{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:25:42Z","timestamp":1740144342516,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T00:00:00Z","timestamp":1689897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100023890","name":"Technische Universit\u00e4t Hamburg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100023890","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>\n                           <jats:bold>Purpose<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Methods<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>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.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Results<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>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 \u00b1 11.92% and 4.27 \u00b1 5.04% by sampling and 28.86 \u00b1 12.80% and 9.85 \u00b1 4.02% by sampling and MIE, respectively.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Conclusion<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>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.\n<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-023-02990-3","type":"journal-article","created":{"date-parts":[[2023,7,21]],"date-time":"2023-07-21T16:03:04Z","timestamp":1689955384000},"page":"223-231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus"],"prefix":"10.1007","volume":"19","author":[{"given":"Debayan","family":"Bhattacharya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Finn","family":"Behrendt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin Tobias","family":"Becker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Beyersdorff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elina","family":"Petersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marvin","family":"Petersen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Eggert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Betz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna Sophie","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Schlaefer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,21]]},"reference":[{"key":"2990_CR1","unstructured":"Martini, F., Timmons, M.J., Tallitsch, R.B.: Human anatomy. 6th edn. San Francisco, Pearson Benjamin Cummings (2009)"},{"issue":"4","key":"2990_CR2","first-page":"379","volume":"18","author":"M Bal","year":"2014","unstructured":"Bal M, Berkiten G, Uyan\u0131k E (2014) Mucous retention cysts of the paranasal sinuses. Hippokratia 18(4):379","journal-title":"Hippokratia"},{"issue":"2","key":"2990_CR3","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s12070-015-0827-6","volume":"68","author":"H Varshney","year":"2015","unstructured":"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\u2013172","journal-title":"Indian J Otolaryngol Head Neck Surg"},{"issue":"1","key":"2990_CR4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/1472-6815-14-13","volume":"14","author":"AG Hansen","year":"2014","unstructured":"Hansen AG, Helvik A-S, Nordg\u00e5rd S, Bugten V, Stovner LJ, H\u00e5berg AK, G\u00e5rseth M, Eggesb\u00f8 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","journal-title":"BMC Ear, Nose, and Throat Disord"},{"issue":"1","key":"2990_CR5","first-page":"33","volume":"38","author":"B Tarp","year":"2000","unstructured":"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\u201338","journal-title":"Rhinology"},{"issue":"2","key":"2990_CR6","doi-asserted-by":"publisher","first-page":"381","DOI":"10.2214\/ajr.156.2.1898819","volume":"156","author":"KM Rak","year":"1991","unstructured":"Rak KM, Newell JD, Yakes WF, Damiano MA, Luethke JM (1991) Paranasal sinuses on MR images of the brain: significance of mucosal thickening. AJR Am J Roentgenol 156(2):381\u2013384. https:\/\/doi.org\/10.2214\/ajr.156.2.1898819","journal-title":"AJR Am J Roentgenol"},{"key":"2990_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3205\/cto000113","volume":"13","author":"M Stenner","year":"2014","unstructured":"Stenner M, Rudack C (2014) Diseases of the nose and paranasal sinuses in child. GMS Curr Top Otorhinolaryngol, Head Neck Surg 13:10. https:\/\/doi.org\/10.3205\/cto000113","journal-title":"GMS Curr Top Otorhinolaryngol, Head Neck Surg"},{"key":"2990_CR8","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/1472-6831-12-30","volume":"12","author":"ICC Rege","year":"2012","unstructured":"Rege ICC, Sousa TO, Leles CR, Mendon\u00e7a EF (2012) Occurrence of maxillary sinus abnormalities detected by cone beam CT in asymptomatic patients. BMC Oral Health 12:30. https:\/\/doi.org\/10.1186\/1472-6831-12-30","journal-title":"BMC Oral Health"},{"issue":"4","key":"2990_CR9","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1017\/s0022215100115609","volume":"105","author":"LD Cooke","year":"1991","unstructured":"Cooke LD, Hadley DM (1991) MRI of the paranasal sinuses: incidental abnormalities and their relationship to symptoms. J Laryngol Otol 105(4):278\u2013281. https:\/\/doi.org\/10.1017\/s0022215100115609","journal-title":"J Laryngol Otol"},{"key":"2990_CR10","doi-asserted-by":"crossref","unstructured":"Brierley J, Gospodarowicz MK, Wittekind C (eds) (2017) TNM classification of malignant tumours, 8th edn. Wiley, Chichester, West Sussex, Hoboken","DOI":"10.1002\/9780471420194.tnmc26.pub3"},{"issue":"6164","key":"2990_CR11","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1126\/science.1248764","volume":"342","author":"A Gutmann","year":"2013","unstructured":"Gutmann A (2013) Ethics. The bioethics commission on incidental findings. Science (New York) 342(6164):1321\u20131323. https:\/\/doi.org\/10.1126\/science.1248764","journal-title":"Science (New York)"},{"issue":"2","key":"2990_CR12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.13201\/j.issn.1001-1781.2012.02.005","volume":"26","author":"Z Ma","year":"2012","unstructured":"Ma Z, Yang X (2012) Research on misdiagnosis of space occupying lesions in unilateral nasal sinus. Lin chuang er bi yan hou tou jing wai ke za zhi = J Clin Otorhinolaryngol, Head, Neck Surg 26(2):59\u201361. https:\/\/doi.org\/10.13201\/j.issn.1001-1781.2012.02.005","journal-title":"Lin chuang er bi yan hou tou jing wai ke za zhi = J Clin Otorhinolaryngol, Head, Neck Surg"},{"issue":"1","key":"2990_CR13","first-page":"12727","volume":"13","author":"A-M Papadopoulou","year":"2021","unstructured":"Papadopoulou A-M, Chrysikos D, Samolis A, Tsakotos G, Troupis T (2021) Anatomical variations of the nasal cavities and paranasal sinuses: a systematic review. Cureus 13(1):12727","journal-title":"Cureus"},{"key":"2990_CR14","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/978-981-15-8297-4_53","volume-title":"Recent innovations in computing","author":"V Mohindru","year":"2021","unstructured":"Mohindru V, Singla S (2021) A review of anomaly detection techniques using computer vision. In: Singh PK, Singh Y, Kolekar MH, Kar AK, Chhabra JK, Sen A (eds) Recent innovations in computing. Springer, Singapore, pp 669\u2013677"},{"key":"2990_CR15","first-page":"33","volume-title":"Data Sci-Analyt Appl","author":"ME Tschuchnig","year":"2022","unstructured":"Tschuchnig ME, Gadermayr M (2022) Anomaly detection in medical imaging\u2014a mini review. In: Haber P, Lampoltshammer TJ, Leopold H, Mayr M (eds) Data Sci-Analyt Appl. Springer, Wiesbaden, pp 33\u201338"},{"key":"2990_CR16","doi-asserted-by":"publisher","first-page":"942","DOI":"10.21037\/QIMS.2019.05.15","volume":"9","author":"HG Kim","year":"2019","unstructured":"Kim HG, Lee KM, Kim EJ, Lee JS (2019) Improvement diagnostic accuracy of sinusitis recognition in paranasal sinus X-ray using multiple deep learning models. Quant Imaging Med Surg 9:942\u2013951. https:\/\/doi.org\/10.21037\/QIMS.2019.05.15","journal-title":"Quant Imaging Med Surg"},{"key":"2990_CR17","doi-asserted-by":"publisher","first-page":"65","DOI":"10.5755\/J02.EIE.31133","volume":"28","author":"S Ozbay","year":"2022","unstructured":"Ozbay S, Tunc O (2022) Deep learning in analysing paranasal sinuses. Elektron Elektrotech 28:65\u201370. https:\/\/doi.org\/10.5755\/J02.EIE.31133","journal-title":"Elektron Elektrotech"},{"issue":"2","key":"2990_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0263125","volume":"17","author":"K-S Kim","year":"2022","unstructured":"Kim K-S, Kim BK, Chung MJ, Cho HB, Cho BH, Jung YG (2022) Detection of maxillary sinus fungal ball via 3-d CNN-based artificial intelligence: fully automated system and clinical validation. PLoS One 17(2):1\u201319. https:\/\/doi.org\/10.1371\/journal.pone.0263125","journal-title":"PLoS One"},{"issue":"2","key":"2990_CR19","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s10654-019-00577-4","volume":"35","author":"A Jagodzinski","year":"2020","unstructured":"Jagodzinski A, Blankenberg S et al (2020) Rationale and design of the Hamburg city health study. Eur J Epidemiol 35(2):169\u2013181. https:\/\/doi.org\/10.1007\/s10654-019-00577-4","journal-title":"Eur J Epidemiol"},{"key":"2990_CR20","doi-asserted-by":"publisher","first-page":"8","DOI":"10.3389\/FNINF.2014.00008\/BIBTEX","volume":"8","author":"E Garyfallidis","year":"2014","unstructured":"Garyfallidis E, Brett M, Amirbekian B, Rokem A, van der Walt S, Descoteaux M, Nimmo-Smith I (2014) Dipy, a library for the analysis of diffusion MRI data. Front Neuroinform 8:8. https:\/\/doi.org\/10.3389\/FNINF.2014.00008\/BIBTEX","journal-title":"Front Neuroinform"},{"key":"2990_CR21","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3D residual networks for action recognition. arXiv: 1708.07632v1"},{"issue":"6","key":"2990_CR22","doi-asserted-by":"publisher","first-page":"2859","DOI":"10.1002\/mp.14800","volume":"48","author":"J Fu","year":"2021","unstructured":"Fu J, Singhrao K, Qi XS, Yang Y, Ruan D, Lewis JH (2021) Three-dimensional multipath densenet for improving automatic segmentation of glioblastoma on pre-operative multimodal MR images. Med Phys 48(6):2859\u20132866. https:\/\/doi.org\/10.1002\/mp.14800","journal-title":"Med Phys"},{"key":"2990_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, G., Lin, L., Wang, J.: Lung nodule classification in ct images using 3d densenet. Journal of Physics: Conference Series 1827 (2021)","DOI":"10.1088\/1742-6596\/1827\/1\/012155"},{"key":"2990_CR24","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.631964","volume":"11","author":"Z Liu","year":"2021","unstructured":"Liu Z, Zhu Y, Yuan Y, Yang L, Wang K, Wang M, Yang X, Wu X, Tian X, Zhang R, Shen B, Luo H, Feng H, Feng S, Ke Z (2021) 3D DenseNet deep learning based preoperative computed tomography for detecting myasthenia gravis in patients with thymoma. Front Oncol 11:631964","journal-title":"Front Oncol"},{"key":"2990_CR25","unstructured":"N\u00e4ppi, J.J., Hironaka, T., Yoshida, H.: Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy. In: Medical Imaging (2018)"},{"key":"2990_CR26","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, Z., Zhan, Y., Cheikh, F.A., Ullah, M.: Interpretable learning approaches in structural MRI: 3d-resnet fused attention for autism spectrum disorder classification. In: Medical Imaging (2022)","DOI":"10.1117\/12.2611435"},{"key":"2990_CR27","doi-asserted-by":"publisher","unstructured":"Suryakanth, B., Hari Prasad, S.A.: 3D CNN-residual neural network based multimodal medical image classification. Int J Eng Trends Technol 70(10), 371\u2013380 (2022). https:\/\/doi.org\/10.14445\/22315381\/IJETT-V70I10P236","DOI":"10.14445\/22315381\/IJETT-V70I10P236"},{"key":"2990_CR28","doi-asserted-by":"crossref","unstructured":"Uemura, T., N\u00e4ppi, J.J., Hironaka, T., Kim, H., Yoshida, H.: Comparative performance of 3d-densenet, 3d-resnet, and 3d-vgg models in polyp detection for CT colonography. In: Medical Imaging (2020)","DOI":"10.1117\/12.2549103"},{"key":"2990_CR29","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269. IEEE Computer Society, Los Alamitos (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02990-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-023-02990-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02990-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,4]],"date-time":"2024-02-04T12:03:19Z","timestamp":1707048199000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-023-02990-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,21]]},"references-count":29,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["2990"],"URL":"https:\/\/doi.org\/10.1007\/s11548-023-02990-3","relation":{},"ISSN":["1861-6429"],"issn-type":[{"type":"electronic","value":"1861-6429"}],"subject":[],"published":{"date-parts":[[2023,7,21]]},"assertion":[{"value":"12 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Debayan Bhattacharya states no conflict of interest. Finn Behrendt states no conflict of interest. Benjamin Tobias Becker states no conflict of interest. Dirk Beyersdorff states no conflict of interest. Elina Petersen states no conflict of interest. Marvin Petersen states no conflict of interest. Bastian Cheng states no conflict of interest. Dennis Eggert states no conflict of interest. Christian Betz states no conflict of interest. Anna Sophie Hoffmann states no conflict of interest. Alexander Schlaefer states no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The study protocol received approval from the local ethics committee (Landes\u00e4rztekammer Hamburg, PV5131) and was approved by the Data Protection Commissioners for the University Medical Center of the University Hamburg-Eppendorf and the Free and Hanseatic City of Hamburg. It is registered on ClinicalTrial.gov (NCT03934957) and adheres to Good Clinical Practice, Good Epidemiological Practice, and ethical principles outlined in the Declaration of Helsinki.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}