Radiology. Imaging cancer最新文献

Purpose To compare diffusion-weighted imaging (DWI) with thermal dosimetry as a noncontrast method to predict ablation margins in individuals with prostate cancer treated with MRI-guided focused ultrasound (MRgFUS) ablation. Materials and Methods This secondary analysis of a prospective trial (ClinicalTrials.gov no. NCT01657942) included 17 participants (mean age, 64 years ± 6 [SD]; all male) who were treated for prostate cancer using MRgFUS in whom DWI was performed immediately after treatment. Ablation contours from computed thermal dosimetry and DWI as drawn by two blinded radiologists were compared against the reference standard of ablation assessment, posttreatment contrast-enhanced nonperfused volume (NPV) contours. The ability of each method to predict the ablation zone was analyzed quantitively using Dice similarity coefficients (DSCs) and mean Hausdorff distances (mHDs). Results DWI revealed a hyperintense rim at the margin of the ablation zone. While DWI accurately helped predict treatment margins, thermal dose contours underestimated the extent of the ablation zone compared with the T1-weighted NPV imaging reference standard. Quantitatively, contour assessment between methods showed that DWI-drawn contours matched postcontrast NPV contours (mean DSC = 0.84 ± 0.05 for DWI, mHD = 0.27 mm ± 0.13) better than the thermal dose contours did (mean DSC = 0.64 ± 0.12, mHD = 1.53 mm ± 1.20) (P < .001). Conclusion This study demonstrates that DWI, which can visualize the ablation zone directly, is a promising noncontrast method that is robust to treatment-related bulk motion compared with thermal dosimetry and correlates better than thermal dosimetry with the reference standard T1-weighted NPV. Keywords: Interventional-Body, Ultrasound-High-Intensity Focused (HIFU), Genital/Reproductive, Prostate, Oncology, Imaging Sequences, MRI-guided Focused Ultrasound, MR Thermometry, Diffusionweighted Imaging, Prostate Cancer ClinicalTrials.gov Identifier no. NCT01657942 Supplemental material is available for this article. © RSNA, 2024.

Purpose To compare two deep learning-based commercially available artificial intelligence (AI) systems for mammography with digital breast tomosynthesis (DBT) and benchmark them against the performance of radiologists. Materials and Methods This retrospective study included consecutive asymptomatic patients who underwent mammography with DBT (2019-2020). Two AI systems (Transpara 1.7.0 and ProFound AI 3.0) were used to evaluate the DBT examinations. The systems were compared using receiver operating characteristic (ROC) analysis to calculate the area under the ROC curve (AUC) for detecting malignancy overall and within subgroups based on mammographic breast density. Breast Imaging Reporting and Data System results obtained from standard-of-care human double-reading were compared against AI results with use of the DeLong test. Results Of 419 female patients (median age, 60 years [IQR, 52-70 years]) included, 58 had histologically proven breast cancer. The AUC was 0.86 (95% CI: 0.85, 0.91), 0.93 (95% CI: 0.90, 0.95), and 0.98 (95% CI: 0.96, 0.99) for Transpara, ProFound AI, and human double-reading, respectively. For Transpara, a rule-out criterion of score 7 or lower yielded 100% (95% CI: 94.2, 100.0) sensitivity and 60.9% (95% CI: 55.7, 66.0) specificity. The rule-in criterion of higher than score 9 yielded 96.6% sensitivity (95% CI: 88.1, 99.6) and 78.1% specificity (95% CI: 73.8, 82.5). For ProFound AI, a rule-out criterion of lower than score 51 yielded 100% sensitivity (95% CI: 93.8, 100) and 67.0% specificity (95% CI: 62.2, 72.1). The rule-in criterion of higher than score 69 yielded 93.1% (95% CI: 83.3, 98.1) sensitivity and 82.0% (95% CI: 77.9, 86.1) specificity. Conclusion Both AI systems showed high performance in breast cancer detection but lower performance compared with human double-reading. Keywords: Mammography, Breast, Oncology, Artificial Intelligence, Deep Learning, Digital Breast Tomosynthesis © RSNA, 2024.