arXiv:2611.02197v2 cs.CV

Conditional Diffusion-Based Generation of T2-Weighted Prostate MRI for Clinically Significant Prostate Cancer Classification

Xavier Rafael-Palou (Quantitative Imaging Biomarkers in Medicine), Alejandro Vergara-Richart (Quantitative Imaging Biomarkers in Medicine, Universitat Polit\`ecnica de Val\`encia, Val\`encia, Spain), Ignacio Iborra Roncales (Quantitative Imaging Biomarkers in Medicine), Carmen Prieto-de-la-Lastra (Quantitative Imaging Biomarkers in Medicine), Andreu Antolin-Redondo (Department of Radiology, Institut de Diagn\`ostic per la Imatge, Department of Surgery, Universitat Aut\`onoma de Barcelona, Bellaterra, Spain), Juan Morote (Department of Surgery, Universitat Aut\`onoma de Barcelona 외 3명

제출 2026-11-03

원문 초록

Scarce and unrepresentative training data limit the performance of prostate MRI prediction models. Synthetic T2-weighted (T2W) MRI may augment training data containing clinically significant prostate cancer (csPCa) and transition zone (TZ) lesions. In this retrospective, single-center, ethics-committee-approved study, we developed a conditional generative model for T2W prostate MRI extending MAISI-v2 with csPCa class, zonal, and lesion-mask-guided conditioning, incorporating a relative advantage weighted loss fine-tuned on 1,303 patients (1,654 lesions). Fidelity was assessed by incremental ablation, and downstream utility was evaluated with T2W-based csPCa classifiers across five simulated training-data scenarios, each testing 18 synthetic-data configurations. The proposed model reduced Fr\'echet inception distance (FID) from 13.28 (pretrained MAISI-v2) to $2.04 \pm 0.06$ internally (PI-CAI: $3.83 \pm 0.51$). Synthetic augmentation significantly increased AUC in all five scenarios (+0.027 to +0.088; adjusted $p = 0.016$--$0.043$), though cross-institutional augmentation of PI-CAI yielded a non-significant gain (+0.013; $p = 0.397$). Overall, our model improved T2W MRI fidelity, and synthetic images improved csPCa classification under simulated data constraints, although benefit did not transfer significantly across institutions.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2611.02197v2제출 시각 미확인
  2. arXiv:2611.02197v1제출 시각 미확인

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.