Object detection method, object detection system for 3d mammogram, and non-transitory computer-readable storage medium

An object detection system, comprising:

• a storage device configured to store a 3D mammogram, wherein the 3D mammogram comprises a plurality of voxels;
• and
• a processor connected with the storage device, wherein the processor comprises:
• N filters configured to execute a filtering computation in the 3D mammogram respectively to generate N 3D filtering images, wherein N is an integer larger than 1;
• a plurality of differential image operators connected with the N filters, wherein the plurality of differential image operators is configured to compute a difference value between Mth and (M−1)th 3D filtering images to obtain a plurality of 3D differential images, wherein M is an integer between 1 and N;
• a blurriness value computation operator connected with the plurality of differential image operators, wherein the blurriness value computation operator is configured to use the plurality of 3D differential images to execute a filter to generate a plurality of 3D smooth differential images, wherein the blurriness value computation operator is further configured to compute a difference variation among the plurality of voxels of the plurality of 3D smooth differential images to obtain a blurriness value of the plurality of voxels;
• and
• a decision module connected with the blurriness value computation operator, wherein the decision module is configured to use the blurriness value of the plurality of voxels to execute a plurality of first decision operators to generate a plurality of first decision results, use one or the plurality of first decision results to execute a plurality of second decision operators to generate a plurality of second decision results, and execute a final decision operator by using the plurality of first decision results and the plurality of second decision results to generate a detection object of the 3D mammogram.

A non-transitory computer-readable storage medium storing computer-executable code comprising instructions for causing a processor to:

• acquire a 3D mammogram comprising a plurality of voxels;
• control N filers to execute a filtering computation in the 3D mammogram respectively to generate N 3D filtering images, wherein N is an integer larger than 1;
• compute a difference value between Mth and (M−1)th 3D filtering images to generate a plurality of 3D differential images, wherein M is an integer between 1 and N;
• execute a filtering computation in the plurality of 3D differential images to generate a plurality of 3D smooth differential images;
• compute a difference variation among the plurality of 3D smooth differential images to obtain a blurriness value of the plurality of voxels;
• use the blurriness value of the plurality of voxels in a decision module to execute a plurality of first decision operators to generate a plurality of first decision results, and use one or the plurality of first decision results to execute the plurality of second decision operators to generate a plurality of second decision results;
• and
• execute a final decision operator by using the plurality of first decision results and the plurality of second decision results to generate a detection object of the 3D mammogram.