Active contour-based tooth segmentation in radiographs using fuzzy logic and CNN

Year 2024, Volume: 14 Issue: 4, 1058 - 1073, 15.12.2024

Fatih Durmuş , Ferdi Özbilgin , Serap Karagöl

https://doi.org/10.17714/gumusfenbil.1458870

Abstract

Radiographic imaging is a crucial tool frequently employed by dentists for initial diagnosis and treatment planning. However, these images often suffer from distortion or inaccuracies due to incorrect exposure settings, making it challenging to identify critical regions such as tooth roots and margins. This study addresses these issues by presenting two innovative methods for tooth segmentation from radiographs, aimed at isolating the tooth regions for better analysis. The first method utilizes fuzzy logic rules to detect edges within the radiographic images. These detected edges are then used as a mask for the Active Contour Method (ACM) to segment the teeth accurately. The second method involves the creation of a Convolutional Neural Network (CNN) for tooth segmentation. The segmentation performance of the CNN is further refined using the ACM, leveraging the initial segmentation as a mask. Both methods demonstrated notable results with varying performance metrics. Specifically, the Fuzzy-Based Active Contour Method achieved precision, recall, and F1 score values of 0.6246, 0.4169, and 0.50, respectively. In contrast, the CNN-Based Active Contour Method calculated accuracy and specificity values of 0.9706 and 0.9872, respectively. These findings indicate that both approaches have distinct strengths in different performance aspects. Our study suggests that these advanced segmentation techniques can significantly enhance the diagnostic capabilities of dental professionals by providing clearer images of tooth structures, aiding in the detection of issues such as root problems, fractures, and wear patterns. Implementing these methods either independently or in combination could lead to more accurate diagnoses and better patient outcomes. Future work could explore the integration of these techniques to leverage their complementary strengths, potentially leading to even greater segmentation accuracy and reliability.

Keywords

Active contour method, Convolutional neural network (CNN), Fuzzy logic rules, Teeth segmentation

Bulanık mantık ve CNN kullanarak radyograflarda aktif kontur tabanlı diş bölütleme

Abstract

Radyografik görüntüleme, diş hekimlerinin ilk teşhis ve tedavi planlamasında sıklıkla kullandığı önemli bir araçtır. Ancak, bu görüntüler bazen yanlış pozlama ayarlarından dolayı bozulabilir veya hatalı olabilir, bu da diş kökleri ve kenar bölgeleri gibi kritik bölgelerin tanımlanmasını zorlaştırır. Bu çalışma, radyografilerden diş segmentasyonu yaparak diş bölgelerinin izole edilmesini amaçlayan iki yenilikçi yöntem sunmaktadır. İlk yöntemde, radyografik görüntülerdeki kenarları tespit etmek için bulanık mantık kuralları uygulanmıştır. Tespit edilen bu kenarlar, Aktif Kontur Yöntemi (ACM) ile dişlerin doğru bir şekilde segmentasyonu için maske olarak kullanılmıştır. İkinci yöntemde ise, diş segmentasyonu için bir Konvolüsyonel Sinir Ağı (CNN) oluşturulmuştur. CNN'in segmentasyon performansı, başlangıçtaki segmentasyonun maske olarak kullanılmasıyla ACM ile daha da iyileştirilmiştir. Her iki yöntem de farklı performans metrikleri ile dikkate değer sonuçlar göstermiştir. Özellikle, Bulanık Tabanlı Aktif Kontur Yöntemi için doğruluk, geri çağırma ve F1 skoru değerleri sırasıyla 0.6246, 0.4169 ve 0.50 olarak elde edilmiştir. Buna karşılık, CNN Tabanlı Aktif Kontur Yöntemi için doğruluk ve özgüllük değerleri sırasıyla 0.9706 ve 0.9872 olarak rapor edilmiştir. Bu bulgular, her iki yaklaşımın da farklı performans kriterlerinde belirgin güçlü yönlere sahip olduğunu göstermektedir. Çalışmamız, bu ileri düzey segmentasyon tekniklerinin, diş yapılarının daha net görüntülerini sağlayarak diş hekimlerinin teşhis yeteneklerini önemli ölçüde artırabileceğini önermektedir. Bu yöntemlerin bağımsız olarak veya birlikte uygulanması, daha doğru teşhislere ve daha iyi hasta sonuçlarına yol açabilir. Gelecekteki çalışmalar, bu tekniklerin entegrasyonunu araştırarak, tamamlayıcı güçlü yönlerini kullanarak daha yüksek segmentasyon doğruluğu ve güvenilirliğine ulaşmayı hedefleyebilir.

Keywords

Aktif kontur yöntemi, Evrişimli sinir ağı (CNN), Bulanık mantık kuralları, Diş segmentasyonu

References

• Adejoh, T., Ewuzie, O. C., Ogbonna, J. K., Nwefuru, S. O., & Onuegbu, N. C. (2016). A derived exposure chart for computed radiography in a negroid population. Health, 8(10), 953-958. https://doi.org/10.4236/health.2016.810098
• Alfonso-Francia, G., Pedraza-Ortega, J.C., Badillo-Fernández, M., Toledano-Ayala, M., Aceves-Fernandez, M.A., Rodriguez-Resendiz, J., Ko, S.-B., & Tovar-Arriaga, S. (2022). Performance Evaluation of Different Object Detection Models for the Segmentation of Optical Cups and Discs. Diagnostics, 12, 3031. https://doi.org/10.3390/diagnostics12123031
• Bologna M., Michaela, C., Maurizio, C., Deborah, F.., Sergio, P.., Marco, A. (2023). Teeth Segmentation in Panoramic Dental X-ray Using Mask Regional Convolutional Neural Network. Applied Sciences, 13(13):7947-7947. doi: 10.3390/app13137947
• Bozkurt, M. H., & Karagol, S. (2020). Jaw and Teeth Segmentation on the Panoramic X-Ray Images for Dental Human Identification. Journal of digital imaging, 33(6), 1410–1427. https://doi.org/10.1007/s10278-020-00380-8
• Bruellmann, D., Sander, S., & Schmidtmann, I. (2016). The design of an fast Fourier filter for enhancing diagnostically relevant structures - endodontic files. Computers in Biology and Medicine, 72, 212–217. https://doi.org/10.1016/j.compbiomed.2016.03.019
• Cheng, C., Chen, Y. & Jiang, X. (2000). Thresholding using two-dimensional histogram and fuzzy entropy principle. IEEE Transactions on Image Processing, 9(4), 732-735, https://doi.org/10.1109/83.841949
• Cheng, H-D., & Xu, H. (2002). A novel fuzzy logic approach to mammogram contrast enhancement. Information Sciences, 148(1-4), 167-184. https://doi.org/10.1016/S0020-0255(02)00293-1
• Celeghin, A., Borriero, A., Orsenigo, D., Diano, M., Méndez Guerrero, C. A., Perotti, A., ... & Tamietto, M. (2023). Convolutional neural networks for vision neuroscience: Significance, developments, and outstanding issues. Frontiers in Computational Neuroscience, 17, 1153572. https://doi.org/10.3389/fncom.2023.1153572
• Da Silva Rocha, É., & Endo, P. T. (2022). A comparative study of deep learning models for dental segmentation in panoramic radiograph. Applied Sciences, 12(6), 3103. https://doi.org/10.3390/app12063103
• Das, S. (2016). Comparison of Various Edge Detection Technique. International Journal of Signal Processing, Image Processing and Pattern Recognition, 9(2), 143-158. https://dx.doi.org/10.14257/ijsip.2016.2.13
• Datta, S., Chaki, N., Modak B. (2023). A novel technique for dental radiographic image segmentation based on neutrosophic logic. Decision Analytics Journal, 7, 100223. https://doi.org/10.1016/j.dajour.2023.100223
• Dhanachandra, N. & Chanu, Y. J. (2020). An image segmentation approach based on fuzzy c-means and dynamic particle swarm optimization algorithm. Multimedia Tools and Applications, 79, 18839-18858, https://doi.org/10.1007/s11042-020-08699-8
• Gómez, D., Montero, J., & Yanez, J. (2006). A coloring fuzzy graph approach for image classification. Information Sciences, 176(24), 3645-3657, https://doi.org/10.1016/j.ins.2006.01.006
• Hakim, W. L., Rezaie, F., Nur, A. S., Panahi, M., Khosravi, K., Lee, C. W., & Lee, S. (2022). Convolutional neural network (CNN) with metaheuristic optimization algorithms for landslide susceptibility mapping in Icheon, South Korea. Journal of environmental management, 305, 114367. https://doi.org/10.1016/j.jenvman.2021.114367
• Hashemi, S. E., Jouybari, F. G., & Keshteli, M. H. (2023). A fuzzy C-means algorithm for optimizing data clustering. Expert Systems With Applications, 227, 1-14. https://doi.org/10.1016/j.eswa.2023.120377
• Hoang, H. H., & Tran, B. L. (2021). Accurate instance-based segmentation for boundary detection in robot grasping application. Applied Sciences, 11(9), 1-15. https://doi.org/10.3390/app11094248
• Hu, L., Cheng, H-D., & Zhang, M. (2007). A high performance edge detector based on fuzzy inference rules. Information sciences. 177(21), 4768-4784, https://doi.org/10.1016/j.ins.2007.04.001
• Jain, K. R., & Chauhan, N. C. (2019). Dental Image Analysis for Disease Diagnosis (1st ed., pp. 59-83). Springer Cham. https://doi.org/10.1007/978-3-030-14136-3
• Kaseva, T., Omidali, B., Hippeläinen, E., Mäkelä, T., Wilppu, U., Sofiev, A., Merivaara, A., Yliperttula, M., Savolainen, S., & Salli, E. (2022). Marker-controlled watershed with deep edge emphasis and optimized H-minima transform for automatic segmentation of densely cultivated 3D cell nuclei. BMC Bioinformatics, 23(1), 289. https://doi.org/10.1186/s12859-022-04827-3
• Kass, M., Witkin, A., & Terzopoulos, D. (1988). Snakes: Active Contour Models. International Journal of Computer Vision, 1(4), 321-331. https://doi.org/10.1007/BF00133570
• Khalid, N. (2022). Review on region-based segmentation using watershed and region growing techniques and their applications in different fields. Journal La Multiapp, 3(5), 241-249. https://doi.org/10.37899/journallamultiapp.v3i5.714
• Koch, T. L., Perslev, M., Igel, C. & Brandt, S. S. (2019). Accurate Segmentation of Dental Panoramic Radiographs with U-NETS. 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, pp. 15-19, doi: 10.1109/ISBI.2019.8759563.
• Kumar, A., Bhadauria, H.S. & Singh, A. (2020). Semi-supervised OTSU based hyperbolic tangent Gaussian kernel fuzzy C-mean clustering for dental radiographs segmentation. Multimed Tools Appl 79, 2745–2768. https://doi.org/10.1007/s11042-019-08268-8
• Kumar, A., Bhadauria, H. S., & Singh, A. (2021). Descriptive analysis of dental X-ray images using various practical methods: A review. PeerJ. Computer science, 7, e620. https://doi.org/10.7717/peerj-cs.620
• Lee, J. H., Han, S. S., Kim, Y. H., Lee, C., & Kim, I. (2020). Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs. Oral surgery, oral medicine, oral pathology and oral radiology, 129(6), 635-642. https://doi.org/10.1016/j.oooo.2019.11.007
• Li, C., Kao, C. Y., Gore, J. C., & Ding, Z. (2008). Minimization of region-scalable fitting energy for image segmentation. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, 17(10), 1940–1949. https://doi.org/10.1109/TIP.2008.2002304
• Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 3431-3440), Boston, MA, USA. https://doi.org/10.1109/CVPR.2015.7298965
• Milletari, F., Navab, N. & Ahmadi, S-A. (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 fourth international conference on 3D vision (3DV), (pp. 565-571), Stanford, CA, USA, https://doi.org/10.1109/3DV.2016.79
• Minnema, J., van Eijnatten, M., Hendriksen, A. A., Liberton, N., Pelt, D. M., Batenburg, K. J., Forouzanfar, T., & Wolff, J. (2019). Segmentation of dental cone-beam CT scans affected by metal artifacts using a mixed-scale dense convolutional neural network. Medical physics, 46(11), 5027–5035. https://doi.org/10.1002/mp.13793
• Mitra, S. (2021). A scanner smartly. Significance, 18(3), 12–17, https://doi.org/10.1111/1740-9713.01526
• Polizzi, A., Quinzi, V., Ronsivalle, V., Venezia, P., Santonocito, S., Lo Giudice, A., Leonardi, R., & Isola, G. (2023). Tooth automatic segmentation from CBCT images: a systematic review. Clinical oral investigations, 27(7), 3363–3378. https://doi.org/10.1007/s00784-023-05048-5
• Ramachandran, R., Gobalakrishnan, N. & Chokkalingam, A. (2022). A Survey on Various Medical Image Classification and Feature Recognition Techniques. 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), (pp. 1518-1526), Tirunelveli, India, https://doi.org/10.1109/ICOEI53556.2022.9777207
• Sezgin, M., & Sankur, B. (2004). Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 13(1), 146-166. https://doi.org/10.1117/1.1631315
• Silva, S., Oliveira, L., & Pithon, M. (2018). Automatic segmenting teeth in X-ray images: Trends, a novel data set, benchmarking and future perspectives. Expert Systems With Applications, 107, 15-31. https://doi.org/10.1016/j.eswa.2018.04.001
• Thakkar, P., Patel, D., Hirpara, I., Jagani, J., Patel, S., Shah, M., & Kshirsagar, A. (2023). A Comprehensive Review on Computer Vision and Fuzzy Logic in Forensic Science Application. Annals of Data Science, 10, 761-785. https://doi.org/10.1007/s40745-022-00408-6 Thias, A.H., Al Mubarok, A.F., Handayani, A., Danudirdjo, D. & Rajab, T.E. (2019). Brain tumor semi-automatic segmentation on mri t1-weighted images using active contour models. In: 2019 International Conference on Mechatronics, Robotics and Systems Engineering (MoRSE). (pp. 217-221), Bali, Indonesia, https://doi.org/ 10.1109/MoRSE48060.2019.8998651
• Zhang, Y., Zhang, J., & Zhou, W. (2022). Research on Image Classification Improvement Based on Convolutional Neural Networks with Mixed Training. 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), (pp. 7-10), Dali, China. https://doi.org/10.1109/ICCASIT55263.2022.9986643
• Zhao, Y., Li, P., Gao, C., Liu, Y., Chen, Q., Yang, F., & Meng, D. (2020). TSASNet: Tooth segmentation on dental panoramic X-ray images by Two-Stage Attention Segmentation Network. Knowledge-Based Systems, 206, 106338.