Sage Journals: Discover world-class research

Abstract

Background

Computed tomography (CT) plays a crucial role in assessing chronic rhinosinusitis, but lacks objective quantifiable indicators.

Objective

This study aimed to use deep learning for automated sinus segmentation to generate distinct quantitative scores and explore their correlations with disease-specific quality of life.

Methods

From July 2021 to August 2022, 445 CT data were collected from 2 medical centers. A deep learning model based on nnU-Net was trained for automatic sinus segmentation and internally validated using 300 cases. The remaining 145 cases were split into an external testing set (74 cases) and an independent testing set (71 cases). Two quantitative scores, the quantitative Lund-MacKay score and the quantitative opacification score (QOS), were derived from the segmentation results. The quantitative scores’ efficacy was assessed by comparing them with the Lund-MacKay score (LMS), the 22-item Sinonasal Outcome Test score (SNOT-22), and other clinical variables through correlation analyses. Furthermore, the relationship between quantitative scores and postoperative quality of life improvement was explored using single-factor logistic regression.

Result

The segmentation model achieved average Dice similarity coefficients of 0.993, 0.978, 0.958, and 0.871 for the training, validation, external testing, and independent testing sets, respectively. Both quantitative scores significantly correlated with the LMS (rho = 0.87 and rho = 0.70, P < .001). Neither score correlated with the total SNOT-22 score, although the modified QOS showed significant correlations with the nasal and sleep subdomains (rho = 0.26 and rho = 0.27, P < .05). No significant association was found between quantitative score and postoperative improvement in quality of life.

Conclusion

Deep learning enables the automated segmentation of sinuses on CT scans, producing quantitative scores of sinus opacification. These automatic quantitative scores may serve as tools for chronic rhinosinusitis assessment.

Keywords

chronic rhinosinusitis CT scan deep learning sinus imaging radiology SNOT-22 AI quality-of-life Lund-MacKay score

Get full access to this article

View all access options for this article.

References

Fokkens

Lund

Hopkins

, et al. European position paper on rhinosinusitis and nasal polyps 2020. Rhinology. 2020;58(Suppl S29):1-464. 20200220, doi:https://doi.org/10.4193/Rhin20.600

Orlandi

Kingdom

Smith

, et al. International consensus statement on allergy and rhinology: Rhinosinusitis 2021. Int Forum Allergy Rhinol. 2021;11(3):213-739. doi:https://doi.org/10.1002/alr.22741

Lund

Mackay

. Staging in rhinosinusitus. Rhinology. 1993;31(4):183-184.

Hopkins

Browne

Slack

, et al.

The Lund-Mackay staging system for chronic rhinosinusitis: How is it used and what does it predict?

Otolaryngol Head Neck Surg. 2007;137(4):555-561. doi:https://doi.org/10.1016/j.otohns.2007.02.004

Pallanch

Delone

, et al. Three-dimensional volumetric computed tomographic scoring as an objective outcome measure for chronic rhinosinusitis: Clinical correlations and comparison to Lund-Mackay scoring. Int Forum Allergy Rhinol. 2013;3(12):963-972. 20130917, doi:https://doi.org/10.1002/alr.21219

Likness

Pallanch

Sherris

, et al. Computed tomography scans as an objective measure of disease severity in chronic rhinosinusitis. Otolaryngol Head Neck Surg. 2014;150(2):305-311. 20131203, doi:https://doi.org/10.1177/0194599813513881

Garneau

Ramirez

Armato

3rd , et al. Computer-assisted staging of chronic rhinosinusitis correlates with symptoms. Int Forum Allergy Rhinol. 2015;5(7):637-642. 20150408, doi:https://doi.org/10.1002/alr.21499

Lim

Ramirez

Garneau

, et al. Three-dimensional image analysis for staging chronic rhinosinusitis. Int Forum Allergy Rhinol. 2017;7(11):1052-1057. 20170922, doi:https://doi.org/10.1002/alr.22014

Iwamoto

Xiong

Kitamura

, et al. Automatic segmentation of the paranasal sinus from computer tomography images using a probabilistic atlas and a fully convolutional network. Annu Int Conf IEEE Eng Med Biol Soc. 2019;2019:2789-2792. doi:https://doi.org/10.1109/EMBC.2019.8856703

10.

Humphries

Centeno

Notary

, et al. Volumetric assessment of paranasal sinus opacification on computed tomography can be automated using a convolutional neural network. Int Forum Allergy Rhinol. 2020;10(11):1218-1225. 20200615, doi:https://doi.org/10.1002/alr.22588

11.

Wang

Zhou

, et al. Automatic CT image segmentation of maxillary sinus based on VGG network and improved V-Net. Int J Comput Assist Radiol Surg. 2020;15(9):1457-1465. 20200716, doi:https://doi.org/10.1007/s11548-020-02228-6

12.

Jung

Lim

Lee

, et al. Deep active learning for automatic segmentation of maxillary Sinus lesions using a convolutional neural network. Diagnostics (Basel) 2021;11(4):688. 20210412, doi:https://doi.org/10.3390/diagnostics11040688

13.

Zhong

Cui

Adaptive localizing region-based level set for segmentation of maxillary sinus based on convolutional neural networks. Comput Intell Neurosci. 2021;2021:4824613. 20211111, doi:https://doi.org/10.1155/2021/4824613

14.

Hung

QYH

King

, et al. Automatic detection and segmentation of morphological changes of the maxillary sinus mucosa on cone-beam computed tomography images using a three-dimensional convolutional neural network. Clin Oral Investig. 2022;26(5):3987-3998. 20220115, doi:https://doi.org/10.1007/s00784-021-04365-x

15.

Kuo

Liao

Barman

, et al. Semi-supervised deep learning semantic segmentation for 3D volumetric computed tomographic scoring of chronic rhinosinusitis: Clinical correlations and comparison with Lund-Mackay scoring. Tomography. 2022;8(2):718-729. 20220307, doi:https://doi.org/10.3390/tomography8020059

16.

Cheng

Montagnon

Yamashita

, et al. Deep learning: An update for radiologists. Radiographics. 2021;41(5):1427-1445. doi:https://doi.org/10.1148/rg.2021200210

17.

Siddique

Paheding

Elkin

, et al. U-Net and its variants for medical image segmentation: A review of theory and applications. IEEE Access. 2021;9:82031-82057. doi:https://doi.org/10.1109/ACCESS.2021.3086020

18.

Ronneberger

Fischer

Brox

U-Net: Convolutional networks for biomedical image segmentation. ArXiv 2015; abs/1505.04597.

19.

Isensee

Jaeger

Kohl

SAA

, et al. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203-211. doi:https://doi.org/10.1038/s41592-020-01008-z

20.

Hopkins

Gillett

Slack

, et al. Psychometric validity of the 22-item sinonasal outcome test. Clin Otolaryngol. 2009;34(5):447-454. doi:https://doi.org/10.1111/j.1749-4486.2009.01995.x

21.

Chowdhury

Mace

Bodner

, et al. Investigating the minimal clinically important difference for SNOT-22 symptom domains in surgically managed chronic rhinosinusitis. Int Forum Allergy Rhinol. 2017;7(12):1149-1155. 20171020, doi:https://doi.org/10.1002/alr.22028

22.

ten Brinke

Grootendorst

Schmidt

, et al. Chronic sinusitis in severe asthma is related to sputum eosinophilia. J Allergy Clin Immunol. 2002;109(4):621-626. doi:https://doi.org/10.1067/mai.2002.122458

23.

Kimura

Konno

Nakamaru

, et al. Sinus computed tomographic findings in adult smokers and nonsmokers with asthma. Analysis of clinical indices and biomarkers. Ann Am Thorac Soc. 2017;14(3):332-341. doi:https://doi.org/10.1513/AnnalsATS.201606-463OC

24.

Basu

Georgalas

Kumar

, et al. Correlation between symptoms and radiological findings in patients with chronic rhinosinusitis: An evaluation study using the sinonasal assessment questionnaire and Lund-Mackay grading system. Eur Arch Otorhinolaryngol. 2005;262(9):751-754. 20050308, doi:https://doi.org/10.1007/s00405-004-0891-0

25.

Garetier

Barberot

Chinellato

, et al. Clinical-radiological correlation after functional endoscopic sinus surgery in patients with chronic rhinosinusitis: Interest of a sinonasal aerial volumetry. Rhinology. 2013;51(2):162-170. doi:https://doi.org/10.4193/Rhino12.131

26.

Leung

Kern

Conley

, et al. Osteomeatal complex obstruction is not associated with adjacent sinus disease in chronic rhinosinusitis with polyps. Am J Rhinol Allergy. 2011;25(6):401-403. doi:https://doi.org/10.2500/ajra.2011.25.3672

27.

Snidvongs

Chin

Sacks

, et al. Eosinophilic rhinosinusitis is not a disease of ostiomeatal occlusion. Laryngoscope. 2013;123(5):1070-1074. 20130402, doi:https://doi.org/10.1002/lary.23721

28.

Massey

Ramos

Beswick

, et al. Clinical validation and extension of an automated, deep learning-based algorithm for quantitative sinus CT analysis. AJNR Am J Neuroradiol. 2022;43(9):1318-1324. doi:https://doi.org/10.3174/ajnr.A7616

29.

Kuo

C-FJ

Liu

S-C

. Fully automatic segmentation, identification and preoperative planning for nasal surgery of sinuses using semi-supervised learning and volumetric reconstruction. Mathematics. 2022;10(7):1189.

30.

Wabnitz

Nair

Wormald

. Correlation between preoperative symptom scores, quality-of-life questionnaires, and staging with computed tomography in patients with chronic rhinosinusitis. Am J Rhinol. 2005;19(1):91-96.

31.

Kenny

Duncavage

Bracikowski

, et al. Prospective analysis of sinus symptoms and correlation with paranasal computed tomography scan. Otolaryngol Head Neck Surg. 2001;125(1):40-43. doi:https://doi.org/10.1067/mhn.2001.116779

32.

Sedaghat

Bhattacharyya

Chronic rhinosinusitis symptoms and computed tomography staging: Improved correlation by incorporating radiographic density. Int Forum Allergy Rhinol. 2012;2(5):386-391. 20120430, doi:https://doi.org/10.1002/alr.21042

33.

Brooks

Trope

Blasetti

, et al. Preoperative Lund-Mackay computed tomography score is associated with preoperative symptom severity and predicts quality-of-life outcome trajectories after sinus surgery. Int Forum Allergy Rhinol. 2018;8(6):668-675. 20180308, doi:https://doi.org/10.1002/alr.22109

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.22 MB

Deep Learning-Derived Quantitative Scores for Chronic Rhinosinusitis Assessment: Correlation With Quality of Life Outcomes

Abstract

Background

Objective

Methods

Result

Conclusion

Keywords

Get full access to this article

References

Supplementary Material