Bharath R. Modayur

Motivation and Organizational Principles for Anatomical Knowledge Representation: The Digital Anatomist Symbolic Knowledge Base

OBJECTIVE Conceptualization of the physical objects and spaces that constitute the human body at the macroscopic level of organization, specified as a machine-parseable ontology that, in its human-readable form, is comprehensible to both expert and novice users of anatomical information. DESIGN Conceived as an anatomical enhancement of the UMLS Semantic Network and Metathesaurus, the anatomical ontology was formulated by specifying defining attributes and differentia for classes and subclasses of physical anatomical entities based on their partitive and spatial relationships. The validity of the classification was assessed by instantiating the ontology for the thorax. Several transitive relationships were used for symbolically modeling aspects of the physical organization of the thorax. RESULTS By declaring Organ as the macroscopic organizational unit of the body, and defining the entities that constitute organs and higher level entities constituted by organs, all anatomical entities could be assigned to one of three top level classes (Anatomical structure, Anatomical spatial entity and Body substance). The ontology accommodates both the systemic and regional (topographical) views of anatomy, as well as diverse clinical naming conventions of anatomical entities. CONCLUSIONS The ontology formulated for the thorax is extendible to microscopic and cellular levels, as well as to other body parts, in that its classes subsume essentially all anatomical entities that constitute the body. Explicit definitions of these entities and their relationships provide the first requirement for standards in anatomical concept representation. Conceived from an anatomical viewpoint, the ontology can be generalized and mapped to other biomedical domains and problem solving tasks that require anatomical knowledge.

Visualization-Based Mapping of Language Function in the Brain

Cortical language maps, obtained through intraoperative electrical stimulation studies, provide a rich source of information for research on language organization. Previous studies have shown interesting correlations between the distribution of essential language sites and such behavioral indicators as verbal IQ and have provided suggestive evidence for regarding human language cortex as an organization of multiple distributed systems. Noninvasive studies using ECoG, PET, and functional MR lend support to this model; however, there as yet are no studies that integrate these two forms of information. In this paper we describe a method for mapping the stimulation data onto a 3-D MRI-based neuroanatomic model of the individual patient. The mapping is done by comparing an intraoperative photograph of the exposed cortical surface with a computer-based MR visualization of the surface, interactively indicating corresponding stimulation sites, and recording 3-D MR machine coordinates of the indicated sites. Repeatability studies were performed to validate the accuracy of the mapping technique. Six observers-a neurosurgeon, a radiologist, and four computer scientists, independently mapped 218 stimulation sites from 12 patients. The mean distance of a mapping from the mean location of each site was 2.07 mm, with a standard deviation of 1.5 mm, or within 5.07 mm with 95% confidence. Since the surgical sites are accurate within approximately 1 cm, these results show that the visualization-based approach is accurate within the limits of the stimulation maps. When incorporated within the kind of information system envisioned by the Human Brain Project, this anatomically based method will not only provide a key link between noninvasive and invasive approaches to understanding language organization, but will also provide the basis for studying the relationship between language function and anatomical variability.

MUSER: A prototype musical score recognition system using mathematical morphology

Music representation utilizes a fairly rich repertoire of symbols. These symbols appear on a score sheet with relatively little shape distortion, differing from the prototype symbol shapes mainly by a positional translation and scale change. The prototype system we describe in this article is aimed at recognizing printed music notation from digitized music score images. The recognition system is composed of two parts: a low-level vision module that uses morphological algorithms for symbol detection and a high-level module that utilizes prior knowledge of music notation to reason about spatial positions and spatial sequences of these symbols. The high-level module also employs verification procedures to check the veracity of the output of the morphological symbol recognizer. The system produces an ASCII representation of music scores that can be input to a music-editing system. Mathematical morphology provides us the theory and the tools to analyze shapes. This characteristic of mathematical morphology lends itself well to analyzing and subsequently recognizing music scores that are rich in well-defined musical symbols. Since morphological operations can be efficiently implemented in machine vision systems that have special hardware support, the recognition task can be performed in near real-time. The system achieves accuracy in excess of 95% on the sample scores processed so far with a peak accuracy of 99.7% for the quarter and eighth notes, demonstrating the efficacy of morphological techniques for shape extraction.

Visual inspection of machined parts

A CAD-model-based machine vision system for dimensional inspection of machine parts is described, with emphasis on the theory behind the system. The original contributions of this work are: (1) the use of precise definitions of geometric tolerances suitable for use in image processing, (2) the development of measurement algorithms corresponding directly to these definitions, (3) the derivation of the uncertainties in the measurement tasks, and (4) the use of this uncertainty information in the decision-making process. Initial experimental results have verified the uncertainty derivations statistically and proved that the error probabilities obtained by propagating uncertainties are lower than those obtainable without uncertainty propagation. >

PERFORM: a fast object recognition method using intersection of projection

This paper describes an object recognition methodology called PERFORM that finds matches by establishing correspondences between model and image features using this formulation. PERFORM evaluates correspondences by intersecting error regions in the image space. The algorithm is analyzed with respect to theoretical complexity as well as actual running times. When a single solution to the matching problem is sought, the time complexity of the sequential matching algorithm for 2D-2D matching using point features is of the order O(l/sup 3/ N/sup 2/), where N is the number of model features and l is the number of image features. When line features are used, the sequential complexity is of the order O(l/sup 2/ N/sup 2/). When a single solution is sought, PERFORM runs faster than the fastest known algorithm to solve the bounded-error matching problem. The PERFORM method is shown to be easily realizable on both SIMD and MIMD architectures.

Fast parallel object recognition

The problem of model-based object recognition is one of identifying occurrences of objects known a priori in an image. Not all the existing algorithms lend themselves well to parallel implementations. In this paper, we describe a new formulation of the recognition problem that is amenable to a naturally parallel solution. The method that we describe solves the bounded error recognition problem accurately by incorporating an explicit noise model. The time complexity of the sequential matching algorithm using point features is of the order O(I/sup 2/NI), where N is the number of model features and I is the number of image features. The corresponding parallel algorithm using O(I/sup 2/) processors has O(NI) complexity. When line features are used, the sequential complexity is of the order O(I/sup 2/N) and the parallel algorithm, utilizing O(I) processors has O(NI) complexity. Results are presented for a sequential version running on a Sun as well as a parallel version running on a 1024-processor MasPar MP-1.

Automated inspection of machine parts

Describes a CAD-model-based machine vision system for dimensional inspection of machined parts, with emphasis on the theory behind the system. The original contributions of the work are: the use of precise definitions of geometric tolerances suitable for use in image processing, the development of measurement algorithms corresponding directly to these definitions; the derivation of the uncertainties in the measurement tasks; and the use of this uncertainty information in the decision-making process. Experimental results have verified the uncertainty derivations statistically and proved that the error probabilities obtained by propagating uncertainties are lower than those obtainable without uncertainty propagation.<<ETX>>

A Cad-based System For Automated Inspection Of Machined Parts

Although many special purpose inspection systems have been developed, general purpose systems utalizing CAD models of the parts are still in the research stage. While it is easy to define ad hoc algorithms for inspection, it is much more diflcult to justify the algorithms with solid theory. In this paper we describe a CAD-model-based machine vision system for dimensional inspection of machined parts, with emphasis on the theory behind the system, The original contributions of our work are: 1) the use of precise definitions of geometric tolerances suitable for use in image processing, 2) the development of measurement algorithms corresponding directly to these definitions, 3) the derivation of the uncertainties in the measurement tasks, and 4) the use of this uncertainty information in the decision-making process. Our experimental results have verified the uncertainty derivations statistically, proved that the error probabilities obtained by propagating uncertainties are lower than those obtaanable without uncertainty propagation, and demonstrated that the inspection system responds in a predictable manner when applied to deformed objects.

3D matching using statistically significant groupings

Vision programming is defined as the task of constructing explicit object models to be used in object recognition. These object models specify the features to be used in recognizing the object as well as the exact order in which they have to be used. In this article, we describe a vision programming approach to matching 3D models to 2D images. Our system considers feature clusters instead of individual features and dynamically orders unmatched feature clusters based on the existing state of the match. The dynamic feature cluster ordering is achieved through the use of a new dynamic cost function. The automatic vision programming framework is general enough to be used by any feature-based recognition system, and in this article, it is shown to lead to dramatic improvements in the performance of a correspondence-based object recognition system.