Multiparametric Ultrasound Imaging of Prostate Cancer Using Deep Neural Networks.

Autor:	Chan DY; Department of Biomedical Engineering, Duke University, Durham, NC, USA. Electronic address: derek.chan@duke.edu., Morris DC; Department of Biomedical Engineering, Duke University, Durham, NC, USA., Moavenzadeh SR; Department of Biomedical Engineering, Duke University, Durham, NC, USA., Lye TH; Department of Radiology, Weill Cornell Medicine, New York, NY, USA; Topcon Advanced Biomedical Imaging Laboratory, Topcon Healthcare, Oakland, NJ, USA., Polascik TJ; Departments of Urology and Radiology, Duke University Medical Center, Durham, NC, USA., Palmeri ML; Department of Biomedical Engineering, Duke University, Durham, NC, USA., Mamou J; Department of Radiology, Weill Cornell Medicine, New York, NY, USA., Nightingale KR; Department of Biomedical Engineering, Duke University, Durham, NC, USA.
Jazyk:	angličtina
Zdroj:	Ultrasound in medicine & biology [Ultrasound Med Biol] 2024 Nov; Vol. 50 (11), pp. 1716-1723. Date of Electronic Publication: 2024 Aug 22.
DOI:	10.1016/j.ultrasmedbio.2024.07.012
Abstrakt:	Objective: A deep neural network (DNN) was trained to generate a multiparametric ultrasound (mpUS) volume from four input ultrasound-based modalities (acoustic radiation force impulse [ARFI] imaging, shear wave elasticity imaging [SWEI], quantitative ultrasound-midband fit [QUS-MF], and B-mode) for the detection of prostate cancer. Methods: A DNN was trained using co-registered ARFI, SWEI, MF, and B-mode data obtained in men with biopsy-confirmed prostate cancer prior to radical prostatectomy (15 subjects, comprising 980,620 voxels). Data were obtained using a commercial scanner that was modified to allow user control of the acoustic beam sequences and provide access to the raw image data. For each subject, the index lesion and a non-cancerous region were manually segmented using visual confirmation based on whole-mount histopathology data. Results: In a prostate phantom, the DNN increased lesion contrast-to-noise ratio (CNR) compared to a previous approach that used a linear support vector machine (SVM). In the in vivo test datasets (n = 15), the DNN-based mpUS volumes clearly portrayed histopathology-confirmed prostate cancer and significantly improved CNR compared to the linear SVM (2.79 ± 0.88 vs. 1.98 ± 0.73, paired-sample t-test p < 0.001). In a sub-analysis in which the input modalities to the DNN were selectively omitted, the CNR decreased with fewer inputs; both stiffness- and echogenicity-based modalities were important contributors to the multiparametric model. Conclusion: The findings from this study indicate that a DNN can be optimized to generate mpUS prostate volumes with high CNR from ARFI, SWEI, MF, and B-mode and that this approach outperforms a linear SVM approach. Competing Interests: Conflict of interest K.R. Nightingale and M.L. Palmeri have intellectual property related to radiation force-based imaging technologies that has been licensed to Siemens, Samsung, and MicroElastic Ultrasound Systems. (Copyright © 2024 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu