Deep Learning in Analysing Paranasal Sinuses

Özbay, Serkan; Tunç, Orhan

doi:10.5755/j02.eie.31133

Cited by 3 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We present a CAD system employing CNN to classify MS opacifications and compare them with clinical data. While studies have explored prevalence of MS opacifications, [7][8][9][10][11] they have not been integrated into the broader context of correlating with clinical data using CAD. Our approach offers a less labor-intensive solution for detecting and classifying MS opacifications, leveraging one of the largest datasets available for studying paranasal incidental findings.…”

Section: Discussionmentioning

confidence: 99%

“…For example, one study cropped x-ray images to classify anomalies 7 but failed to distinguish between left and right maxillary sinus anomalies. Another study segmented CT images and classified anomalies, 8 demanding pixel-level annotations for localization. Alternatively, a different approach used a CNN to detect key slices within CT images containing maxillary sinus volumes and subsequently classify maxillary sinus anomalies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer‐Aided Diagnosis of Maxillary Sinus Anomalies: Validation and Clinical Correlation

Bhattacharya,

Becker,

Behrendt

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectiveComputer aided diagnostics (CAD) systems can automate the differentiation of maxillary sinus (MS) with and without opacification, simplifying the typically laborious process and aiding in clinical insight discovery within large cohorts.MethodsThis study uses Hamburg City Health Study (HCHS) a large, prospective, long‐term, population‐based cohort study of participants between 45 and 74 years of age. We develop a CAD system using an ensemble of 3D Convolutional Neural Network (CNN) to analyze cranial MRIs, distinguishing MS with opacifications (polyps, cysts, mucosal thickening) from MS without opacifications. The system is used to find correlations of participants with and without MS opacifications with clinical data (smoking, alcohol, BMI, asthma, bronchitis, sex, age, leukocyte count, C‐reactive protein, allergies).ResultsThe evaluation metrics of CAD system (Area Under Receiver Operator Characteristic: 0.95, sensitivity: 0.85, specificity: 0.90) demonstrated the effectiveness of our approach. MS with opacification group exhibited higher alcohol consumption, higher BMI, higher incidence of intrinsic asthma and extrinsic asthma. Male sex had higher prevalence of MS opacifications. Participants with MS opacifications had higher incidence of hay fever and house dust allergy but lower incidence of bee/wasp venom allergy.ConclusionThe study demonstrates a 3D CNN's ability to distinguish MS with and without opacifications, improving automated diagnosis and aiding in correlating clinical data in population studies.Level of Evidence3 Laryngoscope, 2024

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computer‐Aided Diagnosis of Maxillary Sinus Anomalies: Validation and Clinical Correlation

Bhattacharya,

Becker,

Behrendt

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

show abstract

“…5 . Previous approaches [ 18 ] used a 2-stage CNN pipeline, learning key MS slices first using a CNN and then classifying anomalies with another CNN [ 18 ] or learning to segment the maxillary sinus and then classifying the anomaly [ 17 ], but these methods 2 stage CNN pipeline makes it dependent on datasets hindering generalization. To overcome this limitation, we propose a method that extracts multiple MS volumes without DL, using a CNN only once to compute the final anomaly score for each MS.…”

Section: Discussionmentioning

confidence: 99%

“…For instance, one study cropped X-rays and classified anomalies [ 16 ], but failed to classify left and right MS anomalies separately. Another study segmented Computed Tomography (CT) images and classified anomalies [ 17 ], necessitating pixel-level annotations for localization. A different approach involved using a CNN to detect key slices in CT images containing MS volumes and then classifying MS anomalies [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus

et al. 2023

View full text Add to dashboard Cite

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.

show abstract

Transfer Learning-Based Classification of Maxillary Sinus Using Generative Adversarial Networks

Alhumaid,

Fayoumi

2024

Applied Sciences

View full text Add to dashboard Cite

Paranasal sinus pathologies, particularly those affecting the maxillary sinuses, pose significant challenges in diagnosis and treatment due to the complex anatomical structures and diverse disease manifestations. The aim of this study is to investigate the use of deep learning techniques, particularly generative adversarial networks (GANs), in combination with convolutional neural networks (CNNs), for the classification of sinus pathologies in medical imaging data. The dataset is composed of images obtained through computed tomography (CT) scans, covering cases classified into “Moderate”, “Severe”, and “Normal” classes. The lightweight GAN is applied to augment a dataset by creating synthetic images, which are then used to train and test the ResNet-50 and ResNeXt-50 models. The model performance is optimized using random search to perform hyperparameter tuning, and the evaluation is conducted extensively for various metrics like accuracy, precision, recall, and the F1-score. The results demonstrate the effectiveness of the proposed approach in accurately classifying sinus pathologies, with the ResNeXt-50 model achieving superior performance with accuracy: 91.154, precision: 0.917, recall: 0.912, and F1-score: 0.913 compared to ResNet-50. This study highlights the potential of GAN-based data augmentation and deep learning techniques in enhancing the diagnosis of maxillary sinus diseases.

show abstract

Deep Learning in Analysing Paranasal Sinuses

Cited by 3 publications

References 9 publications

Computer‐Aided Diagnosis of Maxillary Sinus Anomalies: Validation and Clinical Correlation

Computer‐Aided Diagnosis of Maxillary Sinus Anomalies: Validation and Clinical Correlation

Multiple instance ensembling for paranasal anomaly classification in the maxillary sinus

Transfer Learning-Based Classification of Maxillary Sinus Using Generative Adversarial Networks

Contact Info

Product

Resources

About