Method and apparatus for classifying a data point in imaging data
The invention provides a method and device for creating a model for classifying a data point in imaging data representing measured intensities, the method comprising: training a model using a first labelled set of imaging data points; determining at least one first image part in the first labelled set which the model incorrectly classifies; generating second image parts similar to at least one image part; further training the model using the second image parts. Preferably the imaging data points and the second image parts comprise 3D data points.
1. Method for creating a model for classifying a data point in imaging data representing measured intensities, the method comprising:
training a model using a first labelled set of imaging data points;
determining at least one first image part in the first labelled set which the model incorrectly classifies;
generating second image parts similar to at least one image part;
further training the model using the second image parts, wherein
the imaging data is 3-dimensional (3D) pixel data and the second image parts comprise 3D pixel data,
the second image parts are generated by a generator model taking a latent vector as input, and
the latent vector is determined corresponding to image part properties of interest.
2. The method according to claim 1 , wherein the model is a convolutional neural network (CNN).
3. The method according to claim 2 , wherein the model is a 3D convolutional neural network (CNN).
4. The method according to claim 1 , wherein the model classifies every point in the imaging data.
5. The method according to claim 1 , wherein the second image parts are generated by a Generative Adersarial Network (GAN).
6. The method according to claim 1 , wherein the at least one first image part in the first labelled set which the model incorrectly classifies, is classified as a false negative.
7. Computation device comprising a processor in communication with a storage, the computation device configured for classifying a data point in imaging data representing measured intensities, by:
training a model using a first labelled set of imaging data points;
determining at least one first image part in the first labelled set which the model incorrectly classifies;
generating second image parts similar to at least one image part;
further training the model using the second image parts, wherein
the imaging data is 3-dimensional (3D) pixel data and the second image parts comprise 3D pixel data,
the second image parts are generated by a generator model taking a latent vector as input, and
the latent vector is determined corresponding to image part properties of interest.
8. The computation device according to claim 7 , wherein the model is a convolutional neural network (CNN).
9. The computation device according to claim 8 , wherein the model is a 3D convolutional neural network (CNN).
10. The computation device according to claim 7 , wherein the model classifies every point in the imaging data.
11. The computation device according to claim 7 , wherein the second image parts are generated by a Generative Adversarial Network (GAN).
12. The computation device according to claim 7 , wherein the at least one first image part in the first labelled set which the model incorrectly classifies, is classified as a false negative.
13. Non-transitory computer readable medium comprising computer instructions for implementing the method according to claim 1 .