The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.

Convolutional neural networks (CNNs) require large amounts of data for training, beyond what can be acquired for current radiomics models. We hypothesize that deep entropy features (DEFs) derived from existing CNNs can be applied to MRI images of prostate cancers (PCa) to reliably predict the Gleason score (GS) of PCa lesions. In this study, we analyzed 112 lesions acquired from 99 PCa patients, either pre-biopsy or pre-treatment, their associated GS, and multi-parametric MRI (mpMRI) sequences. Our approach is based on the extraction of DEF features produced in individual layers of 9 pre-trained CNN models. We first analyze DEFs from separate CNNs using the Wilcoxon test and Spearman correlation to find significant features associated with GS. In a multivariate analysis, we then use the combined DEFs of all CNNs as input to a random forest (RF) classifier for predicting the Gleason grade group of patients. Among the 9 pre-trained CNNs, the NASNet-mobile architecture offered the features most correlated to GS (ρ=0.47; p<0.05). From the 7,857 combined features, 11 DEFs could differentiate GS < 8 from GS ≥ 8 (corrected p < 0.05). Moreover, the RF classifier discerned GS of 6, 3+4, 4+3, 8 and ≥ 9 with an AUC (%) of 80.08, 85.77, 97.30, 98.20, and 86.51, respectively. Our results suggest that the DEFs can be used to differentiate GS of PCa lesions with the highest accuracy of GS ≥ 8 based on mpMRI. DEFs could improve diagnosis accuracy, reduce the risks of misclassification, help to better assess prognosis, and individualize patient care approaches.

Background: Tumor-associated macrophages (TAMs) are principal immune cells in glioma microenvironment which support tumor growth and proliferation. Our aim in this study was to assess the relationship between CD204-expressed TAMs and O 6 -methylguanine-DNA methyltransferase (MGMT)-promoter methylation in World Health Organization (WHO) grade 4 astrocytomas, and its impact on patient's clinical outcome. Methods:The expression of CD204 + TAMs was quantitively assessed on 45 samples of WHO grade 4 astrocytomas using immunohistochemistry. MGMT-promoter methylation was tested by methylation techniques. The relationship between TAMs, MGMT-promoter methylation, and recurrence-free interval (RFI) was statistically analyzed.Results: There were 10 cases (22.2%) with isocitrate dehydrogenase (IDH)-mutant grade 4 astrocytoma and 35 cases (77.8%) with IDHwildtype glioblastoma. MGMT-promotor was methylated in 18 cases (40%), unmethylated in 15 cases (33%), and the remaining 12 cases showed no MGMT status because of nucleic acid degradations. The expression of CD204 + TAMs was high in 32 cases (71.7%) and low in 13 cases (28.8%). The relationship between IDH1 mutation and CD204 + TAM expression was insignificant (P = 0.93). However, the significant difference was found between MGMT methylation and CD204 + TAMs expression (P = 0.01), in which CD204 + TAMs were diffusely expressed in MGMT-methylated cases. There was no significant difference in RFI between CD204 + TAMs expression, MGMTpromoter methylation and treatment modalities.Conclusions: Grade 4 astrocytomas with diffusely expressed CD204 + TAMs are usually associated with MGMT-promoter methylation. Although this association is unclear, CD204 + TAMs may neutralize the effect of MGMT-DNA protein to loss its function, which contributes to tumor progression. This relationship had no significant impact on the patient's clinical outcome after different treatment modalities.

Sirtuin 1 (SIRT1) is a deacetylase that can regulate various biological processes via repression of transcription. Its activity has been linked to the differentiation of neural progenitor cells, although little is known about its function during retinal development. The study described herein was undertaken to evaluate the expression of SIRT1 and its innate inhibitor, DBC1, in retinal tissues and progenitor cells. We found both SIRT1 and DBC1 to be widely expressed in mouse and human retinas, with subtle differences in subcellular distribution of each protein. We further demonstrate that nuclear-localized SIRT1 is only seen in human-derived retinal progenitor cells and not in adult retinas, suggesting that this nuclear localization may be important in retinal development. Moreover, we observed cytoplasmic DBC1 in a subset of progenitor cells as well as in mature ganglion cells, indicating that the progenitor cell subset, which was comprised predominantly of small cells, may represent a population of ganglion cell precursors. Collectively, the data presented in this study provide support for SIRT1 and DBC1 as regulators of retinal development and normal retinal physiology.

Artificial intelligence (AI) has become popular in medical applications, specifically as a clinical support tool for computer-aided diagnosis. These tools are typically employed on medical data (i.e., image, molecular data, clinical variables, etc.) and used the statistical and machine learning methods to measure the model performance. In this review, we summarized and discussed the most recent radiomic pipeline used for clinical analysis. Recent findingsCurrently, limited management of cancers benefits from artificial intelligence, mostly related to a computer-aided diagnosis that avoids a biopsy analysis that presents additional risks and costs.Most AI tools are based on imaging features, known as radiomic analysis that can be refined into predictive models in non-invasively acquired imaging data. This review explores the progress of AI-based radiomic tools for clinical applications with a brief description of necessary technical steps. Explaining new radiomic approaches based on deep learning techniques will explain how the new radiomic models (deep radiomic analysis) can benefit from deep convolutional neural networks and be applied on limited data sets.