LEE- Biyomedikal Mühendisliği-Yüksek Lisans

Bu koleksiyon için kalıcı URI

http://hdl.handle.net/11527/19219

Gözat

Son Başvurular

Şimdi gösteriliyor 1 - 5 / 12
  • Öge
    Self-supervised deep convolutional neural network training for low-dose CT reconstruction
    (Graduate School, 2022) Ünal, Mehmet Ozan ; Yıldırım, İsa ; 504181414 ; Biomedical Engineering Programme
    Computed tomography (CT) is a medical imaging technique to obtain a noninvasively three-dimensional image of the body. CT imaging is one of the most crucial tools which is used for monitoring the human body and diagnosing serious illnesses. In CT imaging, one of the most serious concerns has been ionizing radiation since exposure to large amounts of radiation can cause serious illnesses. Various low-dose CT reconstruction approaches have been proposed to reduce the dose level without compromising image quality. With the emergence of deep learning, the increasing availability of computational power, and huge datasets, data-driven methods have recently gotten a lot of attention. Deep learning-based methods have also been applied in various ways to address low-dose CT reconstruction problem. However, the success of these methods is usually dependent on labeled data, which requires tedious work by radiologists for CT imaging. Recent studies, however, have also shown that training may be done successfully with noisy datasets without the requirement of noise-free target data. In this study, a training scheme is defined to use low-dose projections as their own training targets. We apply the self-supervision principle in the projection domain where the noise is element-wise independent, which is a requisite for self-supervised training methods. The parameters of a denoiser neural network are optimized through self-supervised training. Experiments are done with both analytical and human CT data. Slices from deep lesion dataset for human CT data and ellipses dataset for synthetic data are used. To simulate low-dose settings, 64 views parallel beam geometry is used. The noisy projections are created with additive white Gaussian noise with 30, 33, and 37 dB SNR values. The proposed method is compared with FBP, SART, SART+TV, SART+BM3D, and the supervised FBP+U-Net method. The methods are compared quantitatively with PSNR and SSIM metrics, and the reconstructions are qualitatively assessed regarding background smoothness, the sharpness of the details, and the recoverability of the lesions with some visual examples. In the comparisons, it is shown that the proposed method outperforms both traditional and compressed sensing-based iterative reconstruction methods in the reconstruction of analytic CT phantoms and real-world CT images in the low-dose CT reconstruction task, both qualitatively and quantitatively. Besides, it produces comparable results with the supervised approach.
  • Öge
    Skin lesion classification with machine learning
    (Graduate School, 2023) Sendel, Esra ; Yıldırım, İsa ; 783838 ; Biomedical Engineering Programme
    Skin lesions are the part of the skin that has an abnormal structure and appearance compared to the surrounding areas. While some skin lesions cause only a physically bad appearance, some may have cancer features. Nowadays, skin cancer is one of the most extensive cancers among humans. Therefore, the correct detection of cancerous lesions is of great importance in the treatment of skin cancer. Skin cancers are basically divided into two main types, melanoma which is dangerous, and non-melanoma. The low contrast between the lesioned and non-lesion areas in the images of melanoma skin cancers requires expertise in the application of diagnostic methods and involves relativity among dermatologists. In addition, it is very difficult to automatically analyze human skin due to geographical and climatic effects, roughness, tonal diversity, hair and many other complex structures, and low contrast problem. However, a successful automatic analysis system to be created will help dermatologists to diagnose and speed up the process. Technology advancements have made it possible for doctors to diagnose skin cancer from dermatoscopic images using computer-aided diagnosis techniques, such as deep learning and machine learning models. In this study, image processing and machine learning techniques were used to classify skin lesions. In image processing, different mathematical algorithms have been applied to increase image quality. After an image preprocessing stage, which includes filtering the unwanted pixels in the images, image segmentation was performed using the watershed method and the lesioned regions were separated. Then, based on the ABCDT rule, feature extraction was performed with the lesions, asymmetry, border irregularity, color, diameter, and texture analysis. Texture analysis was performed based on Haralick texture properties. Finally, classification was performed with softmax regression, k-nearest neighbor (KNN), and support vector machines (SVM) algorithm. Standard performance measures called accuracy, precision, recall, and F1-score values are used to evaluate the results of the methods used for classification. When the results obtained from the classifiers are compared, it has been observed that the accuracy of the SVM classifier is higher than the softmax regression and k-nearest neighbor (KNN) algorithm. Keywords: Skin lesion, skin cancer, image processing, ABCDT analysis, machine learning, support vector machine algorithm, softmax regression, k-nearest neighbor algorithm.
  • Öge
    1H-MRSI of the deep gray matter structures in patients with amyotrophic lateral sclerosis
    (Graduate School, 2024-08-19) Torlak, Meryem ; Yıldırım, İsa ; Işık Öztürk, Esin ; 504211408 ; Biomedical Engineering
    Amyotrophic Lateral Sclerosis (ALS) is a life-threatening disease that causes degeneration in nerve cells in the brain and spinal cord. In ALS patients, voluntary control of the arms and legs are affected. Currently, there is no cure for ALS. The primary goal of treatment is to manage symptoms to the greatest extent possible. Magnetic Resonance Spectroscopy (MRS) is employed to assess the concentration of metabolites in specific brain regions. This method has not been fully explored to understand the metabolic deficits in individuals diagnosed with ALS. It is crucial to understand the metabolic effects of ALS through various brain regions, particularly at the deep gray matter structures. 1H-MRSI data for 30 ALS patients, with a mean age of 57.8±9.55 years (17 females, 13 males) and 27 healthy controls, with a mean age of 48.44±10.5 years (16 females, 11 males) were acquired using a clinical 3T Siemens magnetic resonance imaging (MRI) scanner equipped with a multivoxel semi-LASER (sLASER) sequence (TR=1700ms, TE=40ms, VOI=10x10x15 mm3). In this study it is aimed to assess the metabolic differences between ALS patients and healthy controls (HC) at the thalamus, putamen, caudate and white matter regions. To achieve this, multivoxel magnetic resonance spectral data from ALS patients and HC were analyzed and metabolites Glx, GSH, tNAA, tCho, and Tau, as well as their ratio to tCr were quantified using LCModel. A Cramer-Rao lower bound (CRLB) threshold of less than 30 was employed to identify properly fitted metabolites. The metabolite peak ratios at the thalamus, putamen, caudate, and white matter regions were then compared between these two groups. A Wilcoxon signed-rank test was used to detect statistically significant differences in metabolite peak ratios between the left and right hemispheres at the thalamus, putamen, caudate, and white matter regions. The Mann-Whitney rank-sum test was used to evaluate metabolite peak ratio differences between ALS patients and healthy controls at some deep gray matter structures and white matter. MNI152 brain atlas was consulted to define the thalamus, putamen, and caudate regions. In conclusion, in this study, it was observed that ALS patients had a higher tCho/tCr ratio at the putamen compared to HC. Additionally, there was a trend for a lower Glx/tCr ratio at the left putamen of ALS patients compared to HC. ALS patients also showed a trend towards higher tCho/tCr and GSH/tCr ratios at the left caudate compared to HC. In ALS patients, higher Glx/tCr ratios were observed in the right thalamus and putamen compared to the left side. A trend towards a lower Glx/tCr ratio at the right caudate of ALS patients was observed compared to the left side. Additionally, ALS patients showed a lower tNAA/tCr ratio at the right caudate compared to the left side. In HC, higher Glx/tCr ratios were observed at the right thalamus compared to the left side. A trend towards higher tNAA/tCr and Glx/tCr ratios at the right putamen and right white of HC compared to the left sides were also observed. In this study, metabolic alterations were detected at the deep gray matter regions associated with executive function and behavior. Results of this study showed increased gliosis because of increased tCho/tCr ratio in ALS patients, a response to oxidative stress because of elevated GSH/tCr ratio in ALS patients, and deficiency in glutamate within these structures in individuals with ALS. The results of this study can contribute to a deeper understanding of ALS. Moreover, the findings obtained from this study suggest that MRS is a significant diagnostic and monitoring tool for neurodegenerative diseases such as ALS.
  • Öge
    Denetimsiz derin öğrenme kullanılarak dijital meme tomosentezi görüntülerinde gürültünün giderilmesi
    (Lisansüstü Eğitim Enstitüsü, 2023) Özcan, Osman Alpcan ; Yıldırım, İsa ; 833551 ; Biyomedikal Mühendisliği Bilim Dalı
    Meme kanseri, kadınlarda en yaygın kanser türüdür ve genellikle süt bezi dokusu hücrelerinin kontrolsüz ve aşırı çoğalması sonucu ortaya çıkar. Erken aşamada teşhis edilmezse ölümcül hale gelebilir. Erken aşama teşhisinde en çok tercih edilen görüntüleme yöntemi olan mamografi, 2 boyutlu (2D) bir görüntüleme yöntemidir. 2D yöntemler doğaları gereği bir projeksiyondan görüntü oluştururlar ve bu, dokuların üst üste binmesi nedeniyle yanlış pozitif ve yanlış negatif oranlarının artmasına yol açar; bu oranın artması da ölüm oranlarını artırır. Bu durumu önlemek için 3D görüntüleme yöntemleri önerilmiş ve kullanımları artmıştır. Dijital meme tomosentezi (DBT), 3 boyutlu (3D) bir görüntüleme yöntemi olarak tercih edilir. DBT, sınırlı açılarda alınan projeksiyonlarla birlikte 3D bir görüntü oluşturur ve düşük radyasyon dozlarıyla çalışır. 2D görüntülemede oluşan dokuların üst üste binmesi sorunu aşılmış ve böylece dokular daha ayırt edilebilir hale gelmiş ve radyologların erken teşhis oranları artmıştır. Ancak, DBT görüntülerinde sınırlı açı ve düşük radyasyon dozu nedeniyle her projeksiyonun gürültü içereceği ve gürültünün rekonstrüksiyon görüntüsünde artmış şekilde görüneceği kaçınılmazdır. Gürültü giderimi için birçok matematiksel yöntem önerilmiş ve belirli bir ölçüde başarılı oldukları gözlemlenmiştir, ancak hala tatmin edici bir performans sağlama konusunda eksiklikleri vardır. Yapay zekâ ve derin öğrenme ağlarının gelişimi ve yaygınlaşmasıyla birlikte, tıbbi görüntü işleme alanında kullanımı da artmıştır. Bu bağlamda, derin öğrenme ağları, tıbbi görüntülerde bir gürültü giderici olarak mekânsal düzenleyicilere alternatif olarak önerilmiştir. Bu çalışmada, bir denetimsiz gürültü giderici sinir ağı, DBT görüntüleri üzerinden gürültüleri ortadan kaldırmak için geliştirilmiştir. Önerilen yöntemin performansını analiz etmek için iki farklı veri seti kullanılmıştır. İlk veri seti kanser görüntü arşivinden BSC-DBT (Meme Kanseri Taraması- Dijital Meme Tomosentezi) veri setidir. Bu veri seti, normal, aksiyon alınması gereken, biyopsi ile kanıtlanmış iyi huylu ve biyopsi ile kanıtlanmış kanser olarak etiketlenmiş 5060 hasta içermektedir. Görüntüler dilimler halinde 2 boyutlu olarak kullanılmıştır. Her kategoriden eşit ve toplam verilerin %70 eğitim verisi, %15 validasyon verisi ve %15 test verisi olacak şekilde belirlenmiştir. Bu veri setine ek olarak DBT-2D Phantom veri seti kullanılmıştır. Toplamda 2148 veri ve yine görüntüler iki boyutlu dilim görüntüsü olacak şekilde veri setinin %70'i eğitim verisi %15'i validasyon verisi ve %15 test verisi olarak organize edilmiştir. Düşük doz ve dar açı kaynaklı en belirgin gürültü şekilleri Gaussian ve Poisson gürültüleri olması sebebiyle gürültü giderici hedefi bu iki gürültü olarak belirlenmiş ve eğitim parametreleri bu gürültülerin giderilmesi üzerine belirlenerek eğitim tamamlanmıştır. Önerilen modelin başarısını değerlendirmek için CNR (kontrast-gürültü oranı), PSNR (zirve sinyal gürültü oranı) ve SSIM (yapısal benzerlik indeksi) metrikleri kullanılmıştır. Çalışma sırasında matematiksel yöntemler ile önerilen modelin başarısı metrikler üzerinde kıyaslanmış ve çalışmanın sonucunda önerilen denetimsiz gürültü giderici ağ ile belirlenen metriklerdeki iyileşmenin daha üstün olduğu gözlemlenmiştir. Görüntülerdeki niteliksel iyileşme, önerilen modelinin oldukça umut verici olduğunu göstermektedir.
  • Öge
    Segmentation of breast microwave imaging using fuzzy c-mean clustering
    (Graduate School, 2023) Mamizadeh, Asal ; Akduman, İbrahim ; 847155 ; Biomedical Engineering Programme
    Breast cancer is the uncontrolled growth of breast cells, which grows mainly in fatty tissue and lobules. It could also spread over the blood or lymph system to other organs, causing virulent metastasis. In 2020, Female Breast cancer was the most frequently diagnosed cancer with 2.3 million cases, based on World Health Organization's (WHO) reports. According to statistics, 684 996 deaths from the disease were recorded in the same year. The most effective way to control the spread of breast cancer and reduce the number of deaths is early detection and treatment through clinical evaluation. There are several imaging techniques for screening female breast tissue abnormalities and cancer, such as Magnetic Resonance Imaging (MRI), Ultrasonography, Positron Emission Tomography (PET), and Mammography. Currently, mammography is considered to be the gold standard methodology in order to screen breast cancer. However, in accordance with the mammography restrictions, such as high radiation dose and low sensitivity in dense breasts, the mentioned method is not remarkably efficient. For this purpose, other screening methods are necessary to eliminate these restrictions. Microwave imaging (MWI) is a new modality that could potentially become a supplementary method, to already existing ones, to contribute the breast cancer diagnosis at an early stage, due to using non-ionizing radiation, safe and inexpensive technology. MWI is based on differences between the dielectric properties of cancerous and normal breast tissue. Moreover, lesion segmentation is essential for diagnosing breast cancer. To do this, specialists examine the images manually, which may lead to misdiagnosis due to human visual perception error. Also, in some cases, this process can be time-consuming. In order to solve these problems, automated segmentation methods have been utilized to reduce these errors. Clustering algorithms or unsupervised machine learning techniques could be employed to segment images to minimize human involvement in segmentation and achieve a precise detection of the cancerous lesion. In this thesis, a segmentation method is suggested to extract lesions from low-resolution MWI images with the help of the Fuzzy C-mean algorithm and statistical features. Microwave images used in the thesis were taken from a clinical study. The study's codes are all implemented in MATLAB. To evaluate the effectiveness of texture features of MWI for segmentation by FCM algorithm, three statistical features in the spatial domain i.e., intensity, entropy, and energy were used to form the feature vector. Two series of experiments were performed on the data. The first experiment included a combination of features consisting of intensity, energy, and entropy matrix of each image were form. Energy and entropy matrices were calculated for each image and combined with intensity matrices and applied to FCM. No difference was observed regarding the effect of entropy and energy matrices in segmentation with only intensity features. In the second experiment, only different combinations of intensity (i.e. color features) of the images were used. Three feature matrices were formed using red, green, and blue planes of each image, in RGB color space. A three-dimensional matrix using RGB planes, a matrix using the mean of RGB planes, and at the end, only red plane as feature matrix, were formed and applied on FCM algorithm as the first trial, separately for each image. The segmented images compare to ground truth images. The experimental results demonstrate that the segmentation method using only the red plane, to segment the dark red region of the image, which represents the highest values of dielectric activity of the tumor, outperforms the other two methods in the case of most overlapping with the ground-truth image. Also, in respect of specificity, this method has performed better compared to multi-channel methods. However, in terms of sensitivity, the red single-channel method does not provide the expected reliable results. Finally, the achieved size of the segmented tumor in each trial was compared with the size of the tumor in conventional imaging measured by a specialist. In certain sizes, there are acceptable achievements, but for satisfying results, existing algorithms need more improvements.