Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging
Abstract Background The SI-CURA project (Soluzioni Innovative per la gestione del paziente e il follow up terapeutico della Colite UlceRosA) is an Italian initiative aimed at the development of artificial intelligence solutions to discriminate pathologies of different nature, including inflammatory...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-02043-w |
| _version_ | 1797355756571328512 |
|---|---|
| author | Marco Chierici Nicolae Puica Matteo Pozzi Antonello Capistrano Marcello Dorian Donzella Antonio Colangelo Venet Osmani Giuseppe Jurman |
| author_facet | Marco Chierici Nicolae Puica Matteo Pozzi Antonello Capistrano Marcello Dorian Donzella Antonio Colangelo Venet Osmani Giuseppe Jurman |
| author_sort | Marco Chierici |
| collection | DOAJ |
| description | Abstract Background The SI-CURA project (Soluzioni Innovative per la gestione del paziente e il follow up terapeutico della Colite UlceRosA) is an Italian initiative aimed at the development of artificial intelligence solutions to discriminate pathologies of different nature, including inflammatory bowel disease (IBD), namely Ulcerative Colitis (UC) and Crohn’s disease (CD), based on endoscopic imaging of patients (P) and healthy controls (N). Methods In this study we develop a deep learning (DL) prototype to identify disease patterns through three binary classification tasks, namely (1) discriminating positive (pathological) samples from negative (healthy) samples (P vs N); (2) discrimination between Ulcerative Colitis and Crohn’s Disease samples (UC vs CD) and, (3) discrimination between Ulcerative Colitis and negative (healthy) samples (UC vs N). Results The model derived from our approach achieves a high performance of Matthews correlation coefficient (MCC) > 0.9 on the test set for P versus N and UC versus N, and MCC > 0.6 on the test set for UC versus CD. Conclusion Our DL model effectively discriminates between pathological and negative samples, as well as between IBD subgroups, providing further evidence of its potential as a decision support tool for endoscopy-based diagnosis. |
| first_indexed | 2024-03-08T14:15:38Z |
| format | Article |
| id | doaj.art-e77ed6c287f94494b01e077870e22102 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-03-08T14:15:38Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-e77ed6c287f94494b01e077870e221022024-01-14T12:25:35ZengBMCBMC Medical Informatics and Decision Making1472-69472022-11-0122S611010.1186/s12911-022-02043-wAutomatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imagingMarco Chierici0Nicolae Puica1Matteo Pozzi2Antonello Capistrano3Marcello Dorian Donzella4Antonio Colangelo5Venet Osmani6Giuseppe Jurman7Fondazione Bruno KesslerPagoPA S.p.A.Fondazione Bruno KesslerGPI S.p.A.GPI S.p.A.GPI S.p.A.Fondazione Bruno KesslerFondazione Bruno KesslerAbstract Background The SI-CURA project (Soluzioni Innovative per la gestione del paziente e il follow up terapeutico della Colite UlceRosA) is an Italian initiative aimed at the development of artificial intelligence solutions to discriminate pathologies of different nature, including inflammatory bowel disease (IBD), namely Ulcerative Colitis (UC) and Crohn’s disease (CD), based on endoscopic imaging of patients (P) and healthy controls (N). Methods In this study we develop a deep learning (DL) prototype to identify disease patterns through three binary classification tasks, namely (1) discriminating positive (pathological) samples from negative (healthy) samples (P vs N); (2) discrimination between Ulcerative Colitis and Crohn’s Disease samples (UC vs CD) and, (3) discrimination between Ulcerative Colitis and negative (healthy) samples (UC vs N). Results The model derived from our approach achieves a high performance of Matthews correlation coefficient (MCC) > 0.9 on the test set for P versus N and UC versus N, and MCC > 0.6 on the test set for UC versus CD. Conclusion Our DL model effectively discriminates between pathological and negative samples, as well as between IBD subgroups, providing further evidence of its potential as a decision support tool for endoscopy-based diagnosis.https://doi.org/10.1186/s12911-022-02043-wArtificial intelligenceMachine learningInflammatory bowel diseaseEndoscopyPredictive modelsDiagnosis |
| spellingShingle | Marco Chierici Nicolae Puica Matteo Pozzi Antonello Capistrano Marcello Dorian Donzella Antonio Colangelo Venet Osmani Giuseppe Jurman Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging BMC Medical Informatics and Decision Making Artificial intelligence Machine learning Inflammatory bowel disease Endoscopy Predictive models Diagnosis |
| title | Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging |
| title_full | Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging |
| title_fullStr | Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging |
| title_full_unstemmed | Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging |
| title_short | Automatically detecting Crohn’s disease and Ulcerative Colitis from endoscopic imaging |
| title_sort | automatically detecting crohn s disease and ulcerative colitis from endoscopic imaging |
| topic | Artificial intelligence Machine learning Inflammatory bowel disease Endoscopy Predictive models Diagnosis |
| url | https://doi.org/10.1186/s12911-022-02043-w |
| work_keys_str_mv | AT marcochierici automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT nicolaepuica automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT matteopozzi automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT antonellocapistrano automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT marcellodoriandonzella automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT antoniocolangelo automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT venetosmani automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging AT giuseppejurman automaticallydetectingcrohnsdiseaseandulcerativecolitisfromendoscopicimaging |