Abstract - This review provides detailed background information on lung cancer detection. Various filters like Median filters, adaptive ring filters, Iris filters, Quoit filters are studied which are used to detect nodules in peripherals of lung fields. The study of these filters helps serving better Computer Aided Diagnosis of lung carcinoma tissue images improving the ability to identify early tumors for successful treatments.
Index Terms-Cancer Detection, Computer Aided Diagnosis, Adaptive ring filter, Median filters, Convolution filters.
Lung cancer is leading cause of cancer deaths in the world. It is important to detect and treat cancer in early stages to improve the survival rate of cancer patients. Usually the cancer is developed when the lung cells grow at an uncontrollable rate. The abnormal tissue masses inside the lung are called tumors and there are of two types benign(non-cancerous) or malignant(cancerous).The diagnosis of cancer includes X-rays chest films, CT scan, MRI, isotope, bronchoscope. Nevertheless, it is difficult to detect and diagnose lung cancer in chest x-ray images as there are many tissues overlapping each other in the X-ray chest film and also there are many objects obscuring the cancer tissue such as ribs, blood vessels and other anatomic structures. So it is important to develop a reliable Computer Aided Diagnosis (CAD) system for detection of lung cancer.CAD involves the use of computers to bring suspicious areas on a medical image to the attention of radiologist.CAD systems for lung cancer detection typically follows a two stage process. The first stage includes the initial processing of the image to detect a set of potential nodule. In this stage the original image is set for smoothing and enhancement, it not only removes the unwanted background information but also enhances the image. The second stage consists of classifying these suspicious regions into positive or negative regions. The positive regions are the ones which the radiologists feel the suspicion of finding possible tumors in that region. This is the stage where the image gets segmented and classified according to its wanted or required features.
This review describes various filtering methodologies that are used in preprocessing of the original image obtained from diagnosis and deals with image processing part of CAD system. Linear and non Linear filters, Local or global filters are used for image enhancement. The Deblurring techniques uses inverse or Wiener filters
II. Filters used for preprocessing of image
1) Wavelet thresholding :
Image enhancement is important for better visualization of the object. The removal of noise from the original image is required for preprocessing. Many spatial filters have been used to reduce the noise in the image. These spatial filters generally smooth the data to reduce noise but in this process they also create the blurring effect. The most optimal method for de-noising the image is by wavelet thresholding and this method provides excellent performance for noise removal. The simple and fast wavelet thresholding suppress the corrupting noise and preserve edges well.
2) Median Filters
When the image is set to thresholding it may contain some salt and pepper noise and this noise is due to the presence of minute grey scale variations in the image. The median filters reduce the salt and pepper noise without reducing the sharpness of the original image. These are pretty popular filters for noise reduction with considerably less blurring effect and linear smoothing. Median filters offers a great deal of high spatial frequency detail to pass while remaining very effective in removing noise on images there by affecting less than half of the image pixels in smoothing neighborhood.
3) Iris Filters
4) Adaptive Wiener Filters
The adaptive Wiener filters are similar to median filters which are applied for the process of de-ionizing tailored on statistics estimated from the local neighborhood of each image pixel. The amount of smoothing performed by the filter depends on the local image mean and variance around the pixel of interest. The Wiener filter is popular linear filter but it adaptive implementation preserves better the high frequency parts of the image.
ns and extensions.
- G. Eason, B. Noble, and I. N. Sneddon, “On certain integrals of Lipschitz-Hankel type involving products of Bessel functions,” Phil. Trans. Roy. Soc. London, vol. A247, pp. 529-551, Apr. 1955.
- J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp. 68-73.
- I. S. Jacobs and C. P. Bean, “Fine particles, thin films and exchange anisotropy,” in Magnetism, vol. III, G. T. Rado and H. Suhl, Eds. New York: Academic, 1963, pp. 271-350.
- T. L. Gilbert, Formulation, Foundations and Applications of the Phenomenological Theory of Ferromagnetism, Ph.D. dissertation, Illinois Inst. Tech., Chicago, IL, 1956, unpublished.
- D. P. Arnold, “Review of microscale magnetic power generation,” submitted for publication.
- S. O. Demokritov and V. E. Demidov, “Micro-Brillouin light scattering spectroscopy of magnetic nanostructures,” IEEE Trans. Magn., to be published.
- C. J. Kaufman, Rocky Mountain Research Laboratories, Boulder, CO, private communication, 2004.
- Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, “Electron spectroscopy studies on magneto-optical media and plastic substrate interface,” IEEE Transl. J. Magn. Jpn., vol. 2, pp. 740-741, August 1987 [Dig. 9th Annual Conf. Magn. Jpn., p. 301, 1982].
- M. Young, The Technical Writer's Handbook. Mill Valley, CA: University Science, 1989.