Breast tumor segmentation
Breast tumor segmentation
- Tez No: 725985
- Danışmanlar: DR. TUTOR MEMBER OF IHAB ELAFF
- Tez Türü: Yüksek Lisans
- Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 2022
- Dil: İngilizce
- Üniversite: Üsküdar Üniversitesi
- Enstitü: Fen Bilimleri Enstitüsü
- Ana Bilim Dalı: Bilgisayar Mühendisliği Ana Bilim Dalı
- Bilim Dalı: Bilgisayar Mühendisliği Bilim Dalı
- Sayfa Sayısı: 60
Özet
Cancer is a killer disease, a very common one at that but sadly until date, there are no over the counter drugs that can manage or cure cancer. Annually, approximately 180,000 new cases of breast cancer are observed in the United States. Breast cancer is the leading cause of mortality in women since this commonly occurs in female patients. To ramp up the chances of survivors of breast cancer, early detection is important and should be supported. Breast magnetic resonance imaging (MRI) could provide comprehensive data on the extent and existence of breast lesions and could be used to support early detection, diagnosis and suggest possible treatment of breast cancer. In this work, techniques and alternative solutions for generating higher breast MR images within limited time are discussed. Breast cancer, the second most prevalent cancer in the universe and the direct cause of cancer-related death in women, commences in the breast's ductal or lobular cells and propagates to the deeper structures. Breast cancer is always induced by gene mutations, either as a consequence of a hereditary irregularity or as an outcome of acquired genetic variations. These acquired mutations could be as a result of environmental factors or predisposition to cancer cells. Although some school of thoughts support mammography or ultrasound breast screening, this method is mainly seen as a complement to magnetic resonance imaging (MRI) of the breast. Breast MRIs are most widely used for women who have been diagnosed with terminal cancer to track and measure the tumor volume, look for other tumor cells in the breast, and check for tumors in the lateral breast. A breast MRI, in addition to a yearly mammogram is recommended for women at significantly higher risk. The MRI has been known for producing inaccurate results, leading to additional tests and/or biopsies for the physician. Therefore, while breast MRI is beneficial for women at high risk, it is infrequently suggested as a screening test for women at typical risk of breast cancer. Breast MRI also does not identify calcium deposits, known as micro-calcifications, which can be an indication of breast cancer. To further understand breast cancer and detect the region of interests, this work explores K-Means segmentation technique, Otsu segmentation technique and FCM segmentation technique. Sample images taken from the lateral and sagittal planes are observed and interpreted and recommendation given.
Özet (Çeviri)
Cancer is a killer disease, a very common one at that but sadly until date, there are no over the counter drugs that can manage or cure cancer. Annually, approximately 180,000 new cases of breast cancer are observed in the United States. Breast cancer is the leading cause of mortality in women since this commonly occurs in female patients. To ramp up the chances of survivors of breast cancer, early detection is important and should be supported. Breast magnetic resonance imaging (MRI) could provide comprehensive data on the extent and existence of breast lesions and could be used to support early detection, diagnosis and suggest possible treatment of breast cancer. In this work, techniques and alternative solutions for generating higher breast MR images within limited time are discussed. Breast cancer, the second most prevalent cancer in the universe and the direct cause of cancer-related death in women, commences in the breast's ductal or lobular cells and propagates to the deeper structures. Breast cancer is always induced by gene mutations, either as a consequence of a hereditary irregularity or as an outcome of acquired genetic variations. These acquired mutations could be as a result of environmental factors or predisposition to cancer cells. Although some school of thoughts support mammography or ultrasound breast screening, this method is mainly seen as a complement to magnetic resonance imaging (MRI) of the breast. Breast MRIs are most widely used for women who have been diagnosed with terminal cancer to track and measure the tumor volume, look for other tumor cells in the breast, and check for tumors in the lateral breast. A breast MRI, in addition to a yearly mammogram is recommended for women at significantly higher risk. The MRI has been known for producing inaccurate results, leading to additional tests and/or biopsies for the physician. Therefore, while breast MRI is beneficial for women at high risk, it is infrequently suggested as a screening test for women at typical risk of breast cancer. Breast MRI also does not identify calcium deposits, known as micro-calcifications, which can be an indication of breast cancer. To further understand breast cancer and detect the region of interests, this work explores K-Means segmentation technique, Otsu segmentation technique and FCM segmentation technique. Sample images taken from the lateral and sagittal planes are observed and interpreted and recommendation given.
Benzer Tezler
- Breast tumor segmentation and classification on histopathological images using machine learning
Makine öğrenmeyi kullanarak histopatolojik görüntüler üzerinden meme tümörünün bölümlendirilmesi ve sınıflandırılması
ZEYAD ABDALKAREEM KHALAF KHALAF
Yüksek Lisans
İngilizce
2023
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolKarabük ÜniversitesiBilgisayar Mühendisliği Ana Bilim Dalı
DR. ÖĞR. ÜYESİ NEHAD T.A RAMAHA
- Computer aided diagnosis of breast tumor segmentation and classification on CT images using machine learning
Başlık çevirisi yok
BARISH MOHAMMED IZADDIN IZADDIN
Yüksek Lisans
İngilizce
2021
Elektrik ve Elektronik MühendisliğiAltınbaş ÜniversitesiElektrik ve Bilgisayar Mühendisliği Ana Bilim Dalı
DR. ÖĞR. ÜYESİ AYÇA KURNAZ TÜRKBEN
- Superpixel assisted deep neural network for breast tumor segmentation in ultrasound images
Süperpiksel destekli derin sinir ağı ile meme ultrason görüntülerinde tümör segmentasyonu
NEFİSE UYSAL
Yüksek Lisans
İngilizce
2022
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik ÜniversitesiElektronik ve Haberleşme Mühendisliği Ana Bilim Dalı
PROF. DR. ENDER METE EKŞİOĞLU
ÖĞR. GÖR. MURAT GEZER
- Değiştirilmiş U-Net modeli ile biyomedikal görüntü segmentasyonu
Biomedical image segmentation with modified U-Net
UMUT TATLİ
Yüksek Lisans
Türkçe
2024
Elektrik ve Elektronik MühendisliğiDicle ÜniversitesiBiyomedikal Mühendisliği Ana Bilim Dalı
DOÇ. DR. CAFER BUDAK
- Kontrast tutucu maddeli meme MR'ı örneğinde yapay sinir ağları ile görüntü segmentasyonu
Automatic tumor segmentation in contrast-enhanced dynamic MR images by using artificial neural network technique
HİLMİ KEMAL KOCA
Yüksek Lisans
Türkçe
2007
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolYıldız Teknik ÜniversitesiJeodezi ve Fotogrametri Mühendisliği Ana Bilim Dalı
YRD. DOÇ. DR. BÜLENT BAYRAM