Objective: Dual-Energy CT (DECT) is an imaging modality in which the objects are scanned by two different energy spectra. Using these two measurements, two type of materials can be separated and density image pairs can be generated as well. Decomposing more than two materials is necessary in both clinical and industrial CT applications. Methods: In our MMD, barycentric coordinates were chosen using an innovative local clustering method. Local clustering increases precision in the barycentric coordinates assignment by decreasing search domain. Therefore the algorithm can be run in parallel. For optimizing coordinates selection, a fast bi-directional Hausdorff distance measurement is used. To deal with the significant obstacle of noise, we used Doubly Local Wiener Filter Directional Window (DLWFDW) algorithm. Results: Briefly, the proposed algorithm separates blood and fat ROIs with errors of less than 2 and 9 % respectively on the clinical images. Also, the ability to decompose different materials with different concentrations is evaluated employing the phantom data. The highest accuracy obtained in separating different materials with different concentrations was 93 % (for calcium plaque) and 97.1 % (for iodine contrast agent) respectively. The obtained results discussed in detail in the following results section. Conclusion: In this study, we propose a new material decomposition algorithm. It improves the MMD work flow by employing tools which are easy to implement. Furthermore, in this study, an effort has been made to turn the MMD algorithm into a semi-automatic algorithm by employing clustering concept in material coordinate’s assignment. The performance of the proposed method is comparable to existing methods from qualitative and quantitative aspects. Advances in knowledge: All decomposition methods have their own specific problems. Image- domain decomposition also has barriers and problems, including the need for a predetermined table for the separation of different materials with specified coordinates. In the present study, it attempts to solve this problem by using clustering methods and relying on the intervals between different materials in the attenuation domain.

Interpreting brain MR images are becoming automated, to such extent that in some cases "all" the diagnostic procedure is done by computers. Therefore, diagnosing the patients is done by a comparably higher accuracy. Computer models that have been trained by a priori knowledge act as the decision makers. They make decisions about each new image, based on the training data fed to them previously. In case of cancerous images, the model picks that image up, and isolates the malignant tissue in the image as neatly as possible. In this paper we have developed an unsupervised learning system for automatic tumor segmentation and detection that can be applied to low contrast images.