E-Science technologies in a workflow for personalized medicine using cancer screening as a case study

Using tears as a non-invasive source for early detection of breast cancer

The changing expression levels of ocular proteins in response to systemic disease has been well established in literature. In this study, we examined the ocular proteome to identify protein biomarkers with altered expression levels in women diagnosed with breast cancer. Tear samples were collected from 273 participants using Schirmer strip collection methods. Following protein elution, proteome wide trypsin digestion with Liquid chromatography/tandem mass spectrometry (LC-MS/MS) was used to identify potential protein biomarkers with altered expression levels in breast cancer patients. Selected biomarkers were further validated by enzyme linked immunosorbent assay (ELISA). A total of 102 individual tear samples (51 breast cancer, 51 control) were analyzed by LC-MS/MS which identified 301 proteins. Spectral intensities between the groups were compared and 14 significant proteins (p-value <0.05) were identified as potential biomarkers in breast cancer patients. Three biomarkers, S100A8 (p-value = 0.0069, 7.8-fold increase), S100A9 (p-value = 0.0048, 10.2-fold increase), and Galectin-3 binding protein (p-value = 0.01, 3.0-fold increase) with an increased expression in breast cancer patients were selected for validation using ELISA. Validation by ELISA was conducted using 171 individual tear samples (75 Breast Cancer and 96 Control). Similar to the observed LC-MS/MS results, S100A8 (p-value <0.0001) and S100A9 (p-value <0.0001) showed significantly higher expression in breast cancer patients. However, galectin-3 binding protein had increased expression in the control group. Our results provide further support for using tear proteins to detect non-ocular systemic diseases such as breast cancer. Our work provides crucial details to support the continued evaluation of tear samples in the screening and diagnosis of breast cancer and paves the way for future evaluation of the tear proteome for screening and diagnosis of systemic diseases.

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

Simple Summary

The increasing interest in implementing artificial intelligence in radiomic models has occurred alongside advancement in the tools used for computer-aided diagnosis. Such tools typically apply both statistical and machine learning methodologies to assess the various modalities used in medical image analysis. Specific to prostate cancer, the radiomics pipeline has multiple facets that are amenable to improvement. This review discusses the steps of a magnetic resonance imaging based radiomics pipeline. Present successes, existing opportunities for refinement, and the most pertinent pending steps leading to clinical validation are highlighted.

Abstract

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.