System and method for prostate visualization and cancer detection

1. A method for detecting a disease of a prostate, comprising:

receiving an image dataset acquired with at least one acquisition mode;

segmenting a region of interest including the prostate from the dataset;

applying conformal mapping to map the region of interest to a canonical shape;

generating a 3D visualization of the prostate using the canonically mapped dataset; and

applying computer aided detection (CAD) to the canonically mapped volume to detect a region of disease of the organ.

2. The method of claim 1 , wherein the disease includes a cancer.

3. The method of claim 1 , wherein the dataset comprises a plurality of datasets acquired with at least two different acquisition modes.

4. The method of claim 1 , further comprising registering the plurality of datasets.

5. The method of claim 1 , further comprising correlating the plurality of datasets.

6. The method of claim 1 , wherein the computer-aided arrangement includes an electronic biopsy.

7. The method of claim 1 , f wherein the conformal mapping further comprises the use of texture analysis.

8. A method for volume rendering of an organ, comprising:

receiving a plurality of datasets acquired with at least two acquisition modes;

segmenting the plurality of datasets to define a region of interest;

executing a multi-volume ray casting algorithm;

performing multi-modal shading;

processing the plurality of datasets using the boundary pre-passes and the multi-volume ray casting algorithm;

generating an image of the organ using the processed plurality of datasets; and

detecting a disease of the organ using a computer-aided arrangement.

9. The method of claim 8 , wherein the plurality of datasets includes at least one of a T2-weighted endorectal axial scan; a T2-weighted endorectal sagittal scan; a T2-weighted endorectal coronal scan; a T1-weighted pelvic axial scan; and a MRSI.

10. The method of claim 8 , wherein segmenting includes manually segmenting at least a portion of the plurality of datasets.

11. The method of claim 8 , further comprising upsampling at least a portion of the plurality of datasets to create an upsampled volume, and the image is generated using the upsampled volume.

12. The method of claim 11 , wherein the upsampling includes creating an interpolated slice between two neighboring slices.

13. The method of claim 12 , wherein the upsampling includes labeling at least some voxels of the interpolated slice.

14. The method of claim 13 , wherein the upsampling includes eroding at least some voxels labeled as undetermined or uncertain.

15. The method of claim 8 , wherein the multi-volume ray casting algorithm includes a plurality of boundary pre-passes configured to identify at least one of a direction for each ray and a step size for each ray.

16. The method of claim 15 , wherein the plurality of boundary pre-passes identifies at least one of a starting position in world space for each ray and a starting position in local space for each ray.

17. The method of claim 8 , wherein the multi-volume ray casting algorithm includes a single pass performing a ray casting via a single traversal.

18. The method of claim 8 , further comprising extracting the plurality of datasets and combining images to form a plurality of volumes.

19. The method of claim 18 , further comprising scoring the volumes to facilitate a diagnosis of a disease.

20. The method of claim 8 , wherein extracting the plurality of datasets includes aligning the volumes in a world space.

21. The method of claim 20 , wherein the disease is cancer.

22. The method of claim 8 , wherein the organ is a prostate.

23. The method of claim 8 , further comprising classifying at least portions of the generated image as at least one of cancerous or normal.

24. The method of claim 23 , wherein the classifying includes scoring at least a portion of the processed data set.

25. The method of claim 8 , further comprising creating a score volume including at least one score, each score associated with at least one of T2-weighted images, T1-weighted images, or MRSI images.

26. The method of claim 25 , wherein the image is generated at least partially based on the score volume.

27. The method of claim 8 , further comprising processing the plurality of datasets into at least one 3-dimensional texture.

28. The method of claim 27 , wherein the 3-dimensional texture include a volume cuboid.

29. A system for multi-modal volume rendering of an organ, comprising:

an imaging arrangement configured to acquire an image dataset acquired with at least one acquisition mode; and

a computing arrangement configured to segment a region of interest including the prostate from the dataset, apply conformal mapping to map the region of interest to a canonical shape, generate a 3D visualization of the prostate using the canonically mapped dataset, and apply computer aided detection (CAD) to the canonically mapped volume to detect a region of disease of the organ.

30. A non-transitory computer readable medium including instructions thereon that are accessible by a hardware processing arrangement, wherein, when the processing arrangement executes the instructions, the processing arrangement is configured to:

receive an image dataset acquired with at least one acquisition mode;

segment a region of interest including the prostate from the dataset;

apply conformal mapping to map the region of interest to a canonical shape;

generate a 3D visualization of the prostate using the canonically mapped dataset; and

apply computer aided detection (CAD) to the canonically mapped volume to detect a region of disease of the organ.