Application of neural networks to flow cytometry data analysis and real-time cell classification.

Conventional analysis of flow cytometric data requires that population identification be performed graphically after a sample has been run using two-parameter scatter plots. As more parameters are measured, the number of possible two-parameter plots increases geometrically, making data analysis increasingly cumbersome. Artificial Neural Systems (ANS), also known as neural networks, are a powerful and convenient method for overcoming this data bottleneck. ANS "learn" to make classifications using all of the measured parameters simultaneously. Mathematical models and programming expertise are not required. ANS are inherently parallel so that high processing speed can be achieved. Because ANS are nonlinear, curved class boundaries and other nonlinearities can emerge naturally. Here, we present biomedical and oceanographic data to demonstrate the useful properties of neural networks for processing and analyzing flow cytometry data. We show that ANS are equally useful for human leukocytes and marine plankton data. They can easily accommodate nonlinear variations in data, detect subtle changes in measurements, interpolate and classify cells they were not trained on, and analyze multiparameter cell data in real time. Real-time classification of a mixture of six cyanobacteria strains was achieved with an average accuracy of 98%.

Use of a neural net computer system for analysis of flow cytometric data of phytoplankton populations.

Flow cytometry has been used over the past 5 years to begin detailed exploration of the distribution and abundance of picoplankton in the oceans. Light scattering and fluorescence measurements on individual plankton cells in seawater samples allow construction of population signatures from size and pigment characteristics. The use of "list mode" data has made these studies possible, but on-shore analysis of copious data does not permit on-site reexamination of important or unexpected observations, and overall effort is greatly handicapped by data analysis time. Here we describe the application of neural net computer technology to the analysis of flow cytometry data. Although the data used in this study are from oceanographic research, the results are general and should be directly applicable to flow cytometry data of any sort. Neural net computers are ideally suited to perform the pattern recognition required for the quantitative analysis of flow cytometry data. Rather than being programmed to perform analysis, the neural net computer is "taught" how to analyze the cell populations by presenting examples of inputs and correct results. Once the system is "trained," similar data sets can be analyzed rapidly and objectively, minimizing the need for laborious user interaction. The neural network described here offers the advantages of 1) adaptability to changing conditions and 2) potential real-time analysis. High accuracy and processing speed near that required for real-time classification have been achieved in a software simulation of the neural network on a Macintosh SE personal computer.

Essex-Lopresti type II joint depression calcaneal fracture from a fall of eighteen inches.

A brief review of calcaneal fractures is presented with a case report of an Essex-Lopresti type II joint depression fracture sustained from a vertical fall of 18 inches.

Steroid injection of a unicameral bone cyst of the calcaneus: literature review and two case reports.

Two interesting cases are presented, describing the diagnosis and treatment of unicameral bone cysts of the calcaneus. The first case report presents a patient who had a 5-month history of a painful right heel. The pain had been getting progressively worse and was aggravated by prolonged walking and physical activity. The second case report presents a patient whose unicameral bone cyst was discovered as a relatively incidental finding on radiographs; however, the patient later admitted that he had mild tenderness upon the plantar-lateral aspect of his right calcaneus with weightbearing. The authors reviewed the literature concerning the etiology and treatment of unicameral bone cysts. Attention is directed to the use of injectable steroid as an alternative means to open surgical intervention. Certain potential problems exist, in spite of the various surgical approaches utilized, including infection, postoperative fracture, recurrence, immobilization, and prolonged hospitalization.

Unusual osteochondroma of the foot and ankle.

Osteochondroma, also known as osteocartilaginous exostosis, is by far the most commonly occurring benign bone neoplasm. Its occurrence is the most frequent of all osseous tumors found in the foot. A basic review is discussed along with two case reports. The first case describes an osteochondroma of the third metatarsal shaft that became symptomatic during boot camp. The second case presents an atypical osteochondroma arising from the posterior aspect of the talus.

Sesamoid pain secondary to a plantar neuroma.

Two cases are presented in which the necessity of a plantar incision for removal of a fibular sesamoid led to the incidental finding of an undiagnosed plantar neuroma and bursal sac. The first case presented a hypertrophic fibular sesamoid fused to the plantar aspect of the first metatarsal head. The second case presented a dystrophic fibular sesamoid consistent with a healing fracture or avascular necrosis. Plantar neuromas are a known cause of pain in the forefoot. The authors review the literature concerning plantar neuromas and provide a discussion of their etiology, clinical findings, and surgical treatment. Attention is directed to the use of a plantar incision as a viable alternative to the dorsal approach for excision of a fibular sesamoid and associated soft tissue masses.

Chemical laser operation and n-butane absorption of DF R branch lines.

Laser emission on the R branch lines of DF has been demonstrated. The emission is much weaker than the P branch radiation from the same laser but is useful for absorption coefficient measurements or excitation of C-H bonds. Absorption coefficients of normal butane at the laser frequencies have been measured and are shown to be potentially useful for remote sensing of the atmosphere and studies of vibrationally excited molecules.