The invention relates to the technical field of medical
image detection, and discloses a medical
image quality control
report generation method which comprises the following steps: firstly, performing
soft tissue background field correction on a near-end
femur scanning image to remove low-frequency interference, and determining a stress conduction direction of a main pressure-bearing bone trabecula based on an anatomical geometric position; converting the image into a
spatial frequency domain, respectively extracting a structure
frequency spectrum and a full-angle average structure
frequency spectrum along the stress conduction direction, and calculating effective texture
cut-off frequencies of the structure
frequency spectrum and the full-angle average structure frequency spectrum by using a
breakpoint regression model; calculating the logarithmic ratio of the two
cut-off frequencies to obtain a quantitative index reflecting the
anisotropy retention degree of the structure, and comparing the quantitative index with an adaptive threshold constructed based on the number of frequency points to generate a
quality control report indicating whether the
image quality is qualified or not; according to the method, an anatomical mechanical path is used as a physical reference, and the homomorphism and heterogeneity problem that
image quality degradation and
pathological change are similar in performance is solved.