Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus
-
Published:2023-07-21
Issue:
Volume:
Page:
-
ISSN:1861-6429
-
Container-title:International Journal of Computer Assisted Radiology and Surgery
-
language:en
-
Short-container-title:Int J CARS
Author:
Bhattacharya Debayan,Behrendt Finn,Becker Benjamin Tobias,Beyersdorff Dirk,Petersen Elina,Petersen Marvin,Cheng Bastian,Eggert Dennis,Betz Christian,Hoffmann Anna Sophie,Schlaefer Alexander
Abstract
Abstract
Purpose
Paranasal anomalies are commonly discovered during routine radiological screenings and can present with a wide range of morphological features. This diversity can make it difficult for convolutional neural networks (CNNs) to accurately classify these anomalies, especially when working with limited datasets. Additionally, current approaches to paranasal anomaly classification are constrained to identifying a single anomaly at a time. These challenges necessitate the need for further research and development in this area.
Methods
We investigate the feasibility of using a 3D convolutional neural network (CNN) to classify healthy maxillary sinuses (MS) and MS with polyps or cysts. The task of accurately localizing the relevant MS volume within larger head and neck Magnetic Resonance Imaging (MRI) scans can be difficult, but we develop a strategy which includes the use of a novel sampling technique that not only effectively localizes the relevant MS volume, but also increases the size of the training dataset and improves classification results. Additionally, we employ a Multiple Instance Ensembling (MIE) prediction method to further boost classification performance.
Results
With sampling and MIE, we observe that there is consistent improvement in classification performance of all 3D ResNet and 3D DenseNet architecture with an average AUPRC percentage increase of 21.86 ± 11.92% and 4.27 ± 5.04% by sampling and 28.86 ± 12.80% and 9.85 ± 4.02% by sampling and MIE, respectively.
Conclusion
Sampling and MIE can be effective techniques to improve the generalizability of CNNs for paranasal anomaly classification. We demonstrate the feasibility of classifying anomalies in the MS. We propose a data enlarging strategy through sampling alongside a novel MIE strategy that proves to be beneficial for paranasal anomaly classification in the MS.
Funder
Technische Universität Hamburg
Publisher
Springer Science and Business Media LLC
Subject
Health Informatics,Radiology, Nuclear Medicine and imaging,General Medicine,Surgery,Computer Graphics and Computer-Aided Design,Computer Science Applications,Computer Vision and Pattern Recognition,Biomedical Engineering
Reference29 articles.
1. Martini, F., Timmons, M.J., Tallitsch, R.B.: Human anatomy. 6th edn. San Francisco, Pearson Benjamin Cummings (2009)
2. Bal M, Berkiten G, Uyanık E (2014) Mucous retention cysts of the paranasal sinuses. Hippokratia 18(4):379
3. Varshney H, Varshney J, Biswas S, Ghosh SK (2015) Importance of CT scan of paranasal sinuses in the evaluation of the anatomical findings in patients suffering from sinonasal polyposis. Indian J Otolaryngol Head Neck Surg 68(2):167–172
4. Hansen AG, Helvik A-S, Nordgård S, Bugten V, Stovner LJ, Håberg AK, Gårseth M, Eggesbø HB (2014) Incidental findings in MRI of the paranasal sinuses in adults: a population-based study (hunt MRI). BMC Ear, Nose, and Throat Disord 14(1):13. https://doi.org/10.1186/1472-6815-14-13
5. Tarp B, Fiirgaard B, Christensen T, Jensen JJ, Black FT (2000) The prevalence and significance of incidental paranasal sinus abnormalities on MRI. Rhinology 38(1):33–38
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献