Multicoil MRI data improves detection of prostate lesions from undersampled scans
End-to-end prostate lesion segmentation and detection from undersampled diffusion-weighted MRI
Computer Vision and Pattern Recognition
Summary
Detecting prostate lesions from MRI scans usually relies on fully processed images, which might lose some raw information. The authors developed a new method that works directly from the raw multicoil MRI data and uses all acquisition details to detect lesions more accurately, especially when the scan data is undersampled to make imaging faster. Their approach, called VarNet-Seg, performed better than other methods in tests with simulated faster scans. This improvement may help in faster and more accurate prostate cancer detection when further tested in real clinical settings.
What this means in practice
- •For medical imaging engineers: Develop MRI scan processing tools that use raw multicoil data to improve prostate lesion detection in accelerated imaging protocols.
- •For radiology software developers: Integrate end-to-end networks that enhance lesion segmentation accuracy in prostate MRI to support faster diagnostic workflows.
Authors
Lukas T. Rotkopf, Marco Schlimbach, Kevin Kröninger, Stefan O. Schoenberg, Heinz-Peter Schlemmer, Jens Kleesiek, Moritz Rempe
Abstract
Automated prostate lesion detection from diffusion-weighted MR imaging (DWI) conventionally relies on reconstructed images and does not fully use all acquisition information. We present an end-to-end network that uses complex multicoil DWI data and coil sensitivity information for prostate lesion segmentation. We included 269 fastMRI prostate examinations with additional voxel-level lesion annotations. Of these, 64 examinations contained PIRADS 4 or 5 lesions. The proposed network, VarNet-Seg, consists of a k-space variational network (VarNet) with six variational cascades and an image-space 3D segmentation U-Net. Comparator models used the same segmentation architecture with fully coil-combined images (CC-Seg), fixed root-sum-of-squares reconstruction (RSS-Seg), or fixed SENSE reconstruction (SENSE-Seg). We performed ablations with end-to-end training and data consistency (DC) enabled or disabled. We evaluated lesion segmentation using Dice and patient-level detection using AUROC in five-fold cross-validation with full sampling, simulated undersampling, added noise, or both. VarNet-Seg achieved the highest Dice at every undersampling level. At eight-fold acceleration, Dice was 0.22 for VarNet-Seg, 0.14 for SENSE-Seg and 0.16 for VarNet-Seg (no DC). The paired difference from SENSE-Seg was 0.08 (95% CI, 0.04-0.11). With full sampling, VarNet-Seg and RSS-Seg performed similarly (0.40 vs 0.39). Patient-level AUROC decreased from 0.75 with full sampling to 0.63 at eight-fold acceleration; corresponding RSS-Seg AUROCs were 0.76 and 0.64. The proposed multicoil network improved prostate lesion segmentation under simulated undersampling compared to conventional models. Matched ablations supported contributions from both end-to-end training and data consistency. Prospective evaluation is needed to establish whether this approach can be used clinically in accelerated prostate DWI.