Your browser doesn't support javascript.
loading
Automated prostate gland segmentation in challenging clinical cases: comparison of three artificial intelligence methods.
Johnson, Latrice A; Harmon, Stephanie A; Yilmaz, Enis C; Lin, Yue; Belue, Mason J; Merriman, Katie M; Lay, Nathan S; Sanford, Thomas H; Sarma, Karthik V; Arnold, Corey W; Xu, Ziyue; Roth, Holger R; Yang, Dong; Tetreault, Jesse; Xu, Daguang; Patel, Krishnan R; Gurram, Sandeep; Wood, Bradford J; Citrin, Deborah E; Pinto, Peter A; Choyke, Peter L; Turkbey, Baris.
Afiliación
  • Johnson LA; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Harmon SA; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Yilmaz EC; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Lin Y; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Belue MJ; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Merriman KM; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Lay NS; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Sanford TH; Department of Urology, Hawaii Pacific Health, Honolulu, HI, USA.
  • Sarma KV; Department of Psychiatry and Behavioral Sciences, University of California, San Francisco, CA, USA.
  • Arnold CW; Department of Radiology, University of California, Los Angeles, Los Angeles, CA, USA.
  • Xu Z; NVIDIA Corporation, Santa Clara, CA, USA.
  • Roth HR; NVIDIA Corporation, Santa Clara, CA, USA.
  • Yang D; NVIDIA Corporation, Santa Clara, CA, USA.
  • Tetreault J; NVIDIA Corporation, Santa Clara, CA, USA.
  • Xu D; NVIDIA Corporation, Santa Clara, CA, USA.
  • Patel KR; Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Gurram S; Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Wood BJ; Center for Interventional Oncology, National Cancer Institute, NIH, Bethesda, MD, USA.
  • Citrin DE; Department of Radiology, Clinical Center, NIH, Bethesda, MD, USA.
  • Pinto PA; Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Choyke PL; Urologic Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Turkbey B; Molecular Imaging Branch, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
Abdom Radiol (NY) ; 49(5): 1545-1556, 2024 05.
Article en En | MEDLINE | ID: mdl-38512516
ABSTRACT

OBJECTIVE:

Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters. MATERIALS AND

METHODS:

A single institution retrospective database was queried for the following conditions at prostate MRI prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model.

RESULTS:

683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001).

CONCLUSION:

Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.
Asunto(s)
Palabras clave

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Neoplasias de la Próstata / Algoritmos / Inteligencia Artificial / Imagen por Resonancia Magnética Idioma: En Revista: Abdom Radiol (NY) Año: 2024 Tipo del documento: Article

Texto completo: 1 Base de datos: MEDLINE Asunto principal: Neoplasias de la Próstata / Algoritmos / Inteligencia Artificial / Imagen por Resonancia Magnética Idioma: En Revista: Abdom Radiol (NY) Año: 2024 Tipo del documento: Article