Search

Pancreatic ductal adenocarcinoma (PDAC) is the third most common cause of cancer death in the United States. Predicting tumors like PDACs (including both classification and segmentation) from medical images by deep learning is becoming a growing trend, but usually a large number of annotated data are required for training, which is very labor-intensive and time-consuming. In this paper, we consider a partially supervised setting, where cheap image-level annotations are provided for all the training data, and the costly per-voxel annotations are only available for a subset of them. We propose an Inductive Attention Guidance Network (IAG-Net) to jointly learn a global image-level classifier for normal/PDAC classification and a local voxel-level classifier for semi-supervised PDAC segmentation. We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier. Experimental results show that our IAG-Net boosts PDAC segmentation accuracy by more than 5% compared with the state-of-the-arts. [ABSTRACT FROM AUTHOR]

In this paper, we propose bag of adversarial features (BAFs) for identifying mild traumatic brain injury (MTBI) patients from their diffusion magnetic resonance images (MRIs) (obtained within one month of injury) by incorporating unsupervised feature learning techniques. MTBI is a growing public health problem with an estimated incidence of over 1.7 million people annually in USA. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. Unlike most of the previous works, which use hand-crafted features extracted from different parts of brain for MTBI classification, we employ feature learning algorithms to learn more discriminative representation for this task. A major challenge in this field thus far is the relatively small number of subjects available for training. This makes it difficult to use an end-to-end convolutional neural network to directly classify a subject from MRIs. To overcome this challenge, we first apply an adversarial auto-encoder (with convolutional structure) to learn patch-level features, from overlapping image patches extracted from different brain regions. We then aggregate these features through a bag-of-words approach. We perform an extensive experimental study on a dataset of 227 subjects (including 109 MTBI patients, and 118 age and sex-matched healthy controls) and compare the bag-of-deep-features with several previous approaches. Our experimental results show that the BAF significantly outperforms earlier works relying on the mean values of MR metrics in selected brain regions. [ABSTRACT FROM AUTHOR]

This paper proposes a practical and effective model for the generation forecasting of a wind farm with an emphasis on its scheduling and trading in a wholesale electricity market. A novel forecasting model is developed based on indepth investigations of meteorological information. This model adopts a two-stage hybrid network with Bayesian clustering by dynamics and support vector regression. The proposed structure is robust with different input data types and can deal with the nonstationarity of wind speed and generation series well. Once the network is trained, we can straightforward predict the 48-h ahead wind power generation. To demonstrate the effectiveness, the model is applied and tested on a 74-MW wind farm located in the southwest Oklahoma of the United States. [ABSTRACT FROM AUTHOR]

Prostatic adenocarcinoma is the most commonly occurring cancer among men in the United States, second only to skin cancer. Currently, the only definitive method to ascertain the presence of prostatic cancer is by trans-rectal ultrasound (TRUS) directed biopsy. Owing to the poor image quality of ultrasound, the accuracy of TRUS is only 20%-25%. High-resolution magnetic resonance imaging (MRI) has been shown to have a higher accuracy of prostate cancer detection compared to ultrasound. Consequently, several researchers have been exploring the use of high resolution MRI in performing prostate biopsies. Visual detection of prostate cancer, however, continues to be difficult owing to its apparent lack of shape, and the fact that several malignant and benign structures have overlapping intensity and texture characteristics. In this paper, we present a fully automated computer-aided detection (CAD) system for detecting prostatic adenocarcinoma from 4 Tesla ex vivo magnetic resonance (MR) imagery of the prostate. After the acquired MR images have been corrected for background inhomogeneity and nonstandardness, novel three-dimensional (3-D) texture features are extracted from the 3-D MRI scene. A Bayesian classifier then assigns each image voxel a "likelihood" of malignancy for each feature independently. The "likelihood" images generated in this fashion are then combined using an optimally weighted feature combination scheme. Quantitative evaluation was performed by comparing the CAD results with the manually ascertained ground truth for the tumor on the MRI. The tumor labels on the MR slices were determined manually by an expert by visually registering the MR slices with the corresponding regions on the histology slices. We evaluated our CAD system on a total of 33 two-dimensional (2-D) MR slices from five different 3-D MR prostate studies. Five slices from two different glands were used for training. Our feature combination scheme was found to outperform the individual texture features, and also other popularly used feature combination methods, including AdaBoost, ensemble averaging, and majority voting. Further, in several instances our CAD system performed better than the experts in terms of accuracy, the expert segmentations being determined solely from visual inspection of the MRI data. In addition, the intrasystem variability (changes in CAD accuracy with changes in values of system parameters) was significantly lower than the corresponding intraobserver and interobserver variability. CAD performance was found to be very similar for different training sets. Future work will focus on extending the methodology to guide high-resolution MRI-assisted in vivo prostate biopsies. [ABSTRACT FROM AUTHOR]

Opioid misuse and overdose have become a public health hazard and caused drug addiction and death in the United States due to rapid increase in prescribed and non-prescribed opioid usage. The misuse and overdose are highly related to opioid over-prescription for chronic and acute pain treatment, where a one-size-fits-all prescription plan is often adopted but can lead to substantial leftovers for patients who only consume a few. To reduce over-prescription and opioid overdose, each patient's opioid usage pattern should be taken into account. As opioids are often prescribed for patients after total joint replacement surgeries, this study introduces a machine learning model to predict each patient's opioid usage level in the first 2 weeks after discharge. Specifically, the electronic health records, patient prescription history, and consumption survey data are collected to investigate the level of short-term opioid usage after joint replacement surgeries. However, there are a considerable number of answers missing in the surveys, which degrades data quality. To overcome this difficulty, a semi-supervised learning model that assigns pseudo labels via Bayesian regression is proposed. Using this model, the missing survey answers of opioids amount taken by the patients are predicted first. Then, based on the prediction, pseudo labels are assigned to those patients to improve classification performance. Extensive experiments indicate that such a semi-supervised learning model has shown a better performance in the resulting patients classification. It is expected that by using such a model the providers can adjust the amount of prescribed opioids to meet each patient's actual need, which can benefit the management of opioid prescription and pain intervention. [ABSTRACT FROM AUTHOR]

Edward Feigenbaum, the recipient of the 2013 Pioneer Award, is one of the founders of the field of artificial intelligence and has been one of its leaders for more than 50 years. He became aware of the birth of AI when he was an undergraduate at Carnegie Tech (later, Carnegie Mellon University). Continuing to graduate school there, he was mentored by Herbert Simon, and he also collaborated with Allen Newell. His career has taken him from Carnegie to the University of California, Berkeley, Stanford University, RAND, and the Pentagon. Feigenbaum has also authored and coedited several seminal AI books: Computers and Thought (1963), The Fifth Generation (1983), and the four-volume Handbook of Artificial Intelligence (1980s). In this interview, David Alan Grier and Feigenbaum talk about his career, his mentor Herbert Simon, and the development of AI. [ABSTRACT FROM PUBLISHER]

The article focuses on the Crusher autonomous system designed to allow robots to navigate through unstructured terrain. It states that getting a robot to move from point A to B on a non-flat environment with many obstacles is a challenge, resulting in many advances. One such was developed by the U.S. Defense Advanced Research Projects Agency (DARPA), which created the UGCV-Perceptor Integration (UPI) program. The development of UPI as a guidance system for Crusher is discussed in detail.

Application of remote sensing data to extrapolate evapotranspiration (ET) measured at eddy covariance flux towers is a potentially powerful method to estimate continental-scale ET. In support of this concept, we used meteorological and flux data from the AmeriFlux network and an inductive machine learning technique called support vector machine (SVM) to develop a predictive ET model. The model was then applied to the conterminous U.S. In this process, we first trained the SVM to predict 2000-2002 ET measurements from 25 AmeriFlux sites using three remotely sensed variables [land surface temperature, enhanced vegetation index (EVI), and land cover] and one ground-measured variable (surface shortwave radiation). Second, we evaluated the model performance by predicting ET for 19 flux sites in 2003. In this independent evaluation, the SVM predicted ET with a root-mean-square error (rmse) of 0.62 mm/day (approximately 23% of the mean observed values) and an R2 of 0.75. The rmse from SVM was significantly smaller than that from neural network and multiple-regression approaches in a cross-validation experiment. Among the explanatory variables, EVI was the most important factor. Indeed, removing this variable induced an rmse increase from 0.54 to 0.77 mm/day. Third, with forcings from remote sensing data alone, we used the SVM model to predict the spatial and temporal distributions of ET for the conterminous U.S. for 2004. The SVM model captured the spatial and temporal variations of ET at a continental scale. [ABSTRACT FROM AUTHOR]

The U.S. wholesale power market comprises a large commodity market. The growth in power trading is due to the ongoing deregulation policy of the electric power industry. Most deregulation scenarios indicate a further separation of power production from transmission and retailing. The power production is opened to more competition. Unfortunately, the power trading mechanism is not clearly investigated in the level that we can predict a price change in the U.S. wholesale power market. Such a price change in the U.S. wholesale power market is explored from a simulation system with learning capabilities. Using the new intelligence system, we investigate the bidding strategies of traders in the wholesale power market and examine how the price change occurs under different economic and engineering environments. [ABSTRACT FROM AUTHOR]