Diagnosis of prostate cancer by multi-modal ultrasound imaging.
- 1Department of Ultrasound, Deyang People's Hospital, Deyang, Sichuan, China.
- 2Medical Records Statistics Management Section, Deyang People's Hospital, Deyang, Sichuan, China.
Abstract
To evaluate the diagnostic performance of multi-modal ultrasound imaging, combining transrectal ultrasound (TRUS), shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS), for differentiating benign and malignant prostate lesions, and to provide new evidence for the early diagnosis of prostate cancer. A total of 85 patients who prospectively underwent multi-modal ultrasound examination, ultrasound-guided prostate biopsy, and pathological and immunohistochemical marker detection at our hospital between September 2022 and June 2023 were included. All ultrasound examinations and biopsies were performed within a 2-week interval. The diagnostic performance of TRUS, SWE, CEUS, and multi-modal ultrasound imaging was compared, with 95% confidence intervals (CIs) calculated for all accuracy measures. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 89.80% (95% CI: 77.81 to 95.83), 86.11% (95% CI: 70.98-93.91), 88.24%, 89.80%, and 86.11% for TRUS; 85.71% (95% CI: 72.87-92.96), 72.22% (95% CI: 55.72-84.09), 80.00%, 80.77%, and 78.79% for SWE; 93.88% (95% CI: 83.13-97.97), 91.67% (95% CI: 77.46-97.20), 92.94%, 93.88%, and 91.67% for CEUS; and 97.96% (95% CI: 89.21-99.65), 94.44% (95% CI: 81.34-98.48), 96.47%, 96.00%, and 97.14% for multi-modal ultrasound imaging, respectively. The areas under the receiver operating characteristic curves (AUCs) were 0.880 (95% CI: 0.808-0.952), 0.790 (95% CI: 0.694-0.886), 0.928 (95% CI: 0.872-0.984), and 0.962 (95% CI: 0.924-1.000) for TRUS, SWE, CEUS, and multi-modal ultrasound imaging, respectively. The diagnostic performance of multi-modal ultrasound was significantly superior to that of TRUS and SWE (P < .05). Multi-modal ultrasound imaging demonstrates complementary diagnostic advantages, particularly for prostate tumors with atypical ultrasound features that are difficult to diagnose by a single modality. For these tumors, multi-modal ultrasound imaging improves diagnostic accuracy and provides a reliable basis for the differential diagnosis of prostate tumors, warranting further clinical application.
Related
- Histopathological Imaging and Artificial Intelligence for Cancer Diagnosis and Gleason Grading: A Brief Review of Prostate Cancer.
- Artificial intelligence-based prostate cancer risk stratification via large-scale ultrasound images paired with histopathology
- Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
- Prospective Comparison of Cognitive MRI-Targeted Biopsy Under Micro-Ultrasound Guidance Versus MRI/Ultrasound Fusion-Guided Transperineal Biopsy for Clinically Significant Prostate Cancer Detection
- Global trends and hotspots of machine learning in the diagnosis of prostate cancer: a bibliometric analysis from 1997 to 2024
BibTeX
@article{li2026diagnosis,
title = {{Diagnosis of prostate cancer by multi-modal ultrasound imaging.}},
author = {Jin Li and Kang He and Hao Zhang and Dejun Hu and Xin Wei and Le Luo},
journal = {Medicine},
year = {2026},
month = oct,
doi = {10.1097/md.0000000000051135},
url = {https://europepmc.org/article/MED/42888615},
note = {CC BY},
}
RIS
TY - JOUR
TI - Diagnosis of prostate cancer by multi-modal ultrasound imaging.
AU - Jin Li
AU - Kang He
AU - Hao Zhang
AU - Dejun Hu
AU - Xin Wei
AU - Le Luo
PY - 2026
DA - 2026/10/01
JO - Medicine
DO - 10.1097/md.0000000000051135
UR - https://europepmc.org/article/MED/42888615
AB - To evaluate the diagnostic performance of multi-modal ultrasound imaging, combining transrectal ultrasound (TRUS), shear wave elastography (SWE), and contrast-enhanced ultrasound (CEUS), for differentiating benign and malignant prostate lesions, and to provide new evidence for the early diagnosis of prostate cancer. A total of 85 patients who prospectively underwent multi-modal ultrasound examination, ultrasound-guided prostate biopsy, and pathological and immunohistochemical marker detection at our hospital between September 2022 and June 2023 were included. All ultrasound examinations and biopsies were performed within a 2-week interval. The diagnostic performance of TRUS, SWE, CEUS, and multi-modal ultrasound imaging was compared, with 95% confidence intervals (CIs) calculated for all accuracy measures. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 89.80% (95% CI: 77.81 to 95.83), 86.11% (95% CI: 70.98-93.91), 88.24%, 89.80%, and 86.11% for TRUS; 85.71% (95% CI: 72.87-92.96), 72.22% (95% CI: 55.72-84.09), 80.00%, 80.77%, and 78.79% for SWE; 93.88% (95% CI: 83.13-97.97), 91.67% (95% CI: 77.46-97.20), 92.94%, 93.88%, and 91.67% for CEUS; and 97.96% (95% CI: 89.21-99.65), 94.44% (95% CI: 81.34-98.48), 96.47%, 96.00%, and 97.14% for multi-modal ultrasound imaging, respectively. The areas under the receiver operating characteristic curves (AUCs) were 0.880 (95% CI: 0.808-0.952), 0.790 (95% CI: 0.694-0.886), 0.928 (95% CI: 0.872-0.984), and 0.962 (95% CI: 0.924-1.000) for TRUS, SWE, CEUS, and multi-modal ultrasound imaging, respectively. The diagnostic performance of multi-modal ultrasound was significantly superior to that of TRUS and SWE (P < .05). Multi-modal ultrasound imaging demonstrates complementary diagnostic advantages, particularly for prostate tumors with atypical ultrasound features that are difficult to diagnose by a single modality. For these tumors, multi-modal ultrasound imaging improves diagnostic accuracy and provides a reliable basis for the differential diagnosis of prostate tumors, warranting further clinical application.
SN - 0304-5412
SN - 1536-5964
ER -