Search

Background. An artificial neural network (ANN) was developed to predict breast cancer from mammographic findings. This network was evaluated in a retrospective study. Methods. For a set of patients who were scheduled for biopsy, radiologists interpreted the mammograms and provided data on eight mammographic findings as part of the standard mammographic workup. These findings were encoded as features for an ANN. Results of biopsies were taken as truth in the diagnosis of malignancy. The ANN was trained and evaluated using a jackknife sampling on a set of 260 patient records. Performance of the network was evaluated in terms of sensitivity and specificity over a range of decision thresholds and was expressed as a receiver operating characteristic curve. Results. The ANN performed more accurately than the radiologists (P< 0.08) with a relative sensitivity of 1.0 and specificity of 0.59. Conclusions. An ANN can be trained to predict malignancy from mammographic findings with a high degree of accuracy. Cancer 1994; 74:2944-8.

Neutron stimulated emission computed tomography (NSECT) is presented as a new technique for in vivo tomographic spectroscopic imaging. A full implementation of NSECT is intended to provide an elemental spectrum of the body or part of the body being interrogated at each voxel of a three-dimensional computed tomographic image. An external neutron beam illuminates the sample and some of these neutrons scatter inelastically, producing characteristic gamma emission from the scattering nuclei. These characteristic gamma rays are acquired by a gamma spectrometer and the emitting nucleus is identified by the emitted gamma energy. The neutron beam is scanned over the body in a geometry that allows for tomographic reconstruction. Tomographic images of each element in the spectrum can be reconstructed to represent the spatial distribution of elements within the sample. Here we offer proof of concept for the NSECT method, present the first single projection spectra acquired from multi-element phantoms, and discuss potential biomedical applications.

Architectural distortion (AD) is a sign of malignancy often missed during mammographic interpretation. The purpose of this study was to explore the application of fractal analysis to the investigation of AD in screening mammograms. The study was performed using mammograms from the Digital Database for Screening Mammography (DDSM). The fractal dimension (FD) of mammographic regions of interest (ROIs) was calculated using the circular average power spectrum technique. Initially, the variability of the FD estimates depending on ROI location, mammographic view and breast side was studied on normal mammograms. Then, the estimated FD was evaluated using receiver operating characteristics (ROC) analysis to determine if it can discriminate ROIs depicting AD from those depicting normal breast parenchyma. The effect of several factors such as ROI size, image subsampling and breast density was studied in detail. Overall, the average FD of the normal ROIs was statistically significantly higher than that of the ROIs with AD. This result was consistent across all factors studied. For the studied set of implementation parameters, the best ROC performance achieved was 0.89 0.02. The generalizability of these conclusions across different digitizers was also demonstrated.

The authors improved the nonivasive diagnosis of acute pulmonary embolism (PE) by studying the clinical and chest radiographic findings of patients suspected of having PE and correlating those findings with the physicians' clinical impression.

RATIONALE AND OBJECTIVES. An artificial neural network (ANN) has been developed to detect nonactive circular lesions on single-slice, single-photon emission computed tomographic (SPECT) images reconstructed using filtered back projection (FBP).

The authors presented a new posterior beam-stop (PBS) technique for measuring the ratio of scattered to total-detected photon flux (scatter fraction) in a radiographic examination while preserving the diagnostic quality of the image. The scatter measurement was made using a standard imaging geometry with both beam stops and an additional x-ray detector placed behind the standard imaging detector. This PBS geometry differs from the standard beam-stop (SBS) technique for scatter measurement. With SBS, a beam-stop shadow appears on the image. To evaluate the PBS technique, scatter fraction measurements were performed on an anatomic phantom using both the PBS and SBS techniques. When compared with the standard technique, PBS provided accurate estimation of scatter fractions. Since the measurement can be performed without degrading a standard clinical radiographic examination, the PBS technique allows simultaneous acquisition of scatter measurements from human patients in combination with a standard radiographic examination.

Purpose. To study the effect of data sampling on the predictive assessment of artificial neural networks (ANNs) for medical diagnostic tasks. Methods.Three statistical techniques were used to evaluate the diagnostic performances of ANNs: 1) cross validation, 2) round robin, and 3) bootstrap. These techniques are different sampling plans designed to reduce the small-sample estimation bias and variance contributions. The study was based on two networks, one developed for the diagnosis of pulmonary embolism (1,064 cases) and the other developed for the diagnosis of breast cancer (206 cases). Results.The three sampling techniques produced different performance estimates for both networks. The estimates varied substantially depending on the training sample size and the training-stopping criterion. Conclusion.The predictive assessment of ANNs in medical diagnosis can vary substantially based on the complexity of the problem, the data sampling technique, and the number of cases available. Key words:computer-aided diagnosis; artificial neural networks; sampling; cross validation; round robin; bootstrap; receiver operating characteristic analysis. (Med Decis Making 1997;17:186-192)

he authors compared standard digital portable chest radiographs (DPCXR) to scatter-subtracted DPCXR.

An artificial neural network was developed for cold lesion detection and localization in single photon emission computed tomography (SPECT) images.

An iterative maximum likelihood expectation maximization algorithm (MLEM) has been developed for scatter compensation in chest radiography.

The authors present a numerical deconvolution technique to compensate for image degrading effects caused by scattered photons in radiographic chest images. Fourier transform techniques are used to deconvolve a shift invariant model of the two dimensional point spread response functions of the scattered radiation. This approach uses a digitized radiograph acquired with a standard chest imaging protocol, so no specialized imaging equipment is required. While the shift variant shape of the scatter model is optimized for the lung field, effective compensation is provided when this model shape is applied to other chest regions. Preliminary evaluation suggests that this technique can provide improved image contrast over the entire chest region.

The scatter-reduction properties of a new infinity-focused grid incorporated into a radiographic imaging cassette were analyzed.

Floyd Jr CE, Baydush AH, Lo JY, Bowsher JE, Ravin CE. Bayesian restoration of chest radiographs scatter compensation with improved signal–to–noise ratio.

Chotas HG, Dobbins JT III, Floyd CE Jr, Ravin CE. Single-exposure conventional and computed radiography image acquisition. Invest Radiol 1991;26438–445.