Search

Your search keyword '"Eelbode, Tom"' showing total 35 results
Start Over Author "Eelbode, Tom"
35 results on '"Eelbode, Tom"'

1. Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging

Author

Berenguer, Abel Díaz, Sahli, Hichem, Joukovsky, Boris, Kvasnytsia, Maryna, Dirks, Ine, Alioscha-Perez, Mitchel, Deligiannis, Nikos, Gonidakis, Panagiotis, Sánchez, Sebastián Amador, Brahimetaj, Redona, Papavasileiou, Evgenia, Chana, Jonathan Cheung-Wai, Li, Fei, Song, Shangzhen, Yang, Yixin, Tilborghs, Sofie, Willems, Siri, Eelbode, Tom, Bertels, Jeroen, Vandermeulen, Dirk, Maes, Frederik, Suetens, Paul, Fidon, Lucas, Vercauteren, Tom, Robben, David, Brys, Arne, Smeets, Dirk, Ilsen, Bart, Buls, Nico, Watté, Nina, de Mey, Johan, Snoeckx, Annemiek, Parizel, Paul M., Guiot, Julien, Deprez, Louis, Meunier, Paul, Gryspeerdt, Stefaan, De Smet, Kristof, Jansen, Bart, and Vandemeulebroucke, Jef

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Our motivating application is a real-world problem: COVID-19 classification from CT imaging, for which we present an explainable Deep Learning approach based on a semi-supervised classification pipeline that employs variational autoencoders to extract efficient feature embedding. We have optimized the architecture of two different networks for CT images: (i) a novel conditional variational autoencoder (CVAE) with a specific architecture that integrates the class labels inside the encoder layers and uses side information with shared attention layers for the encoder, which make the most of the contextual clues for representation learning, and (ii) a downstream convolutional neural network for supervised classification using the encoder structure of the CVAE. With the explainable classification results, the proposed diagnosis system is very effective for COVID-19 classification. Based on the promising results obtained qualitatively and quantitatively, we envisage a wide deployment of our developed technique in large-scale clinical studies.Code is available at https://git.etrovub.be/AVSP/ct-based-covid-19-diagnostic-tool.git.

Published
2020

2. Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index

Author

Eelbode, Tom, Bertels, Jeroen, Berman, Maxim, Vandermeulen, Dirk, Maes, Frederik, Bisschops, Raf, and Blaschko, Matthew B.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

In many medical imaging and classical computer vision tasks, the Dice score and Jaccard index are used to evaluate the segmentation performance. Despite the existence and great empirical success of metric-sensitive losses, i.e. relaxations of these metrics such as soft Dice, soft Jaccard and Lovasz-Softmax, many researchers still use per-pixel losses, such as (weighted) cross-entropy to train CNNs for segmentation. Therefore, the target metric is in many cases not directly optimized. We investigate from a theoretical perspective, the relation within the group of metric-sensitive loss functions and question the existence of an optimal weighting scheme for weighted cross-entropy to optimize the Dice score and Jaccard index at test time. We find that the Dice score and Jaccard index approximate each other relatively and absolutely, but we find no such approximation for a weighted Hamming similarity. For the Tversky loss, the approximation gets monotonically worse when deviating from the trivial weight setting where soft Tversky equals soft Dice. We verify these results empirically in an extensive validation on six medical segmentation tasks and can confirm that metric-sensitive losses are superior to cross-entropy based loss functions in case of evaluation with Dice Score or Jaccard Index. This further holds in a multi-class setting, and across different object sizes and foreground/background ratios. These results encourage a wider adoption of metric-sensitive loss functions for medical segmentation tasks where the performance measure of interest is the Dice score or Jaccard index., Comment: 15 pages, 14 figures, accepted for publication in IEEE Transactions on Medical Imaging (2020)

Published
2020
Full Text
View/download PDF

3. Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients

Author

Tilborghs, Sofie, Dirks, Ine, Fidon, Lucas, Willems, Siri, Eelbode, Tom, Bertels, Jeroen, Ilsen, Bart, Brys, Arne, Dubbeldam, Adriana, Buls, Nico, Gonidakis, Panagiotis, Sánchez, Sebastián Amador, Snoeckx, Annemiek, Parizel, Paul M., de Mey, Johan, Vandermeulen, Dirk, Vercauteren, Tom, Robben, David, Smeets, Dirk, Maes, Frederik, Vandemeulebroucke, Jef, and Suetens, Paul

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Recent research on COVID-19 suggests that CT imaging provides useful information to assess disease progression and assist diagnosis, in addition to help understanding the disease. There is an increasing number of studies that propose to use deep learning to provide fast and accurate quantification of COVID-19 using chest CT scans. The main tasks of interest are the automatic segmentation of lung and lung lesions in chest CT scans of confirmed or suspected COVID-19 patients. In this study, we compare twelve deep learning algorithms using a multi-center dataset, including both open-source and in-house developed algorithms. Results show that ensembling different methods can boost the overall test set performance for lung segmentation, binary lesion segmentation and multiclass lesion segmentation, resulting in mean Dice scores of 0.982, 0.724 and 0.469, respectively. The resulting binary lesions were segmented with a mean absolute volume error of 91.3 ml. In general, the task of distinguishing different lesion types was more difficult, with a mean absolute volume difference of 152 ml and mean Dice scores of 0.369 and 0.523 for consolidation and ground glass opacity, respectively. All methods perform binary lesion segmentation with an average volume error that is better than visual assessment by human raters, suggesting these methods are mature enough for a large-scale evaluation for use in clinical practice., Comment: Updated acknowledgments

Published
2020

4. Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method

Author

Ahmad, Omer F, Mori, Yuichi, Misawa, Masashi, Kudo, Shin-ei, Anderson, John T, Bernal, Jorge, Berzin, Tyler M, Bisschops, Raf, Byrne, Michael F, Chen, Peng-Jen, East, James E, Eelbode, Tom, Elson, Daniel S, Gurudu, Suryakanth R, Histace, Aymeric, Karnes, William E, Repici, Alessandro, Singh, Rajvinder, Valdastri, Pietro, Wallace, Michael B, Wang, Pu, Stoyanov, Danail, and Lovat, Laurence B

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Cancer, Prevention, Artificial Intelligence, Colonoscopy, Delphi Technique, Humans, Gastroenterology & Hepatology, Clinical sciences
Abstract

BACKGROUND : Artificial intelligence (AI) research in colonoscopy is progressing rapidly but widespread clinical implementation is not yet a reality. We aimed to identify the top implementation research priorities. METHODS : An established modified Delphi approach for research priority setting was used. Fifteen international experts, including endoscopists and translational computer scientists/engineers, from nine countries participated in an online survey over 9 months. Questions related to AI implementation in colonoscopy were generated as a long-list in the first round, and then scored in two subsequent rounds to identify the top 10 research questions. RESULTS : The top 10 ranked questions were categorized into five themes. Theme 1: clinical trial design/end points (4 questions), related to optimum trial designs for polyp detection and characterization, determining the optimal end points for evaluation of AI, and demonstrating impact on interval cancer rates. Theme 2: technological developments (3 questions), including improving detection of more challenging and advanced lesions, reduction of false-positive rates, and minimizing latency. Theme 3: clinical adoption/integration (1 question), concerning the effective combination of detection and characterization into one workflow. Theme 4: data access/annotation (1 question), concerning more efficient or automated data annotation methods to reduce the burden on human experts. Theme 5: regulatory approval (1 question), related to making regulatory approval processes more efficient. CONCLUSIONS : This is the first reported international research priority setting exercise for AI in colonoscopy. The study findings should be used as a framework to guide future research with key stakeholders to accelerate the clinical implementation of AI in endoscopy.

Published
2021

5. Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice

Author

Bertels, Jeroen, Eelbode, Tom, Berman, Maxim, Vandermeulen, Dirk, Maes, Frederik, Bisschops, Raf, and Blaschko, Matthew

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

The Dice score and Jaccard index are commonly used metrics for the evaluation of segmentation tasks in medical imaging. Convolutional neural networks trained for image segmentation tasks are usually optimized for (weighted) cross-entropy. This introduces an adverse discrepancy between the learning optimization objective (the loss) and the end target metric. Recent works in computer vision have proposed soft surrogates to alleviate this discrepancy and directly optimize the desired metric, either through relaxations (soft-Dice, soft-Jaccard) or submodular optimization (Lov\'asz-softmax). The aim of this study is two-fold. First, we investigate the theoretical differences in a risk minimization framework and question the existence of a weighted cross-entropy loss with weights theoretically optimized to surrogate Dice or Jaccard. Second, we empirically investigate the behavior of the aforementioned loss functions w.r.t. evaluation with Dice score and Jaccard index on five medical segmentation tasks. Through the application of relative approximation bounds, we show that all surrogates are equivalent up to a multiplicative factor, and that no optimal weighting of cross-entropy exists to approximate Dice or Jaccard measures. We validate these findings empirically and show that, while it is important to opt for one of the target metric surrogates rather than a cross-entropy-based loss, the choice of the surrogate does not make a statistical difference on a wide range of medical segmentation tasks., Comment: MICCAI 2019

Published
2019
Full Text
View/download PDF

6. Convolutional LSTM

Author

Eelbode, Tom, Sinonquel, Pieter, Bisschops, Raf, Maes, Frederik, Bernal, Jorge, editor, and Histace, Aymeric, editor

Published
2021
Full Text
View/download PDF

10. CLINICAL VALIDATION OF A COMPUTER-AIDED DETECTION MODEL FOR COLORECTAL POLYP DETECTION (CAD-ARTIPOD) TRIAL USING A SECOND OBSERVER AND REAL-TIME UNBLINDING

Author

Sinonquel, Pieter, primary, Eelbode, Tom, additional, Pech, Oliver, additional, De Wulf, Dominiek, additional, Dewint, Pieter, additional, Neumann, Helmut, additional, Antonelli, Giulio, additional, Tate, David, additional, Lemmers, Arnaud, additional, Pilonis, Nastazja, additional, Kaminski, Michal, additional, Demedts, Ingrid, additional, Hassan, Cesare, additional, Roelandt, Philip, additional, Maes, Frederik, additional, and Bisschops, Raf, additional

Published
2023
Full Text
View/download PDF

12. Clinical consequences of computer-aided colorectal polyp detection

Author

Sinonquel, Pieter, Eelbode, Tom, Pech, Oliver, De Wulf, Dominiek, Dewint, Pieter, Neumann, Helmut, Antonelli, Giulio, Iacopini, Federico, Tate, David, Lemmers, Arnaud, Pilonis, Nastazja Dagny, Kaminski, Michal Filip, Roelandt, Philip, Hassan, Cesare, Ingrid, Demedts, Maes, Frederik, and Bisschops, Raf

Abstract

Background and aimRandomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe’s true benefit. Clinical outcomes of increased detection have not yet been fully elucidated.MethodsIn this multicentre trial, CADe combining convolutional and recurrent neural networks was used for polyp detection. Blinded endoscopists were monitored in real time by a second observer with CADe access. CADe detections prompted reinspection. Adenoma detection rates (ADR) and polyp detection rates were measured prestudy and poststudy. Histological assessments were done by independent histopathologists. The primary outcome compared polyp detection between endoscopists and CADe.ResultsIn 946 patients (51.9% male, mean age 64), a total of 2141 polyps were identified, including 989 adenomas. CADe was not superior to human polyp detection (sensitivity 94.6% vs 96.0%) but outperformed them when restricted to adenomas. Unblinding led to an additional yield of 86 true positive polyp detections (1.1% ADR increase per patient; 73.8% were <5 mm). CADe also increased non-neoplastic polyp detection by an absolute value of 4.9% of the cases (1.8% increase of entire polyp load). Procedure time increased with 6.6±6.5 min (+42.6%). In 22/946 patients, the additional detection of adenomas changed surveillance intervals (2.3%), mostly by increasing the number of small adenomas beyond the cut-off.ConclusionEven if CADe appears to be slightly more sensitive than human endoscopists, the additional gain in ADR was minimal and follow-up intervals rarely changed. Additional inspection of non-neoplastic lesions was increased, adding to the inspection and/or polypectomy workload.

Published
2024
Full Text
View/download PDF

13. Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

Author

Messmann, Helmut, primary, Bisschops, Raf, primary, Antonelli, Giulio, additional, Libânio, Diogo, additional, Sinonquel, Pieter, additional, Abdelrahim, Mohamed, additional, Ahmad, Omer F., additional, Areia, Miguel, additional, Bergman, Jacques J. G. H. M., additional, Bhandari, Pradeep, additional, Boskoski, Ivo, additional, Dekker, Evelien, additional, Domagk, Dirk, additional, Ebigbo, Alanna, additional, Eelbode, Tom, additional, Eliakim, Rami, additional, Häfner, Michael, additional, Haidry, Rehan J., additional, Jover, Rodrigo, additional, Kaminski, Michal F., additional, Kuvaev, Roman, additional, Mori, Yuichi, additional, Palazzo, Maxime, additional, Repici, Alessandro, additional, Rondonotti, Emanuele, additional, Rutter, Matthew D., additional, Saito, Yutaka, additional, Sharma, Prateek, additional, Spada, Cristiano, additional, Spadaccini, Marco, additional, Veitch, Andrew, additional, Gralnek, Ian M., additional, Hassan, Cesare, additional, and Dinis-Ribeiro, Mario, additional

Published
2022
Full Text
View/download PDF

14. Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

Author

Messmann, Helmut, Bisschops, Raf, Antonelli, Giulio, Libânio, Diogo, Sinonquel, Pieter, Abdelrahim, Mohamed, Ahmad, Omer F, Areia, Miguel, Bergman, Jacques J G H M, Bhandari, Pradeep, Boskoski, Ivo, Dekker, Evelien, Domagk, Dirk, Ebigbo, Alanna, Eelbode, Tom, Eliakim, Rami, Häfner, Michael, Haidry, Rehan J, Jover, Rodrigo, Kaminski, Michal F, Kuvaev, Roman, Mori, Yuichi, Palazzo, Maxime, Repici, Alessandro, Rondonotti, Emanuele, Rutter, Matthew D, Saito, Yutaka, Sharma, Prateek, Spada, Cristiano, Spadaccini, Marco, Veitch, Andrew, Gralnek, Ian M, Hassan, Cesare, Dinis-Ribeiro, Mario, Boskoski, Ivo (ORCID:0000-0001-8194-2670), Spada, Cristiano (ORCID:0000-0002-5692-0960), Messmann, Helmut, Bisschops, Raf, Antonelli, Giulio, Libânio, Diogo, Sinonquel, Pieter, Abdelrahim, Mohamed, Ahmad, Omer F, Areia, Miguel, Bergman, Jacques J G H M, Bhandari, Pradeep, Boskoski, Ivo, Dekker, Evelien, Domagk, Dirk, Ebigbo, Alanna, Eelbode, Tom, Eliakim, Rami, Häfner, Michael, Haidry, Rehan J, Jover, Rodrigo, Kaminski, Michal F, Kuvaev, Roman, Mori, Yuichi, Palazzo, Maxime, Repici, Alessandro, Rondonotti, Emanuele, Rutter, Matthew D, Saito, Yutaka, Sharma, Prateek, Spada, Cristiano, Spadaccini, Marco, Veitch, Andrew, Gralnek, Ian M, Hassan, Cesare, Dinis-Ribeiro, Mario, Boskoski, Ivo (ORCID:0000-0001-8194-2670), and Spada, Cristiano (ORCID:0000-0002-5692-0960)

Abstract

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. Main recommendations: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in >= 90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma

Published
2022

18. Establishing key research questions for the implementation of artificial intelligence in colonoscopy : a modified Delphi method

Author

Ahmad, Omer, Mori, Yuichi, Misawa, Masashi, Kudo, Toyoki, Anderson, John, Bernal del Nozal, Jorge, Berzin, Tyler M., Bisschops, Raf, Byrne, Michael F., Chen, Peng Jen, East, James, Eelbode, Tom, Elson, Daniel, Gurudu, Suryakanth R., Histace, Aymeric, Karnes, William E., Repici, Alessandro, Singh, Rajvinder, Valdastri, Pietro, Wallace, Michael, Wang, Pu, Stoyanov, Danail, Lovat, Laurence B., Ahmad, Omer, Mori, Yuichi, Misawa, Masashi, Kudo, Toyoki, Anderson, John, Bernal del Nozal, Jorge, Berzin, Tyler M., Bisschops, Raf, Byrne, Michael F., Chen, Peng Jen, East, James, Eelbode, Tom, Elson, Daniel, Gurudu, Suryakanth R., Histace, Aymeric, Karnes, William E., Repici, Alessandro, Singh, Rajvinder, Valdastri, Pietro, Wallace, Michael, Wang, Pu, Stoyanov, Danail, and Lovat, Laurence B.

Abstract

Background Artificial intelligence (AI) research in colonoscopy is progressing rapidly but widespread clinical implementation is not yet a reality. We aimed to identify the top implementation research priorities. Methods An established modified Delphi approach for research priority setting was used. Fifteen international experts, including endoscopists and translational computer scientists/engineers, from nine countries participated in an online survey over 9 months. Questions related to AI implementation in colonoscopy were generated as a long-list in the first round, and then scored in two subsequent rounds to identify the top 10 research questions. Results The top 10 ranked questions were categorized into five themes. Theme 1: clinical trial design/end points (4 questions), related to optimum trial designs for polyp detection and characterization, determining the optimal end points for evaluation of AI, and demonstrating impact on interval cancer rates. Theme 2: technological developments (3 questions), including improving detection of more challenging and advanced lesions, reduction of false-positive rates, and minimizing latency. Theme 3: clinical adoption/integration (1 question), concerning the effective combination of detection and characterization into one workflow. Theme 4: data access/annotation (1 question), concerning more efficient or automated data annotation methods to reduce the burden on human experts. Theme 5: regulatory approval (1 question), related to making regulatory approval processes more efficient. Conclusions This is the first reported international research priority setting exercise for AI in colonoscopy. The study findings should be used as a framework to guide future research with key stakeholders to accelerate the clinical implementation of AI in endoscopy.

Published
2020

20. Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method

Author

Ahmad, Omer F., additional, Mori, Yuichi, additional, Misawa, Masashi, additional, Kudo, Shin-ei, additional, Anderson, John T., additional, Bernal, Jorge, additional, Berzin, Tyler M., additional, Bisschops, Raf, additional, Byrne, Michael F., additional, Chen, Peng-Jen, additional, East, James E., additional, Eelbode, Tom, additional, Elson, Daniel S., additional, Gurudu, Suryakanth R., additional, Histace, Aymeric, additional, Karnes, William E., additional, Repici, Alessandro, additional, Singh, Rajvinder, additional, Valdastri, Pietro, additional, Wallace, Michael B., additional, Wang, Pu, additional, Stoyanov, Danail, additional, and Lovat, Laurence B., additional

Published
2020
Full Text
View/download PDF

23. 879 A PROSPECTIVE MULTI-CENTER VALIDATION STUDY FOR AUTOMATED POLYP DETECTION AS A SECOND OBSERVER

Author

Eelbode, Tom, primary, Hassan, Cesare, additional, Neumann, Helmut, additional, Demedts, Ingrid, additional, Sinonquel, Pieter, additional, Roelandt, Philip, additional, Camps, Chelsea, additional, Coron, Emmanuel, additional, Bhandari, Pradeep, additional, Pech, Oliver, additional, Willekens, Hilde, additional, Maes, Frederik, additional, and Bisschops, Raf, additional

Published
2020
Full Text
View/download PDF

26. Automatic, computer-aided determination of endoscopic and histological inflammation in patients with mild to moderate ulcerative colitis based on red density

Author

Bossuyt, Peter, primary, Nakase, Hiroshi, additional, Vermeire, Séverine, additional, de Hertogh, Gert, additional, Eelbode, Tom, additional, Ferrante, Marc, additional, Hasegawa, Tadashi, additional, Willekens, Hilde, additional, Ikemoto, Yousuke, additional, Makino, Takao, additional, and Bisschops, Raf, additional

Published
2020
Full Text
View/download PDF

30. Tu1931 INCORPORATION OF TEMPORAL INFORMATION IN A DEEP NEURAL NETWORK IMPROVES PERFORMANCE LEVEL FOR AUTOMATED POLYP DETECTION AND DELINEATION

Author

Eelbode, Tom, primary, Demedts, Ingrid, additional, Bisschops, Raf, additional, Roelandt, Philip, additional, Hassan, Cesare, additional, Coron, Emmanuel, additional, Bhandari, Pradeep, additional, Neumann, Helmut, additional, Pech, Oliver, additional, Repici, Alessandro, additional, and Maes, Frederik, additional

Published
2019
Full Text
View/download PDF

31. Artificial intelligence and its impact on quality improvement in upper and lower gastrointestinal endoscopy.

Author

Sinonquel, Pieter, Eelbode, Tom, Bossuyt, Peter, Maes, Frederik, and Bisschops, Raf

Subjects
*ENDOSCOPY, *ARTIFICIAL intelligence, *DIAGNOSIS, *REGULATORY approval, *COLONOSCOPY
Abstract

Artificial intelligence (AI) and its application in medicine has grown large interest. Within gastrointestinal (GI) endoscopy, the field of colonoscopy and polyp detection is the most investigated, however, upper GI follows the lead. Since endoscopy is performed by humans, it is inherently an imperfect procedure. Computer‐aided diagnosis may improve its quality by helping prevent missing lesions and supporting optical diagnosis for those detected. An entire evolution in AI systems has been established in the last decades, resulting in optimization of the diagnostic performance with lower variability and matching or even outperformance of expert endoscopists. This shows a great potential for future quality improvement of endoscopy, given the outstanding diagnostic features of AI. With this narrative review, we highlight the potential benefit of AI to improve overall quality in daily endoscopy and describe the most recent developments for characterization and diagnosis as well as the recent conditions for regulatory approval. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

33. Building Machine Learning Models in Gastrointestinal Endoscopy

Author

Antonelli, Giulio, Eelbode, Tom, Elsaman, Touka, Sharma, Mrigya, Bisschops, Raf, and Hassan, Cesare

Abstract

The integration of artificial intelligence (AI) into gastrointestinal (GI) endoscopy heralds a transformative shift in diagnostic capabilities, promising significant improvements in accuracy and efficiency. AI's ability to provide precise, real-time analysis can significantly aid endoscopists in detecting and characterizing various GI conditions, such as polyps, adenomas, and other lesions, potentially leading to improved patient outcomes through earlier detection and more accurate diagnoses. However, the current landscape of machine learning models in GI endoscopy is fraught with considerable variability in methodologies and quality, posing challenges for validation and generalization. Key issues include inconsistent reference standards across studies, a lack of external validation, and the use of disease-prevalence-enriched populations. These factors result in discrepancies in performance metrics and limit the comparability of results. Furthermore, the common practice of using high-quality imagery that does not reflect routine clinical practice can lead to AI models that underperform in real-world settings. To ensure the effective integration of AI in clinical practice, it is crucial to develop and validate models rigorously across diverse and representative datasets. This involves standardizing reference standards, ensuring thorough external validation, using representative patient populations, and incorporating a range of image qualities. Addressing these methodological discrepancies will enhance the reliability and robustness of AI models, thereby facilitating their adoption and improving patient care in GI endoscopy.

Published
2024
Full Text
View/download PDF

34. Development of an automated tool for the estimation of histological remission in ulcerative colitis using single wavelength endoscopy technology.

Author

Sinonquel P, Lenfant M, Eelbode T, Watanabe H, Callaerts B, Bossuyt P, Verstockt B, Sabino JPG, De Hertogh G, Maes F, Vermeire S, and Bisschops R

Abstract

Introduction: Ulcerative colitis (UC) management employs a strategy targeting histological and endoscopic remission. Correlation of white-light endoscopy (WLE) scores with histological activity is limited. Single-wavelength endoscopy (SWE) addressing microvascular changes reflecting histological disease activity, may better assess histological remission., Aims and Methods: Our goal was to assess the accuracy of a computer-aided diagnosis (CAD) system for histological activity estimation in UC, based on either WLE or SWE. We collected 6926 sets of corresponding WLE and SWE frames in 112 patients with UC, using a prototype endoscopic system enabling both imaging methods (FUJIFILM, Tokyo, Japan). Histological remission (Geboes score ≤2B.0) assessed at the location of imaging was annotated for all frames and separate WLE-CAD and SWE-CAD models were trained using deep learning for automated detection of histological remission with either imaging modality., Results: Initial training of both models on the same subset of 42 patients, resulted in SWE-CAD outperforming WLE-CAD with a mean sensitivity of 88.0% vs 73.9% (p < 0.001), a mean specificity of 71.7% vs 65.6% (p=0.45), and a diagnostic accuracy of 83.3% vs 67.5% (p<0.005), respectively. Further training of the SWE-CAD model on the entire dataset of 112 patients resulted in SWE-CAD achieving a 95.2% accuracy, 96.4% sensitivity, and 92.9% specificity on a section level., Conclusion: By utilizing automated CAD based on non-magnifying SWE for enhanced capillary visibility versus WLE, histological remission was detected with 95.2% diagnostic accuracy in patients with UC, offering stable objectivity and helping to exclude inter-reader variability., (© The Author(s) 2024. Published by Oxford University Press on behalf of European Crohn’s and Colitis Organisation. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com.)

Published
2024
Full Text
View/download PDF

35. QUAIDE - Quality assessment of AI preclinical studies in diagnostic endoscopy.

Author

Antonelli G, Libanio D, De Groof AJ, van der Sommen F, Mascagni P, Sinonquel P, Abdelrahim M, Ahmad O, Berzin T, Bhandari P, Bretthauer M, Coimbra M, Dekker E, Ebigbo A, Eelbode T, Frazzoni L, Gross SA, Ishihara R, Kaminski MF, Messmann H, Mori Y, Padoy N, Parasa S, Pilonis ND, Renna F, Repici A, Simsek C, Spadaccini M, Bisschops R, Bergman JJGHM, Hassan C, and Dinis Ribeiro M

Abstract

Artificial intelligence (AI) holds significant potential for enhancing quality of gastrointestinal (GI) endoscopy, but the adoption of AI in clinical practice is hampered by the lack of rigorous standardisation and development methodology ensuring generalisability. The aim of the Quality Assessment of pre-clinical AI studies in Diagnostic Endoscopy (QUAIDE) Explanation and Checklist was to develop recommendations for standardised design and reporting of preclinical AI studies in GI endoscopy.The recommendations were developed based on a formal consensus approach with an international multidisciplinary panel of 32 experts among endoscopists and computer scientists. The Delphi methodology was employed to achieve consensus on statements, with a predetermined threshold of 80% agreement. A maximum three rounds of voting were permitted.Consensus was reached on 18 key recommendations, covering 6 key domains: data acquisition and annotation (6 statements), outcome reporting (3 statements), experimental setup and algorithm architecture (4 statements) and result presentation and interpretation (5 statements). QUAIDE provides recommendations on how to properly design (1. Methods, statements 1-14), present results (2. Results, statements 15-16) and integrate and interpret the obtained results (3. Discussion, statements 17-18).The QUAIDE framework offers practical guidance for authors, readers, editors and reviewers involved in AI preclinical studies in GI endoscopy, aiming at improving design and reporting, thereby promoting research standardisation and accelerating the translation of AI innovations into clinical practice., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2024. No commercial re-use. See rights and permissions. Published by BMJ.)

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results