwent colonoscopies from March 2017 through August 2017, was then used to test the diagnostic ability of the DNN-CAD vs endoscopists (2 expert and 4 novice), who were asked to classify the images of the test set as neoplastic or hyperplastic. Their classifications were compared with findings from histologic analysis. The primary outcome measures were diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic time. The accuracy, sensitivity, specificity, PPV, NPV, and diagnostic time were compared among DNN-CAD, the novice endoscopists, and the expert endoscopists. The study was designed to detect a difference of 10% in accuracy by a 2-sided McNemar test.

RESULTS

In the test set, the DNN-CAD identified neoplastic or hyperplastic polyps with 96.3% sensitivity, 78.1% specificity, a PPV of 89.6%, and a NPV of 91.5%. Fewer than half of the novice endoscopists classified polyps with a NPV of 90% (their NPVs ranged from 73.9% to 84.0%). DNN-CAD classified polyps as neoplastic or hyperplastic in 0.45 ± 0.07 seconds-shorter than the time required by experts (1.54 ± 1.30 seconds) and nonexperts (1.77 ± 1.37 seconds) (both P < .001). DNN-CAD classified polyps with perfect intra-observer agreement (kappa score of 1). There was a low level of intra-observer and inter-observer agreement in classification among endoscopists.

CONCLUSIONS

We developed a system called DNN-CAD to identify neoplastic or hyperplastic colorectal polyps less than 5 mm. The system classified polyps with a PPV of 89.6%, and a NPV of 91.5%, and in a shorter time than endoscopists. This deep-learning model has potential for not only endoscopic image recognition but for other forms of medical image analysis, including sonography, computed tomography, and magnetic resonance images.

Authors+Show Affiliations

Division of Gastroenterology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan. Electronic address: endoscopy@mail.ndmctsgh.edu.tw.Department of Biological Science and Technology, National Chiao Tung University, Hsinchu, Taiwan; Division of Gastroenterology, Taichung Armed Forces General Hospital, Taichung, Taiwan.Department of Pathology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.Division of Gastroenterology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan.Big Data Research Center and Institute of Statistics, National Chiao Tung University, Hsinchu, Taiwan.Department of Computer Science, National Chiao Tung University, Hsinchu, Taiwan. Electronic address: vtseng@cs.nctu.edu.tw.

Pub Type(s)

Comparative Study
Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

29042219

Citation

Chen, Peng-Jen, et al. "Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis." Gastroenterology, vol. 154, no. 3, 2018, pp. 568-575.
Chen PJ, Lin MC, Lai MJ, et al. Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology. 2018;154(3):568-575.
Chen, P. J., Lin, M. C., Lai, M. J., Lin, J. C., Lu, H. H., & Tseng, V. S. (2018). Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology, 154(3), pp. 568-575. doi:10.1053/j.gastro.2017.10.010.
Chen PJ, et al. Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology. 2018;154(3):568-575. PubMed PMID: 29042219.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. AU - Chen,Peng-Jen, AU - Lin,Meng-Chiung, AU - Lai,Mei-Ju, AU - Lin,Jung-Chun, AU - Lu,Henry Horng-Shing, AU - Tseng,Vincent S, Y1 - 2017/10/16/ PY - 2017/07/25/received PY - 2017/10/04/revised PY - 2017/10/09/accepted PY - 2017/10/19/pubmed PY - 2018/5/4/medline PY - 2017/10/19/entrez KW - Colon Cancer Detection KW - Cost-effectiveness KW - Machine Learning KW - Magnifying SP - 568 EP - 575 JF - Gastroenterology JO - Gastroenterology VL - 154 IS - 3 N2 - BACKGROUND & AIMS: Narrow-band imaging is an image-enhanced form of endoscopy used to observed microstructures and capillaries of the mucosal epithelium which allows for real-time prediction of histologic features of colorectal polyps. However, narrow-band imaging expertise is required to differentiate hyperplastic from neoplastic polyps with high levels of accuracy. We developed and tested a system of computer-aided diagnosis with a deep neural network (DNN-CAD) to analyze narrow-band images of diminutive colorectal polyps. METHODS: We collected 1476 images of neoplastic polyps and 681 images of hyperplastic polyps, obtained from the picture archiving and communications system database in a tertiary hospital in Taiwan. Histologic findings from the polyps were also collected and used as the reference standard. The images and data were used to train the DNN. A test set of images (96 hyperplastic and 188 neoplastic polyps, smaller than 5 mm), obtained from patients who underwent colonoscopies from March 2017 through August 2017, was then used to test the diagnostic ability of the DNN-CAD vs endoscopists (2 expert and 4 novice), who were asked to classify the images of the test set as neoplastic or hyperplastic. Their classifications were compared with findings from histologic analysis. The primary outcome measures were diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic time. The accuracy, sensitivity, specificity, PPV, NPV, and diagnostic time were compared among DNN-CAD, the novice endoscopists, and the expert endoscopists. The study was designed to detect a difference of 10% in accuracy by a 2-sided McNemar test. RESULTS: In the test set, the DNN-CAD identified neoplastic or hyperplastic polyps with 96.3% sensitivity, 78.1% specificity, a PPV of 89.6%, and a NPV of 91.5%. Fewer than half of the novice endoscopists classified polyps with a NPV of 90% (their NPVs ranged from 73.9% to 84.0%). DNN-CAD classified polyps as neoplastic or hyperplastic in 0.45 ± 0.07 seconds-shorter than the time required by experts (1.54 ± 1.30 seconds) and nonexperts (1.77 ± 1.37 seconds) (both P < .001). DNN-CAD classified polyps with perfect intra-observer agreement (kappa score of 1). There was a low level of intra-observer and inter-observer agreement in classification among endoscopists. CONCLUSIONS: We developed a system called DNN-CAD to identify neoplastic or hyperplastic colorectal polyps less than 5 mm. The system classified polyps with a PPV of 89.6%, and a NPV of 91.5%, and in a shorter time than endoscopists. This deep-learning model has potential for not only endoscopic image recognition but for other forms of medical image analysis, including sonography, computed tomography, and magnetic resonance images. SN - 1528-0012 UR - https://www.unboundmedicine.com/medline/citation/29042219/Accurate_Classification_of_Diminutive_Colorectal_Polyps_Using_Computer_Aided_Analysis_ L2 - https://linkinghub.elsevier.com/retrieve/pii/S0016-5085(17)36251-0 DB - PRIME DP - Unbound Medicine ER -