Charles A. Harlow

Towards computer analysis of pulmonary infiltration.

A feasibility study is described to provide quantitative texture measures to distinguish between normal lung, alveolar infiltrates and interstitial infiltrates. Advanced computer imaging technology and decision making processes were applied to distinguish between these textural patterns. The results, based on computer extracted quantitative measures, show an excellent separation of the three classes considered with 95% accuracy in the training phase and 90% accuracy in the testing phase.

Automated Inspection of Electronic Assemblies

Significant technological advances in the design and production of electronic assemblies have sizably increased their reliability and durability while greatly reducing their physical size. New manufacturing technologies have been developed which markedly increase the speed and accuracy of production. Such advances in production greatly complicate the inspection of these devices by humans. Essentially, the techniques used 10 years ago are still used for inspection in production lines. Much of the inspection is done by humans whose performance–not surprisingly–is generally inadequate and variable. The human visual system is adapted to perform in a world of variety and change; the inspection process, on the other hand, requires observing the same type of image repeatedly to detect anomalies. This requirement can often be met successfully by automation.

Image analysis and graphs

Some problems in the construction of image analysis programs are discussed. A systein is proposed which utilizes a graph to model the program control and the scene. The system is applied to chest X-rays and printed circuit hoards. A method for using heuristic programming in edge detection is discussed and applied to chest x-rays.

Automatic Visual Inspection Of Printed Circuit Boards

A description of research work on the automatic visual inspection of printed circuit boards is presented as an example of a practical industrial automation problem. The major goal of this research is to develop a programmable visual inspection system applicable to printed circuit boards and other electronic assemblies. Described methods are the dimensional verification technique and the pattern matching technique. In dimensional verification, the inspection is accomplished by verifying the dimensional accuracy of certain features of the board. In pattern matching, standard features of the board are extracted interactively. The inspection is accomplished by matching these standard features with patterns of the unit under test.

Computer analysis of chest radiographs

A method is described for the automatic recognition of congenital heart abnormalities via digitized images of posteroanterior (PA) view chest radiographs. a closed curve representing the hearts outline is determined by computer; measurements on the outline are extracted via the Fourier descriptor technique; and these measurements are used for normal-abnormal grouping via a modified maximum likelihood classification algorithm. The system has been implemented on a dec pdp-11/20 and is capable of performing real-time diagnoses at the rate of about two minutes per radiograph.

COMPUTER ALGORITHMS FOR THE DETECTION OF BRAIN SCINTIGRAM ABNORMALITIES.

Abstract Algorithms for computer analysis of digitized brain scintigrams are described. A technique of variable thresholding and region enumeration is used to detect abnormalities which project clear of the calvarium, while a metric comparison detects distortions of the brain outline. The methods have been employed to process scintigrams digitized by means of an image dissector camera operating under control of an SEL-840A computer. It is felt that the algorithms will be equally applicable to brain scintigrams digitized by other means and that they may prove adaptable to the analysis of other organ system images.

Computer diagnosis of radiographic images

The potential of optical scanning equipment and digital computers for assisting or replacing human judgment in medical diagnosis has been recognized by investigators for some time. A number of efforts have been made, with varying degrees of success, in developing automatic techniques for recognizing and classifying blood cells, chromosome analysis and karyotyping, identifying leucocytes, and processing scintigram images obtained in nuclear medicine. These image analysis techniques are now being extended to the clinical specialty of diagnostic radiology where there is an urgent need to provide assistance in handling the several million radiographs read by radiologists each year. The need for computer-aided diagnosis in radiology is becoming increasingly urgent because of the expanding population and the continuing demand for improved quality of medical care. The use of computers in radiology can free the diagnostic radiologist from routine tasks while providing more accurate measurements that lead to consistent and reliable diagnoses.

Toward a Structural Textural Analyzer Based on Statistical Methods

This paper reports investigations aimed at developing a feature set for the Spatial Gray Level Dependence Method (SGLDM) which measures visually perceivable qualities of textures. In particular it will be shown that the inertia measure commonly used with the SGLDM can be used to characterize the placement rules and the unit pattern of periodic textures. In this way one may formulate a structural approach to texture analysis based on the statistical SGLDM. To mathematically verify that the features used with the SGLDM can be used to characterize the unit pattern and placement rules of a periodic texture, a mathematical tiling theory model is proposed. This model allows one to develop the mathematical machinery necessary to prove the result. In a companion paper other features which measure visually perceivable qualities of patterns will be developed. The reason for concentrating on the SGLDM for developing such a feature set is predicated on perceptual psychology experiments and comparison studies of various texture algorithms. All of these studies indicate that second-order probabilities of the type measured by the spatial gray level dependence matrices are important in human texture discrimination and that these matrices contain more important texture-context information than the intermediate matrices of other statistical texture analysis algorithms.

The computer analysis of chest radiographs

This paper describes a program for automatically extracting lung and heart features in the digitized image of posteroanterior (PA) view chest radiographs. A graph-directed analysis is used to guide the search for objects from the largest to the smallest in the radiograph. Global information is used to guide the analysis of the program. Consequently, only the points in a small range are searched and tested against local criteria to detect boundary points. The entire lung boundary is broken into four segments: upper inside boundary, lower inside boundary, boundary along the diaphragm and outside boundary. Slightly different global-local criteria for detecting the edge points along each segment have been developed and tested on 423 PA chest radiographs of patients of all ages. The results obtained indicate the program can locate the accurate boundary on all cases except infants. Twenty-seven measurements which describe the shape and size of the heart are extracted; these measurements are used for normal abnormal classification via a modified maximum likelihood classification algorithm.

Feedback in Sequential Machine Realizations

In this paper we study feedback in sequential machines that are implemented with trigger or set-reset flip-flop memory elements. A method is given for determining when a machine can be implemented with either trigger or set-reset flip-flop memory elements where the feedback in the machine is given by a Boolean function f. Several results are presented that compare the feedback when a machine is implemented with different memory elements. It is shown that if a sequential machine can be implemented with unit delay memory elements with feedback function f, then it can be realized with set-reset flip-flop with the same feedback function f. For completely specified machines, it is shown that if a machine implemented with trigger flip-flop has no feedback, then the some machine implemented with unit delays will have feedback. Conversely, if an implementation with unit delays has no feedback, then an implementation with trigger flip-flops will have feedback.