Search

A loss function has two crucial roles in training a conventional discriminant deep neural network (DNN): (i) it measures the goodness of classification and (ii) generates the gradients that drive the training of the network. In this paper, we approximate the gradients of cross-entropy loss which is the most often used loss function in the classification DNNs. The proposed approximations are noise-free, which means they depend only on the labels of the training set. They have a fixed length to avoid the vanishing gradient problem of the cross-entropy loss. By skipping the forward pass, the computational complexities of the proposed approximations are reduced to O(n) where n is the batch size. Two claims are established based on the experiments of training DNNs using the proposed approximations: (i) It is possible to train a discriminant network without explicitly defining a loss function. (ii) The success of training does not imply the convergence of network parameters to fixed values. The experiments show that the proposed gradient approximations achieve comparable classification accuracy to the conventional loss functions and can accelerate the training process on multiple datasets.

An automated method for ?-emission spectrum calibration and deconvolution is presented for spaceflight applications for a Cerium doped Lanthanum Chloride, (LaCl3(Ce)) ?-ray detector system. This detector will be coupled with a pulsed neutron generator (PNG) to induce and enhance nuclide signal quality and rates, yielding large volumes of spectral information. Automated analytical methods are required to deconvolve and quantify nuclide signals from spectra; this will both reduce human interactions in spectrum analysis and facilitate feedback to automated robotic and operations planning. Initial system tests indicate significant energy calibration drifts (>6%), that which must be mitigated for spectrum analysis. A linear energy calibration model is presently considered, with gain and zero factors. Deconvolution methods incorporate a tabu search heuristic to formulate and optimize searches using memory structures. Iterative use of a peak likelihood methodology identifies global calibration minima and peak areas. The method is compared to manual methods of calibration and indicates superior performance using tabu methods. Performance of the Tabu enhanced calibration method is superior to similar unoptimized local search. The techniques are also applicable to other emission spectroscopy, eg. X-ray and neutron.

Texture analysis for tissue characterization is a current area of optical coherence tomography (OCT) research. We discuss some of the differences between OCT systems and the effects those differences have on the resulting images and subsequent image analysis. In addition, as an example, two algorithms for the automatic recognition of bladder cancer are compared: one that was developed on a single system with no consideration for system differences, and one that was developed to address the issues associated with system differences. The first algorithm had a sensitivity of 73 and specificity of 69 when tested using leave-one-out cross-validation on data taken from a single system. When tested on images from another system with a different central wavelength, however, the method classified all images as cancerous regardless of the true pathology. By contrast, with the use of wavelet analysis and the removal of system-dependent features, the second algorithm reported sensitivity and specificity values of 87 and 58, respectively, when trained on images taken with one imaging system and tested on images taken with another. [ABSTRACT FROM AUTHOR]

The vast majority of bladder cancers originate within 600 μm of the tissue surface, making optical coherence tomography (OCT) a potentially powerful tool for recognizing cancers that are not easily visible with current techniques. OCT is a new technology, however, and surgeons are not familiar with the resulting images. Technology able to analyze and provide diagnoses based on OCT images would improve the clinical utility of OCT systems. We present an automated algorithm that uses texture analysis to detect bladder cancer from OCT images. Our algorithm was applied to 182 OCT images of bladder tissue, taken from 68 distinct areas and 21 patients, to classify the images as noncancerous, dysplasia, carcinoma in situ (CIS), or papillary lesions, and to determine tumor invasion. The results, when compared with the corresponding pathology, indicate that the algorithm is effective at differentiating cancerous from noncancerous tissue with a sensitivity of 92% and a specificity of 62%. With further research to improve discrimination between cancer types and recognition of false positives, it may be possible to use OCT to guide endoscopic biopsies toward tissue likely to contain cancer and to avoid unnecessary biopsies of normal tissue. [ABSTRACT FROM AUTHOR]