start adding script to visualize correlation as a 2d histogram

mu_map/vis/hist2d.py

+import cv2 as cv
+import matplotlib.pyplot as plt
+import numpy as np
+import pydicom
+
+from mu_map.dataset.util import load_dcm_img, align_images
+from mu_map.util import to_grayscale
+
+mu_map = load_dcm_img("./data/second/images/0085-stress-mu_map.dcm")
+# mu_map_syn = load_dcm_img("./tmp/0085-stress-mu_map-dl.dcm")
+mu_map_syn = load_dcm_img("./data/second/images/0084-stress-mu_map.dcm")
+
+mu_map, mu_map_syn = align_images(mu_map, mu_map_syn)
+
+_max = max(mu_map.max(), mu_map_syn.max())
+_mu_map = to_grayscale(mu_map[mu_map.shape[0] // 2], max_val=_max, min_val=0)
+_mu_map_syn = to_grayscale(mu_map_syn[mu_map_syn.shape[0] // 2], max_val=_max, min_val=0)
+
+_mu_map = cv.resize(_mu_map, (512, 512))
+_mu_map_syn = cv.resize(_mu_map_syn, (512, 512))
+s = np.full((512, 10), 239, np.uint8)
+
+# cv.imshow("Test", np.hstack((_mu_map, s, _mu_map_syn)))
+# cv.waitKey(0)
+
+fig, axs = plt.subplots(1, 2)
+for ax in axs:
+    ax.set_xlabel(r"μ-Map CT (cm$^{-1}$)")
+    ax.set_ylabel(r"μ-Map DL (cm$^{-1}$)")
+
+hist, _, _, _ = axs[0].hist2d(mu_map.flatten(), mu_map_syn.flatten(), bins=[100, 100], range=((0.0, 0.2), (0.0, 0.2)))
+hist[0, 0] = 0
+axs[1].imshow(hist, origin="lower")
+
+plt.tight_layout()
+plt.show()
+
+
+