Structure-enhanced local phase filtering using L₀ gradient minimization for efficient semiautomated knee magnetic resonance imaging segmentation

Abstract

The segmentation of bone surfaces from magnetic resonance imaging (MRI) data has applications in the quantitative measurement of knee osteoarthritis, surgery planning for patient-specific total knee arthroplasty, and its subsequent fabrication of artificial implants. However, due to the problems associated with MRI imaging, such as low contrast between bone and surrounding tissues, noise, bias fields, and the partial volume effect, segmentation of bone surfaces continues to be a challenging operation. A framework is presented for the enhancement of knee MRI scans prior to segmentation in order to obtain high contrast bone images. During the first stage, a contrast enhanced relative total variation regularization method is used in order to remove textural noise from the bone structures and surrounding soft tissue interface. This salient bone edge information is further enhanced using a sparse gradient counting method based on [Formula: see text] gradient minimization, which globally controls how many nonzero gradients are resulted in order to approximate prominent bone structures in a structure-sparsity-management manner. The last stage of the framework involves incorporation of local phase bone boundary information in order to provide an intensity invariant enhancement of contrast between the bone and surrounding soft tissue. The enhanced images are segmented using a fast random walker algorithm. Validation against expert segmentation was performed on 20 clinical knee MRI volumes and achieved a mean dice similarity coefficient of 0.949.

Improving performance of deep learning models using 3.5D U-Net via majority voting for tooth segmentation on cone beam computed tomography

“…3 27 . Slice-based evaluation of the performance of a DLM was conducted using four-fold cross validation to reflect the performance of a DLM in every slice 28 . The overall segmentation performance was calculated by averaging the performance of every slice 28 .…”

“…Slice-based evaluation of the performance of a DLM was conducted using four-fold cross validation to reflect the performance of a DLM in every slice 28 . The overall segmentation performance was calculated by averaging the performance of every slice 28 . Each voxel of the CBCT image was defined as true positive (TP), true negative (TN), false positive (FP) and false negative (FN) by comparing the prediction to the GT.…”