SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images
Background: The Sella Turcica is a critical structure from an orthodontic perspective, and its morphological characteristics can help in understanding craniofacial deformities. However, accurately extracting Sella Turcica shapes can be challenging due to the indistinct edges and indefinite boundarie...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/16/9114 |
| _version_ | 1797585715478921216 |
|---|---|
| author | Kaushlesh Singh Shakya Manojkumar Jaiswal Julie Porteous Priti K Vinay Kumar Azadeh Alavi Amit Laddi |
| author_facet | Kaushlesh Singh Shakya Manojkumar Jaiswal Julie Porteous Priti K Vinay Kumar Azadeh Alavi Amit Laddi |
| author_sort | Kaushlesh Singh Shakya |
| collection | DOAJ |
| description | Background: The Sella Turcica is a critical structure from an orthodontic perspective, and its morphological characteristics can help in understanding craniofacial deformities. However, accurately extracting Sella Turcica shapes can be challenging due to the indistinct edges and indefinite boundaries present in X-ray images. This study aimed to develop and validate an automated Sella Morphology Network (SellaMorph-Net), a hybrid deep learning pipeline for segmenting Sella Turcica structure and extracting different morphological types; Methods: The SellaMorph-Net model proposed in this study combined attention-gating and recurrent residual convolutional layers (AGM and RrCL) to enhance the encoder’s abilities. The model’s output was then passed through a squeeze-and-excitation (SE) module to improve the network’s robustness. In addition, dropout layers were added to the end of each convolution block to prevent overfitting. A Zero-shot classifier was employed for multiple classifications, and the model’s output layer used five colour codes to represent different morphological types. The model’s performance was evaluated using various quantitative metrics, such as global accuracy and mean pixel-wise Intersection over Union (IoU) and dice coefficient, based on qualitative results; Results: The study collected 1653 radiographic images and categorised them into four classes based on the predefined shape of Sella Turcica. These classes were further divided into three subgroups based on the complexity of the Sella structures. The proposed SellaMorph-Net model achieved a global accuracy of 97.570, mean pixel-wise IoU scores of 0.7129, and a dice coefficient of 0.7324, significantly outperforming the VGG-19 and InceptionV3 models. The publicly available IEEE ISBI 2015 challenge dataset and our dataset were used to evaluate the test performance between the state-of-the-art and proposed models. The proposed model provided higher testing results, which were 0.7314 IoU and 0.7768 dice for our dataset and 0.7864 IoU and 0.8313 dice for the challenge dataset; Conclusions: The proposed hybrid SellaMorph-Net model provides an accurate and reliable pipeline for detecting morphological types of Sella Turcica using full lateral cephalometric images. Future work will focus on further improvement and utilisation of the developed model as a prognostic tool for predicting anomalies related to Sella structures. |
| first_indexed | 2024-03-11T00:10:01Z |
| format | Article |
| id | doaj.art-e827df99b9ac41dcb91d113286c475ed |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T00:10:01Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-e827df99b9ac41dcb91d113286c475ed2023-11-19T00:04:32ZengMDPI AGApplied Sciences2076-34172023-08-011316911410.3390/app13169114SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric ImagesKaushlesh Singh Shakya0Manojkumar Jaiswal1Julie Porteous2Priti K3Vinay Kumar4Azadeh Alavi5Amit Laddi6Academy of Scientific & Innovative Research (AcSIR), Ghaziabad 201002, IndiaOral Health Sciences Centre, Post Graduate Institute of Medical Education & Research (PGIMER), Chandigarh 160012, IndiaSchool of Computing Technologies, RMIT University, Melbourne, VIC 3000, AustraliaAcademy of Scientific & Innovative Research (AcSIR), Ghaziabad 201002, IndiaOral Health Sciences Centre, Post Graduate Institute of Medical Education & Research (PGIMER), Chandigarh 160012, IndiaSchool of Computing Technologies, RMIT University, Melbourne, VIC 3000, AustraliaCSIR—Central Scientific Instruments Organisation, Chandigarh 160030, IndiaBackground: The Sella Turcica is a critical structure from an orthodontic perspective, and its morphological characteristics can help in understanding craniofacial deformities. However, accurately extracting Sella Turcica shapes can be challenging due to the indistinct edges and indefinite boundaries present in X-ray images. This study aimed to develop and validate an automated Sella Morphology Network (SellaMorph-Net), a hybrid deep learning pipeline for segmenting Sella Turcica structure and extracting different morphological types; Methods: The SellaMorph-Net model proposed in this study combined attention-gating and recurrent residual convolutional layers (AGM and RrCL) to enhance the encoder’s abilities. The model’s output was then passed through a squeeze-and-excitation (SE) module to improve the network’s robustness. In addition, dropout layers were added to the end of each convolution block to prevent overfitting. A Zero-shot classifier was employed for multiple classifications, and the model’s output layer used five colour codes to represent different morphological types. The model’s performance was evaluated using various quantitative metrics, such as global accuracy and mean pixel-wise Intersection over Union (IoU) and dice coefficient, based on qualitative results; Results: The study collected 1653 radiographic images and categorised them into four classes based on the predefined shape of Sella Turcica. These classes were further divided into three subgroups based on the complexity of the Sella structures. The proposed SellaMorph-Net model achieved a global accuracy of 97.570, mean pixel-wise IoU scores of 0.7129, and a dice coefficient of 0.7324, significantly outperforming the VGG-19 and InceptionV3 models. The publicly available IEEE ISBI 2015 challenge dataset and our dataset were used to evaluate the test performance between the state-of-the-art and proposed models. The proposed model provided higher testing results, which were 0.7314 IoU and 0.7768 dice for our dataset and 0.7864 IoU and 0.8313 dice for the challenge dataset; Conclusions: The proposed hybrid SellaMorph-Net model provides an accurate and reliable pipeline for detecting morphological types of Sella Turcica using full lateral cephalometric images. Future work will focus on further improvement and utilisation of the developed model as a prognostic tool for predicting anomalies related to Sella structures.https://www.mdpi.com/2076-3417/13/16/9114Sella Turcicalateral cephalogrammorphological typesSella segmentationSellaMorph-Net |
| spellingShingle | Kaushlesh Singh Shakya Manojkumar Jaiswal Julie Porteous Priti K Vinay Kumar Azadeh Alavi Amit Laddi SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images Applied Sciences Sella Turcica lateral cephalogram morphological types Sella segmentation SellaMorph-Net |
| title | SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images |
| title_full | SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images |
| title_fullStr | SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images |
| title_full_unstemmed | SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images |
| title_short | SellaMorph-Net: A Novel Machine Learning Approach for Precise Segmentation of Sella Turcica Complex Structures in Full Lateral Cephalometric Images |
| title_sort | sellamorph net a novel machine learning approach for precise segmentation of sella turcica complex structures in full lateral cephalometric images |
| topic | Sella Turcica lateral cephalogram morphological types Sella segmentation SellaMorph-Net |
| url | https://www.mdpi.com/2076-3417/13/16/9114 |
| work_keys_str_mv | AT kaushleshsinghshakya sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT manojkumarjaiswal sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT julieporteous sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT pritik sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT vinaykumar sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT azadehalavi sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages AT amitladdi sellamorphnetanovelmachinelearningapproachforprecisesegmentationofsellaturcicacomplexstructuresinfulllateralcephalometricimages |