IRR-Net: A Joint Learning Framework for Image Reconstruction and Recognition of Photoacoustic Tomography

Figure 3

Example of image reconstruction and object recognition from the simulated data. In the binary labels, the “lesions” are the regions enclosed by red lines, and the unmarked ones are the “others”. In the multiclass labels, “lipid pool,” “calcification,” “fibrous cap,” and “mixed calcification” are the regions enclosed by the blue, red, green, and yellow lines, respectively. The unmarked parts are “other”.