Encoding Clinical Priori in 3D Convolutional Neural Networks for Prostate Cancer Detection in bpMRI
원문 초록
We hypothesize that anatomical priors can be viable mediums to infuse domain-specific clinical knowledge into state-of-the-art convolutional neural networks (CNN) based on the U-Net architecture. We introduce a probabilistic population prior which captures the spatial prevalence and zonal distinction of clinically significant prostate cancer (csPCa), in order to improve its computer-aided detection (CAD) in bi-parametric MR imaging (bpMRI). To evaluate performance, we train 3D adaptations of the U-Net, U-SEResNet, UNet++ and Attention U-Net using 800 institutional training-validation scans, paired with radiologically-estimated annotations and our computed prior. For 200 independent testing bpMRI scans with histologically-confirmed delineations of csPCa, our proposed method of encoding clinical priori demonstrates a strong ability to improve patient-based diagnosis (upto 8.70% increase in AUROC) and lesion-level detection (average increase of 1.08 pAUC between 0.1-10 false positives per patient) across all four architectures.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CLAIM: Clinically-Guided LGE Augmentation for Realistic and Diverse Myocardial Scar Synthesis and Segmentation
Diffusion-based Counterfactual Augmentation: Towards Robust and Interpretable Knee Osteoarthritis Grading
Towards generating more interpretable counterfactuals via concept vectors: a preliminary study on chest X-rays
Fine-grained List-wise Alignment for Generative Medication Recommendation
MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment
Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.