Search

Funder: Nanne and Gullord's foundation, BACKGROUND: The dual upregulation of TOP2A and EZH2 gene expression has been proposed as a biomarker for recurrence in prostate cancer patients to be treated with radical prostatectomy. A low tissue level of the metabolite citrate has additionally been connected to aggressive disease and recurrence in this patient group. However, for radiotherapy prostate cancer patients, few prognostic biomarkers have been suggested. The main aim of this study was to use an integrated tissue analysis to evaluate metabolites and expression of TOP2A and EZH2 as predictors for recurrence among radiotherapy patients. METHODS: From 90 prostate cancer patients (56 received neoadjuvant hormonal treatment), 172 transrectal ultrasound-guided (TRUS) biopsies were collected prior to radiotherapy. Metabolic profiles were acquired from fresh frozen TRUS biopsies using high resolution-magic angle spinning MRS. Histopathology and immunohistochemistry staining for TOP2A and EZH2 were performed on TRUS biopsies containing cancer cells (n = 65) from 46 patients, where 24 of these patients (n = 31 samples) received hormonal treatment. Eleven radical prostatectomy cohorts of a total of 2059 patients were used for validation in a meta-analysis. RESULTS: Among radiotherapy patients with up to 11 years of follow-up, a low level of citrate was found to predict recurrence, p = 0.001 (C-index = 0.74). Citrate had a higher predictive ability compared with individual clinical variables, highlighting its strength as a potential biomarker for recurrence. The dual upregulation of TOP2A and EZH2 was suggested as a biomarker for recurrence, particularly for patients not receiving neoadjuvant hormonal treatment, p = 0.001 (C-index = 0.84). While citrate was a statistically significant biomarker independent of hormonal treatment status, the current study indicated a potential of glutamine, glutamate and choline as biomarkers for recurrence among patients receiving neoadjuvant hormonal treatment, and glucose among patients not receiving neoadjuvant hormonal treatment. CONCLUSION: Using an integrated approach, our study shows the potential of citrate and the dual upregulation of TOP2A and EZH2 as biomarkers for recurrence among radiotherapy patients.

Purpose To bypass manual data preprocessing and optimize deep learning performance, we developed and evaluated CROPro, a tool to standardize automated cropping of prostate magnetic resonance (MR) images. Approach CROPro enables automatic cropping of MR images regardless of patient health status, image size, prostate volume, or pixel spacing. CROPro can crop foreground pixels from a region of interest (e.g., prostate) with different image sizes, pixel spacing, and sampling strategies. Performance was evaluated in the context of clinically significant prostate cancer (csPCa) classification. Transfer learning was used to train five convolutional neural network (CNN) and five vision transformer (ViT) models using different combinations of cropped image sizes (64 × 64, 128 × 128, and 256 × 256 pixels2), pixel spacing (0.2 × 0.2, 0.3 × 0.3, 0.4 × 0.4, and 0.5 × 0.5 mm2), and sampling strategies (center, random, and stride cropping) over the prostate. T2-weighted MR images (N = 1475) from the online available PI-CAI challenge were used to train (N = 1033), validate (N = 221), and test (N = 221) all models. Results Among CNNs, SqueezeNet with stride cropping (image size: 128 × 128, pixel spacing: 0.2 × 0.2 mm2) achieved the best classification performance (0.678 ± 0.006). Among ViTs, ViT-H/14 with random cropping (image size: 64 × 64 and pixel spacing: 0.5 × 0.5 mm2) achieved the best performance (0.756 ± 0.009). Model performance depended on the cropped area, with optimal size generally larger with center cropping (∼40 cm2) than random/stride cropping (∼10 cm2). Conclusion We found that csPCa classification performance of CNNs and ViTs depends on the cropping settings. We demonstrated that CROPro is well suited to optimize these settings in a standardized manner, which could improve the overall performance of deep learning models.

PurposeRestriction spectrum imaging (RSI) decomposes the diffusion-weighted MRI signal into separate components of known apparent diffusion coefficients (ADCs). The number of diffusion components and optimal ADCs for RSI are organ-specific and determined empirically. The purpose of this work was to determine the RSI model for breast tissues.MethodsThe diffusion-weighted MRI signal was described using a linear combination of multiple exponential components. A set of ADC values was estimated to fit voxels in cancer and control ROIs. Later, the signal contributions of each diffusion component were estimated using these fixed ADC values. Relative-fitting residuals and Bayesian information criterion were assessed. Contrast-to-noise ratio between cancer and fibroglandular tissue in RSI-derived signal contribution maps was compared to DCE imaging.ResultsA total of 74 women with breast cancer were scanned at 3.0 Tesla MRI. The fitting residuals of conventional ADC and Bayesian information criterion suggest that a 3-component model improves the characterization of the diffusion signal over a biexponential model. Estimated ADCs of triexponential model were D1,3 = 0, D2,3 = 1.5 × 10-3 , and D3,3 = 10.8 × 10-3 mm2 /s. The RSI-derived signal contributions of the slower diffusion components were larger in tumors than in fibroglandular tissues. Further, the contrast-to-noise and specificity at 80% sensitivity of DCE and a subset of RSI-derived maps were equivalent.ConclusionBreast diffusion-weighted MRI signal was best described using a triexponential model. Tumor conspicuity in breast RSI model is comparable to that of DCE without the use of exogenous contrast. These data may be used as differential features between healthy and malignant breast tissues.

Additional file 1.