Authors:
Ahmad Chaddad
;
Camel Tanougast
and
Abbas Dandache
Affiliation:
University of Lorraine, France
Keyword(s):
Cancer, FPGA, Implementation, Segmentation, Snake.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Biomedical Instrumentation
;
Biomedical Instruments and Devices
;
Imaging and Visualization Devices
Abstract:
Optical microscopy is widely used for cancer cell detection via biopsy. Unfortunately this technique requires a large number of samples to determine the grade of the cancer cells. Because time is critical in this operation, a search for a method to reduce the length of this process is important. One such method showing promise is the implementation of the snake method for cancer cell detection. Ideally, this method will aim toward minimizing cost while maximizing efficiency. Using optical microscopy at LCOMS, we performed a proof-of-concept study to distinguish between normal and abnormal cells. We developed a snake/active contour method by which several curves move within images in order to find normal/abnormal cell boundaries. Abnormal cell identification typically takes more than one hour; however. The implementation of field programmable gate array (FPGA) technology solves this problem. A novel embedded architecture of the snake method is developed for an efficient and fast compu
tation of active contour used in high throughput image analysis applications, where time performance is critical. This architecture allows for a scalable and a totally embedded processing on FPGA of a large number of images. The architecture of the snake method is able to detect objects from images which have irregular shapes, such as carcinoma cell types. To demonstrate the effectiveness of the approach, the architecture is implemented on Xilinx ISE 12.3-FPGA technology using Verilog hardware description language (VHDL). The very promising results using Snake method implementation and real cancer cell images from optical microscopy demonstrate the potentials of our approach.
(More)