Automatic CT image segmentation of maxillary sinus based on VGG network and improved V-Net

Xu, Jiangchang; Wang, Shiming; Zhou, Zijie; Liu, Jiannan; Jiang, Xiaoyi; Chen, Xiaojun

doi:10.1007/s11548-020-02228-6

Cited by 36 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent investigations showed excellent results in the interpretation of various medical images including chest X-rays, mammograms, and computed tomography scans [ 2 ]. In the otolaryngology field, a deep learning algorithm successfully diagnosed maxillary sinusitis from a plain Waters’ view radiograph [ 3 , 4 ]. Furthermore, AI technology is being used not only to interpret medical images but also to predict the prognosis of disease.…”

Section: Introductionmentioning

confidence: 99%

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

Byun

et al. 2021

JCM

View full text Add to dashboard Cite

The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images.

show abstract

Section: Introductionmentioning

confidence: 99%

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

Byun

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

“…If there is mucosal thickening, the border is not clearly de ned, which may make automatic segmentation more di cult. A few studies have explored the application of automatic maxillary sinus segmentation using CT images 13,14 . Xu et al 13 reported a DSC of 0.94 for clear maxillary sinuses and stated that the results for hazy maxillary sinuses were not satisfactory.…”

Section: Discussionmentioning

confidence: 99%

“…A few studies have explored the application of automatic maxillary sinus segmentation using CT images 13,14 . Xu et al 13 reported a DSC of 0.94 for clear maxillary sinuses and stated that the results for hazy maxillary sinuses were not satisfactory. In another study, Iwamoto et al 14 reported a DSC of 0.83 in both clear and hazy maxillary sinuses.…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, the results of the analysis may be highly dependent on experts' knowledge and experience. For these reasons, deep learning-based studies have been conducted with the goal of achieving equivalent accuracy in various cases, and several studies have made attempts to perform automatic segmentation of the maxillary sinus [13][14][15] . However, automatic segmentation of the maxillary sinus is challenging because it is connected to adjacent anatomical structures such as the frontal, ethmoid, and sphenoid sinuses, as well as nasal structures.…”

Section: Introductionmentioning

confidence: 99%

“…In recent studies, deep-learning algorithms have shown good performance in automated detection, segmentation, and diagnosis based on 3D medical imaging [13][14][15] . Various networks have been used for segmentation, and many studies have used U-Net models [18][19][20] .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Fully Automatic Segmentation of the Maxillary Sinus on Cone-Beam Computed Tomographic Images

Choi

Jeon

Kim

et al. 2022

Preprint

View full text Add to dashboard Cite

This study proposes a deep learning-based method for fully automatic segmentation of the maxillary sinus, including clear or hazy states, on cone-beam computed tomographic (CBCT) images. The model, which consisted of a U-Net architecture with post-processing, was developed using 19,350 CBCT images from 90 maxillary sinuses (34 clear sinuses, 56 hazy sinuses). Post-processing was performed to improve the accuracy of the prediction results of U-Net. Model performance was evaluated compared to manual labeling by an oral radiologist. The artificial intelligence (AI) prediction results before post-processing were DSC of 0.9071 ± 0.1842, HD of 2.6207 ± 4.9279 in clear sinuses and DSC of 0.9107 ± 0.1988, HD of 2.7812 ± 4.2835 in hazy sinuses. After post-processing, the results all improved (DSC: 0.9072 ± 0.1842, HD: 2.4057 ± 2.4496 in clear sinuses and DSC: 0.9123 ± 0.1977, HD: 1.9158 ± 2.0887 in hazy sinuses). The proposed deep learning model showed good performance for clear and hazy maxillary sinus segmentation with minimal time and effort, and the post-processing method improved the accuracy of automatic segmentation.

show abstract

Surgical Navigation in the Anterior Skull Base Using 3-Dimensional Endoscopy and Surface Reconstruction

Bartholomew,

Zhou,

Boreel

et al. 2024

JAMA Otolaryngol Head Neck Surg

View full text Add to dashboard Cite

ImportanceImage guidance is an important adjunct for endoscopic sinus and skull base surgery. However, current systems require bulky external tracking equipment, and their use can interrupt efficient surgical workflow.ObjectiveTo evaluate a trackerless surgical navigation system using 3-dimensional (3D) endoscopy and simultaneous localization and mapping (SLAM) algorithms in the anterior skull base.Design, Setting, and ParticipantsThis interventional deceased donor cohort study and retrospective clinical case study was conducted at a tertiary academic medical center with human deceased donor specimens and a patient with anterior skull base pathology.ExposuresParticipants underwent endoscopic endonasal transsphenoidal dissection and surface model reconstruction from stereoscopic video with registration to volumetric models segmented from computed tomography (CT) and magnetic resonance imaging.Main Outcomes and MeasuresTo assess the fidelity of surface model reconstruction and accuracy of surgical navigation and surface-CT model coregistration, 3 metrics were calculated: reconstruction error, registration error, and localization error.ResultsIn deceased donor models (n = 9), high-fidelity surface models of the posterior wall of the sphenoid sinus were reconstructed from stereoscopic video and coregistered to corresponding volumetric CT models. The mean (SD; range) reconstruction, registration, and localization errors were 0.60 (0.24; 0.36-0.93), 1.11 (0.49; 0.71-1.56) and 1.01 (0.17; 0.78-1.25) mm, respectively. In a clinical case study of a patient who underwent a 3D endoscopic endonasal transsphenoidal resection of a tubercular meningioma, a high-fidelity surface model of the posterior wall of the sphenoid was reconstructed from intraoperative stereoscopic video and coregistered to a volumetric preoperative fused CT magnetic resonance imaging model with a root-mean-square error of 1.38 mm.Conclusions and RelevanceThe results of this study suggest that SLAM algorithm–based endoscopic endonasal surgery navigation is a novel, accurate, and trackerless approach to surgical navigation that uses 3D endoscopy and SLAM-based algorithms in lieu of conventional optical or electromagnetic tracking. While multiple challenges remain before clinical readiness, a SLAM algorithm–based endoscopic endonasal surgery navigation system has the potential to improve surgical efficiency, economy of motion, and safety.

show abstract

Automatic CT image segmentation of maxillary sinus based on VGG network and improved V-Net

Cited by 36 publications

References 16 publications

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

Deep Learning-Based Fully Automatic Segmentation of the Maxillary Sinus on Cone-Beam Computed Tomographic Images

Surgical Navigation in the Anterior Skull Base Using 3-Dimensional Endoscopy and Surface Reconstruction

Contact Info

Product

Resources

About