D.B. Goldgof

Noise Reduction and Atmospheric Correction for Coastal Applications of Landsat Thematic Mapper Imagery

Abstract The Landsat Thematic Mapper (TM) has three visible bands centered at 485 nm, 560 nm, and 660 nm which can be used for ocean applications. This article presents a method for deriving the bottom albedo from the TM in coastal waters. Our study of historical TM images shows degradation of the sensor through time. Pattern noise in the imagery in Bands 2 and 3 was analyzed and removed using a combination of Fourier filtering and edge-detection techniques. Noise was first examined over clear and deep nearby oceanic waters, and the filter algorithms developed there were applied to the entire image. To estimate water-leaving radiance from the satellite sensor, Rayleigh and aerosol path radiance were removed. Radiance due to aerosol scattering was calculated for offshore pixels assuming a marine aerosol type, and it was removed as a constant from the entire scene. The TM sensor calibration was validated by comparing water-leaving radiance values over the clear waters of the Florida current with known, normalized water-leaving radiance values. Corrections for water path radiance and water-column attenuation of bottom-reflected radiance were made for regions of known depth, allowing the bottom albedo and vegetative pixel fraction to be determined for shallow reef areas in the Florida Keys.

Selection of patients for clinical trials: an interactive web-based system

The purpose of a clinical trial is to evaluate a new treatment procedure. When medical researchers conduct a trial, they recruit participants with appropriate health problems and medical histories. To select participants, they analyze medical records of the available patients, which has traditionally been a manual procedure. We describe an expert system that helps to select patients for clinical trials. If the available data are insufficient for choosing patients, the system suggests additional medical tests and finds an ordering of the tests that reduces their total cost. Experiments show that the system can increase the number of selected patients. We also present an interface that enables a medical researcher to add clinical trials and selection criteria without the help of a programmer. The addition of a new trial takes 10-20 min, and novice users learn the functionality of the interface in about an hour.

Structure and semi-fluid motion analysis of stereoscopic satellite images for cloud tracking

Time-varying multispectral observations of clouds from meteorological satellites are used to estimate cloud-top heights (structure) and cloud winds (semi-fluid motion). Stereo image pairs over several time steps were acquired by two geostationary satellites with synchronized scanning instruments. Cloud-top height estimation from these image pairs is performed using an improved automatic stereo analysis algorithm on a massively parallel Maspar computer with 16 K processors. A new category of motion behavior known as semi-fluid motion is described for modeling cloud motions and an automatic algorithm for extracting semi-fluid motion is developed to track cloud winds. The time sequential dense estimates of cloud-top height depth maps in conjunction with intensity data are used to estimate local semi-fluid motion parameters for cloud tracking. Both stereo disparities and motion correspondences are estimated to sub-pixel accuracy. The Interactive Image SpreadSheet (IISS) is a new versatile visualization tool that was enhanced to analyze and visualize the results of the stereo analysis and semi-fluid motion estimation algorithms. Experimental results using time-varying data of the visible channel from two satellites in geosynchronous orbit is presented for the Hurricane Frederic.<<ETX>>

Experiments on the automated selection of patients for clinical trials

When clinicians test a new treatment procedure, they need to identify and recruit patients with appropriate medical conditions. We have developed an expert system that helps clinicians select patients for experimental treatments, and to reduce the number and overall cost of related medical tests. We describe experiments on selecting patients for new treatments at the Moffitt Cancer Center. The experiments have shown that the system can increase the number of selected patients by a factor of three, and that it can also reduce the cost of the selection process.

Sequence tolerant segmentation system of brain MRI

An automatic human brain segmentation system for magnetic resonance images is presented. It has two main parts: a fuzzy clustering algorithm and a set of cluster combination rules. Images are segmented into ten classes by the unsupervised fuzzy c-means clustering algorithm. Then a knowledge-based system labels the clusters into the tissues of interest: cerebrospinal fluid, gray matter and white matter. This approach can process MRI data that comes from different scanners with different sequences and head coils, using several different spin-echo images (with different echo times) and different slice thickness. The system adapts without manual intervention. Segmented synthetic image data from the brainWeb simulated normal brain database resulted in a one voxel away accuracy of 90%. The results from real data from various magnetic resonance imagers were compared with a radiologists segmentation and found to generally agree within 10%, the typical range of inter-rater radiologist agreement.

Curvature‐based nonrigid motion analysis from three‐dimensional correspondences

We describe a curvature‐based approach for estimating nonrigid motion of moving surfaces. We deal with conformal motion, which can be characterized by stretching of the surface. At each point, this stretching is equal in all directions but different for different points. The stretching function can be defined as additional (with global translation and rotation) motion parameter. We present a new algorithm for local stretching recovery from Gaussian curvature, based on polynomial (linear and quadratic) approximations of the stretching function. It requires point correspondences between time frames but not the complete knowledge of nonrigid transformation. Experiments on simulated and real data are performed to illustrate performance and accuracy of derived algorithms. Noise sensitivity of the algorithm is also evaluated using Gaussian noise on simulated data.©1993 John Wiley & Sons Inc

Knowledge acquisition for clinical-trial selection

When medical researchers test a new treatment procedure, they recruit patients with appropriate medical histories. An experiment with a new procedure is called a clinical trial. The selection of patients for clinical trials has traditionally been a labor-intensive task, which involves the matching of medical records with a list of eligibility criteria, and studies have shown that clinicians can miss up to 60% of the eligible patients. A recent project at the University of South Florida has been aimed at the automation of this task. We have developed an intelligent agent that selects trials for eligible patients. We report the work on the representation and entry of the related knowledge about clinical trials. We describe the structure of the agent’s knowledge base and the interface for adding new trials. Keywords— Knowledge representation, medical expert systems, user interfaces.

Fuzzy analysis of satellite images to find phytoplankton blooms

A knowledge-based approach to automatic classification of Coastal Zone Color Scanner (CZCS) images of the west Florida Shelf is described. The approach is utilized to monitor red tides and phytoplankton plumes, such as green river off the west Florida shelf. CZCS images are initially segmented by the unsupervised mrFCM algorithm, then a knowledge based system is applied to the centroid values of resultant clusters to label case I and case II waters, green river and red tide. Our knowledge base consists of a rule based system and an embedded neural network. Our results show, among 25 ground truth images, this system can correctly recognize all 15 images with green river and 10 images without. The system can correctly classify 75% of the pixels belonging to green river. A time series of red tide in 1978 is also successfully identified.

On a study of invariant features in nonrigid transformations

Invariant features are of prime importance in computer vision. These features are any properties of the surface that are not changed during a transformation, and which can be used for object recognition or motion analysis. Two categories of invariancies can be identified: invariance with respect to the rigid motion, and invariance with respect to the nonrigid motion. The authors concentrate on the differential geometric properties that can be used to detect the nonrigid motion of a given surface. Analysis of invariant features of a surface that can be used in recognition of nonrigid motion has been addressed. A novel method for estimating point correspondences between surfaces undergoing a small deformation is presented.<<ETX>>

Using probabilistic methods to optimize data entry in accrual of patients to clinical trials

A clinical trial is a study conducted on a group of patients to evaluate a new treatment procedure. Usually, clinicians manually select patients for a clinical trial; the choice of eligible patients is a labor-intensive process, and clinicians are often unable to identify sufficient number of patients, which delays the evaluation of new treatments. We have developed a Web-based system that helps clinicians to determine the eligibility of patients for multiple clinical trials. It uses probabilistic techniques that minimize the amount of manual data entry, by ordering the related data-entry steps. We describe the developed system and give the results of applying it to retrospective data of breast cancer patients at the Moffitt Cancer Center.