https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

A survey on deep learning in medical image analysis

Artificial intelligence (AI) is gradually changing medical practice. With recent progress in digitized data acquisition, machine learning and computing infrastructure, AI applications are expanding into areas that were previously thought to be only the province of human experts. In this Review Article, we outline recent breakthroughs in AI technologies and their biomedical applications, identify the challenges for further progress in medical AI systems, and summarize the economic, legal and social implications of AI in healthcare.

Artificial Intelligence in Healthcare

Tractography based on non-invasive diffusion imaging is central to the study of human brain connectivity. To date, the approach has not been systematically validated in ground truth studies. Based on a simulated human brain data set with ground truth tracts, we organized an open international tractography challenge, which resulted in 96 distinct submissions from 20 research groups. Here, we report the encouraging finding that most state-of-the-art algorithms produce tractograms containing 90% of the ground truth bundles (to at least some extent). However, the same tractograms contain many more invalid than valid bundles, and half of these invalid bundles occur systematically across research groups. Taken together, our results demonstrate and confirm fundamental ambiguities inherent in tract reconstruction based on orientation information alone, which need to be considered when interpreting tractography and connectivity results. Our approach provides a novel framework for estimating reliability of tractography and encourages innovation to address its current limitations.

/pdf/the-challenge-of-mapping-the-human-connectome-based-on-xi6eaf30xo.pdf

The challenge of mapping the human connectome based on diffusion tractography

MRI-based medical image analysis for brain tumor studies is gaining attention in recent times due to an increased need for efficient and objective evaluation of large amounts of data. While the pioneering approaches applying automated methods for the analysis of brain tumor images date back almost two decades, the current methods are becoming more mature and coming closer to routine clinical application. This review aims to provide a comprehensive overview by giving a brief introduction to brain tumors and imaging of brain tumors first. Then, we review the state of the art in segmentation, registration and modeling related to tumor-bearing brain images with a focus on gliomas. The objective in the segmentation is outlining the tumor including its sub-compartments and surrounding tissues, while the main challenge in registration and modeling is the handling of morphological changes caused by the tumor. The qualities of different approaches are discussed with a focus on methods that can be applied on standard clinical imaging protocols. Finally, a critical assessment of the current state is performed and future developments and trends are addressed, giving special attention to recent developments in radiological tumor assessment guidelines.

/pdf/a-survey-of-mri-based-medical-image-analysis-for-brain-tumor-4mtl4fktmo.pdf

A survey of MRI-based medical image analysis for brain tumor studies

Medical Image Computing and Computer-Assisted Intervention

Recursive median filtering can be applied to images at a number of scales and orientations giving a scale space description at a pixel level. The resulting scale-orientation signatures can be used to discriminate between different structures, most easily between linear and blob-like structures, but also to describe any remaining texture in the image. As a specific example, the technique is applied to mammography, in the detection of mass-like structures associated with spiculated lesions. For structures of diameter 12mm, a sensitivity of 80% is achieved with 0.25 false positives per image, which compares favourably with the best results found in the literature.

The detection of abnormal masses in mammograms

Breast cancer is a leading cause of fatality in women, with approximately 1 in 12 women affected by the disease during their lifetime1. Mass screening of women using x–ray mammography is currently the most effective method of early detection of the disease, which is essential for successful treatment2. Malignant breast lesions in x–ray mammograms are often characterised by abnormal patterns of linear structures. Architectural distortions and stellate lesions are examples of patterns frequently presenting with an appearance of radiating linear structures3. These malignancies can be extremely subtle and a significant proportion of them are undetected by radiologists. We have previously performed experiments which demonstrate that a radiologist’s performance can be improved by prompting the possible locations of abnormalities4. Attempts to detect stellate lesions automatically have generally concentrated on features of known importance, such as radiating linear structure concurrency, spread of focus and radial distance5,6,7. Recent work in our laboratory provides quantitive targets for clinically useful algorithm performance8. Most published techniques provide useful insight into the problem but fall well below the level of prompting accuracy that leads to an improvement in radiologists’ performance. This implies that existing methods are failing to fully exploit the available image evidence. We present an alternative approach that has a compact statistical representation of pattern structure, based on factor analysis, which completely encapsulates all patterns yet remains uncommitted to specific types of pattern. We present the results of an experiment in which the technique was applied to a set of 129 mammograms. We demonstrate how this generic technique can be used to detect abnormalities successfully with an accuracy of 0.23 false positives per image at a sensitivity of 80% for lesions with an effective diameter of 12mm. For lesions 16mm 0.06 false positives per image are obtained with the same sensitivity. These results compare favorably with existing methods, without the need for noise equalisation or any form of mammogram normalisation.

J A Noble

Papers

Medical Image Computing and Computer-Assisted Intervention

The detection of abnormal masses in mammograms

The detection of stellate lesions in digital mammography

Anatomical classification of linear structures in mammograms