Classification of lung nodules in CT images using convolutional neural networks

Download
2018
Polat, Görkem
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computeraided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this thesis, we proposed a framework that analyzes CT lung screenings using convolutional neural networks (CNNs) to reduce false positives. Our framework shows that even non-complex architectures are very powerful to classify 3D nodule data when compared to traditional methods. We trained our model with different volume sizes and showed that volume size plays a critical role in the performance of the system. We also used different fusions in order to show their power and effect on the overall accuracy. 3D CNNs were preferred over 2D CNNs because data was in 3D and 2D convolutional operations may result in information loss. The proposed framework has been tested on the dataset provided by the LUNA16 Challenge and got a sensitivity of 0.831 at 1 false positive per scan.

Suggestions

Effect of input size on the classification of lung nodules using convolutional neural networks Akciǧer nodüllerinin evrişimsel sinir aǧlari kullanilarak siniflandirilmasinda girdi boyutunun etkisi
POLAT, Gorkem; Serinağaoğlu Doğrusöz, Yeşim; Halıcı, Uğur (2018-05-05)
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computer-aided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this...
The serum immunoglobulin G glycosylation signature of gastric cancer
Ruhaak, L. Renee; Barkauskas, Donald A.; Torres, Javier; Cooke, Cara L.; Wu, Lauren D.; Stroble, Carol; Özcan Kabasakal, Süreyya; Williams, Cynthia C.; Camorlinga, Margarita; Rocke, David M.; Lebrilla, Carlito B.; Solnick, Jay V. (Elsevier BV, 2015-03-01)
Biomarkers may facilitate detection of gastric cancer at an earlier stage and reduce mortality. Here we sought to determine if the glycosylation profile of serum immunoglobulin G (IgG) could distinguish patients with non-atrophic gastritis (NAG), duodenal ulcer (DU) and gastric cancer (GC). Serum IgG was released and analyzed using nano-LC–TOF mass spectrometry. Statistically significant false discovery rate (FDR)-adjusted p-values were observed for 18 glycans, eight that differed significantly between NAG ...
Characterization of liposomal celecoxib formulation as a drug delivery system in colorectal cancer cell lines
Erdoğ, Aslı; Banerjee, Sreeparna; Department of Biotechnology (2012)
Colorectal carcinoma (CRC) is one of the most common cancers and is the leading cause of cancer deaths in much of the developed world. Owing to the high incidence of drug resistance and potential toxic effects of chemotherapy drugs, much research is currently underway to design better strategies for smart drug delivery systems. Cyclooxygenase-2 (COX-2) pathway is associated with poor prognosis in colon carcinomas. The selective COX-2 inhibitor drug Celecoxib (CLX) has been shown to posses COX-2 independent ...
Risk analysis based on spatial analysis of chronic obstructive pulmonary disease (COPD) and lung cancer with respect to provinces in Turkey
Çiftçi, Sezgin; Başbuğ Erkan, Berna Burçak; Düzgün, H. Şebnem; Department of Actuarial Sciences (2012)
The goal of this thesis is to analyze and understand the risks of Chronic Obstructive Pulmonary Disease (COPD) and lung cancer with respect to the provinces of Turkey according to the results of spatial analysis. The insurance sector of the country needs that kind of analysis to make more precise pricing in insurance products. Especially in health and life insurance products, morbidities like COPD and lung cancer may a ect the life expectancy as much as the premiums. COPD and lung cancer prevalence may exhi...
Reversal of multidrug resistance by synthetic and natural compounds in drug-resistant MCF-7 cell lines
Kars, Meltem Demirel; Iseri, Ozlem Darcansoy; Gündüz, Ufuk; Molnar, Jozsef (2008-01-01)
Background: Ineffectiveness of anticancer drugs is frequently observed in cancer chemotherapy. The resistance of tumor cells to various cytotoxic drugs is defined as multidrug resistance (MDR). The purpose of this study is to investigate the potential reversal effect of some synthetic and natural chemicals on drug-resistant MCF-7 cell lines. The effects of potential MDR modulators combined with some anticancer drugs were also studied. Methods: Flow cytometry, MTT cytotoxicity assays and checkerboard combina...
Citation Formats
G. Polat, “Classification of lung nodules in CT images using convolutional neural networks,” M.S. - Master of Science, Middle East Technical University, 2018.