M M Saraiva1,2,3, L Spindler4, N Fathallah4, H Beaussier5, C Mamma5, M Quesnée4, T Ribeiro6,7, J Afonso6,7, M Carvalho8,9, R Moura8,9, P Andrade6,7,10, H Cardoso6,7,10, J Adam11, J Ferreira8,9, G Macedo6,7,10, V de Parades4. 1. Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427, Porto, Portugal. miguelmascarenhassaraiva@gmail.com. 2. WGO Gastroenterology and Hepatology Training Center, Porto, Portugal. miguelmascarenhassaraiva@gmail.com. 3. Faculty of Medicine, University of Porto, Alameda Professor Hernâni Monteiro, Rua Oliveira Martins 104, 4200-427, Porto, Portugal. miguelmascarenhassaraiva@gmail.com. 4. Department of Proctology, GH Paris Saint-Joseph, 85, Rue Raymond Losserand, 75014, Paris, France. 5. Department of Clinical Research, GH Paris Saint-Joseph, 85, Rue Raymond Losserand, 75014, Paris, France. 6. Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, 4200-427, Porto, Portugal. 7. WGO Gastroenterology and Hepatology Training Center, Porto, Portugal. 8. Department of Mechanical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal. 9. INEGI - Institute of Science and Innovation in Mechanical and Industrial Engineering, Rua Dr. Roberto Frias, 4200-465, Porto, Portugal. 10. Faculty of Medicine, University of Porto, Alameda Professor Hernâni Monteiro, Rua Oliveira Martins 104, 4200-427, Porto, Portugal. 11. Department of Pathology, GH Paris Saint-Joseph, 85, Rue Raymond Losserand, 75014, Paris, France.
Abstract
BACKGROUND: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. Although it is superior to other diagnostic methods, particularly cytology, the visual identification of areas suspected of having high-grade squamous intraepithelial lesions remains difficult. Convolutional neural networks (CNNs) have shown great potential for assessing endoscopic images. The aim of the present study was to develop a CNN-based system for automatic detection and differentiation of HSIL versus LSIL in HRA images. METHODS: A CNN was developed based on 78 HRA exams from a total of 71 patients who underwent HRA at a single high-volume center (GH Paris Saint-Joseph, Paris, France) between January 2021 and January 2022. A total of 5026 images were included, 1517 images containing HSIL and 3509 LSIL. A training dataset comprising 90% of the total pool of images was defined for the development of the network. The performance of the CNN was evaluated using an independent testing dataset comprising the remaining 10%. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated. RESULTS: The algorithm was optimized for the automatic detection of HSIL and its differentiation from LSIL. Our model had an overall accuracy of 90.3%. The CNN had sensitivity, specificity, positive and negative predictive values of 91.4%, 89.7%, 80.9%, and 95.6%, respectively. The area under the curve was 0.97. CONCLUSIONS: The CNN architecture for application to HRA accurately detected precursors of squamous anal cancer. Further development and implementation of these tools in clinical practice may significantly modify the management of these patients.
BACKGROUND: High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. Although it is superior to other diagnostic methods, particularly cytology, the visual identification of areas suspected of having high-grade squamous intraepithelial lesions remains difficult. Convolutional neural networks (CNNs) have shown great potential for assessing endoscopic images. The aim of the present study was to develop a CNN-based system for automatic detection and differentiation of HSIL versus LSIL in HRA images. METHODS: A CNN was developed based on 78 HRA exams from a total of 71 patients who underwent HRA at a single high-volume center (GH Paris Saint-Joseph, Paris, France) between January 2021 and January 2022. A total of 5026 images were included, 1517 images containing HSIL and 3509 LSIL. A training dataset comprising 90% of the total pool of images was defined for the development of the network. The performance of the CNN was evaluated using an independent testing dataset comprising the remaining 10%. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated. RESULTS: The algorithm was optimized for the automatic detection of HSIL and its differentiation from LSIL. Our model had an overall accuracy of 90.3%. The CNN had sensitivity, specificity, positive and negative predictive values of 91.4%, 89.7%, 80.9%, and 95.6%, respectively. The area under the curve was 0.97. CONCLUSIONS: The CNN architecture for application to HRA accurately detected precursors of squamous anal cancer. Further development and implementation of these tools in clinical practice may significantly modify the management of these patients.
Authors: Andreia Albuquerque; Michael Sheaff; Oliver Stirrup; Carmelina Cappello; Julie Bowring; Tamzin Cuming; Anke De Masi; Adam N Rosenthal; Mayura Nathan Journal: Clin Infect Dis Date: 2018-09-28 Impact factor: 9.079
Authors: Renée M F Ebisch; Dominiek W E Rutten; Joanna IntHout; Willem J G Melchers; Leon F A G Massuger; Johan Bulten; Ruud L M Bekkers; Albert G Siebers Journal: J Clin Oncol Date: 2017-05-25 Impact factor: 44.544
Authors: Ashish A Deshmukh; Ryan Suk; Meredith S Shiels; Kalyani Sonawane; Alan G Nyitray; Yuxin Liu; Michael M Gaisa; Joel M Palefsky; Keith Sigel Journal: J Natl Cancer Inst Date: 2020-08-01 Impact factor: 13.506
Authors: Hugo De Vuyst; Gary M Clifford; Maria Claudia Nascimento; Margaret M Madeleine; Silvia Franceschi Journal: Int J Cancer Date: 2009-04-01 Impact factor: 7.396