Pengsheng Wu

This study validates a deep learning model for automated ureteral length measurement on CT using gross specimen measurements as the reference standard. A deep learning model was trained on 3629 CT series from 1502 patients (cohort 1) to segment the ureter and extract centerline length. An independent prospective cohort (cohort 2) of 70 patients undergoing radical nephroureterectomy served as the hold-out test set. Each gross specimen was measured twice by one urologist (D1_length and D2_length), with their mean as the reference length (Ref_length). Model-predicted lengths (AI_length) were compared with Ref_length using repeated-measures one-way ANOVA with Tukey post hoc tests. Determinants of discrepancy were assessed with Spearman correlation and multiple linear regression. Marginal means (± SE) were 266 ± 3.85 mm (D1_length), 273 ± 3.25 mm (D2_length), 269 ± 2.75 mm (AI_length), and 269 ± 3.45 mm (Ref_length). Measurement method had a statistically significant but negligible effect on length (F(3, 207) = 2.73, p = 0.045, η²G = 0.007). D1_length and D2_length differed significantly from Ref_length (both p = 0.002), whereas AI_length was not statistically different from Ref_length (p > 0.999). In regression analysis, reference ureteral length was the only independently associated variable (coefficient − 0.54 mm per mm of reference length, 95% CI − 0.70 to − 0.39; p < 0.001); age, sex, body height, body weight, operation side, and lesion location were not significantly associated. The proposed deep learning pipeline achieved accurate fully automated ureteral segmentation and length measurement across diverse CT acquisition phases and demonstrated close agreement with surgical gross specimen measurements in a prospective clinical cohort, supporting its potential to assist preoperative planning and reduce reliance on manual measurement. The measurement discrepancy was governed primarily by ureteral length itself—with a small systematic underestimation in longer ureters—rather than by patient or procedural factors. However, this tendency, together with the single-center design, and the modest size of the prospective cohort, warrants further multicenter validation before routine clinical deployment.

Purpose To evaluate the performance of a deep learning-based artificial intelligence (AI) model for the multi-sequence automated segmentation and detection of focal liver lesions (FLLs) on non-contrast MRI (NC-MRI). Methods A total of 1010 NC-MRI were included as the training set, and 144 consecutive MRI were collected as the hold-out set. The publicly available LLDMMRI-2023 and CHAOS datasets were utilized for external validation. T1WI, fat-saturated T2WI (fsT2WI), and high-b-value DWI (DWI_High) were included. Radiologist annotations on individual sequences served as the reference standard. A two-stage sequential 3D V-Net was implemented for FLLs segmentation. Segmentation performance was assessed using Dice similarity coefficient (DSC). A lesion was considered detected if the DSC between model-predicted mask and reference standard exceeded zero. Detection performance was evaluated using sensitivity at the lesion and patient level, and false-positive lesion per sequence. For verified sensitivity, a lesion on one sequence was considered a true positive if detected on any other sequence for the same patient. Subgroup analyses were performed according to lesion size. Lesions were first split using a 20 mm cutoff, then classified into four size groups: 0.93. In the external validation set, sensitivities were 0.688 (0.640–0.732), 0.864 (0.833–0.891) and 0.918 (0.889–0.941), while verified sensitivities reached 0.978, 0.978 and 0.972, respectively. Per-sequence false positive lesions were 0.50, 1.94, 1.42 for the hold-out set and 0.60, 1.66, 0.90 for the external validation set. Patient-level sensitivity was 0.988 and 0.987 across the two datasets. In the external validation set, DWI_High showed a statistically significant difference in sensitivity between lesions in < 20 mm and ≥ 40 mm subgroups (p < 0.001). For fsT2WI, benign lesions achieved superior detection sensitivity, with significant differences in 10–20 mm (p < 0.001) and 20–40 mm subgroups (p < 0.05). For DWI_High, malignant lesions yielded higher sensitivity in < 10 mm subgroups (p < 0.001). Conclusion The deep learning-based AI model enables automated segmentation and detection of FLLs on NC-MRI, with acceptable performance across different lesion sizes.

The use of deep learning radiomics to predict whether advanced prostate cancer (PCa) will progress within two years after treatment has been validated, yet there remains a lack of research on estimating time to progression. Patients were enrolled from October 2017 to March 2024. One hundred and eighty-two patients with advanced PCa diagnosed through ultrasound-guided systematic prostate biopsy were enrolled. A deep learning-based radiomics model for predicting progression was firstly developed using pretreatment MR apparent diffusion coefficient (ADC) maps, and the performance of manual (ROIref) versus AI-derived (ROIai) tumor segmentations was compared. Then, survival analysis was performed to compare ROIref-based and ROIai-based radiomics-predicted probabilities in the risk stratification. The area under the receiver operating characteristics curve (AUC) was used to estimate the model efficacy. The model achieved high AUC values for progression prediction in test sets (ROIref: 0.840, ROIai: 0.852). No significant difference was observed between ROIai-based and ROIref-based approaches (ΔAUC = 0.012, p = 0.870) in the test set. Both ROIref-predicted and ROIai-predicted probabilities independently predicted progression in multivariate Cox proportional hazard regression models (p < 0.001) and stratified patients into distinct survival groups (log-rank p < 0.001). Decision curve analysis confirmed equivalent clinical utility across thresholds (0.1–0.6), with net benefit exceeding the “treat all” and “treat none” strategies. In conclusion, deep learning-based radiomics models could effectively predict advanced PCa progression, with AI-derived tumor annotations performing equally to manual expert ones.

Objectives The aim of the study was to externally validate two AI models for the classification of prostate mpMRI sequences and segmentation of the prostate gland on T2WI. Materials and methods MpMRI data from 719 patients were retrospectively collected from two hospitals, utilizing nine MR scanners from four different vendors, over the period from February 2018 to May 2022. Med3D deep learning pretrained architecture was used to perform image classification,UNet-3D was used to segment the prostate gland. The images were classified into one of nine image types by the mode. The segmentation model was validated using T2WI images. The accuracy of the segmentation was evaluated by measuring the DSC, VS,AHD.Finally,efficacy of the models was compared for different MR field strengths and sequences. Results 20,551 image groups were obtained from 719 MR studies. The classification model accuracy is 99%, with a kappa of 0.932. The precision, recall, and F1 values for the nine image types had statistically significant differences, respectively (all P < 0.001). The accuracy for scanners 1.436 T, 1.5 T, and 3.0 T was 87%, 86%, and 98%, respectively (P < 0.001). For segmentation model, the median DSC was 0.942 to 0.955, the median VS was 0.974 to 0.982, and the median AHD was 5.55 to 6.49 mm,respectively.These values also had statistically significant differences for the three different magnetic field strengths (all P < 0.001). Conclusion The AI models for mpMRI image classification and prostate segmentation demonstrated good performance during external validation, which could enhance efficiency in prostate volume measurement and cancer detection with mpMRI. Clinical relevance statement These models can greatly improve the work efficiency in cancer detection, measurement of prostate volume and guided biopsies.

Purpose To study the effect of artificial intelligence (AI) on the diagnostic performance of radiologists in interpreting prostate mpMRI images of the PI-RADS 3 category. Methods In this multicenter study, 16 radiologists were invited to interpret prostate mpMRI cases with and without AI. The study included a total of 87 cases initially diagnosed as PI-RADS 3 by radiologists without AI, with 28 cases being clinically significant cancers (csPCa) and 59 cases being non-csPCa. The study compared the diagnostic efficacy between readings without and with AI, the reading time, and confidence levels. Results AI changed the diagnosis in 65 out of 87 cases. Among the 59 non-csPCa cases, 41 were correctly downgraded to PI-RADS 1-2, and 9 were incorrectly upgraded to PI-RADS 4-5. For the 28 csPCa cases, 20 were correctly upgraded to PI-RADS 4-5, and 5 were incorrectly downgraded to PI-RADS 1-2. Radiologists assisted by AI achieved higher diagnostic specificity and accuracy than those without AI [0.695 vs 0.000 and 0.736 vs 0.322, both P < 0.001]. Sensitivity with AI was not significantly different from that without AI [0.821 vs 1.000, P = 1.000]. AI reduced reading time significantly compared to without AI (mean: 351 seconds, P < 0.001). The diagnostic confidence score with AI was significantly higher than that without AI (Cohen Kappa: -0.016). Conclusion With the help of AI, there was an improvement in the diagnostic accuracy of PI-RADS category 3 cases by radiologists. There is also an increase in diagnostic efficiency and diagnostic confidence.

Purpose: To evaluate the feasibility of using mpMRI image features predicted by AI algorithms in the prediction of clinically significant prostate cancer (csPCa). Materials and methods: This study analyzed patients who underwent prostate mpMRI and radical prostatectomy (RP) at the Affiliated Hospital of Jiaxing University between November 2017 and December 2022. The clinical data collected included age, serum prostate-specific antigen (PSA), and biopsy pathology. The reference standard was the prostatectomy pathology, and a Gleason Score (GS) of 3 + 3 = 6 was considered non-clinically significant prostate cancer (non-csPCa), while a GS ≥ 3 + 4 was considered csPCa. A pre-trained AI algorithm was used to extract the lesion on mpMRI, and the image features of the lesion and the prostate gland were analyzed. Two logistic regression models were developed to predict csPCa: an MR model and a combined model. The MR model used age, PSA, PSA density (PSAD), and the AI-predicted MR image features as predictor variables. The combined model used biopsy pathology and the aforementioned variables as predictor variables. The model’s effectiveness was evaluated by comparing it to biopsy pathology using the area under the curve (AUC) of receiver operation characteristic (ROC) analysis. Results: A total of 315 eligible patients were enrolled with an average age of 70.8 ± 5.9. Based on RP pathology, 18 had non-csPCa, and 297 had csPCa. PSA, PSAD, biopsy pathology, and ADC value of the prostate outside the lesion (ADC_prostate) varied significantly across different ISUP grade groups of RP pathology (P < 0.001). Other clinical variables and image features did not vary significantly across different ISUP grade groups (P > 0.05). The MR model included PSAD, the ratio of ADC value between the lesion and the prostate outside the lesion (ADC_{lesion/prostate}), the signal intensity ratio of DWI between the lesion and the prostate outside the lesion (DWI_{lesion/prostate}), and the ratio of DWI_{lesion/prostate} to ADC_{lesion/prostate}. The combined model included biopsy pathology, ADC_{lesion/prostate}, mean signal intensity of the lesion on DWI (DWI_lesion), DWI signal intensity of the prostate outside the lesion (DWI_prostate), and signal intensity ratio of DWI between the lesion and the prostate outside the lesion (DWI_{lesion/prostate}). The AUC of the MR model (0.830, 95% CI 0.743, 0.916) was not significantly different from that of biopsy pathology (0.820, 95% CI 0.728, 0.912, P = 0.884). The AUC of the combined model (0.915, 95% CI 0.849, 0.980) was higher than that of the biopsy pathology (P = 0.042) and MR model (P = 0.031). Conclusion: The aggressiveness of prostate cancer can be effectively predicted using AI-extracted image features from mpMRI images, similar to biopsy pathology. The prediction accuracy was improved by combining the AI-extracted mpMRI image features with biopsy pathology, surpassing the performance of biopsy pathology alone.