Katrine Paiva1, Anderson Alvarenga de Moura Meneses2, Renan Barcellos3, Mauro Sérgio Dos Santos Moura2, Gabriela Mendes4, Gabriel Fidalgo4, Gabriela Sena5, Gustavo Colaço6, Hélio Ricardo Silva6, Delson Braz5, Marcos Vinicius Colaço4, Regina Cely Barroso4. 1. Laboratory of Applied Physics to Biomedical and Environmental Sciences, Physics Institute, State University of Rio de Janeiro, Rio de Janeiro, Brazil. Electronic address: katrine.ps@gmail.com. 2. Laboratory of Computational Intelligence, Federal University of Western Pará, Pará, Brazil. 3. Laboratory of Applied Physics to Biomedical and Environmental Sciences, Physics Institute, State University of Rio de Janeiro, Rio de Janeiro, Brazil; Nuclear Engineering Program/COPPE, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil. 4. Laboratory of Applied Physics to Biomedical and Environmental Sciences, Physics Institute, State University of Rio de Janeiro, Rio de Janeiro, Brazil. 5. Nuclear Engineering Program/COPPE, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil. 6. Laboratory of Herpetology, Institute of Biological and Health Sciences, Federal Rural University of Rio de Janeiro, Rio de Janeiro, Brazil.
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.
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.