Performance evaluation of segmentation methods for assessing the lens of the frog Thoropa miliaris from synchrotron-based phase-contrast micro-CT images. (February 2022)

• Record Type: Journal Article
• Authors: Paiva, Katrine; Meneses, Anderson Alvarenga de Moura; Barcellos, Renan; Moura, Mauro Sérgio dos Santos; Mendes, Gabriela; Fidalgo, Gabriel; Sena, Gabriela; Colaço, Gustavo; Silva, Hélio Ricardo; Braz, Delson; Colaço, Marcos Vinicius; Barroso, Regina Cely
• Is Part Of: Physica medica. Volume 94(2022)
• Page Start: 43
• Page End: 52
• Publication Date: 2022-02
• Subjects: Synchrotron radiation -- Microtomography -- Biological imaging -- Deep Learning -- Image segmentation; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2021.12.013
• Languages: English
• ISSNs: 1120-1797

Abstract

Highlights: X-ray synchrotron phase-contrast microtomography to obtain 3D images of soft tissues. Phase-contrast effects to improve the visualization of Thoropa miliaris frog lenses. Lenses segmentation methods: Interpolation, Watershed and U-Net architecture. Dice similarity coefficient and volume quantification to assess segmentation methods. Abstract: Purpose: In the context of synchrotron microtomography using propagation-based phase-contrast imaging (XSPCT), we evaluated the performance of semiautomatic and automatic image segmentation of soft biological structures by means of Dice Similarity Coefficient (DSC) and volume quantification. Methods: We took advantage of the phase-contrast effects of XSPCT to provide enhanced object boundaries and improved visualization of the lenses of the frog Thoropa miliaris . Then, we applied semiautomatic segmentation methods 1 and 2 (Interpolation and Watershed, respectively) and method 3, an automatic segmentation algorithm using the U-Net architecture, to the reconstructed images. DSC and volume quantification of the lenses were used to quantify the performance of image segmentation methods. Results: Comparing the lenses segmented by the three methods, the most pronounced difference in volume quantification was between methods 1 and 3: a reduction of 4.24%. Method 1, 2 and 3 obtained the global average DSC of 97.02%, 95.41% and 89.29%, respectively. Although it obtained the lowest DSC, method 3 performed the segmentation in a matter of seconds, while the semiautomatic methods had the average time to segment the lenses around 1 h and 30 min. Conclusions: Our results suggest that the performance of U-Net was impaired due to the irregularities of the ROI edges mainly in its lower and upper regions, but it still showed high accuracy (DSC = 89.29%) with significantly reduced segmentation time compared to the semiautomatic methods. Besides, with the present work we have established a baseline for future assessments of Deep Neural Networks applied to XSPCT volumes.