Search

Histopathological examination of tissue models is basic for the conclusion and reviewing of colon malignancy. In any case, the technique is subjective and prompts imperative intra/bury spectator distinction in the examination as it predominantly relies upon the graphical evaluation of histopathologists. Thus, a tried and true PC supported technique, which can naturally group harmful and ordinary colon tests are required; however, automating this strategy is demanding because of the nearness of exceptions. In this paper, a productive technique for identifying colon disease from biopsy tests which comprise of four imperative stages. DB-SCAN estimation to distinguish colon tumor from biopsy tests is presented in this paper. In the proposed approach, from the outset, the colon biopsy tests are preprocessed using DB-SCAN configuration to make a set of redundant localities in which groups or clusters are formed. At that point, the exceptions inside the bunched areas are created as a tree structure in light of the choice tree in which the anomalies are hubs, and the connection between hubs are delivered based on data about exceptions. At that point, entropy-based exception score calculation will be done on every hub of the tree. The Information picks up technique is utilized to figure the score for the exceptions. At long last, score based grouping is accomplished to order the ordinary or harmful cells. Experimental trials exhibit, the proposed strategy has better outcomes contrasted to existing strategies. It furthermore acclaims that the proposed procedure is adequate for the colon tumor identification process. The proposed strategy is executed on Matlab working platform and the investigations exhibit that the proposed technique has high accomplished high grouping precision contrasted and different strategies.

Tissue identification, tumor margin identification, and therapy are major concerns for surgeons. Endomicroscopy can provide in vivo, in situ cellular-level images for the real-time assessment of tissue pathology. Hence, laser ablation can be performed in a minimally invasive manner to kill cancerous tissue while preserving normal tissue, allowing less pain and shorter recovery time. Combining endomicroscopy with laser ablation is a new area and has high potential to be a promising system. However, it is challenging to assess a surgical site using individual microscopic images due to the limited field-of-view (FoV) and difficulties associated with manually manipulating the probe. In this paper, a novel robotic device for intraoperative large-area endomicroscopy imaging and image-guided ablation is proposed, demonstrating a highly accurate and stable surface-scanning mechanism to obtain histology-level endomicroscopy mosaics. The device also includes a laser ablation fiber to precisely ablate target tissue under image guidance without the need for an additional tool. The device achieves pre-programmed scanning trajectory with a high positioning accuracy of 0.21 mm and obtains a large FoV of more than 13.9 mm2 from a range of ex vivo human and animal tissue experiments. We perform in vivo image-guided ablation of porcine thyroid gland tissue in robotic-assisted endomicroscopy. The experimental results demonstrate that the proposed device can generate large-area, histology-level microscopic images, and ablate suspicious areas of diseased soft biological tissue, showing the potential of the device for future intelligent system and improve robotic-assisted surgery.

Tumor identification is one of the main and most influential factors in the identification of the type of treatment, the treatment process, the success rate of treatment and the follow-up of the disease. Convolution neural networks are one of the most important and practical classes in the field of deep learning and feed-forward neural networks that is highly applicable for analyzing visual imagery. CNNs learn the features extracted by the convolution and maxpooling layers. Extreme Learning Machines (ELM) are a kind of learning algorithm that consists of one or more layers of hidden nodes. These networks are used in various fields such as classification and regression. By using a CNN, this paper tries to extract hidden features from images. Then a kernel ELM (KELM) classifies the images based on these extracted features. In this work, we will use a dataset to evaluate the effectiveness of our proposed method, which consists of three types of brain tumors including meningioma, glioma and pituitary tumor in T1-weighted contrast-enhanced MRI (CE-MRI) images. The results of this ensemble of CNN and KELM (KE-CNN) are compared with different classifiers such as Support Vector Machine, Radial Base Function, and some other classifiers. These comparisons show that the KE-CNN has promising results for brain tumor classification.

Tumor markers are substances, usually proteins that can be found in the blood, urine, stool, tumor tissue and more recently DNA changes, which are produced by the body in response to cancer growth. Thus far, more than 20 different tumor markers have been identified where some of them are specific for a particular type of cancer, while others are associated with several cancer types. The problem of tumor profiling has been extensively studied by the bioinformatics community. Although tumor classification has improved nowadays, there has been no general approach for identifying new cancer classes or for assigning tumors to known classes. In this paper we describe a novel strategy for tumor classification by using Growing Hierarchical Self-Organizing map (GHSOM) since it is able to weigh the contribution of each marker according to its relatedness with other tumor markers as well as handles highly skewed tumor marker expressions well. In the end, experiments are conducted to further demonstrate the feasibility and efficiency of tumor classification approach which provide valuable contribution in the field of oncology and cancer diseases and will be as a guide for the identification of these diseases.