Radiation-Induced Lung Injury Imaging

Radiation-induced lung injury (RILI) occurs in up to 30% of thoracic radiotherapy (RT) cases and is a major limiting factor of dose escalation to achieve tumor control and improve survival. RILI can be separated into two phases: an early inflammatory phase and a late fibrotic phase. Imaging has the potential to provide a helpful understanding of RILI for diagnosis, monitoring and treatment. Current clinical imaging methods rely on anatomical imaging and occasionally incorporate functional imaging. With the advent of molecular imaging, specific targeted probes can be designed to image RILI at every stage of the process. Molecular imaging is still in its infancy and most new RILI imaging techniques are still under development. This chapter summarizes the different imaging methods used clinically for RILI imaging and explores new developments for the future of RILI management.

Radiomics

Recent advances in image-guided and adaptive radiotherapy have ushered new requirements for using single and/or multiple-imaging modalities in staging, treatment planning, and predicting response of different cancer types. Quantitative information analysis from multi-imaging modalities, known as ‘radiomics', have generated great promises to unravel hidden knowledge embedded in imaging for mining it and its association with observed clinical endpoints and/or underlying biological processes. In this chapter, we will review recent advances and discuss current challenges for using radiomics in radiotherapy. We will discuss issues related to image acquisition, registration, contouring, feature extraction and fusion, statistical modeling, and combination with other imaging modalities and other ‘omics' for developing robust models of treatment outcomes. We will provide examples based on our experience and others for predicting cancer outcomes in radiotherapy generally and brain cancer specifically, and their application in personalizing treatment planning and clinical decision-making.

Massive-Training Support Vector Regression With Feature Selection in Application of Computer-Aided Detection of Polyps in CT Colonography

A major challenge in the latest computer-aided detection (CADe) of polyps in CT colonography (CTC) is to improve the false positive (FP) rate while maintaining detection sensitivity. Radiologists prefer CADe system produce small number of false positive detections, otherwise they might not consider CADe system improve their workflow. Towards this end, in this study, we applied a nonlinear regression model operating on CTC image voxels directly and a nonlinear classification model with extracted image features based on support vector machines (SVMs) in order to improve the specificity of CADe of polyps. We investigated the feasibility of a support vector regression (SVR) in the massive-training framework, and we developed a massive-training SVR (MTSVR) in order to reduce the long training time associated with the massive-training artificial neural network (MTANN) for reduction of FPs in CADe of polyps in CTC. In addition, we proposed a feature selection method directly coupled with an SVM classifier to maximize the CADe system performance. We compared the proposed feature selection method with the conventional stepwise feature selection based on Wilks' lambda with a linear discriminant analysis classifier. The FP reduction system based on the proposed feature selection method was able to achieve a 96.0% by-polyp sensitivity with an FP rate of 4.1 per patient. The performance is better than that of the stepwise feature selection based on Wilks' lambda (which yielded the same sensitivity with 18.0 FPs/patient). To test the performance of the proposed MTSVR, we compared it with the original MTANN in the distinction between actual polyps and various types of FPs in terms of the training time reduction and FP reduction performance. The CTC database used in this study consisted of 240 CTC datasets obtained from 120 patients in the supine and prone positions. With MTSVR, we reduced the training time by a factor of 190, while achieving a performance (by-polyp sensitivity of 94.7% with 2.5 FPs/patient) comparable to that of the original MTANN (which has the same sensitivity with 2.6 FPs/patient).

Emerging Technologies Serving Cytopathology

Cytopathology became a popular since George Papanicolaou proposed the famous test Pap 60 years ago. Today cytopathology laboratories use the microscope as primary diagnostic device; however modern laboratories host numerous modalities for molecular tests and exchange data via networks; additionally, there are imaging systems producing pictures and virtual slides at enormous sizes and volume. The latest technological developments for cloud computing, big data and mobile devices has changed the way enterprises, institutions and people use computerized systems. In this chapter are explored potential applications of these technologies in the cytopathology laboratory including: data storage, laboratory information systems, population screening programs, quality control and assurance, education and proficiency testing, e-learning, tele-consultation, primary diagnosis and research. The impact of their adoption on the daily workflow is highlighted, possible shortcomings especially for security and privacy issues are identified and future research directions are presented.

Big Data Approaches to Improve Stereotactic Body Radiation Therapy (SBRT) Outcomes

‘Big data' approaches carry promise for advancing our understanding of stereotactic body radiation therapy (SBRT) (also termed stereotactic ablative radiotherapy, SABR) and is guiding the design of clinical trials using hypofractionated radiotherapy. However, the field of big data in radiotherapy, or in combination with other therapies, is still in its infancy and will likely benefit from multidisciplinary collaborative teams including physicians, physicists, radiobiologists, biostatisticians, bioinformaticists and other data scientists analyzing shared data. We herein review opportunities to use the Big data (including dosimetry, clinical factors, imaging and biomarkers/genomics) to improve SBRT outcomes.

LAS

Rapid technological evolution is providing biomedical research laboratories with huge amounts of complex and heterogeneous data. The LIMS project Laboratory Assistant Suite (LAS), started by our Institution, aims to assist researchers throughout all of their laboratory activities, providing graphical tools to support decision-making tasks and building complex analyses on integrated data. Thanks to a clinical data management module, linking biological samples analysed by translational research with the originating patients and their clinical history, it can effectively provide insight into tumor development. Furthermore, the LAS tracks molecular experiments and allows automatic annotation of biological samples with their molecular results. A genomic annotation module makes use of semantic web technologies to represent relevant concepts from the genomic domain. The LAS system has helped improve the overall quality of the data and broadened the spectrum of interconnections among the data, offering novel perspectives to the biomedical analyst.

Breast Cancer Detection and Diagnosis

Breast cancer in women persist to be one of the primary reason of death in the world. Since the exact causes are not completely known, the most important approach is to reduce this mortality by early detection and treatment. Cancer is very difficult to diagnose in its early stages and patients only experience the symptoms when cancer has fully developed. As yet there are no effective cancer detection techniques that can detect and cure cancer at an early stage. Early cancer detection challenges very much rely on diagnostic imaging techniques at the screening stage. Newer diagnostic techniques in imaging has potential to detect timely and classify women at high possibility of the ailment. There are a several investigations that can assist in the identification of cancer, as well as blood tests, physical checkups and a several of imaging techniques including of ultrasound, MRI, mammograms and chest x-rays. This chapter focuses on the current detection techniques, discusses the shortcomings, and identifies the need for new, safer and cheaper detection techniques.

Epigenetic Signature in Breast Carcinoma, a Hidden Language to Dictate Against Genomic Insults

The bottleneck in breast carcinoma treatment regimen is actually contributed from inherent genetic and epigenetic signatures present in heterogeneous clonal populations. Epigenetic changes are viewed as permanent and inheritable molecular pattern alterations of a cellular phenotype such as the gene expression profile but do not involve changes of the DNA sequence itself. Epigenetic phenomena are mediated by several molecular mechanisms comprising of histone modifications, DNA methylation and microRNA (miRNA) guided tools. Epigenetic reprograming may help in protective adaption to environment insults as chemotherapy and radiation therapy either enhance epigenetic tag or erase the epigenetic tag. Such epigenetic tools are being preferably used by several cancer types including breast carcinoma to achieve distinctive proliferation, metastasis and resistance in the wake of genomic insults. In this book chapter, we highlight the summarized findings on implications of epigenetic landscape in breast carcinoma occurrence and presenting as promising avenues for therapeutic intervention.