Transferable Architecture for Segmenting Maxillary Sinuses on Texture-Enhanced Occipitomental View Radiographs

Chondro, Peter; Haq, Qazi Mazhar ul; Ruan, Shanq-Jang; Li, Lieber Po‐Hung

doi:10.3390/math8050768

Cited by 3 publications

(5 citation statements)

References 22 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10 Recently, there is emerging evidence suggesting that using deep learning models in the diagnosis of maxillary sinusitis on Waters’ view radiograph was associated with superior accuracy. 23–26 In our study, we found that sinus plain films had very high sensitivity in diagnosing both fungal and bacterial maxillary sinusitis (100% and 96.2%, respectively). There are two possible reasons.…”

Section: Discussionmentioning

confidence: 56%

Combining sinus plain film and sinus ultrasound as a screening tool for maxillary fungal sinusitis

Hung

Kuan

et al. 2022

Journal of the Chinese Medical Association

View full text Add to dashboard Cite

Background: Early identification of fungal sinusitis remains a challenge. Previously, we observed a high false negative rate of using A-mode ultrasound to diagnose maxillary fungal sinusitis. This study aims to assess the accuracy of the diagnosis of fungal maxillary sinusitis using sinus plain film and ultrasound. Methods: The screening criteria is defined as the combination of a positive sinus plain film and a false negative sinus ultrasound. We retrospectively reviewed preoperative imaging of patients with fungal sinusitis and unilateral bacterial sinusitis of the maxillary sinus undergoing functional endoscopic sinus surgery from May 2013 to December 2019 in our hospital and evaluated the diagnostic performance of this screening method. Results: Forty-eight patients were included. Twenty-two and 26 patients were diagnosed with fungal sinusitis and bacterial sinusitis, respectively. Sixteen patients (72.7%) with fungal sinusitis presented with a false negative sinus ultrasound and met our screening criteria for fungal sinusitis. The screening criteria reached significance in the receiver operating characteristic curve analysis (p < 0.001). The area under the curve was 0.829. The sensitivity, specificity, and accuracy are 72.7%, 93.2%, and 88.4%, respectively. Conclusion: A high false negative rate of sinus ultrasound in patients with fungal sinusitis was found. A positive sinus plain film combined with a false negative sinus ultrasound can potentially become an easy and cost-effective screening tool for diagnosing fungal maxillary sinusitis before consideration of computed tomography scanning.

show abstract

Section: Discussionmentioning

confidence: 56%

Combining sinus plain film and sinus ultrasound as a screening tool for maxillary fungal sinusitis

Hung

Kuan

et al. 2022

Journal of the Chinese Medical Association

View full text Add to dashboard Cite

show abstract

“…Recent studies used machine learning tools due to the development and advancement in machine learning techniques for classification and detection tasks [ 24 ]. Various machine learning techniques were proposed to analyze and detect human emotion from EEG signals.…”

Section: Related Orkmentioning

confidence: 99%

A Hybrid Hand-Crafted and Deep Neural Spatio-Temporal EEG Features Clustering Framework for Precise Emotional Status Recognition

Haq

Yao

Rahmaniar

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Human emotions are variant with time, non-stationary, complex in nature, and are invoked as a result of human reactions during our daily lives. Continuously detecting human emotions from one-dimensional EEG signals is an arduous task. This paper proposes an advanced signal processing mechanism for emotion detection from EEG signals using continuous wavelet transform. The space and time components of the raw EEG signals are converted into 2D spectrograms followed by feature extraction. A hybrid spatio-temporal deep neural network is implemented to extract rich features. A differential-based entropy feature selection technique adaptively differentiates features based on entropy, based on low and high information regions. Bag of Deep Features (BoDF) is applied to create clusters of similar features and computes the features vocabularies for reduction of feature dimensionality. Extensive experiments are performed on the SEED dataset, which shows the significance of the proposed method compared to state-of-the-art methods. Specifically, the proposed model achieved 96.7%, 96.2%, 95.8%, and 95.3% accuracy with the SJTU SEED dataset, for SVM, ensemble, tree, and KNN classifiers, respectively.

show abstract

“…With the advancement of computer vision technology [ 10 ], such as machine learning [ 11 , 12 ] and deep learning methods [ 13 , 14 , 15 ], a fully automatic process to measure the CA quickly and precisely can potentially overcome the shortcomings mentioned above. Digitalized X-ray images, processed through computerized learning, have previously been used to screen, diagnose, and classify severity of scoliosis [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

“…Digitalized X-ray images, processed through computerized learning, have previously been used to screen, diagnose, and classify severity of scoliosis [ 12 ]. Further development in deep learning has also led to an increase in different measuring and assessing CA [ 13 , 14 , 15 , 16 ]. Automatic detection of the spine anatomy in X-ray images to select the appropriate end vertebrae is an essential stage for CA measurement.…”

Section: Introductionmentioning

confidence: 99%

“…Automatic detection of the spine anatomy in X-ray images to select the appropriate end vertebrae is an essential stage for CA measurement. Studies on the vertebrae and spine detection based on machine learning [ 11 , 12 ] and deep learning methods [ 13 , 14 , 15 , 16 ] have been previously reported. However, automatic detection of the vertebrae in X-ray images can be difficult due to overlapping rib and pelvic shadows, as well as contrast differences between the different vertebrae levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Cobb Angle Measurement for Adolescent Idiopathic Scoliosis Using Convolutional Neural Network

et al. 2022

View full text Add to dashboard Cite

The Cobb angle measurement of the scoliotic spine is prone to inter- and intra-observer variations in the clinical setting. This paper proposes a deep learning architecture for detecting spine vertebrae from X-ray images to evaluate the Cobb angle automatically. The public AASCE MICCAI 2019 anterior-posterior X-ray image dataset and local images were used to train and test the proposed convolutional neural network architecture. Sixty-eight landmark features of the spine were detected from the input image to obtain seventeen vertebrae on the spine. The vertebrae locations obtained were processed to automatically measure the Cobb angle. The proposed method can measure the Cobb angle with accuracies up to 93.6% and has excellent reliability compared to clinicians’ measurement (intraclass correlation coefficient > 0.95). The proposed deep learning architecture may be used as a tool to augment Cobb angle measurement in X-ray images of patients with adolescent idiopathic scoliosis in a real-world clinical setting.

show abstract

Transferable Architecture for Segmenting Maxillary Sinuses on Texture-Enhanced Occipitomental View Radiographs

Cited by 3 publications

References 22 publications

Combining sinus plain film and sinus ultrasound as a screening tool for maxillary fungal sinusitis

Combining sinus plain film and sinus ultrasound as a screening tool for maxillary fungal sinusitis

A Hybrid Hand-Crafted and Deep Neural Spatio-Temporal EEG Features Clustering Framework for Precise Emotional Status Recognition

Automated Cobb Angle Measurement for Adolescent Idiopathic Scoliosis Using Convolutional Neural Network

Contact Info

Product

Resources

About