Endocrine, Journal Year: 2023, Volume and Issue: 83(3), P. 763 - 774
Published: Nov. 15, 2023
Language: Английский
Seminars in Nuclear Medicine, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 1, 2025
This review aims to provide an up-to-date overview of the utility artificial intelligence (AI) in evaluating prostate-specific membrane antigen (PSMA) positron emission tomography (PET) scans for prostate cancer (PCa). A literature was conducted on Medline, Embase, Web Science, and IEEE Xplore databases. The search focused studies that utilizes AI evaluate PSMA PET scans. Original English language published from inception October 2024 were included, while case reports, series, commentaries, conference proceedings excluded. applications show promise automating detection metastatic disease anatomical segmentation also able predict response PSMA-based theragnostic aids tumor burden segmentation, improving radiotherapy planning. could differentiate intraprostatic PCa with higher histological grade extra-prostatic extension. has potential PCa, particularly detecting metastasis, measuring burden, high cancer, predicting treatment outcomes. Larger multicenter prospective are necessary validate enhance generalizability these models.
Language: Английский
Citations
4
BJU International, Journal Year: 2024, Volume and Issue: 134(5), P. 714 - 722
Published: July 14, 2024
Objectives To assess artificial intelligence (AI) ability to evaluate intraprostatic prostate cancer (PCa) on prostate‐specific membrane antigen positron emission tomography (PSMA PET) scans prior active treatment (radiotherapy or prostatectomy). Materials and Methods This systematic review was registered the International Prospective Register of Systematic Reviews (PROSPERO identifier: CRD42023438706). A search performed Medline, Embase, Web Science, Engineering Village with following terms: ‘artificial intelligence’, ‘prostate cancer’, ‘PSMA PET’. All articles published up February 2024 were considered. Studies included if patients underwent PSMA PET scan lesions treatment. The two authors independently evaluated titles, abstracts, full text. Prediction model Risk Of Bias Assessment Tool (PROBAST) used. Results Our yield 948 articles, which 14 eligible for inclusion. Eight studies met primary endpoint differentiating high‐grade PCa. Differentiating between Society Urological Pathology (ISUP) Grade Group (GG) ≥3 PCa had an accuracy 0.671 0.992, sensitivity 0.91, specificity 0.35. ISUP GG ≥4 0.83 0.88, 0.89, 0.87. AI could identify non‐PSMA‐avid 0.87, 0.85, 0.89. Three demonstrated detect extraprostatic extensions area under curve 0.70 0.77. Lastly, can automate segmentation lesion measurement gross tumour volume. Conclusion Although current state is promising, it remains experimental not ready routine clinical application. Benefits using include: local staging, identifying otherwise radiologically occult lesions, standardisation expedite reporting scans. Larger, prospective, multicentre are needed.
Language: Английский
Citations
4
European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2024, Volume and Issue: 51(6), P. 1725 - 1728
Published: March 1, 2024
Language: Английский
Citations
3
British Journal of Radiology, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 23, 2025
To evaluate 18F-DCFPyL-PET/MRI whole-gland-derived radiomics for detecting clinically significant (cs) prostate cancer (PCa) and predicting metastasis. Therapy-naïve PCa patients who underwent 18F-DCFPyL PET/MRI were included. Whole-prostate-segmentation was performed. Feature extraction from each modality done. The selection of potential variables made through regularized binomial logistic regression. oversampled training data used to train regression outcome. estimates the models calculated, mean accuracy reported. trained assessed on test comparative evaluation performance. A total 103 (mean age=65;mean PSA=23.4) studied. Among them, 89 had csPCa, 20 metastatic disease. There 5 selected ISUP-GG≥2 T2w, ADC PET. detect N1, five T2w For M1, four ADC. Regarding performance prediction imaging-based hybrid model (T2w+PET) provided highest AUC(0.98). N1 showed AUC(0.80) T2w+PET. predict T2w+ADC AUC(0.93). Whole-gland PET/MRI-radiomics may provide a reliable csPCa. Also, acceptable reached disease in our limited population. Our findings support value whole-gland non-invasive csPCa detection PET/MRI-radiomics, less operator-dependent segmentation method, can be potentially treatment personalization patients.
Language: Английский
Citations
0
European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 28, 2025
Language: Английский
Citations
0
Abdominal Radiology, Journal Year: 2025, Volume and Issue: unknown
Published: March 6, 2025
To explore the predictive value of radiomics features extracted from anatomical ROIs in differentiating International Society Urological Pathology (ISUP) grading prostate cancer patients. This study included 1,500 patients a multi-center study. The peripheral zone (PZ) and central gland (CG, transition + zone) were segmented using deep learning algorithms defined as regions interest (ROI) this A total 12,918 image-based T2-weighted imaging (T2WI), apparent diffusion coefficient (ADC), diffusion-weighted (DWI) images these two ROIs. Synthetic minority over-sampling technique (SMOTE) algorithm was used to address class imbalance problem. Feature selection performed Pearson correlation analysis random forest regression. prediction model built classification algorithm. Kruskal-Wallis H test, ANOVA, Chi-Square Test for statistical analysis. 20 ISUP grading-related selected, including 10 PZ ROI CG ROI. On test set, combined exhibited better performance, with an AUC 0.928 (95% CI: 0.872, 0.966), compared alone (AUC: 0.838; 95% 0.722, 0.920) 0.904; 0.851, 0.945). demonstrates that radiomic based on sub-region can contribute enhanced grade prediction. combination GG provide more comprehensive information improved accuracy. Further validation strategy future will enhance its prospects improving decision-making clinical settings.
Language: Английский
Citations
0
European Journal of Nuclear Medicine and Molecular Imaging, Journal Year: 2025, Volume and Issue: unknown
Published: April 4, 2025
Language: Английский
Citations
0
Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 15
Published: May 2, 2025
Objective Early detection and timely surgical intervention are crucial in reducing mortality rates associated with clinically significant prostate cancer (csPCa). Currently, clinical diagnostics primarily depend on magnetic resonance imaging (MRI) nuclear medicine, the potential diagnostic value of abdominal computed tomography (CT) remaining underexplored. This study aims to evaluate effectiveness multi-task deep learning neural networks identifying early-stage using CT scans. Methods In this study, we enrolled 539 patients from Department Radiology (N=461) Nuclear Medicine (N=78). We utilized a network model (MTDL), based 3DUnet architecture, segment analyze collected plain images. The predictive performance was compared radiomics single-task ResNet18. A nomogram then developed approach, incorporating prediction results PSAD, age. different models evaluated receiver operating characteristic (ROC) curve area under (AUC). Results 461 were divided into training test sets at ratio 6:4, while formed validation set. Our MTDL demonstrated AUCs 0.941 (95% confidence interval [CI]: 0.905valceedi 0.912 CI: 0.904valceedi 0.932 0.883valceed training, test, cohorts, respectively. indicates that combining effectively diagnoses csPCa, offering superior models. Additionally, outperformed both accuracy. Conclusion can accurately predict presence scans, for early diagnosis cancer.
Language: Английский
Citations
0
Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)
Published: Feb. 29, 2024
Abstract To explore the feasibility of combined radiomics post-treatment I-131 total body scan (TBS) and clinical parameter to predict successful ablation in low-risk papillary thyroid carcinoma (PTC) patients. Data PTC patients who underwent total/near thyroidectomy 30 mCi between April 2015 July 2021 were retrospectively reviewed. The factors studied included age, sex, pre-ablative serum thyroglobulin (Tg). Radiomic features extracted via PyRadiomics, radiomic feature selection was performed. predictive performance for parameter, radiomic, models (radiomics with parameter) calculated using area under receiver operating characteristic curve (AUC). One hundred thirty included. Successful achieved 77 (59.2%). mean Tg unsuccessful group (15.50 ± 18.04 ng/ml) statistically significantly higher than those (7.12 7.15 ng/ml). produced AUCs 0.66, 0.77, 0.87 training sets, 0.65, 0.69, 0.78 validation respectively. model a AUC that (p < 0.05). analysis TBS showed significant improvement compared use alone. Thai Clinical Trials Registry TCTR identification number is TCTR20230816004 ( https://www.thaiclinicaltrials.org/show/TCTR20230816004 ).
Language: Английский
Citations
2
EJNMMI Research, Journal Year: 2024, Volume and Issue: 14(1)
Published: Nov. 21, 2024
The aim is to develop and validate radiomics based on 2-[18F]fluoro-D-glucose positron emission tomography/computed tomography (2-[18F]FDG PET/CT) parameters for predicting the World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade clear cell renal carcinoma (ccRCC). A total 209 patients with 214 lesions, who underwent 2-[18F]FDG PET/CT scans between December 2016 2023, were included in our study. All ccRCC lesions categorized into low (WHO/ISUP I-II) high III-IV). allocated a training group testing ratio 7:3. features extracted by serious maximum standardized uptake value (SUVmax) thresholds (0,2.5%,25%,40%) utilization minimum redundancy relevance (mRMR) least absolute shrinkage selection operator (LASSO) regression algorithm. clinical, combined models constructed. receiver operating characteristic (ROC) curve, decision curve calibration curves plotted assess performance. area under (AUC) PET-0, PET-2.5%, PET-25%, PET-40% model 0.881(95% CI: 0.822–0.940),0.883(95% 0.825–0.942),0.889(95% 0.831–0.946),0.887(95% 0.826–0.948); 0.878(95% 0.777–0.978),0.876(95% 0.776–0.977),0.871(95% 0.769–0.972),0.882(95% 0.786–0.979) group. Due perfect prediction verification performance, volume interest (VOI) from PET images SUVmax threshold 40% selected construct model. AUC clinical was 0.859 (sensitivity = 0.846, specificity 0.747) 0.909 0.808, 0.751) group, respectively; 0.882 0.857, 0.857) 0.901 0.905, 0.833) respectively. In models, 0.916, sensitivity 0.923 0.808 group; 0.881 0.792 Radiomics can be helpful predict WHO/ISUP ccRCC.
Language: Английский
Citations
2