-
Splenomegaly Segmentation on Multi-modal MRI using Deep Convolutional Networks
The findings of splenomegaly, abnormal enlargement of the spleen, is a n...
read it
-
3D segmentation of mandible from multisectional CT scans by convolutional neural networks
Segmentation of mandibles in CT scans during virtual surgical planning i...
read it
-
Automatic Pulmonary Lobe Segmentation Using Deep Learning
Pulmonary lobe segmentation is an important task for pulmonary disease r...
read it
-
Deep learning based automatic segmentation of lumbosacral nerves on non-contrast CT for radiographic evaluation: a pilot study
Background and objective: Combined evaluation of lumbosacral structures ...
read it
-
Py3DFreeHandUS: a library for voxel-array reconstruction using Ultrasonography and attitude sensors
In medical imaging, there is a growing interest to provide real-time ima...
read it
-
NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines
NeuroNet is a deep convolutional neural network mimicking multiple popul...
read it
-
Splenomegaly Segmentation using Global Convolutional Kernels and Conditional Generative Adversarial Networks
Spleen volume estimation using automated image segmentation technique ma...
read it
Multi-modal segmentation of 3D brain scans using neural networks
Purpose: To implement a brain segmentation pipeline based on convolutional neural networks, which rapidly segments 3D volumes into 27 anatomical structures. To provide an extensive, comparative study of segmentation performance on various contrasts of magnetic resonance imaging (MRI) and computed tomography (CT) scans. Methods: Deep convolutional neural networks are trained to segment 3D MRI (MPRAGE, DWI, FLAIR) and CT scans. A large database of in total 851 MRI/CT scans is used for neural network training. Training labels are obtained on the MPRAGE contrast and coregistered to the other imaging modalities. The segmentation quality is quantified using the Dice metric for a total of 27 anatomical structures. Dropout sampling is implemented to identify corrupted input scans or low-quality segmentations. Full segmentation of 3D volumes with more than 2 million voxels is obtained in less than 1s of processing time on a graphical processing unit. Results: The best average Dice score is found on T_1-weighted MPRAGE (85.3±4.6 %). However, for FLAIR (80.0±7.1 %), DWI (78.2±7.9 %) and CT (79.1± 7.9 %), good-quality segmentation is feasible for most anatomical structures. Corrupted input volumes or low-quality segmentations can be detected using dropout sampling. Conclusion: The flexibility and performance of deep convolutional neural networks enables the direct, real-time segmentation of FLAIR, DWI and CT scans without requiring T_1-weighted scans.
READ FULL TEXT
Comments
There are no comments yet.