Where Do We Stand in AI for Endoscopic Image Analysis? Deciphering Gaps and Future Directions

Overview

Journal NPJ Digit Med

Specialty Medical Informatics

Date 2022 Dec 20

PMID 36539473

Authors

Sharib Ali

Affiliations

Soon will be listed here.

Abstract

Recent developments in deep learning have enabled data-driven algorithms that can reach human-level performance and beyond. The development and deployment of medical image analysis methods have several challenges, including data heterogeneity due to population diversity and different device manufacturers. In addition, more input from experts is required for a reliable method development process. While the exponential growth in clinical imaging data has enabled deep learning to flourish, data heterogeneity, multi-modality, and rare or inconspicuous disease cases still need to be explored. Endoscopy being highly operator-dependent with grim clinical outcomes in some disease cases, reliable and accurate automated system guidance can improve patient care. Most designed methods must be more generalisable to the unseen target data, patient population variability, and variable disease appearances. The paper reviews recent works on endoscopic image analysis with artificial intelligence (AI) and emphasises the current unmatched needs in this field. Finally, it outlines the future directions for clinically relevant complex AI solutions to improve patient outcomes.

Citing Articles

Exploring the benefits and challenges of AI-driven large language models in gastroenterology: Think out of the box.

Kral J, Hradis M, Buzga M, Kunovsky L Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub. 2024; 168(4):277-283.

PMID: 39234774 DOI: 10.5507/bp.2024.027.

Intraoperative detection of parathyroid glands using artificial intelligence: optimizing medical image training with data augmentation methods.

Lee J, Ku E, Chung Y, Kim Y, Kim K Surg Endosc. 2024; 38(10):5732-5745.

PMID: 39138679 PMC: 11458679. DOI: 10.1007/s00464-024-11115-z.

Optimizing cystoscopy and TURBT: enhanced imaging and artificial intelligence.

Shkolyar E, Zhou S, Carlson C, Chang S, Laurie M, Xing L Nat Rev Urol. 2024; 22(1):46-54.

PMID: 38982304 DOI: 10.1038/s41585-024-00904-9.

Resolution-enhanced multi-core fiber imaging learned on a digital twin for cancer diagnosis.

Wang T, Dremel J, Richter S, Polanski W, Uckermann O, Eyupoglu I Neurophotonics. 2024; 11(Suppl 1):S11505.

PMID: 38298866 PMC: 10828892. DOI: 10.1117/1.NPh.11.S1.S11505.

Artificial intelligence: a new field of knowledge for nephrologists?.

Fayos de Arizon L, Viera E, Pilco M, Perera A, De Maeztu G, Nicolau A Clin Kidney J. 2023; 16(12):2314-2326.

PMID: 38046016 PMC: 10689169. DOI: 10.1093/ckj/sfad182.

References

Jin Y, Li H, Dou Q, Chen H, Qin J, Fu C . Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Anal. 2019; 59:101572. DOI: 10.1016/j.media.2019.101572. View

Bernal J, Tajkbaksh N, Sanchez F, Matuszewski B, Chen H, Yu L . Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge. IEEE Trans Med Imaging. 2017; 36(6):1231-1249. DOI: 10.1109/TMI.2017.2664042. View

Gupta S, Ali S, Goldsmith L, Turney B, Rittscher J . Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy. Comput Med Imaging Graph. 2022; 101:102112. DOI: 10.1016/j.compmedimag.2022.102112. View

Namazi B, Sankaranarayanan G, Devarajan V . A contextual detector of surgical tools in laparoscopic videos using deep learning. Surg Endosc. 2021; 36(1):679-688. PMC: 8349373. DOI: 10.1007/s00464-021-08336-x. View

Shkolyar E, Jia X, Chang T, Trivedi D, Mach K, Meng M . Augmented Bladder Tumor Detection Using Deep Learning. Eur Urol. 2019; 76(6):714-718. PMC: 6889816. DOI: 10.1016/j.eururo.2019.08.032. View

Gutierrez Becker B, Arcadu F, Thalhammer A, Gamez Serna C, Feehan O, Drawnel F . Training and deploying a deep learning model for endoscopic severity grading in ulcerative colitis using multicenter clinical trial data. Ther Adv Gastrointest Endosc. 2021; 14:2631774521990623. PMC: 7917417. DOI: 10.1177/2631774521990623. View

He Q, Bano S, Ahmad O, Yang B, Chen X, Valdastri P . Deep learning-based anatomical site classification for upper gastrointestinal endoscopy. Int J Comput Assist Radiol Surg. 2020; 15(7):1085-1094. PMC: 7316667. DOI: 10.1007/s11548-020-02148-5. View

Srivastava A, Jha D, Chanda S, Pal U, Johansen H, Johansen D . MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation. IEEE J Biomed Health Inform. 2021; 26(5):2252-2263. DOI: 10.1109/JBHI.2021.3138024. View

Schmelzle M, Krenzien F, Schoning W, Pratschke J . Laparoscopic liver resection: indications, limitations, and economic aspects. Langenbecks Arch Surg. 2020; 405(6):725-735. PMC: 7471173. DOI: 10.1007/s00423-020-01918-8. View

10.

Turan M, Durmus F . UC-NfNet: Deep learning-enabled assessment of ulcerative colitis from colonoscopy images. Med Image Anal. 2022; 82:102587. DOI: 10.1016/j.media.2022.102587. View

11.

Tokat M, van Tilburg L, Koch A, Spaander M . Artificial Intelligence in Upper Gastrointestinal Endoscopy. Dig Dis. 2021; 40(4):395-408. DOI: 10.1159/000518232. View

12.

Ali S, Bailey A, Ash S, Haghighat M, Leedham S, Lu X . A Pilot Study on Automatic Three-Dimensional Quantification of Barrett's Esophagus for Risk Stratification and Therapy Monitoring. Gastroenterology. 2021; 161(3):865-878.e8. PMC: 7617121. DOI: 10.1053/j.gastro.2021.05.059. View

13.

Kim Y, Bae J, Chung J, Park D, Kim K, Kim Y . New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images. Sci Rep. 2021; 11(1):3605. PMC: 7878472. DOI: 10.1038/s41598-021-83199-9. View

14.

Okagawa Y, Abe S, Yamada M, Oda I, Saito Y . Artificial Intelligence in Endoscopy. Dig Dis Sci. 2021; 67(5):1553-1572. DOI: 10.1007/s10620-021-07086-z. View

15.

Madad Zadeh S, Francois T, Calvet L, Chauvet P, Canis M, Bartoli A . SurgAI: deep learning for computerized laparoscopic image understanding in gynaecology. Surg Endosc. 2020; 34(12):5377-5383. DOI: 10.1007/s00464-019-07330-8. View

16.

Ali N, Bolenz C, Todenhofer T, Stenzel A, Deetmar P, Kriegmair M . Deep learning-based classification of blue light cystoscopy imaging during transurethral resection of bladder tumors. Sci Rep. 2021; 11(1):11629. PMC: 8172542. DOI: 10.1038/s41598-021-91081-x. View

17.

Ali S, Zhou F, Braden B, Bailey A, Yang S, Cheng G . An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy. Sci Rep. 2020; 10(1):2748. PMC: 7026422. DOI: 10.1038/s41598-020-59413-5. View

18.

Zhou D, Tian F, Tian X, Sun L, Huang X, Zhao F . Diagnostic evaluation of a deep learning model for optical diagnosis of colorectal cancer. Nat Commun. 2020; 11(1):2961. PMC: 7289893. DOI: 10.1038/s41467-020-16777-6. View

19.

Mascarenhas Saraiva M, Afonso J, Ribeiro T, Ferreira J, Cardoso H, Andrade A . Deep learning and capsule endoscopy: automatic identification and differentiation of small bowel lesions with distinct haemorrhagic potential using a convolutional neural network. BMJ Open Gastroenterol. 2021; 8(1). PMC: 8477239. DOI: 10.1136/bmjgast-2021-000753. View

20.

Chen P, Lin M, Lai M, Lin J, Lu H, Tseng V . Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology. 2017; 154(3):568-575. DOI: 10.1053/j.gastro.2017.10.010. View