Classification Of Different Tumors Research Articles

Ensembled liver cancer detection and classification using CT images.

Computed tomography (CT) images are commonly used to diagnose liver disease. It is sometimes very difficult to comment on the type, category and level of the tumor, even for experienced radiologists, directly from the CT image, due to the varying intensities. In recent years, it has been important to design and develop computer-assisted imaging techniques to help doctors/physicians improve their diagnosis. The proposed work is to detect the presence of a tumor region in the liver and classify the different stages of the tumor from CT images. CT images of the liver have been classified between normal and tumor classes. In addition, CT images of the tumor have been classified between Hepato Cellular Carcinoma (HCC) and Metastases (MET). The performance of six different classifiers was evaluated on different parameters. The accuracy achieved for different classifiers varies between 98.39% and 100% for tumor identification and between 76.38% and 87.01% for tumor classification. To further, improve performance, a multi-level ensemble model is developed to detect a tumor (liver cancer) and to classify between HCC and MET using features extracted from CT images. The k-fold cross-validation (CV) is also used to justify the robustness of the classifiers. Compared to the individual classifier, the multi-level ensemble model achieved high accuracy in both the detection and classification of different tumors. This study demonstrates automated tumor characterization based on liver CT images and will assist the radiologist in detecting and classifying different types of tumors at a very early stage.

A parasitic metric learning net for breast mass classification based on mammography

Accurate classification of different tumors in mammography plays a critical role in the early diagnosis of breast cancer. However, owing to variations in appearance, it is a challenging task to distinguish malignant instances from benign ones. For this purpose, we train a deep convolutional neural networks (CNNs) to obtain more discriminative description of breast tissues. Benefiting from the discriminative representation, metric learning layers are proposed to further improve performance of the deep structure. The best-performing model restricts the depth of backpropagation of joint training in only the metric learning layers. Relation between metric learning layers and tradition CNNs structures seems like parasitism relationship between species, where one species, the parasite, benefits at the expense of the other. Therefore, the proposed method is named as parasitic metric learning net. To confirm veracity of our method, classification experiments on breast mass images of two widely used databases are performed. Comparing performance of the proposed method with traditional ones, competitive results are achieved. Meanwhile, the parameter updating strategy for our parasitic metric net may inspire a way of improving performance of a pre-trained CNNs model on particular medical image processing or other computer vision tasks.

Abstract 797: Kinase activity profiling of tumor tissues of different origin

Abstract Introduction: Many new anti-cancer drugs target kinase activity. Unfortunately, methods to monitor the drug effects at the enzymatic level in patient derived tumor tissue are lacking. Here, a novel molecular profiling method for application in biomarker discovery is presented. This method is based on measuring kinase activities in tumor tissue extracts, and involves assessment of inhibition by a drug of interest. This ex vivo activity-based approach is enabled by dynamic peptide microarrays. These arrays comprise of peptides, which are known substrates for phosphorylation by protein kinases. Here we investigated the applicability of this approach in the classification of multiple tumors of different origin. Method: Patient-derived fresh frozen tissues of different tumor types (24 breast cancer (BC), 14 non-small cell lung cancer (NSCLC), 12 renal cell carcinomas (RCC)) were used for extraction of total protein in lysis buffer. Dependent on the tissue source, 6 slices of 10 µm were sufficient for 20-100 microarray analyses. Equal amounts of total protein were analyzed for kinase activity on dynamic PamChip peptide microarrays. These arrays comprised 144 or 256 different peptides. A PamChip96 plate format was used, enabling 96 microarray incubations per run. Protein amounts ranging from 1 − 5 µg were used per microarray analysis. Tumor extracts were analysed in the presence and absence of kinase inhibitor drugs (RCC: sorafenib and sunitinib, NSCLC: gefitinib). Results: We show here that from different tumors kinase activity profiles could be generated reproducibly (10-15% CV for selected peptides). Control experiments showed protein concentration and ATP dependency. In the RCC experiments different phosphorylation profiles were obtained when the non-tumor tissue was compared to tumor tissue derived from the same patient, showing higher kinase activities in the latter. In addition, inhibitor dependent modulation of the peptide phosphorylations was observed (sorafenib vs. sunitinib). Furthermore, differential kinase activity profiles were obtained that could be correlated to different patient subgroups (BC) or clinical data (long vs. short term survivors; NSCLC). Conclusion: A novel molecular profiling approach was successfully applied for classification of different tumors. This approach is based on detection of kinase activities as well as inhibition of kinase activity in tumor tissues. Application of this method in the discovery of biomarkers for diagnosis, prognosis or prediction of drug response is foreseen. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 101st Annual Meeting of the American Association for Cancer Research; 2010 Apr 17-21; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2010;70(8 Suppl):Abstract nr 797.