BMC Medical Imaging最新文献

Background: Prostate Cancer (PCa) is a heterogeneous disease, where hypoxia and cribriform growth have been established as adverse prognostic features. Hypoxia refers to a condition of limited oxygen concentration within the tumor microenvironment, associated with enhanced tumor aggressiveness, resistance to therapy, and poor clinical outcome. Likewise, cribriform growth has also been related to poor prognosis, though the biologic basis remains unclear. Recent pathological studies suggest that there is an association between cribriform growth and tumor hypoxia, but evidence from PCa patient studies are scarce. To fill this knowledge gap, this study aims to investigate the association between hypoxia measured by MR imaging and cribriform growth identified in whole-mount histological specimens.

Methods: A retrospective cohort of 291 patients with biopsy-confirmed PCa who underwent radical prostatectomy and pre-operative MRI was analyzed. Tumors were graded according to the 2019 ISUP classification, and cribriform growth presence and length were assessed on whole-mount histology. The oxygen consumption and supply based model using apparent diffusion coefficient and fractional blood volume was applied to estimate hypoxia level (HL) and hypoxia fraction (HF_DWI). Differences in HL and HF_DWI across Gleason patterns and between cribriform growth-positive and -negative tumors were assessed. Furthermore, a linear regression model was used to evaluate the association between cribriform growth and hypoxia after adjusting for confounders.

Results: Cribriform growth-positive tumors exhibited significantly higher HF_DWI values compared to cribriform growth-negative tumors (p < 0.001). Within individual cancer Grade Groups (GG), cribriform growth length was significantly associated with increased HF_DWI in pGG 3 tumors. HL_median values were highest in Gleason Pattern 3 (GP3) regions and lowest in cribriform growth (GP4Crib+) regions, with significant differences observed between GP3 vs. non-cribriform growth GP4 regions (p < 0.001) and GP3 vs. GP4Crib+ (p < 0.001), consistent with more hypoxia in GP4Crib+. Multivariable regression confirmed cribriform growth presence as an independent predictor of increased hypoxia fraction, even after adjusting for tumor volume and GG.

Conclusions: This study shows an association between cribriform growth and tumor hypoxia using an MRI-based biomarker. These findings provide further biological insights into the aggressive nature of cribriform growth architecture and highlight the potential clinical utility of non-invasive hypoxia quantification for risk stratification in prostate cancer management.

Clinical trial number: Not applicable.

Purpose: To compare image quality (IQ) of reduced field-of-view (rFOV) diffusion-weighted imaging (DWI) for rectal cancer at 5.0T compared with 3.0T and determine whether tumor apparent diffusion coefficient (ADC) values are correlated with histopathological T staging.

Materials and methods: In a prospective cohort, 36 patients diagnosed with rectal cancer underwent MRI scans at both 3.0T and 5.0T systems. Two experienced radiologists independently evaluated the subjective and objective IQ parameters. Objective IQ metrics were statistically analyzed using paired t-test. Subjective assessments were compared using the Wilcoxon signed-rank test. Tumor ADC values obtained at the two magnetic field strengths were further compared, and their association with histopathological T staging was examined through Spearman's rank correlation.

Results: Objective measures demonstrated evidently improved IQ at 5.0T rFOV DWI relative to 3.0T (all P < 0.001). Subjective evaluations confirmed superior image clarity, lesion delineation, and overall diagnostic confidence at the 5.0T platform (P < 0.001). The two systems demonstrated comparable performance with respect to image artifacts and geometric distortions, showing no meaningful statistical divergence. However, the mean tumor ADC values differed significantly between 3.0T and 5.0T imaging (P < 0.001). A notable inverse correlation was identified between ADC values and histopathological T staging at both field strengths (P < 0.001).

Conclusion: rFOV DWI at 5.0T offers enhanced IQ and improved tumor visualization relative to 3.0T. The mean tumor ADC values were significantly different at 3.0T and 5.0T, which could be utilized for assessing histopathological T staging of rectal cancer.

Background: Determining isocitrate dehydrogenase (IDH) mutation status in glioma is important for determining prognosis. We aimed to compare supervised and semi-supervised machine learning (ML) models in glioma IDH1 mutation status prediction using magnetic resonance imaging (MRI)-derived radiomics features.

Methods: Images and segmentation masks from several public collections, including ACRIN-FMISO, CPTAC-GBM, IvyGAP, TCGA-GBM, TCGA-LGG, UCSF-PDGM, UPENN-GBM, and REMBRANDT, were retrieved from The Cancer Imaging Archive (TCIA) portal. These data were divided into training cohort 1, unlabeled cohort, holdout internal validation (HOIV) cohort, and external validation (EV) cohort. After image preprocessing, radiomics features were extracted from T1-weighted, T1 contrast-enhanced (T1CE), T2-weighted, and fluid-attenuated inversion recovery (FLAIR) sequences. The least absolute shrinkage and selection operator (Lasso) algorithm was used for feature selection. Supervised and semi-supervised models were then constructed using 10 ML algorithms and various sequence combinations. For supervised models, we used training cohort 1 to develop the models. Regarding semi-supervised models, we initially predicted the labels of the unlabeled cohort using the training cohort 1 (pseudolabeling), then concatenated the training cohort 1 with these pseudolabeled data to create training cohort 2, and subsequently developed models using the training cohort 2. Both supervised and semi-supervised models were then validated on HOIV and EV cohorts.

Results: Data for 436, 151, 110, and 535 patients were included in the training cohort 1, unlabeled cohort, HOIV cohort, and EV cohort, respectively. A semi-supervised model using 24 features from T1CE images yielded the highest AUC on EV (0.951), which was significantly higher than the best supervised model (AUC = 0.917, p = 0.005). The latter model was constructed using 30 features from FLAIR and T1CE sequences. Furthermore, across all sequence combinations, the semi-supervised models consistently achieved higher AUCs in the EV cohort.

Conclusion: Semi-supervised approaches may improve the performance of radiomics-based ML models in predicting glioma IDH1 status. Using pseudolabels, these models can increase the size of training data, potentially leading to enhancement of model predictive performance. Additionally, these models may improve prediction efficiency by requiring fewer image sequences.

Background: This work aims to develop and validate a novel CycleGan-based methodology to transfer the kV planning CT (pCT) to the reference MV portal images, potentially applicable to in vivo treatment dose monitoring.

Methods: The kV projections of pCT were prepared based on the various gantry angles of MV projections using treatment beams on Varian Halcyon system. A CycleGAN-based network incorporating attention module (ECA-CycleGAN) was trained to learn the relationship between kV and MV images, which performance was compared with the conventional Pix2pix and CycleGAN methods quantitatively. The beam angles and multi-leaf collimator parameters retrieved from the clinical plans were used to segment the treatment apertures on the model-generated reference MV images, within which the sensitivity to the artificial errors were tested using gamma analysis. Cross-institutional validations were performed on multiple machines and scanning protocols.

Results: Comparing the 2574 model-generated MV images with the measured ground truth of 13 validation cases, the mean ± standard deviation of the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR) and root mean square error (RMSE) were 0.969 ± 0.007, 41.3 ± 3.2 and 1.6·10^- 2±3.8·10^- 4 for ECA-CycleGAN, consistently better than that of using CycleGAN (0.940 ± 0.004, 35.7 ± 3.3 and 2.6·10^- 2±4.5·10^- 4) and pix2pix (0.931 ± 0.005, 32.4 ± 4.0 and 4.2·10^- 2±4.8·10^- 4) respectively. After introducing artificial translational or rotational errors, the gamma passing rates decreased and the gamma indices increased significantly (all P < 0.05). The ECA-CycleGAN model displayed good generalizability across various pCT scanners, imaging protocols and Halcyon accelerators from 2 institutions.

Conclusion: Without complex and time-consuming Monte Carlo simulations, the proposed ECA-CycleGAN network facilitates the efficient establishment of the reference MV portal images applicable to in vivo transmitted dosimetry. It may potentially improve the accuracy of dose delivery especially for the advanced treatment techniques when pretreatment measurement verification or inter-fractional dose remediation are impossible.

Accurate diagnosis of upper cervical spine abnormalities is crucial for effective treatment and prognosis. However, the diversity of anatomical structures and pathological abnormalities poses significant challenges to the diagnostic process. These challenges highlight the need for deep learning models, which are capable of identifying multiple abnormalities to assist in diagnosis. Traditional deep learning approaches have exhibited limitations in extracting sequential features from multi-positional X-ray images and in performing joint diagnosis of multiple coexisting abnormalities. Therefore, a CerviHFENet-based framework is proposed to perform multi-label classification of six upper cervical spine abnormalities using three-view radiographs (extension, neutral, and flexion) obtained from individual patients. The system first incorporates an adaptive region of interest (ROI) detection module to minimize irrelevant information by precisely localizing the upper cervical spine. Following this, the CerviHFENet model integrates a hybrid feature extraction (HFE) mechanism that extracts both the anatomical features of the upper cervical vertebrae and the dynamic variations in bone structure across different neck positions, thereby fully representing the comprehensive characteristics of the upper cervical spine. Furthermore, a modified focal loss function is employed to enable the model to learn the mutual exclusivity or conditionally dependent relationships among the six abnormalities. A total of 249 patients participated in the study, contributing 747 X-ray images. The model achieved a mean AUC of 96.22% and a mean mAP of 94.6% on the test set, indicating promising diagnostic performance and validating the feasibility and effectiveness of the proposed model.