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

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 V.; Barroso, R.C.

doi:10.1016/j.ejmp.2021.12.013

Cited by 4 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Precisely because of the fact that the database of biomedical images uses not to be very large, the authors created a network that is able to be trained end-to-end and presents accurate results. Paiva et al (2022) used U-Net to segment microcomputed tomography images which the Region of Interest (ROI) corresponds to lenses of an imago specimen of the frog Thoropa miliaris and compared the performance to methods of semiautomatic segmentation. The research concluded that the automatic segmentation using Fully Convnet was much faster than the semiautomatic processes and it also showed high accuracy.…”

Section: U-netmentioning

confidence: 99%

Lung Computed Tomography Image Segmentation Using U-Net Convolutional Neural Network

Pereira¹,

Silva²,

Barroso³

et al. 2022

Anais Do(a) Anais Do Encontro Nacional De Modelagem Computacional, Encontro De Ciência E Tecnologia De Materiais, Conferência S

View full text Add to dashboard Cite

Image segmentation is one of the main resources in computer vision. Nowadays, this procedure can be made with high precision using Deep Learning, and this fact is important to applications of several research areas including medical image analysis. Image segmentation is currently applied to find tumors, bone defects and other elements that are crucial to achieve accurate diagnoses. The objective of the present work is to perform segmentation of lung computed tomography from a dataset of the website Kaggle (www.kaggle.com) using U-Net, a Deep Convolutional Neural Network with Deep Learning, used in biomedical image segmentation. The dataset contains 267 volumes, which are composed of the 2D images and the masks that corresponds to the manual segmented lungs, the reference image called ground truth. In the present work, the dataset was subdivided in such a way that 80% of the volumes were dedicated for training and 20% were used for testing. The results were evaluated using the Dice Similarity Coefficient as metric and the value 0.83 was the mean obtained segmenting images of test data.

show abstract

Section: U-netmentioning

confidence: 99%