The Chinese University of Hong Kong

Lin Shi

Defeng Wang

Hui Lin

Pheng Ann Heng

James Griffith

Matthew Lun Wong

Segmentation of bony regions in MRI images of joints is automated using a two-stage process. In a first stage, a machine-learning image-slice categorizer is used to categorize image slices of the MRI image data as belonging to one of a set of image-slice categories, depending on presence or absence of bone and/or tendon in the image slice. In a second stage, a first instance of a machine-learning segmentation classifier is used to segment image slices that contain both bone and tendon into bone and non-bone regions, and a second instance of a machine-learning segmentation classifier is used to segment image slices that contain bone but not tendon into bone regions and non-bone regions. Results from the two segmentation classifiers can be combined across image slices to provide a final segmentation of the bony structures, including inflammatory regions, in the image data.

Automatic computerized joint segmentation and inflammation quantification in MRI

A computer-implemented method for modeling an orthopedic cast, including scanning an injured limb to extract raw body data; determining, from the extracted raw body data, a target portion data of the injured limb, the determined data representing a fine cast surface for the orthopedic cast; patterning the fine cast surface to form a ventilation structure and a blank area thereon; forming an opening gap on the blank area for assembling and disassembling the orthopedic cast; and offsetting the cast surface in parallel to thicken the orthopedic cast.

Modeling method for orthopedic casts

Disclosed are methods, systems and apparatuses for detection of arterial input function (AIF) in MRI, specially DCE MR images, comprising automatic selection of AIF based on affinity propagation (AP) clustering method.

Systems and methods for detecting arterial input function (AIF)

Disclosed are methods and apparatus for analyzing medical image change, particularly bone changes, either bone gain or loss. Disclosed also are methods and apparatus for bone registration of computed tomography (CT) images. These new methods and apparatus significantly improve the efficiency of current matching procedure.

Growing community of inventors

Hong Kong, China

Lin Shi