Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus

Standard

Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus. / Bhattacharya, Debayan; Behrendt, Finn; Becker, Benjamin Tobias; Beyersdorff, Dirk; Petersen, Elina; Petersen, Marvin; Cheng, Bastian; Eggert, Dennis; Betz, Christian; Hoffmann, Anna Sophie; Schlaefer, Alexander.

in: INT J COMPUT ASS RAD, Jahrgang 19, Nr. 2, 02.2024, S. 223–231.

Publikationen: SCORING: Beitrag in Fachzeitschrift/ZeitungSCORING: ZeitschriftenaufsatzForschungBegutachtung

Harvard

APA

Vancouver

Bibtex

@article{49e0a476211e469a8b7835aef533c105,
title = "Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus",
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.",
author = "Debayan Bhattacharya and Finn Behrendt and Becker, {Benjamin Tobias} and Dirk Beyersdorff and Elina Petersen and Marvin Petersen and Bastian Cheng and Dennis Eggert and Christian Betz and Hoffmann, {Anna Sophie} and Alexander Schlaefer",
note = "{\textcopyright} 2023. The Author(s).",
year = "2024",
month = feb,
doi = "10.1007/s11548-023-02990-3",
language = "English",
volume = "19",
pages = "223–231",
journal = "INT J COMPUT ASS RAD",
issn = "1861-6410",
publisher = "Springer",
number = "2",

}

RIS

TY - JOUR

T1 - Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus

AU - Bhattacharya, Debayan

AU - Behrendt, Finn

AU - Becker, Benjamin Tobias

AU - Beyersdorff, Dirk

AU - Petersen, Elina

AU - Petersen, Marvin

AU - Cheng, Bastian

AU - Eggert, Dennis

AU - Betz, Christian

AU - Hoffmann, Anna Sophie

AU - Schlaefer, Alexander

N1 - © 2023. The Author(s).

PY - 2024/2

Y1 - 2024/2

N2 - 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.

AB - 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.

U2 - 10.1007/s11548-023-02990-3

DO - 10.1007/s11548-023-02990-3

M3 - SCORING: Journal article

C2 - 37479942

VL - 19

SP - 223

EP - 231

JO - INT J COMPUT ASS RAD

JF - INT J COMPUT ASS RAD

SN - 1861-6410

IS - 2

ER -