Automatic Scan Planning for Magnetic Resonance Imaging of the Knee Joint

Abstract

Automatic scan planning for magnetic resonance imaging of the knee aims at defining an oriented bounding box around the knee joint from sparse scout images in order to choose the optimal field of view for the diagnostic images and limit acquisition time. We propose a fast and fully automatic method to perform this task based on the standard clinical scout imaging protocol. The method is based on sequential Chamfer matching of 2D scout feature images with a three-dimensional mean model of femur and tibia. Subsequently, the joint plane separating femur and tibia, which contains both menisci, can be automatically detected using an information-augmented active shape model on the diagnostic images. This can assist the clinicians in quickly defining slices with standardized and reproducible orientation, thus increasing diagnostic accuracy and also comparability of serial examinations. The method has been evaluated on 42 knee MR images. It has the potential to be incorporated into existing systems because it does not change the current acquisition protocol.

Automatic model‐based semantic registration of multimodal MRI knee data

“…The automated landmark detection method used in the registration scheme obtained promising accuracy and robustness at localizing anatomical landmarks in MR images with various contrasts, patient positioning and health conditions of the knee joint. The accuracy of the detected landmarks was 1-3 mm higher than that other reported findings for automated knee MR landmarking (31)(32)(33)(34). The high landmark detection accuracy will improve the performance of subsequent image processing techniques like segmentation or kinematics.…”

FISICO: Fast Image SegmentatIon COrrection

“…To create the statistical model of the knee joints, we used the database of Kozic et al [ 27 ] and Bou Sleiman et al [ 28 ], which consists of 190 manually segmented computed tomography (CT) images from normal volunteers. For the ASM-based segmentation, we used the database of Bauer et al [ 29 ], which comprises 42 MR images of knee joints. From the 42 segmented cases, we selected ten cases with the lowest quality.…”

Feasibility and impact of using an automated user interface for proton spectroscopy in multiparametric MRI of the prostate

“…Automated scanning protocols facilitate the positioning of scan volumes and saturation bands by recognizing anatomical landmarks in the examination region. Today, the feasibility and effectiveness to achieve shorter and optimized MRI examinations using a variety of automated examination protocols has already been proven in different body regions [16][17][18], and such software solutions are so far available for routine examinations in the brain, heart, abdomen, and knee. Recently, an experimental solution for the rapidly increasing prostate exams has been developed.…”