Method and apparatus for adaptive computer-aided diagnosis
The invention provides a method and apparatus for classifying a region of interest in imaging data, the method comprising: calculating a feature vector for at least one region of interest in the imaging data; projecting the feature vector for the at least one region of interest in the imaging data using a plurality of decision functions to generate a corresponding plurality of classifications; calculating an ensemble classification based on the plurality of classifications. receiving from the user feedback information concerning the ensemble classification; forming an additional classified feature vector from the feature vector and the feedback information; and updating at least one of the plurality of decision functions using the additional classified feature vector.
1. Method for classifying a region of interest in medical imaging data, the method comprising:
calculating a feature vector for at least one region of interest in the medical imaging data;
projecting the feature vector for the at least one region of interest in the medical imaging data using a plurality of decision functions to generate a corresponding plurality of classifications;
calculating an ensemble classification based on the plurality of classifications
determining a diagnosis based on the ensemble classification,
the method further comprising
receiving from the user feedback information concerning the ensemble classification;
forming an additional classified feature vector from the feature vector and the feedback information; and
updating at least one of the plurality of decision functions using the additional classified feature vector,
wherein each decision function is based on a different respective set of classified feature vectors.
2. The method according to claim 1 , wherein the ensemble classification is a weighted average or ranked value of the plurality of classifications.
3. The method according to claim 1 , wherein each decision function has been trained using the respective set of classified feature vectors to project a feature vector to a classification.
4. The method according to claim 3 , wherein the at least one of the plurality of decision functions is updated by adjusting said decision function so that the updated decision function has effectively been trained using the respective set of classified feature vectors and the additional classified feature vector.
5. The method according to claim 4 , wherein each decision function is based on one of a support vector machine (SVM), a decision tree, or a boosted stump.
6. The method according to claim 1 , wherein the medical imaging data represents a human lung or a human breast.
7. The method according to claim 6 , wherein the medical imaging data is a computer tomography (CT) image.
8. Computation platform comprising a computation device, the computation device comprising a processing unit, wherein the processing unit is adapted for:
calculating a feature vector for at least one region of interest in received medical imaging data;
projecting the feature vector for the at least one region of interest in the medical imaging data using a plurality of decision functions to generate a corresponding plurality of classifications;
calculating an ensemble classification based on the plurality of classifications
determining a diagnosis based on the ensemble classification,
wherein the computation device is further adapted for:
receiving from the user feedback information concerning the ensemble classification;
forming an additional classified feature vector from the feature vector and the feedback information; and
updating at least one of the plurality of decision functions using the additional classified feature vector,
wherein each decision function is based on a different respective set of classified feature vectors.
9. System of a computation platform according to claim 8 and a workstation, wherein the workstation is adapted to receive the ensemble classification and to transmit the feedback information.
10. Non-transitory computer readable medium comprising computer instructions for implementing the method according to claim 1 .