Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81--7.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... reported for the characterization of ROI such as, rule based systems [9,12] fuzzy logic systems [11] statistical methods based on Markov random fields [20] and support vector machines [3] Nevertheless, the most work reported in the literature employs neural networks for cluster characterization [10,27,33,37,51,54,55,58,59,61]. Typically, a neural network accepts as input features computed for a specific region of interest and provides as output a characterization of the region as true microcalcification cluster or not. Recently, neural networks have also been used to characterize a microcalcification as malignant or ....

Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81--7.

....For example, the Fig. 2. The two ROC curves have equal Az values, but, depending upon the relative preferences concerning the sensitivity or specificity of the detection task, one curve is typically preferred over the other. output threshold is usually varied to generate a ROC curve for ANN s [22]. Traditionally, the classifier is trained prior to the generation of the ROC curve [22] 23] In this situation, all but one point on the ROC curve represent operating points other than the one to which the classifier was naturally trained. A ROC curve that was generated with the same dataset ....

....the relative preferences concerning the sensitivity or specificity of the detection task, one curve is typically preferred over the other. output threshold is usually varied to generate a ROC curve for ANN s [22] Traditionally, the classifier is trained prior to the generation of the ROC curve [22], 23] In this situation, all but one point on the ROC curve represent operating points other than the one to which the classifier was naturally trained. A ROC curve that was generated with the same dataset that was used to train the classifier is referred to as a consistency ROC curve. A ....

Y. Wu, M. L. Giger, K. Doi, C. J. Vyborny, R. A. Schmidt, and C. E. Metz, "Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer," Radiology, vol. 187, no. 1, pp. 81--87, 1993.

....Keywords Pareto optimization, di#erential evolution, artificial neural networks, breast cancer. 1 Introduction The economic and social values of Breast Cancer Diagnosis (BCD) are very high. As a result, the problem has attracted many researchers in the area of computational intelligence recently [6, 8, 10, 22, 26, 32, 33, 34]. Because of the importance of achieving highly accurate classification, Artificial Neural Networks (ANNs) are among the most common methods for BCD. Research in the area of using ANNs for medical purposes more specifically BCD [6, 8, 10, 22, 26, 32, 34] has been at the center of attention ....

....intelligence recently [6, 8, 10, 22, 26, 32, 33, 34] Because of the importance of achieving highly accurate classification, Artificial Neural Networks (ANNs) are among the most common methods for BCD. Research in the area of using ANNs for medical purposes more specifically BCD [6, 8, 10, 22, 26, 32, 34] has been at the center of attention for several years. Unfortunately, to our present knowledge, none of this type of research was able to enter the clinic either in terms of routine use or to replace the radiologist. This could be ascribed to a number of factors. The first problem was the ....

[Article contains additional citation context not shown here]

Y.Z. Wu, M.L. Giger, K. Doi, C.J. Vyborny, R.A. Schmidt, and C.E. Metz. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology, 187:81--87, 1993.

.... approaches particularly ANN s have been used for a number of disparate clinical diagnosis tasks; diagnosing, for example, skin lesions [101] appendicitis [26] and myocardial infarction [5] In breast cancer, different researchers have applied neural networks to diagnosing from mammograms [100], ultrasound images [34] and pathological markers [2] Still, few of these systems have received general clinical usage. Machine learning methods have also been applied to prognosis. Burke [16] uses a traditional backpropagation network to predict 10 year survival in breast cancer patients. A ....

Y. Wu, M. L. Giger, K. Doi, C. J. Vyborny, R. A. Schmidt, and C. E. Metz. Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer. Radiology, 187:81--87, 1993.

....as a means of identifying malignancies. These research trends were followed in applying ANNs to the problem of differentiating between malignant and benign changes. Similarly to detection, two types of inputs are used: i) 2 D images, e.g. 31] 52] and (ii) 1 D feature pattern vectors, e.g. [53] [57] The 1 D patterns are formed either by encoding perceptual evaluation of medical experts, e.g. 53] 54] or by automated feature extraction from ROIs, e.g. 55] 57] In the former case, the primary objective is to correlate the established semiology of malignancy with known diagnosis. ....

....of differentiating between malignant and benign changes. Similarly to detection, two types of inputs are used: i) 2 D images, e.g. 31] 52] and (ii) 1 D feature pattern vectors, e.g. 53] 57] The 1 D patterns are formed either by encoding perceptual evaluation of medical experts, e.g. [53], 54] or by automated feature extraction from ROIs, e.g. 55] 57] In the former case, the primary objective is to correlate the established semiology of malignancy with known diagnosis. Breast cancer diagnosis methods using ANN are summarized in Table 2. 4.1 Diagnosis using ANN with 2 D ....

[Article contains additional citation context not shown here]

Y Wu, M.L. Giger, K. Doi, C.J. Vyborny, R.A. Schmidt, and C.E. Metz, "Artificial Neural Networks in Mammography: Application to Decision Making in the Diagnosis of Breast Cancer," Radiology, vol. 187, pp. 81-87, 1993.

....This paper describes ongoing work investigating machine learning (ML) techniques to support computer based oral cancer screening in primary and secondary healthcare. The studies described here were partly encouraged by other successful applications of machine learning in cancer diagnosis [8, 11, 17, 20, 21]. Until forty years ago, the incidence of oral cancer was continuing to decline but it is now rising in the UK and in other industrialised countries in Europe and North America. Approximately 2,000 cases of oral cancer are newly diagnosed in England and Wales each year, with an incidence of 4.5 ....

Wu, Y., Giger, M.L., Doi, K., Vyborny, C.J., Schmidt, R.A., Metz, C.E.: Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 187 (1993) 81-87.

....parameters in the corresponding non linear regression model implies the risk of substantial overfitting of the observed data which has to be taken into account. In such a case, single reporting that a neural net has been successfully applied to decision making in the diagnosis of breast cancer (Wu et al. 1993) is not interesting without a comparison to the results obtained by standard statistical techniques. Thus it is not sufficient to mention the need for such comparisons (Tu Guerriere 1993) they have to be done and their results explicitly given. Finally, there is the question when and under ....

Wu, Y., Giger, M.L., Doi, K., Vyborny, C.J., Schmidt, R.A., Metz, C.E. (1993): Artificial neural networks in mammography: Application to decision making in the diagnosis of breast cancer. Radiology 187, 81-87.

....density. The performance of the model was assessed using the LABROC1 program [18] for receiver operating characteristic (ROC) analysis (Figure 3) MammoNet s performance as measured by the very high A z value of 0. 881 compares very favorably with that of artificial neural network models [28] and expert mammographers. 0 0.2 0.4 0.6 0.8 1 0 0.2 0.4 0.6 0.8 True positive fraction (TPF) False positive fraction (FPF) Figure 3: Receiver operating characteristic (ROC) curve for MammoNet. 7 Discussion MammoNet is a Bayesian network designed to assist radiologists in diagnosing breast ....

Wu Y, et al. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993; 81-87.

.... methods, and they are of proven value in many areas of medicine (Westenskow et al. Westenskow92] Tourassi et al. [Tourassi93] Leong and Jabri [Leong92] Palombo [Palombo92] Gabor and Seyal [Gabor92] Goldberg et al. Goldberg92] O Leary et al. O Leary92] Dawson et al. Dawson91] Wu et al. [Wu93]; Astin and Wilding [Astin92] Weinstein et al. Weinstein92] In medical research, the most commonly used artificial neural networks are feed forward networks of simple computing units that use backpropagation training. A feed forward network is usually composed of three interconnected layers of ....

Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, & Metz CE. (1993) Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81-87.

....the most from finest to coarsest density. The performance of the model was assessed using Receiver Operating Characteristic (ROC) analysis [17] MammoNet s performance as measured by the very high A z value of 0. 9585 compares very favorably with that of artificial neural network models [26] and expert mammographers. 7 Discussion MammoNet is a Bayesian network designed to assist radiologists in diagnosing breast cancer. It uses the Bayesian Network Generator software package, producing a minimal network. MammoNet successfully models the information to diagnose breast cancer with ....

Wu Y, et al. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993; 81-87.

....difficult. Only 15 30 of biopsies performed on nonpalpable but mammographically suspicious lesions prove malignant [3] Automated classification of mammographic findings using discriminant analysis and artificial neural networks has indicated the potential usefulness of computeraided diagnosis [4,5]. We explored the use of Bayesian networks as a Section of Information and Decision Sciences, Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin 53226 0509; and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, University of ....

....statistical studies. MammoNet s performance as measured by its area under the ROC curve (A z ) compares very favorably with that of artificial neural network (ANN) models and expert mammographers. An ANN with 14 input features achieved an A z value of 0.89 (vs. 0. 84 for attending radiologists) [5] on cases from the same mammography atlas as used in this study [14] ANNs learn directly from observations, but cannot meaningfully explain their decisions. Their knowledge consists of an impenetrable thicket of numerical connection values. The ability of Bayesian networks to explain their ....

Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993; 187:81-87.

No context found.

Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81-87.

No context found.

Wu Y, Giger ML, Doi K, et al: Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 187:81, 36

No context found.

Wu Y, Giger ML, Doi K, Vyborny CJ, Schmidt RA, Metz CE. Artificial neural networks in mammography: application to decision making in the diagnosis of breast cancer. Radiology 1993;187:81-87.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC