International Journal of Medical Advances and Discoveries

International Journal of Medical Advances and Discoveries ISSN 2756-3812 Vol. 4 (2), pp. 001-007, February, 2013. Available online at www.internationalscholarsjournals.org © International Scholars Journals

Full Length Research Paper

Artificial Neural Network-Assisted Ultrasound Image Capture on Personal Computers

Mitra Ahmad Soltani-MD, MS

Lutalo Medical Research Corporation 15- Shariaty all- Kord St- Ressalat HW- Tehran –Iran.
E-mail: [email protected]. Tel: 00989127964990.

Accepted 20 October, 2012

Abstract

Traditional probes consist of 40 to 60 crystals each attached to a pin attached to a specialized cable of minimum 2 to 3 m. Each crystal has piezoelectric properties. To capture images by personal computers to improve accessibility and reduce the cost of having ultrasonic image with special reference to obstetrics and gynecology emergency settings, a probe was designed consisting of three Doppler transducers (each with 4 pins hence generating 4 signals, altogether 12 signal) that by an analog switching with micro (1000 HZ per second) can generate 12000 signals per second changing the scan line form linear into a plane. The signals are translated into WAV sound format file that can be displayed by a Windows-based program of a personal computer. The pattern produced is created by the sound of blood flow in an organ. This vascular pattern was matched with traditional sonography of the organ. By training the network, the resolution of images can be improved further based on the formula: output = 0.77*target + 38. The probe can capture images 1/6 resolution of a traditional probe, deeper penetration (19 cm depth), 1/34 price and weight of a traditional ultrasound equipment

Key words: Doppler transducers, scan line, artificial neural network, ultrasound, obstetrics and gynecology.