A traditional method of localizing brain functions has been to identify shared areas of brain damage in individuals who have a particular deficit. The rationale of this ‘lesion overlap’ approach is straightforward: if the individuals can no longer perform the function, the area of brain damaged in most of these individuals must have been responsible for that function. However, the reciprocal association, i.e. the probability of the lesion causing the deficit, is often not evaluated. In this study, we illustrate potential weaknesses of this approach, by re‐examining regions of the brain essential for orchestrating speech articulation. A particularly elegant and widely cited lesion overlap study identified the superior part of the precentral gyrus of the insula (in the anterior insula) as the shared area of damage in chronic stroke patients with ‘apraxia of speech’, a disorder of motor planning and programming of speech. Others have confirmed that patients with apraxia of speech commonly have damage to the anterior insula. However, this reliable association might reflect the vulnerability of the insula to damage following occlusion or narrowing of the middle cerebral artery (which can independently cause apraxia of speech and many other deficits). To evaluate this possibility, we examined the relationship between apraxia of speech and the insula in three unique ways: (i) we determined the probability of the lesion causing the deficit, as well as the deficit being associated with the lesion, by examining speech articulation and advanced MRIs in two consecutive series of patients with acute left hemisphere, non‐lacunar stroke, 40 with and 40 without insular damage; (ii) we studied patients at stroke onset to identify the deficit before it resolved in cases of small stroke; and (iii) we identified regions of dysfunctional brain tissue, as well as structural damage. Using this approach, we found no association between apraxia of speech and lesions of the left insula, anterior insula or superior tip of the precentral gyrus of the insula. Instead, in patients with and without insular lesions, apraxia of speech was associated with structural damage or low blood flow in left posterior inferior frontal gyrus. These results illustrate a potential limitation of lesion overlap studies, and illustrate an alternative method for identifying brain–behaviour relationships.

In this paper, we extend a previously reported intensity-based nonrigid registration algorithm by using a novel regularization term to constrain the deformation. Global motion is modeled by a rigid transformation while local motion is described by a free-form deformation based on B-splines. An information theoretic measure, normalized mutual information, is used as an intensity-based image similarity measure. Registration is performed by searching for the deformation that minimizes a cost function consisting of a weighted combination of the image similarity measure and a regularization term. The novel regularization term is a local volume-preservation (incompressibility) constraint, which is motivated by the assumption that soft tissue is incompressible for small deformations and short time periods. The incompressibility constraint is implemented by penalizing deviations of the Jacobian determinant of the deformation from unity. We apply the nonrigid registration algorithm with and without the incompressibility constraint to precontrast and postcontrast magnetic resonance (MR) breast images from 17 patients. Without using a constraint, the volume of contrast-enhancing lesions decreases by 1%-78% (mean 26%). Image improvement (motion artifact reduction) obtained using the new constraint is compared with that obtained using a smoothness constraint based on the bending energy of the coordinate grid by blinded visual assessment of maximum intensity projections of subtraction images. For both constraints, volume preservation improves, and motion artifact correction worsens, as the weight of the constraint penalty term increases. For a given volume change of the contrast-enhancing lesions (2% of the original volume), the incompressibility constraint reduces motion artifacts better than or equal to the smoothness constraint in 13 out of 17 cases (better in 9, equal in 4, worse in 4). The preliminary results suggest that incorporation of the incompressibility regularization term improves intensity-based free-form nonrigid registration of contrast-enhanced MR breast images by greatly reducing the problem of shrinkage of contrast-enhancing structures while simultaneously allowing motion artifacts to be substantially reduced.

The increasing use of biomarkers in cancer have led to the concept of personalized medicine for patients. Personalized medicine provides better diagnosis and treatment options available to clinicians. Radiological imaging techniques provide an opportunity to deliver unique data on different types of tissue. However, obtaining useful information from all radiological data is challenging in the era of ‘big data’. Recent advances in computational power and the use of genomics have generated a new area of research termed Radiomics. Radiomics is defined as the high throughput extraction of quantitative imaging features or texture (radiomics) from imaging to decode tissue pathology and creating a high dimensional data set for feature extraction. Radiomic features provide information about the gray-scale patterns, inter-pixel relationships. In addition, shape and spectral properties can be extracted within the same regions of interest on radiological images. Moreover, these features can be further used to develop computational models using advanced machine learning algorithms that may serve as a tool for personalized diagnosis and treatment guidance.

Principles of diffusion-weighted imaging and apparent diffusion coefficient mapping as an imaging biomarker in whole-body imaging for tissue characterization, cancer detection and staging, and assessment of treatment response are reviewed, with a focus on evaluations of the breast, liver, kidneys, and pelvis. Diffusion-weighted imaging relies on the detection of the random microscopic motion of free water molecules known as Brownian movement. With the development of new magnetic resonance (MR) imaging technologies and stronger diffusion gradients, recent applications of diffusion-weighted imaging in whole-body imaging have attracted considerable attention, especially in the field of oncology. Diffusion-weighted imaging is being established as a pivotal aspect of MR imaging in the evaluation of specific organs, including the breast, liver, kidney, and those in the pelvis. When used in conjunction with apparent diffusion coefficient mapping, diffusion-weighted imaging provides information about the functional environment of water in tissues, thereby augmenting the morphologic information provided by conventional MR imaging. Detected changes include shifts of water from extracellular to intracellular spaces, restriction of cellular membrane permeability, increased cellular density, and disruption of cellular memb...

Adding quantitative diffusion-weighted imaging to the conventional MR imaging protocol resulted in significant diagnostic improvement. PurposeTo evaluate the incremental value of diffusion-weighted (DW) imaging and apparent diffusion coefficient (ADC) mapping in relation to conventional breast magnetic resonance (MR) imaging in th...

Introduction: The radiological reading room is undergoing a paradigm shift to a symbiosis of computer science and radiology using artificial intelligence integrated with machine and deep learning with radiomics to better define tissue characteristics. The goal is to use integrated deep learning and radiomics with radiological parameters to produce a personalized diagnosis for a patient. Areas covered: This review provides an overview of historical and current deep learning and radiomics methods in the context of precision medicine in radiology. A literature search for ‘Deep Learning’, ‘Radiomics’, ‘Machine learning’, ‘Artificial Intelligence’, ‘Convolutional Neural Network’, ‘Generative Adversarial Network’, ‘Autoencoders’, Deep Belief Networks”, Reinforcement Learning”, and ‘Multiparametric MRI’ was performed in PubMed, ArXiv, Scopus, CVPR, SPIE, IEEE Xplore, and NIPS to identify articles of interest. Expert opinion: In conclusion, both deep learning and radiomics are two rapidly advancing technologies that will unite in the future to produce a single unified framework for clinical decision support with a potential to completely revolutionize the field of precision medicine.