论文信息 - Diagnosis of cardiac problems from SPECT images by feedforward networks

Diagnosis of cardiac problems from SPECT images by feedforward networks

In this work, the performance of the feedforward networks on myocardial diagnosis using SPECT (single photon emission computed tomography) images is investigated. Results of the work shows that feedforward artificial neural networks reached 100% accuracy on diagnosis while machine learning algorithms have achieved maximum 90.4% accuracy up to now.

T. Yildirim | O. Bakirci

[1] Krzysztof J. Cios,et al. An algorithm which learns multiple covers via integer linear programming. Part II: experimental results and conclusions , 1995 .

[2] Krzysztof J. Cios,et al. Hybrid inductive machine learning: an overview of CLIP algorithms , 2002 .

[3] Lukasz A. Kurgan,et al. Knowledge discovery approach to automated cardiac SPECT diagnosis , 2001, Artif. Intell. Medicine.

[4] Lukasz Kurgan,et al. Ensemble of classifiers to improve accuracy of the CLIP4 machine-learning algorithm , 2002, SPIE Defense + Commercial Sensing.

[5] Krzysztof J. Cios,et al. CLIP3: Cover learning using integer programming , 1997 .