Biomedical subjects

Bruce E Hirsch

Publications and source records attributed to Bruce E Hirsch.

3 recordsLinked to original sources

PubMed2006

A framework for evaluating image segmentation algorithms.

The purpose of this paper is to describe a framework for evaluating image segmentation algorithms. Image segmentation consists of object recognition and delineation. For evaluating segmentation methods, three factors-precision (reliability), accuracy (validity), and efficiency (viability)-need to be considered for both recognition and delineation. To assess precision, we need to choose a figure of merit, repeat segmentation considering all sources of variation, and determine variations in figure of merit via statistical analysis. It is impossible usually to establish true segmentation. Hence, to assess accuracy, we need to choose a surrogate of true segmentation and proceed as for precision. In determining accuracy, it may be important to consider different 'landmark' areas of the structure to be segmented depending on the application. To assess efficiency, both the computational and the user time required for algorithm training and for algorithm execution should be measured and analyzed. Precision, accuracy, and efficiency factors have an influence on one another. It is difficult to improve one factor without affecting others. Segmentation methods must be compared based on all three factors, as illustrated in an example wherein two methods are compared in a particular application domain. The weight given to each factor depends on application.

Algorithms↗

PubMed2004

Iso-shaping rigid bodies for estimating their motion from image sequences.

In many medical imaging applications, due to the limited field of view of imaging devices, acquired images often include only a part of a structure. In such situations, it is impossible to guarantee that the images will contain exactly the same physical extent of the structure at different scans, which leads to difficulties in registration and in many other tasks, such as the analysis of the morphology, architecture, and kinematics of the structures. To facilitate such analysis, we developed a general method, referred to as iso-shaping, that generates structures of the same shape from segmented image sequences. The basis for this method is to automatically find a set of key points, called shape centers, in the segmented partial anatomic structure such that these points are present in all images and that they represent the same physical location in the object, and then trim the structure using these points as reference. The application area considered here is the analysis of the morphology, architecture, and kinematics of the joints of the foot from magnetic resonance images acquired at different joint positions and load conditions. The accuracy of the method is analyzed by utilizing ten data sets for iso-shaping the tibia and the fibula via four evaluative experiments. The analysis indicates that iso-shaping produces results as predicted by the theoretical framework.

Algorithms↗

PubMed2002

The geometric architecture of the subtalar and midtarsal joints in rheumatoid arthritis based on magnetic resonance imaging.

OBJECTIVE: To compare in vivo the 3-dimensional (3-D) geometric architecture of the subtalar and midtarsal joints in normal and rheumatoid arthritic (RA) feet, using magnetic resonance imaging (MRI) analysis. METHODS: MRI was performed on 23 patients with RA, all of whom had disease activity in the subtalar and/or midtarsal joints. Image processing techniques were used to create 3-D reconstructions of the calcaneus (C), cuboid (c), navicular (N), and talus (T) bones. Twenty-four standard architectural parameters were measured from the reconstructions and were compared with data from 10 normal subjects. These parameters defined both 3-D distance and angular relationships among the 4 bones studied. Pattern classification techniques were used to establish a geometric architecture foot profile for the RA patients. The degree of individual patient fit to the new RA foot profile and to profiles for normal, pes planus, and pes cavus foot types was derived. Logistic regression was used to examine the relationship of foot architecture to inflammatory disease characteristics and physical examination variables. RESULTS: Subtalar or midtarsal pain was reported by all 23 patients, and 22 of the 23 patients presented with >/=1 clinical feature of pes planovalgus deformity. In 21 patients, ultrasonography revealed synovitis at >/=1 tarsal joint or surrounding tendon. In the RA group, the normalized distances between the geometric centroids were significantly closer for bone pairs Cc and cT and significantly distracted for bone pair CN compared with the distances in normal subjects. In RA patients (versus normal subjects), the angles subtended at the bone centroids were significantly decreased in 3 bone groups (CNc, TCN, and TNc) and significantly increased in 3 bone groups (CcN, CcT, NTc). The angles formed between the major principal axes of bone pairs CT and cT were significantly increased in RA patients compared with those in normal subjects. Pattern classification defined 11 RA feet as having normal structure and 12 as having abnormal structure. However, the abnormal feet did not fit consistently with structures defined for RA, pes planus, or pes cavus foot types. Logistic regression demonstrated that subtalar joint synovitis was the only predictive factor for abnormal subtalar and midtarsal architecture (odds ratio 19.2, 95% confidence interval 1.77-200.0). CONCLUSION: This unique 3-D MRI-based technique successfully quantified the effects of RA on the geometric architecture of the foot and the patient-specific nature of these changes. This technique can be used to provide logical therapy for correction.

Adult↗