Artificial Tactile Sensing and Robotic Surgery Using Higher Order Neural Networks

Artificial Tactile Sensing and Robotic Surgery Using Higher Order Neural Networks

Siamak Najarian (Amirkabir University of Technology, Iran), Sayyed Mohsen Hosseini (Amirkabir University of Technology, Iran) and Mehdi Fallahnezhad (Amirkabir University of Technology, Iran)
DOI: 10.4018/978-1-61520-711-4.ch021
OnDemand PDF Download:
No Current Special Offers


In this chapter, a new medical instrument, namely, the Tactile Tumor Detector (TTD) able to simulate the sense of touch in clinical and surgical applications is introduced. All theoretical and experimental attempts for its construction are presented. Theoretical analyses are mostly based on finite element method (FEM), artificial neural networks (ANN), and higher order neural networks (HONN). The TTD is used for detecting abnormal masses in biological tissue, specifically for breast examinations. We also present a research work on ANN and HONN done on the theoretical results of the TTD to reduce the subjectivity of estimation in diagnosing tumor characteristics. We used HONN as a stronger open box intelligent unit than traditional black box neural networks (NN) for estimating the characteristics of tumor and tissue. The results show that by having an HONN model of our nonlinear input-output mapping, there are many advantages compared with ANN model, including faster running for new data, lesser RMS error and better fitting properties.
Chapter Preview


Tactile sensors are utilized to sense a wide range of stimuli in various biomedical engineering and medical robotics applications, such as detection of the presence or absence of a grasped tissue/object or even mapping of a complete tactile image (Dargahi, 2001; Dargahi & Najarian, 2004a; Najarian et al, 2009). These sensors normally consist of an array of sensors (Fisch et al, 2003; Najarian et al, 2006).

In clinical practice, doctors routinely palpate the patients’ body with the fingers and palm, especially for those diseases where a palpable nodule or lump in tissue is the most common symptom. Even if the nodule is detected via palpation, there is a lack of any precise measuring devices, so all that can be documented is the general location of the tumor within the tissue (Barman & Guha, 2006). In some patients, this technique has preference over some imaging techniques (Zeng et al, 1997). In consequence, many new breast examination techniques have been proposed, most of which are based on the difference between tissue stiffness and tumor stiffness (Kane et al, 1996). Artificial tactile sensing is a new method for obtaining the characteristics of a tumor in the soft tissue (Dargahi & Najarian, 2004b; Dargahi & Najarian, 2005). This includes detecting the presence or absence of a tumor or even mapping a complete tactile image (Bar-Cohen et al, 2000; Dargahi, 2002; Singh et al, 2003). Artificial palpation is another important application of tactile sensing.

Complete Chapter List

Search this Book: