Artificial intelligence for automatic detection and segmentation of nasal polyposis: a pilot study.

Artificial intelligence Data analysis Diagnosis Nasal polyps Sinusitis

Journal

European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery
ISSN: 1434-4726
Titre abrégé: Eur Arch Otorhinolaryngol
Pays: Germany
ID NLM: 9002937

Informations de publication

Date de publication:
13 Jul 2024
Historique:
received: 18 04 2024
accepted: 23 06 2024
medline: 14 7 2024
pubmed: 14 7 2024
entrez: 13 7 2024
Statut: aheadofprint

Résumé

Accurate diagnosis and quantification of polyps and symptoms are pivotal for planning the therapeutic strategy of Chronic rhinosinusitis with nasal polyposis (CRSwNP). This pilot study aimed to develop an artificial intelligence (AI)-based image analysis system capable of segmenting nasal polyps from nasal endoscopy videos. Recorded nasal videoendoscopies from 52 patients diagnosed with CRSwNP between 2019 and 2022 were retrospectively analyzed. Images extracted were manually segmented on the web application Roboflow. A dataset of 342 images was generated and divided into training (80%), validation (10%), and testing (10%) sets. The Ultralytics YOLOv8.0.28 model was employed for automated segmentation. The YOLOv8s-seg model consisted of 195 layers and required 42.4 GFLOPs for operation. When tested against the validation set, the algorithm achieved a precision of 0.91, recall of 0.839, and mean average precision at 50% IoU (mAP50) of 0.949. For the segmentation task, similar metrics were observed, including a mAP ranging from 0.675 to 0.679 for IoUs between 50% and 95%. The study shows that a carefully trained AI algorithm can effectively identify and delineate nasal polyps in patients with CRSwNP. Despite certain limitations like the focus on CRSwNP-specific samples, the algorithm presents a promising complementary tool to existing diagnostic methods.

Identifiants

DOI: 10.1007/s00405-024-08809-4 PMID: 39001915
pubmed: 39001915
doi: 10.1007/s00405-024-08809-4
pii: 10.1007/s00405-024-08809-4
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Références

Fokkens WJ, Viskens AS, Backer V et al (2023) EPOS/EUFOREA update on indication and evaluation of Biologics in Chronic Rhinosinusitis with nasal polyps. Rhinology 61(3):194–202. https://doi.org/10.4193/Rhin22.489
doi: 10.4193/Rhin22.489 pubmed: 36999780
Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25(1):44–56. https://doi.org/10.1038/s41591-018-0300-7
doi: 10.1038/s41591-018-0300-7 pubmed: 30617339
Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88. https://doi.org/10.1016/j.media.2017.07.005
doi: 10.1016/j.media.2017.07.005 pubmed: 28778026
Xu J, Wang J, Bian X et al (2022) Deep learning for nasopharyngeal Carcinoma Identification using both white light and narrow-Band Imaging Endoscopy. Laryngoscope 132(5):999–1007. https://doi.org/10.1002/lary.29894
doi: 10.1002/lary.29894 pubmed: 34622964
Wu Q, Wang X, Liang G et al (2023) Advances in image-based Artificial Intelligence in Otorhinolaryngology-Head and Neck surgery: a systematic review. Otolaryngol Head Neck Surg 169(5):1132–1142. https://doi.org/10.1002/ohn.391
doi: 10.1002/ohn.391 pubmed: 37288505
Mäkitie AA, Alabi RO, Ng SP et al (2023) Artificial Intelligence in Head and Neck Cancer: a systematic review of systematic reviews. Adv Ther 40(8):3360–3380. https://doi.org/10.1007/s12325-023-02527-9
doi: 10.1007/s12325-023-02527-9 pubmed: 37291378 pmcid: 10329964
Bulfamante AM, Ferella F, Miller AM et al (2023) Artificial intelligence, machine learning, and deep learning in rhinology: a systematic review. Eur Arch Otorhinolaryngol 280(2):529–542. https://doi.org/10.1007/s00405-022-07701-3
doi: 10.1007/s00405-022-07701-3 pubmed: 36260141
Osie G, Darbari Kaul R, Alvarado R et al (2023) A Scoping Review of Artificial Intelligence Research in Rhinology. Am J Rhinol Allergy 37(4):438–448. https://doi.org/10.1177/19458924231162437
doi: 10.1177/19458924231162437 pubmed: 36895144
Paderno A, Gennarini F, Sordi A et al (2022) Artificial intelligence in clinical endoscopy: insights in the field of videomics. Front Surg 9:933297. https://doi.org/10.3389/fsurg.2022.933297
doi: 10.3389/fsurg.2022.933297 pubmed: 36171813 pmcid: 9510389
Paderno A, Villani FP, Fior M et al (2023) Instance segmentation of upper aerodigestive tract cancer: site-specific outcomes. Acta Otorhinolaryngol Ital 43(4):283–290. https://doi.org/10.14639/0392-100X-N2336
doi: 10.14639/0392-100X-N2336 pubmed: 37488992 pmcid: 10366566
Bi M, Zheng S, Li X et al (2023) MIB-ANet: a novel multi-scale deep network for nasal endoscopy-based adenoid hypertrophy grading. Front Med (Lausanne) 10:1142261. https://doi.org/10.3389/fmed.2023.1142261
doi: 10.3389/fmed.2023.1142261 pubmed: 37122318
Li C, Jing B, Ke L et al (2018) Development and validation of an endoscopic images-based deep learning model for detection with nasopharyngeal malignancies. Cancer Commun (Lond) 38(1):59. https://doi.org/10.1186/s40880-018-0325-9
doi: 10.1186/s40880-018-0325-9 pubmed: 30253801
Liu X, Sinha A, Ishii M et al (2020) Dense depth estimation in Monocular Endoscopy with Self-supervised learning methods. IEEE Trans Med Imaging 39(5):1438–1447. https://doi.org/10.1109/TMI.2019.2950936
doi: 10.1109/TMI.2019.2950936 pubmed: 31689184
Girdler B, Moon H, Bae MR, Ryu SS, Bae J, Yu MS (2021) Feasibility of a deep learning-based algorithm for automated detection and classification of nasal polyps and inverted papillomas on nasal endoscopic images. Int Forum Allergy Rhinol 11(12):1637–1646. https://doi.org/10.1002/alr.22854
doi: 10.1002/alr.22854 pubmed: 34148298
Shu C, Yan H, Zheng W et al (2021) Deep learning-guided fiberoptic Raman Spectroscopy enables real-time in vivo diagnosis and Assessment of Nasopharyngeal Carcinoma and Post-treatment Efficacy during Endoscopy. Anal Chem 93(31):10898–10906. https://doi.org/10.1021/acs.analchem.1c01559
doi: 10.1021/acs.analchem.1c01559 pubmed: 34319713
Staartjes VE, Volokitin A, Regli L, Konukoglu E, Serra C (2021) Machine vision for Real-Time Intraoperative Anatomic Guidance: a proof-of-Concept study in endoscopic pituitary surgery. Oper Neurosurg (Hagerstown) 21(4):242–247. https://doi.org/10.1093/ons/opab187
doi: 10.1093/ons/opab187 pubmed: 34131753
Kwon KW, Park SH, Lee DH et al (2024) Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images. PLoS ONE 19(3):e0297536. https://doi.org/10.1371/journal.pone.0297536
doi: 10.1371/journal.pone.0297536 pubmed: 38478548 pmcid: 10936791

Auteurs

Vittorio Rampinelli (V)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy. vittorio.rampinelli@gmail.com.
ORCID: 0000-0002-0901-6266

Alberto Paderno (A)

Otorhinolaryngology Unit, IRCCS Humanitas Research Hospital, Milano, Italy.

Carlo Conti (C)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Gabriele Testa (G)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Claudia Lodovica Modesti (CL)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Edoardo Agosti (E)

Division of Neurosurgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Isabelle Dohin (I)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Tommaso Saccardo (T)

Section of Otorhinolaryngology - Head and Neck Surgery, Department of Neurosciences, University of Padova, Padova, PD, Italy.

Alessandro Vinciguerra (A)

Otorhinolaryngology and Skull Base Center, AP-HP, Hospital Lariboisière, Paris, France.

Marco Ferrari (M)

Section of Otorhinolaryngology - Head and Neck Surgery, Department of Neurosciences, University of Padova, Padova, PD, Italy.

Alberto Schreiber (A)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Davide Mattavelli (D)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Piero Nicolai (P)

Section of Otorhinolaryngology - Head and Neck Surgery, Department of Neurosciences, University of Padova, Padova, PD, Italy.

Chris Holsinger (C)

Division of Head and Neck Surgery, Department of Otolaryngology, Stanford University, Palo Alto, CA, USA.

Cesare Piazza (C)

Unit of Otorhinolaryngology - Head and Neck Surgery, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, School of Medicine, ASST Spedali Civili, University of Brescia, Brescia, Italy.

Classifications MeSH