Evaluation of an artificial intelligence system for diagnosing scaphoid fracture on direct radiography.

PURPOSE: The aim of this study is to determine the diagnostic performance of artificial intelligence with the use of convolutional neural networks (CNN) for detecting scaphoid fractures on anteroposterior wrist radiographs. The performance of the deep learning algorithm was also compared with that of the emergency department (ED) physician and two orthopaedic specialists (less experienced and experienced in the hand surgery). METHODS: A total 390 patients with AP wrist radiographs were included in the study. The presence/absence of the fracture on radiographs was confirmed via CT. The diagnostic performance of the CNN, ED physician and two orthopaedic specialists (less experienced and experienced) as measured by AUC, sensitivity, specificity, F-Score and Youden index, to detect scaphoid fractures was evaluated and compared between the groups. RESULTS: The CNN had 76% sensitivity and 92% specificity, 0.840 AUC, 0.680 Youden index and 0.826 F score values in identifying scaphoid fractures. The experienced orthopaedic specialist had the best diagnostic performance according to AUC. While CNN's performance was similar to a less experienced orthopaedic specialist, it was better than the ED physician. CONCLUSION: The deep learning algorithm has the potential to be used for diagnosing scaphoid fractures on radiographs. Artificial intelligence can be useful for scaphoid fracture diagnosis particularly in the absence of an experienced orthopedist or hand surgeon.

Pro-metastatic functions of Notch signaling is mediated by CYR61 in breast cells.

Metastasis is the main cause of cancer related deaths, and unfolding the molecular mechanisms underlying metastatic progression is critical for the development of novel therapeutic approaches. Notch is one of the key signaling pathways involved in breast tumorigenesis and metastasis. Notch activation induces pro-metastatic processes such as migration, invasion and epithelial to mesenchymal transition (EMT). However, molecular mediators working downstream of Notch in these processes are not fully elucidated. CYR61 is a secreted protein implicated in metastasis, and its inhibition by a monoclonal antibody suppresses metastasis in xenograft breast tumors, indicating the clinical importance of CYR61 targeting. Here, we aimed to investigate whether CYR61 works downstream of Notch in inducing pro-metastatic phenotypes in breast cells. We showed that CYR61 expression is positively regulated by Notch activity in breast cells. Notch1-induced migration, invasion and anchorage independent growth of a normal breast cell line, MCF10A, were abrogated by CYR61 silencing. Furthermore, upregulation of core EMT markers upon Notch1-activation was impaired in the absence of CYR61. However, reduced migration and invasion of highly metastatic cell line, MDA MB 231, cells upon Notch inhibition was not dependent on CYR61 downregulation. In conclusion, we showed that in normal breast cell line MCF10A, CYR61 is a mediator of Notch1-induced pro-metastatic phenotypes partly via induction of EMT. Our results imply CYR61 as a prominent therapeutic candidate for a subpopulation of breast tumors with high Notch activity.

Introduction to machine learning.

The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.

BRIEF: Computing a Local Binary Descriptor Very Fast.

Binary descriptors are becoming increasingly popular as a means to compare feature points very fast while requiring comparatively small amounts of memory. The typical approach to creating them is to first compute floating-point ones, using an algorithm such as SIFT, and then to binarize them. In this paper, we show that we can directly compute a binary descriptor, which we call BRIEF, on the basis of simple intensity difference tests. As a result, BRIEF is very fast both to build and to match. We compare it against SURF and SIFT on standard benchmarks and show that it yields comparable recognition accuracy, while running in an almost vanishing fraction of the time required by either.

Fast keypoint recognition using random ferns.

While feature point recognition is a key component of modern approaches to object detection, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. In this paper, we show that formulating the problem in a naive Bayesian classification framework makes such preprocessing unnecessary and produces an algorithm that is simple, efficient, and robust. Furthermore, it scales well as the number of classes grows. To recognize the patches surrounding keypoints, our classifier uses hundreds of simple binary features and models class posterior probabilities. We make the problem computationally tractable by assuming independence between arbitrary sets of features. Even though this is not strictly true, we demonstrate that our classifier nevertheless performs remarkably well on image data sets containing very significant perspective changes.