Cancerous lesion identifying method via hyper-spectral imaging technique

1. A cancerous lesion identifying method via hyper-spectral imaging technique, comprising steps of:

acquiring a plurality of first pathology images via an endoscopy, wherein the first pathology images are cancerous lesion images respectively;

importing the first pathology images into an image processing module to acquire a plurality of first simulating spectra of the first pathology images so as to generate a principle component score diagram in accordance with the first simulating spectra;

defining a plurality of triangle areas in the principle component score diagram in accordance with the first simulating spectra;

determining whether a principle component score of a second simulating spectrum of a second pathology image is within any one of the triangle areas; and

confirming the second pathology image belongs to one of the cancerous lesion images when the principle component score of the second simulating spectrum is within any one of the triangle areas.

2. The cancerous lesion identifying method as claimed in claim 1 , wherein the first pathology images and the second pathology image are imported into a hyper-spectral imaging system to obtain the first simulating spectra and the second simulating spectrum.

3. The cancerous lesion identifying method as claimed in claim 1 , wherein the step of defining the triangle areas in the principle component score diagram in accordance with the first simulating spectra includes steps of:

converting the first pathology images to be gray scale via a gray scale image converting module;

enhancing contrast of the first pathology images via an image enhancing module;

binarizing the gray scale of the first pathology images via an image binarizating module;

recording a plurality of pixel coordinates of the first pathology images after binarization; and

generating the principle component score diagram by exporting the pixel coordinates of the recorded first pathology images.

4. The cancerous lesion identifying method as claimed in claim 1 , wherein the step of defining the triangle areas in the principle component score diagram in accordance with the first simulating spectra is to implement a principle component analysis method to generate the principle component score diagram.

5. The cancerous lesion identifying method as claimed in claim 1 , wherein the principle component score is a test point located within one of the triangle areas, and the second pathology image is determined to be a precancerous lesion corresponding to one of the triangle areas when the test point is located within one of the triangle areas.

6. The cancerous lesion identifying method as claimed in claim 1 , wherein the first pathology images are a plurality of esophageal lesion images.

7. The cancerous lesion identifying method as claimed in claim 1 , wherein the first pathology images and the second pathology image are epidermis intravascular images.

8. The cancerous lesion identifying method as claimed in claim 1 , wherein the triangle areas are maximum triangle areas in the principle component score diagram.