The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction:
Introduction Panoramic dental images gives an in-depth understanding of the tooth structure, both lower and upper jaws, and surrounding structures throughout the cavity in our mouth.The Panoramic dental images provided have significance for dental diagnostics since they aid in the detection of an a...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SJORANM GmbH (Ltd.)
2024-09-01
|
| Series: | Swiss Journal of Radiology and Nuclear Medicine |
| Subjects: | |
| Online Access: | https://sjoranm.com/sjoranm/article/view/43 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849715764097974272 |
|---|---|
| author | Raghavendra H. Bhalerao Abhijeet Ashok Salunke Shristi Sharan Kamlesh Kumar Priyank Rathod Prince Kumar Manish Chaturvedi Nandlal Bharwani Krupa Shah Dhruv Patel Keval Patel Vikas Warikoo Manisha Abhijeet Salunke Shashank Pandya |
| author_facet | Raghavendra H. Bhalerao Abhijeet Ashok Salunke Shristi Sharan Kamlesh Kumar Priyank Rathod Prince Kumar Manish Chaturvedi Nandlal Bharwani Krupa Shah Dhruv Patel Keval Patel Vikas Warikoo Manisha Abhijeet Salunke Shashank Pandya |
| author_sort | Raghavendra H. Bhalerao |
| collection | DOAJ |
| description | Introduction
Panoramic dental images gives an in-depth understanding of the tooth structure, both lower and upper jaws, and surrounding structures throughout the cavity in our mouth.The Panoramic dental images provided have significance for dental diagnostics since they aid in the detection of an array of dental disorders, including oral cancer. We propose a novel approach to automatic joint teeth segmentation using the pioneer Mask Recurrent Convolutional Neural Network (MRCNN) model for dental image segmentation.
Material and Methods
In this study, a sequence of residual blocks are used to construct a 62-layer feature extraction network in lieu of ResNet50/101 in MRCNN. To evaluate the efficacy of our method, the UFBA-UESC and Tufts dental image dataset (2500 panoramic dental x-rays) were utilised. 252 x-rays were used in test set, rest of the x-rays were utilised as training(1800 images) and validation datasets(448images) in ratio of 8:2 of the modified MRCNN model.
Results
Modified MRCNN achieved the final training and validation accuracies as 99.67% and 98.94%, respectively.The achieved accuracy of Dice coefficient (97.8%), Intersection over Union, (98.67%), and Pixel Accuracy(96.53%) respectively over the whole dataset. We also compare the performance of proposed model and other well established networks such as FPN, UNet, PSPNet, and DeepLabV3. The Modified MRCNN provides better results segmenting any two teeth which are close.
Conclusion
Our proposed method will serve as a valuable tool for automatic segmentation of individual teeth for medical management. This current method leads to higher accuracy and precision. Segmented images can be used to evaluate periodic changes, providing valuable data for assessing the progression of oral cancer and the efficacy of management.Future research should focus on developing less complex, lightweight, and faster vision models while maintaining high accuracy.
|
| format | Article |
| id | doaj-art-e18bc04a175841caa81de5439cc2231a |
| institution | DOAJ |
| issn | 2813-7221 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | SJORANM GmbH (Ltd.) |
| record_format | Article |
| series | Swiss Journal of Radiology and Nuclear Medicine |
| spelling | doaj-art-e18bc04a175841caa81de5439cc2231a2025-08-20T03:13:13ZengSJORANM GmbH (Ltd.)Swiss Journal of Radiology and Nuclear Medicine2813-72212024-09-0112110.59667/sjoranm.v12i1.18The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction:Raghavendra H. Bhalerao0Abhijeet Ashok Salunke1https://orcid.org/0000-0003-0103-8599Shristi Sharan2Kamlesh Kumar3Priyank Rathod4Prince Kumar5Manish Chaturvedi6Nandlal Bharwani7Krupa Shah8Dhruv Patel9Keval Patel10Vikas Warikoo11Manisha Abhijeet Salunke12Shashank Pandya13Dept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaDept of Electrical Engineering, IITRAM, Ahemdabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaDental Surgeon, Ahmedabad, IndiaDepartment of Surgical Oncology, The Gujarat Cancer and Research Institute, Ahemdabad, IndiaIntroduction Panoramic dental images gives an in-depth understanding of the tooth structure, both lower and upper jaws, and surrounding structures throughout the cavity in our mouth.The Panoramic dental images provided have significance for dental diagnostics since they aid in the detection of an array of dental disorders, including oral cancer. We propose a novel approach to automatic joint teeth segmentation using the pioneer Mask Recurrent Convolutional Neural Network (MRCNN) model for dental image segmentation. Material and Methods In this study, a sequence of residual blocks are used to construct a 62-layer feature extraction network in lieu of ResNet50/101 in MRCNN. To evaluate the efficacy of our method, the UFBA-UESC and Tufts dental image dataset (2500 panoramic dental x-rays) were utilised. 252 x-rays were used in test set, rest of the x-rays were utilised as training(1800 images) and validation datasets(448images) in ratio of 8:2 of the modified MRCNN model. Results Modified MRCNN achieved the final training and validation accuracies as 99.67% and 98.94%, respectively.The achieved accuracy of Dice coefficient (97.8%), Intersection over Union, (98.67%), and Pixel Accuracy(96.53%) respectively over the whole dataset. We also compare the performance of proposed model and other well established networks such as FPN, UNet, PSPNet, and DeepLabV3. The Modified MRCNN provides better results segmenting any two teeth which are close. Conclusion Our proposed method will serve as a valuable tool for automatic segmentation of individual teeth for medical management. This current method leads to higher accuracy and precision. Segmented images can be used to evaluate periodic changes, providing valuable data for assessing the progression of oral cancer and the efficacy of management.Future research should focus on developing less complex, lightweight, and faster vision models while maintaining high accuracy. https://sjoranm.com/sjoranm/article/view/43Medical image segmentationImage segmentation using MRCNN Medical ImagingTeeth segmentationAI in Oral CancerCNN in Oral Cancer |
| spellingShingle | Raghavendra H. Bhalerao Abhijeet Ashok Salunke Shristi Sharan Kamlesh Kumar Priyank Rathod Prince Kumar Manish Chaturvedi Nandlal Bharwani Krupa Shah Dhruv Patel Keval Patel Vikas Warikoo Manisha Abhijeet Salunke Shashank Pandya The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: Swiss Journal of Radiology and Nuclear Medicine Medical image segmentation Image segmentation using MRCNN Medical Imaging Teeth segmentation AI in Oral Cancer CNN in Oral Cancer |
| title | The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: |
| title_full | The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: |
| title_fullStr | The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: |
| title_full_unstemmed | The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: |
| title_short | The Automatic Joint Teeth Segmentation in Panoramic Dental Images using Mask Recurrent Convolutional Neural Networks with Residual Feature Extraction: |
| title_sort | automatic joint teeth segmentation in panoramic dental images using mask recurrent convolutional neural networks with residual feature extraction |
| topic | Medical image segmentation Image segmentation using MRCNN Medical Imaging Teeth segmentation AI in Oral Cancer CNN in Oral Cancer |
| url | https://sjoranm.com/sjoranm/article/view/43 |
| work_keys_str_mv | AT raghavendrahbhalerao theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT abhijeetashoksalunke theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT shristisharan theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT kamleshkumar theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT priyankrathod theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT princekumar theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT manishchaturvedi theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT nandlalbharwani theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT krupashah theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT dhruvpatel theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT kevalpatel theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT vikaswarikoo theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT manishaabhijeetsalunke theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT shashankpandya theautomaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT raghavendrahbhalerao automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT abhijeetashoksalunke automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT shristisharan automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT kamleshkumar automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT priyankrathod automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT princekumar automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT manishchaturvedi automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT nandlalbharwani automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT krupashah automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT dhruvpatel automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT kevalpatel automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT vikaswarikoo automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT manishaabhijeetsalunke automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction AT shashankpandya automaticjointteethsegmentationinpanoramicdentalimagesusingmaskrecurrentconvolutionalneuralnetworkswithresidualfeatureextraction |