Search Results

You are looking at 1 - 10 of 43 items for :

  • "artificial intelligence" x
Clear All
Restricted access

Is the dream of a voluntary society still possible?

The 1980 Harvey Cushing oration

Kingman Brewster

right that organizations have outstripped our intelligence. But now we have artificial intelligence in the form of the computer. With it has come operations analysis and other planning and managerial techniques that expand the power, if not the wisdom, of the lords of private corporate fiefdoms, principalities, and even empires. I do not think that penal law should be used to attach penalties to monopolistic power unless it was wrongfully obtained or maintained. Punitive law should be confined to reprehensible conduct which the defendant could have avoided. But our

Restricted access

Minds and brains: angels, humans, and brutes

The 1982 Harvey Cushing oration

Mortimer J. Adler

the Nervous System ; C. Judson Herrick's The Brain of Rats and Men ; J. C. Eccles' The Neurophysiological Basis of Mind ; Ward Halstead's Brain and Intelligence ; Warren McCulloch's Embodiments of Mind ; K. S. Lashley's Brain Mechanisms and Intelligence ; and Wilder Penfield's extraordinary essay on “The Physiological Basis of the Mind,” in Control of the Mind . Even more recently, the rise of experimental researches and technological advances in the field of artificial intelligence has opened up another vein of interest in the physical basis of mind; and I

Restricted access

Eben Alexander III, Hanne M. Kooy, Marcel van Herk, Marc Schwartz, Patrick D. Barnes, Nancy Tarbell, Robert V. Mulkern, Edward J. Holupka and Jay S. Loeffler

-guided procedures performed in our center have used image fusion of MR with stereotactic CT via this method, yielding more precise stereotactic localization of anatomical structures. For MR-guided neurosurgical and radiosurgical procedures in which spatial localization accuracy of less than 5 mm is mandatory, image fusion offers an elegant solution. References 1. Barrow HG , Tenenbaum JM , Bolles RC , et al : Parametric correspondence and chamfer matching , in Proc 5th Int Joint Conf on Artificial Intelligence. Cambridge, MA , 1977

Restricted access

Christine Decaestecker, Isabelle Salmon, Olivier Dewitte, Isabelle Camby, Philippe Van Ham, Jean-Lambert Pasteels, Jacques Brotchi and Robert Kiss

chromatin patterns; 21, 22 and 2) the objective determination of the diagnosis and/or prognosis value contributed by each of these quantitative variables. Such an objective determination can be reached by means of artificial intelligence—related algorithms. 9 In the current study we focus our attention on the biological frontier that might form a distinction between low- and high-grade astrocytic tumors. Morphonuclear (that is, nucleus morphology and chromatin pattern) and DNA content—related variables were used to characterize the biological profiles of these

Restricted access

In times of change learners inherit the earth

The 1997 presidential address

J. Charles Rich

preceding this one, Nick Hopkins touched on new applications of technology for the benefit of those with cerebrovascular disease. There are 20 known core technologies that will shape the future: genetic engineering; distributed computing; advanced biochemistry; advanced computers; lasers; artificial intelligence; fiber optics; optical data storage; microwaves; digital electronics; superconductors; advanced video displays; high-tech ceramics; micromechanics; new polymers; photovoltaic cells; thin-film deposition; molecular designing; fiber-reinforced composites; and

Full access

Jeffrey E. Arle, Kenneth Perrine, Orrin Devinsky and Werner K. Doyle

Because appropriate patient selection is essential for achieving successful outcomes after epilepsy surgery, the need for more robust methods of predicting postoperative seizure control has been created. Standard multivariate techniques have been only 75 to 80% accurate in this regard. Recent use of artificial intelligence techniques, including neural networks, for analyzing multivariate clinical data, has been successful in predicting medical outcome. The authors applied neural network techniques to 80 consecutive patients undergoing epilepsy surgery in whom demographic, seizure, operative, and clinical variables to predict postoperative seizures data were obtained.

Neural networks were able to predict postoperative seizures in up to 98% of cases. Student's t tests or chi-square analysis performed on individual variables revealed that only the preoperative medication index was significantly different (p = 0.02) between the two outcome groups. Six different combinations of input variables were used to train the networks. Neural network accuracies differed in their ability to predict seizures using all data (96%); all data minus electroencephalography concordance and operative side (93%); all data except intra- or postoperative variables such as tissue pathology (98%); all data excluding pathology, intelligence quotient (IQ) data, and Wada results (84%); only using demographics and tissue pathology (65%); and only using IQ data (63%).

Analysis of the results reveals that several networks that are trained with the usual accepted variables characterizing the typical evaluation of epilepsy patients can predict postoperative seizures with greater than 95% accuracy.

Restricted access

Jeffrey E. Arle, Kenneth Perrine, Orrin Devinsky and Werner K. Doyle

Object. Because appropriate patient selection is essential for achieving successful outcomes after epilepsy surgery, the need for more robust methods of predicting postoperative seizure control has been created. Standard multivariate techniques have been only 75 to 80% accurate in this regard. Recent use of artificial intelligence techniques, including neural networks, for analyzing multivariate clinical data has been successful in predicting medical outcome.

Methods. The authors applied neural network techniques to 80 consecutive patients undergoing epilepsy surgery in whom data on demographic, seizure, operative, and clinical variables to predict postoperative seizures were collected.

Neural networks could be used to predict postoperative seizures in up to 98% of cases. Student's t-tests or chi-square analysis performed on individual variables revealed that only the preoperative medication index was significantly different (p = 0.02) between the two outcome groups. Six different combinations of input variables were used to train the networks. Neural network accuracies differed in their ability to predict seizures: using all data (96%); all data minus electroencephalography concordance and operative side (93%); all data except intra- or postoperative variables such as tissue pathological category (98%); all data excluding pathological category, intelligence quotient (IQ) data, and Wada results (84%); only demographics and tissue pathological category (65%); and only IQ data (63%).

Conclusions. Analysis of the results reveals that several networks that are trained with the usual accepted variables characterizing the typical evaluation of epilepsy patients can predict postoperative seizures with greater than 95% accuracy.

Restricted access

Jeffrey D. Atkinson, D. Louis Collins, Gilles Bertrand, Terry M. Peters, G. Bruce Pike and Abbas F. Sadikot

applications of non-linear registration-based segmentation. Int J Pattern Recog Artificial Intelligence 11 : 1271 – 1294 , 1997 Collins DL, Evans AC: ANIMAL: validation and applications of non-linear registration-based segmentation. Int J Pattern Recog Artificial Intelligence 11: 1271–1294, 1997 20. Collins DL , Holmes CJ , Peters TM , et al : Automatic 3D model-based neuro-anatomical segmentation. Hum Brain Mapp 3 : 190 – 208 , 1995 Collins DL, Holmes CJ, Peters TM, et al: Automatic 3D model-based neuro

Restricted access

Peter J. D. Andrews, Derek H. Sleeman, Patrick F. X. Statham, Andrew McQuatt, Vincent Corruble, Patricia A. Jones, Timothy P. Howells and Carol S. A. Macmillan

intracranial pressure? J Neurosurg 92 : 191 – 192 , 2000 (Letter) Young JS: Cerebral perfusion pressure or intracranial pressure? J Neurosurg 92: 191–192, 2000 (Letter) Data collection for this study was supported by Grant No. G9508752 from the Medical Research Council, United Kingdom, awarded to Dr. Andrews. This work was presented in part at the Artificial Intelligence in Medicine Conference (AIMDM'99), Aalborg, Denmark, in June 1999.

Restricted access

Jeffrey I. Berman, Mitchel S. Berger, Pratik Mukherjee and Roland G. Henry

minute of computer processing. The diffusion-tensor imaging fiber tracks were visualized in three dimensions by using Interactive Data Language and the 3D Slicer program (MIT Artificial Intelligence Laboratory and Surgical Planning Lab at Brigham & Women's Hopital, website: http://www.slicer.org). In each case, the cerebral peduncle was identified and manually outlined on the echo planar images. If DT imaging—demonstrated fiber tracks reached the cerebral peduncle, false tracks not passing through the cerebral peduncle itself were excluded 7 ( Fig. 1C ). In cases in