Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)
The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detecti...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.927868/full |
| _version_ | 1811252153362153472 |
|---|---|
| author | Jing Jin Qianqian Zhang Bill Dong Tao Ma Xuecan Mei Xi Wang Shaofang Song Jie Peng Aijiu Wu Lanfang Dong Derun Kong |
| author_facet | Jing Jin Qianqian Zhang Bill Dong Tao Ma Xuecan Mei Xi Wang Shaofang Song Jie Peng Aijiu Wu Lanfang Dong Derun Kong |
| author_sort | Jing Jin |
| collection | DOAJ |
| description | The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ2 = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ2 = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ2 = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ2 = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ2 = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings. |
| first_indexed | 2024-04-12T16:30:39Z |
| format | Article |
| id | doaj.art-fa46373504054780864d194ecdd3bc9e |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-12T16:30:39Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-fa46373504054780864d194ecdd3bc9e2022-12-22T03:25:10ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-10-011210.3389/fonc.2022.927868927868Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)Jing Jin0Qianqian Zhang1Bill Dong2Tao Ma3Xuecan Mei4Xi Wang5Shaofang Song6Jie Peng7Aijiu Wu8Lanfang Dong9Derun Kong10Key Laboratory of Digestive Diseases of Anhui Province, Department of Gastroenterology, The First Affiliated Hospital of Anhui Medical University, Hefei, ChinaKey Laboratory of Digestive Diseases of Anhui Province, Department of Gastroenterology, The First Affiliated Hospital of Anhui Medical University, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaKey Laboratory of Digestive Diseases of Anhui Province, Department of Gastroenterology, The First Affiliated Hospital of Anhui Medical University, Hefei, ChinaKey Laboratory of Digestive Diseases of Anhui Province, Department of Gastroenterology, The First Affiliated Hospital of Anhui Medical University, Hefei, ChinaResearch and Development Department, Hefei Zhongna Medical Instrument Co. LTD, Hefei, ChinaResearch and Development Department, Hefei Zhongna Medical Instrument Co. LTD, Hefei, ChinaResearch and Development Department, Hefei Zhongna Medical Instrument Co. LTD, Hefei, ChinaSchool of Computer Science and Technology, University of Science and Technology of China, Hefei, ChinaKey Laboratory of Digestive Diseases of Anhui Province, Department of Gastroenterology, The First Affiliated Hospital of Anhui Medical University, Hefei, ChinaThe artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ2 = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ2 = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ2 = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ2 = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ2 = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings.https://www.frontiersin.org/articles/10.3389/fonc.2022.927868/fullartificial intelligence - AIregion-based convolutional neural networks (R-CNN)endoscopyEarly gastric cancer (EGC)white light imagingnarrow band imaging (NBI) |
| spellingShingle | Jing Jin Qianqian Zhang Bill Dong Tao Ma Xuecan Mei Xi Wang Shaofang Song Jie Peng Aijiu Wu Lanfang Dong Derun Kong Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) Frontiers in Oncology artificial intelligence - AI region-based convolutional neural networks (R-CNN) endoscopy Early gastric cancer (EGC) white light imaging narrow band imaging (NBI) |
| title | Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) |
| title_full | Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) |
| title_fullStr | Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) |
| title_full_unstemmed | Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) |
| title_short | Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video) |
| title_sort | automatic detection of early gastric cancer in endoscopy based on mask region based convolutional neural networks mask r cnn with video |
| topic | artificial intelligence - AI region-based convolutional neural networks (R-CNN) endoscopy Early gastric cancer (EGC) white light imaging narrow band imaging (NBI) |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.927868/full |
| work_keys_str_mv | AT jingjin automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT qianqianzhang automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT billdong automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT taoma automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT xuecanmei automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT xiwang automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT shaofangsong automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT jiepeng automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT aijiuwu automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT lanfangdong automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo AT derunkong automaticdetectionofearlygastriccancerinendoscopybasedonmaskregionbasedconvolutionalneuralnetworksmaskrcnnwithvideo |