Enhanced U-Net Architecture for Glottis Segmentation with VGG-16

Febri Aldi - University of Putra Indonesia YPTK, Lubuk Begalung, Padang, 25221, Indonesia
Yuhandri Yuhandri - University of Putra Indonesia YPTK, Lubuk Begalung, Padang, 25221, Indonesia
Muhammad Tajuddin - University of Putra Indonesia YPTK, Lubuk Begalung, Padang, 25221, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.4.3088

Abstract


Laryngeal endoscopic image analysis with segmentation techniques has great potential in detecting various diseases in the glottic area, which is essential for early diagnosis and proper treatment. This study proposes developing the U-Net architecture by integrating the VGG-16 model, aiming to improve the accuracy in detecting glottic areas. VGG-16 is applied to the encoder and bridge sections so that the model can take advantage of previously learned knowledge. This modification is expected to improve segmentation performance compared to standard U-Net, especially in handling variations in laryngeal image complexity. The dataset used consisted of 1,200 images taken randomly from the BAGLS website, a collection of laryngeal endoscopic image data rich in variation. The training results show that the standard U-Net produces an accuracy of 0.9995, IoU 0.6744, and DSC 0.7814. The improved U-Net showed a significant performance improvement, with an accuracy of 0.9998, an IoU of 0.8223, and a DSC of 0.9153. This improvement confirms that modifying the U-Net architecture using VGG-16 provides superior results in detecting glottic areas precisely. VGG-16 also helps model performance in overcoming the problem of smaller datasets. In addition, both models were tested using relevant evaluation metrics, and the test results showed that the improved U-Net consistently outperformed other CNN-based segmentation methods. These advantages show that the proposed approach improves accuracy and contributes significantly to developing glottic disease detection methods through laryngeal endoscopic image analysis, which can ultimately support clinical practice in detecting abnormalities in glottis more effectively.

Keywords


BAGLS; Glottis segmentation; U-Net; VGG-16

Full Text:

PDF

References


S. Chen et al., “A review of the ethnobotanical value, phytochemistry, pharmacology, toxicity and quality control of Tussilago farfara L. (coltsfoot),” J. Ethnopharmacol., vol. 267, p. 113478, Mar. 2021, doi: 10.1016/J.JEP.2020.113478.

L. N. Alfano, K. L. Focht Garand, G. A. Malandraki, S. Salam, P. M. Machado, and M. M. Dimachkie, “Measuring change in inclusion body myositis: clinical assessments versus imaging.,” Clin. Exp. Rheumatol. , 40 pp. 404-413. , Feb. 2022, Accessed: Jan. 12, 2023. [Online]. Available: https://www.clinexprheumatol.org/abstract.asp?a=18325

A. A. E. H. Gadalla, K. M. Othman, M. A. A. Hamela, and A. E. M. M. El Bohy, “Value of laryngeal ultrasound in comparison with flexible laryngoscope in diagnosis of various laryngeal masses: a cross-sectional study,” Egypt. J. Radiol. Nucl. Med., vol. 53, no. 1, pp. 1–9, Dec. 2022, doi: 10.1186/S43055-022-00904-Y/FIGURES/5.

H. Ding, Q. Cen, X. Si, Z. Pan, and X. Chen, “Automatic glottis segmentation for laryngeal endoscopic images based on U-Net,” Biomed. Signal Process. Control, vol. 71, p. 103116, Jan. 2022, doi: 10.1016/J.BSPC.2021.103116.

L. Wu and Z. Zhang, “Effects of implant and vocal fold stiffness on voice production after medialization laryngoplasty in an MRI-based vocal fold model,” J. Biomech., vol. 149, p. 111483, Mar. 2023, doi: 10.1016/J.JBIOMECH.2023.111483.

G. Andrade-Miranda, Y. Y. Stylianou, D. D. Deliyski, J. I. Godino-Llorente, and N. H. Bernardoni, “Laryngeal Image Processing of Vocal Folds Motion,” Appl. Sci. 2020, Vol. 10, Page 1556, vol. 10, no. 5, p. 1556, Feb. 2020, doi: 10.3390/APP10051556.

H. I. Turkmen and M. E. Karsligil, “Advanced computing solutions for analysis of laryngeal disorders,” Med. Biol. Eng. Comput., vol. 57, no. 11, pp. 2535–2552, Nov. 2019, doi: 10.1007/S11517-019-02031-9/METRICS.

V. Lungova and S. L. Thibeault, “Mechanisms of larynx and vocal fold development and pathogenesis,” Cell. Mol. Life Sci. 2020 7719, vol. 77, no. 19, pp. 3781–3795, Apr. 2020, doi: 10.1007/S00018-020-03506-X.

C. F. Jeffrey Kuo, Y. C. Li, W. H. Weng, K. B. Pinos Leon, and Y. H. Chu, “Applied image processing techniques in video laryngoscope for occult tumor detection,” Biomed. Signal Process. Control, vol. 55, p. 101633, Jan. 2020, doi: 10.1016/J.BSPC.2019.101633.

C. L. Chin, C. L. Chang, Y. C. Liu, and Y. L. Lin, “AUTOMATIC SEGMENTATION AND INDICATORS MEASUREMENT OF THE VOCAL FOLDS AND GLOTTAL IN LARYNGEAL ENDOSCOPY IMAGES USING MASK R-CNN,” https://doi.org/10.4015/S1016237221500277, vol. 33, no. 4, Apr. 2021, doi: 10.4015/S1016237221500277.

D. D. Nguyen, C. Madill, A. Chacon, and D. Novakovic, “Laryngoscopy and Stroboscopy,” Man. Clin. Phonetics, pp. 282–305, Apr. 2021, doi: 10.4324/9780429320903-22.

A. M. Kist et al., “A Deep Learning Enhanced Novel Software Tool for Laryngeal Dynamics Analysis,” J. Speech, Lang. Hear. Res., vol. 64, no. 6, pp. 1889–1903, May 2021, doi: 10.1044/2021_JSLHR-20-00498.

S. Bhattacharya et al., “Deep learning and medical image processing for coronavirus (COVID-19) pandemic: A survey,” Sustain. Cities Soc., vol. 65, p. 102589, Feb. 2021, doi: 10.1016/J.SCS.2020.102589.

Q. Yuan et al., “Deep learning in environmental remote sensing: Achievements and challenges,” Remote Sens. Environ., vol. 241, p. 111716, May 2020, doi: 10.1016/J.RSE.2020.111716.

X. Liu, L. Song, S. Liu, and Y. Zhang, “A Review of Deep-Learning-Based Medical Image Segmentation Methods,” Sustain. 2021, Vol. 13, Page 1224, vol. 13, no. 3, p. 1224, Jan. 2021, doi: 10.3390/SU13031224.

R. Wang, T. Lei, R. Cui, B. Zhang, H. Meng, and A. K. Nandi, “Medical image segmentation using deep learning: A survey,” IET Image Process., vol. 16, no. 5, pp. 1243–1267, Apr. 2022, doi: 10.1049/IPR2.12419.

O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28/COVER.

G. Du, X. Cao, J. Liang, X. Chen, and Y. Zhan, “Medical image segmentation based on U-Net: A review,” J. Imaging Sci. Technol., vol. 64, no. 2, p. 1, Mar. 2020, doi: 10.2352/J.IMAGINGSCI.TECHNOL.2020.64.2.020508.

D. Rao, P. Koteshwara, R. Singh, and V. Jagannatha, “Glottic lesion segmentation of computed tomography images using deep learning,” Int. J. Electr. Comput. Eng., vol. 13, no. 3, pp. 3432–3439, 2023, doi: 10.11591/ijece.v13i3.pp3432-3439.

F. J. Montalbo, “A Separable Squeezed Similarity Attention-Gated Residual U-Net for Glottis Segmentation,” 2023, doi: 10.2139/SSRN.4376759.

Y. S. Derdiman and T. Koc, “Deep learning model development with U-net architecture for glottis segmentation,” SIU 2021 - 29th IEEE Conf. Signal Process. Commun. Appl. Proc., Jun. 2021, doi: 10.1109/SIU53274.2021.9477843.

F. J. P. Montalbo, “S3AR U-Net: A separable squeezed similarity attention-gated residual U-Net for glottis segmentation,” Biomed. Signal Process. Control, vol. 92, p. 106047, Jun. 2024, doi: 10.1016/J.BSPC.2024.106047.

M. Döllinger et al., “Retraining of Convolutional Neural Networks for Glottis Segmentation in Endoscopic High-Speed Videos,” Appl. Sci. 2022, Vol. 12, Page 9791, vol. 12, no. 19, p. 9791, Sep. 2022, doi: 10.3390/APP12199791.

A. A. Dadras and P. Aichinger, “Deep Learning-Based Detection of Glottis Segmentation Failures,” Bioeng. 2024, Vol. 11, Page 443, vol. 11, no. 5, p. 443, Apr. 2024, doi: 10.3390/BIOENGINEERING11050443.

P. Gómez et al., “BAGLS, a multihospital Benchmark for Automatic Glottis Segmentation,” Sci. Data 2020 71, vol. 7, no. 1, pp. 1–12, Jun. 2020, doi: 10.1038/s41597-020-0526-3.

S. Das, M. ku Swain, G. K. Nayak, S. Saxena, and S. C. Satpathy, “Effect of learning parameters on the performance of U-Net Model in segmentation of Brain tumor,” Multimed. Tools Appl., vol. 81, no. 24, pp. 34717–34735, Aug. 2021, doi: 10.1007/S11042-021-11273-5/METRICS.

F. Pérez-García, R. Sparks, and S. Ourselin, “TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning,” Comput. Methods Programs Biomed., vol. 208, p. 106236, Sep. 2021, doi: 10.1016/J.CMPB.2021.106236.

C. Sitaula and M. B. Hossain, “Attention-based VGG-16 model for COVID-19 chest X-ray image classification,” Appl. Intell., vol. 51, no. 5, pp. 2850–2863, May 2021, doi: 10.1007/S10489-020-02055-X/TABLES/11.

R. O. Ogundokun, R. Maskeliunas, S. Misra, and R. Damaševičius, “Improved CNN Based on Batch Normalization and Adam Optimizer,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 13381 LNCS, pp. 593–604, 2022, doi: 10.1007/978-3-031-10548-7_43.

H. Zunair and A. Ben Hamza, “Sharp U-Net: Depthwise convolutional network for biomedical image segmentation,” Comput. Biol. Med., vol. 136, p. 104699, Sep. 2021, doi: 10.1016/J.COMPBIOMED.2021.104699.

J. S. Long, G. Z. Ma, E. M. Song, and R. C. Jin, “Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation,” Sensors 2021, Vol. 21, Page 3232, vol. 21, no. 9, p. 3232, May 2021, doi: 10.3390/S21093232.

H. Gao, H. Yuan, Z. Wang, and S. Ji, “Pixel Transposed Convolutional Networks,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 5, pp. 1218–1227, May 2020, doi: 10.1109/TPAMI.2019.2893965.

G. Zhao, J. Liu, J. Jiang, H. Guan, and J. R. Wen, “Skip-Connected Deep Convolutional Autoencoder for Restoration of Document Images,” Proc. - Int. Conf. Pattern Recognit., vol. 2018-August, pp. 2935–2940, Nov. 2018, doi: 10.1109/ICPR.2018.8546199.

M. Amiri, R. Brooks, and H. Rivaz, “Fine-Tuning U-Net for Ultrasound Image Segmentation: Different Layers, Different Outcomes,” IEEE Trans. Ultrason. Ferroelectr. Freq. Control, vol. 67, no. 12, pp. 2510–2518, Dec. 2020, doi: 10.1109/TUFFC.2020.3015081.

S. Bera and V. K. Shrivastava, “Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification,” Int. J. Remote Sens., vol. 41, no. 7, pp. 2664–2683, Apr. 2020, doi: 10.1080/01431161.2019.1694725.

S. Ghosh, A. Chaki, and K. Santosh, “Improved U-Net architecture with VGG-16 for brain tumor segmentation,” Phys. Eng. Sci. Med., vol. 44, no. 3, pp. 703–712, Sep. 2021, doi: 10.1007/S13246-021-01019-W/METRICS.

Q. Wang, Y. Ma, K. Zhao, and Y. Tian, “A Comprehensive Survey of Loss Functions in Machine Learning,” Ann. Data Sci., vol. 9, no. 2, pp. 187–212, Apr. 2022, doi: 10.1007/S40745-020-00253-5/METRICS.

S. A. Hicks et al., “On evaluation metrics for medical applications of artificial intelligence,” Sci. Reports 2022 121, vol. 12, no. 1, pp. 1–9, Apr. 2022, doi: 10.1038/s41598-022-09954-8.

D. Müller, I. Soto-Rey, and F. Kramer, “Towards a guideline for evaluation metrics in medical image segmentation,” BMC Res. Notes, vol. 15, no. 1, pp. 1–8, Dec. 2022, doi: 10.1186/S13104-022-06096-Y/FIGURES/2.

X. Ma, H. Huang, Y. Wang, S. Romano, S. Erfani, and J. Bailey, “Normalized Loss Functions for Deep Learning with Noisy Labels.” PMLR, pp. 6543–6553, Nov. 21, 2020. Accessed: Jul. 20, 2024. [Online]. Available: https://proceedings.mlr.press/v119/ma20c.html

S. Oh, Y. J. Kim, Y. T. Park, and K. G. Kim, “Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach,” Sensors 2022, Vol. 22, Page 245, vol. 22, no. 1, p. 245, Dec. 2021, doi: 10.3390/S22010245.

C. Leyva-Porras et al., “Application of Differential Scanning Calorimetry (DSC) and Modulated Differential Scanning Calorimetry (MDSC) in Food and Drug Industries,” Polym. 2020, Vol. 12, Page 5, vol. 12, no. 1, p. 5, Dec. 2019, doi: 10.3390/POLYM12010005.

G. Pezzano, V. Ribas Ripoll, and P. Radeva, “CoLe-CNN: Context-learning convolutional neural network with adaptive loss function for lung nodule segmentation,” Comput. Methods Programs Biomed., vol. 198, p. 105792, Jan. 2021, doi: 10.1016/J.CMPB.2020.105792.

I. M. Chen et al., “3D VOSNet: Segmentation of endoscopic images of the larynx with subsequent generation of indicators,” Heliyon, vol. 9, no. 3, p. e14242, 2023, doi: 10.1016/j.heliyon.2023.e14242.

D. Degala et al., “Automatic glottis detection and segmentation in stroboscopic videos using convolutional networks,” Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH, vol. 2020-Octob, pp. 4801–4805, 2020, doi: 10.21437/Interspeech.2020-2599.

M. K. Fehling, F. Grosch, M. E. Schuster, B. Schick, and J. Lohscheller, “Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep Convolutional LSTM Network,” PLoS One, vol. 15, no. 2, pp. 1–29, 2020, doi: 10.1371/journal.pone.0227791.

R. Groh, S. Dürr, A. Schützenberger, M. Semmler, and A. M. Kist, “Long-term performance assessment of fully automatic biomedical glottis segmentation at the point of care,” PLoS One, vol. 17, no. 9, p. e0266989, Sep. 2022, doi: 10.1371/JOURNAL.PONE.0266989.