Klasifikasi stadium kanker ginjal jenis Clear Cell Renal Cell Carcinoma (ccRCC) pada citra CT Scan dengan pendekatan fitur radiomics

Dewi, Tsania Nurhayati Karunia (2021) Klasifikasi stadium kanker ginjal jenis Clear Cell Renal Cell Carcinoma (ccRCC) pada citra CT Scan dengan pendekatan fitur radiomics. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (771kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak.pdf Download (126kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi.pdf Download (140kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (175kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (5MB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (108kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (294kB) | Request a copy

Abstract

According to Global Burden of Cancer data 2018, kidney cancer is one of the cancer cases that causes 9,6 million deaths in 185 countries. Clear cell renal cell carcinoma (ccRCC) is the most common type of RCC cancer. Accurate staging of ccRCC is important for determining prognosis and formulating effective treatment. Clinical staging (preoperative) has limitations in determining the detection of small size cancer, as well as knowing the metastases of lymph and other organs. A radiomics approach is proposed to be able to non-invasively determine prreoperative ccRCC staging based on informative features extracted from CT scan images. A total of 237 CT ccRCC images sourced from the The cancer imaging archive (TCIA) repository and the stadium dataset from the Genomic Data Commons (GDC) portal were used. The research process consists of: patient selection, cancer mask segmentation, feature extraction and selection, and classification. 56 radiomics features were extracted from the ROI image bounded by the mask. 33 radiomics features relevant to stadium labels were selected and used for system training by using Support Vector Machine and Random Forest. The accuracy, sensitivity, and specificity of the SVM classification system were 90%, 90%, and 96,67%, respectively. As for RF, respectively 80%, 80%, and 93,33%. The ROC curves for SVM and RF systems are above the random diagonal prediction line. And the AUC values between SVM and RF systems are 0,954 and 0,957, respectively.

Actions (login required)

View Item