Abstract: Filtering methods, apparatus, and devices are provided. In one aspect, a filtering method includes: determining whether enhanced adaptive leveling filtering is enabled for a current adaptive leveling filtering unit; if it is determined that the enhanced adaptive leveling filtering is enabled for the current adaptive leveling filtering unit, performing adaptive leveling filtering on the current adaptive leveling filtering unit by using a first filter; if it is determined that the enhanced adaptive leveling filtering is disabled for the current adaptive leveling filtering unit, performing adaptive leveling filtering on the current adaptive leveling filtering unit by using a second filter. The first filter includes a centrosymmetric filter with a 7*7 cross shape plus a 5*5 square shape, and the second filter includes a centrosymmetric filter with a 7*7 cross shape plus a 3*3 square shape.

Abstract: A purpose of the present invention is to make it possible, when diagnosing bone marrow edema, to estimate whether bone marrow edema is present in a body part of a subject without using MRI testing using a high-cost MRI device. The present invention is an estimation device that includes a learner that is trained using X-ray images in which the body part is photographed, and learning data including information about whether the body part photographed in the X-ray image has bone marrow edema, the X-ray image in which the body part of the subject is photographed being inputted into the learner, and an estimation result being outputted that relates to the presence of bone marrow edema in the body part photographed in the inputted X-ray image.

Abstract: A filtering method and apparatus, and a device are provided. The filtering method includes: when it is determined to enable Wiener filtering for an adaptive leveling filter unit of a current picture, deriving the adaptive leveling filter unit from a current Largest Coding Unit (LCU) of the current picture; obtaining reference pixels of the adaptive leveling filter unit and filter coefficients of a Wiener filter; and according to the reference pixels and the filter coefficients of the Wiener filter, performing the Wiener filtering based on sample pixels of the adaptive leveling filter unit; where the Wiener filter is a centrosymmetric filter with a shape of a 7*7 cross plus a 5*5 square, and values of the reference pixels are derived from pixel values of a reconstructed picture before the Wiener filtering.