Malignancy assessment for tumors

1. A computer-aided method of malignancy assessment of lesions, the method comprising:

receiving input data;

performing a first analysis on the input data to identify one or more lesions;

generating a probability map for the one or more lesions from the input data;

performing a second analysis on the input data to obtain a malignancy probability mask for the input data, wherein the malignancy probability mask comprises the form of a tensor having probabilities for different lesion classes assigned to each of one or more pixels from the input data; and

generating an overlay for the input data by combining the lesion probability map with the malignancy probability mask.

2. The method of claim 1 , wherein performing the first analysis on the input data is performed through a sliding window.

3. The method of claim 1 , wherein performing the second analysis is performed substantially simultaneously to performing the first analysis.

4. The method of claim 1 , wherein the first analysis is performed using one or more Fully Convolutional Networks (FCNs), and/or the second analysis is performed using one or more Convolutional Neural Networks (CNNs).

5. The method of claim 4 , wherein the or each FCN comprises one or more convolutional layers and/or one or more hidden representations.

6. The method of claim 4 , wherein the or each FCN comprises one or more activation layers, the one or more activation layers comprising one or more rectified linear units (ReLU) and/or exponential linear units (ELU).

7. The method of claim 4 , wherein the or each FCN comprises one or more sigmoid activation layers and/or softmax functions for each of one or more segmented regions.

8. The method of claim 4 , wherein the one or more CNNs are operable to distinguish between a malignant lesion and/or a benign lesion and/or typical tissue.

9. The method of claim 4 , wherein the one or more CNNs are operable to generate a malignancy model.

10. The method of claim 1 , wherein the input data further comprises one or more patches, the method further comprising:

calculating an overall prediction score for the one or more patches or each of the one or more patches; and

determining an overall prediction score which is a mean score across a plurality of the one or more patches.

11. The method of claim 1 , wherein the input data comprises medical image data and/or one or more Digital Imaging and Communications in Medicine (DICOM) files.

12. The method as claimed in claim 11 , wherein the medical image data comprises one or more mammograms.

13. The method of claim 1 , wherein the overlay comprises a selection of one or more elements of the malignancy probability mask based on an application of the probability map.

14. The method of claim 13 , wherein the overlay comprises a segmentation outline and/or probability map showing one or more locations of one or more segmented regions.

15. The method of claim 14 , further comprising removing voids within the segmentation outline.

16. The method of claim 14 , further comprising one or more of:

generating one or more probability masks for the one or more segmented regions;

converting one or more of the one or more probability masks to one or more binary masks, wherein the one or more binary masks comprise one or more identifications of masses and/or calcifications, wherein the converting is performed by thresholding the probabilities; and

removing one or more parts of the one or more binary masks with reference to an assigned threshold.

17. The method of claim 16 , wherein the one or more binary masks are one or both upscaled to the original size of the input data and/or stored in the form of a DICOM file.

18. An apparatus operable to perform the method of claim 1 .

19. A computer program product including one or more non-transitory machine readable mediums encoded with instructions that when executed by one or more processors cause a process to be carried out for assessing malignancy of lesions, the process comprising receiving input data;

performing a first analysis on the input data to identify one or more lesions;

generating a probability map for the one or more lesions from the input data;

performing a second analysis on the input data to obtain a malignancy probability mask for the input data, wherein the malignancy probability mask comprises the form of a tensor having probabilities for different lesion classes assigned to each of one or more pixels from the input data; and

generating an overlay for the input data by combining the lesion probability map with the malignancy probability mask.

20. A method of training a neural network to assess malignancy, the method comprising:

receiving input data;

performing a first analysis on the input data to identify one or more lesions;

generating a probability map for the one or more lesions from the input data;

performing a second analysis on the input data to obtain a malignancy probability mask for the input data, wherein the malignancy probability mask comprises the form of a tensor having probabilities for different lesion classes assigned to each of one or more pixels from the input data; and

using the lesion probability map and malignancy probability mask to train the neural network.