Enhanced Image Quality and Comparable Diagnostic Performance of Prostate Fast Bi-MRI with Deep Learning Reconstruction.
1/5 보강
[RATIONAL AND OBJECTIVES] To evaluate image quality and diagnostic performance of prostate biparametric MRI (bi-MRI) with deep learning reconstruction (DLR).
- p-value P<0.05
- p-value P < 0.05
APA
Shen L, Yuan Y, et al. (2025). Enhanced Image Quality and Comparable Diagnostic Performance of Prostate Fast Bi-MRI with Deep Learning Reconstruction.. Academic radiology, 32(10), 5964-5974. https://doi.org/10.1016/j.acra.2025.06.059
MLA
Shen L, et al.. "Enhanced Image Quality and Comparable Diagnostic Performance of Prostate Fast Bi-MRI with Deep Learning Reconstruction.." Academic radiology, vol. 32, no. 10, 2025, pp. 5964-5974.
PMID
40683764
Abstract
[RATIONAL AND OBJECTIVES] To evaluate image quality and diagnostic performance of prostate biparametric MRI (bi-MRI) with deep learning reconstruction (DLR).
[MATERIALS AND METHODS] This prospective study included 61 adult male urological patients undergoing prostate MRI with standard-of-care (SOC) and fast protocols. Sequences included T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. DLR images were generated from FAST datasets. Three groups (SOC, FAST, DLR) were compared using: (1) five-point Likert scale, (2) signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), (3) lesion slope profiles, (4) dorsal capsule edge rise distance (ERD). PI-RADS scores were assigned to dominant lesions. ADC values were measured in histopathologically confirmed cases. Diagnostic performance was analyzed via receiver operating characteristic (ROC) curves (accuracy/sensitivity/specificity). Statistical tests included Friedman test, one-way ANOVA with post hoc analyses, and DeLong test for ROC comparisons (P<0.05).
[RESULTS] FAST scanning protocols reduced acquisition time by nearly half compared to the SOC scanning protocol. When compared to T2WI, DLR significantly improved SNR, CNR, slope profile, and ERD (P < 0.05). Similarly, DLR significantly enhanced SNR, CNR, and image sharpness when compared to DWI (P < 0.05). No significant differences were observed in PI-RADS scores and ADC values between groups (P > 0.05). The areas under the ROC curves, sensitivity, and specificity of ADC values for distinguishing benign and malignant lesions remained consistent (P > 0.05).
[CONCLUSION] DLR enhances image quality in fast prostate bi-MRI while preserving PI-RADS classification accuracy and ADC diagnostic performance.
[MATERIALS AND METHODS] This prospective study included 61 adult male urological patients undergoing prostate MRI with standard-of-care (SOC) and fast protocols. Sequences included T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. DLR images were generated from FAST datasets. Three groups (SOC, FAST, DLR) were compared using: (1) five-point Likert scale, (2) signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), (3) lesion slope profiles, (4) dorsal capsule edge rise distance (ERD). PI-RADS scores were assigned to dominant lesions. ADC values were measured in histopathologically confirmed cases. Diagnostic performance was analyzed via receiver operating characteristic (ROC) curves (accuracy/sensitivity/specificity). Statistical tests included Friedman test, one-way ANOVA with post hoc analyses, and DeLong test for ROC comparisons (P<0.05).
[RESULTS] FAST scanning protocols reduced acquisition time by nearly half compared to the SOC scanning protocol. When compared to T2WI, DLR significantly improved SNR, CNR, slope profile, and ERD (P < 0.05). Similarly, DLR significantly enhanced SNR, CNR, and image sharpness when compared to DWI (P < 0.05). No significant differences were observed in PI-RADS scores and ADC values between groups (P > 0.05). The areas under the ROC curves, sensitivity, and specificity of ADC values for distinguishing benign and malignant lesions remained consistent (P > 0.05).
[CONCLUSION] DLR enhances image quality in fast prostate bi-MRI while preserving PI-RADS classification accuracy and ADC diagnostic performance.
MeSH Terms
Male; Humans; Deep Learning; Prostatic Neoplasms; Middle Aged; Prospective Studies; Aged; Sensitivity and Specificity; Prostate; Multiparametric Magnetic Resonance Imaging; Image Interpretation, Computer-Assisted; Magnetic Resonance Imaging; Diffusion Magnetic Resonance Imaging; Signal-To-Noise Ratio
같은 제1저자의 인용 많은 논문 (5)
- Functional roles, mechanistic insights, and therapeutic potential of the IGF2BP family in viral infections and virus-associated cancers.
- Clinical efficacy of comprehensive traditional Chinese medicine in adjuvant therapy for stage Ib-IIIa resected non-small cell lung cancer: a multi-center, randomized, double-blind, placebo-controlled trial.
- Clinical and structural insights into concurrent EGFR and MET exon 14 skipping mutations in NSCLC: a multi-center series.
- Tumour-associated macrophages serve as an acetate reservoir to drive hepatocellular carcinoma metastasis.
- Prediction of non-small cell lung cancer subtypes is possible through restricted spectrum imaging.