Anonymization and data sharing are crucial for privacy protection and acquisition of large datasets for medical image analysis. This is a big challenge, especially for neuroimaging. Here, the brain's unique structure allows for re-identification and thus requires non-conventional anonymization. Generative adversarial networks (GANs) have the potential to provide anonymous images while preserving predictive properties. Analyzing brain vessel segmentation, we trained 3 GANs on time-of-flight (TOF) magnetic resonance angiography (MRA) patches for image-label generation 1) Deep convolutional GAN, 2) Wasserstein-GAN with gradient penalty (WGAN-GP) and 3) WGAN-GP with spectral normalization (WGAN-GP-SN). The generated image-labels from each GAN were used to train a U-net for segmentation and tested on real data. Moreover, we applied our synthetic patches using transfer learning on a second dataset. For an increasing number of up to 15 patients we evaluated the model performance on real data with and without pre-training. The performance for all models was assessed by the Dice Similarity Coefficient (DSC) and the 95th percentile of the Hausdorff Distance (95HD). Comparing the 3 GANs, the U-net trained on synthetic data generated by the WGAN-GP-SN showed the highest performance to predict vessels (DSC/95HD 0.85/30.00) benchmarked by the U-net trained on real data (0.89/26.57). The transfer learning approach showed superior performance for the same GAN compared to no pre-training, especially for one patient only (0.91/24.66 vs. 0.84/27.36). In this work, synthetic image-label pairs retained generalizable information and showed good performance for vessel segmentation. Besides, we showed that synthetic patches can be used in a transfer learning approach with independent data. This paves the way to overcome the challenges of scarce data and anonymization in medical imaging.Targeted drug delivery systems represent a promising strategy to treat localised disease with minimum impact on the surrounding tissue. In particular, polymeric nanocontainers have attracted major interest because of their structural and morphological advantages and the variety of polymers that can be used, allowing the synthesis of materials capable of responding to the biochemical alterations of the environment. While experimental methodologies can provide much insight, the generation of experimental data across a wide parameter space is usually prohibitively time consuming and/or expensive. To better understand the influence of varying design parameters on the release profile and drug kinetics involved, appropriately-designed mathematical models are of great benefit. Here, we developed a continuum-scale mathematical model to describe drug transport within, and release from, a hollow nanocontainer consisting of a core and a pH-responsive polymeric shell. Our two-layer mathematical model accounts for drug dissolution and diffusion and includes a mechanism to account for trapping of drug molecules within the shell. We conduct a sensitivity analysis to assess the effect of varying the model parameters on the overall behaviour of the system. To demonstrate the usefulness of our model, we focus on the particular case of cancer treatment and calibrate the model against release profile data for two anti-cancer therapeutical agents. We show that the model is capable of capturing the experimentally observed pH-dependent release. Current research is elucidating how the addition of depth of invasion (DOI) to the 8th edition of the American Joint Committee on Cancer (AJCC) TNM staging for oral cavity squamous cell carcinoma influences its prognostic accuracy. However, there is limited research on survival in pT3N0M0 oral tongue SCC (OTSCC) patients when stratifying by DOI. Determine 5-year overall survival (OS), and cancer-specific survival (CSS) for patients with pT3N0M0 oral OTSCC based on shallow DOI (<10mm) and deep DOI (10-20mm). Retrospective review involving three tertiary care cancer centers in North America. cT3N0M0 OTSCC patients receiving primary surgical treatment from 2004 to 2018 were identified. selleck inhibitor Inclusion age>18years old and confirmation of pT3N0M0 OTSCC on surgical pathology. Exclusion patients undergoing palliative treatment or previous head and neck surgery/radiotherapy. Analysis comprised two groups shallow pT3 (tumor diameter>4cm, DOI<10mm) and deep pT3 (DOI 10mm-20mm). One hundred and four patients with pT3N0M0 OTSCC were included. Mean age was 59.1years (range 18-80.74). Age, gender, and Charlson Comorbidity Index were similar between the two groups (p>0.05). Recurrence, LVI, PNI, and positive margins were more common in deep T3 tumors (P<0.05). 5-year OS (50% vs 26%, p=0.006) and CSS (72% vs 24%, p=0.005) were worse in deep pT3 tumors. Deep pT3 disease was an independent predictor of OS (p=0.004) and CSS (p=0.01) on Cox-Regression analysis. DOI is an independent predictor of poor survival in pT3N0M0 OTSCC patients. Consideration should be given to escalating adjuvant therapy for deep pT3N0M0 OTSCC patients.DOI is an independent predictor of poor survival in pT3N0M0 OTSCC patients. Consideration should be given to escalating adjuvant therapy for deep pT3N0M0 OTSCC patients. In developing countries, oral squamous cell carcinoma (OSCC) is predominantly a cancer affecting older males who smoke tobacco. In countries with effective public health strategies, smoking rates are declining rapidly. It is not clear if patients who develop OSCC without these traditional risk factors represent a clinically distinct cohort with different prognosis. A recent analysis found that elderly non-smoking females with OSCC had significantly worse prognosis, concluding that this was a distinct patient population with poorer survival. The primary aim of this study was to determine the effect of gender and age on prognosis in OSCC, and the interaction between these two variables. Multinational multi-institutional data were collected from six sites. The primary outcome of interest was disease specific survival (DSS). Time to local, regional, and distant recurrence were investigated as secondary outcomes. 3379 patients with OSCC were included. Males had significantly worse DSS compared to females (HR 1.