Tamoor Aziz

Thammasat University, School of Information, Computer and Communication, Graduate Student

Followers

Following

Public Views

I am a Ph.D. graduate of Thammasat University, Thailand. I have artificial intelligence-based research experience in biomedical engineering and computational medicine. My research area includes object detection, fuzzy logic, feature extraction, segmentation, classification, machine learning, and deep learning in image processing and computer vision.

less

Benny Zee

The Chinese University of Hong Kong

Dolly Das

Assam Don Bosco University

seema Hanchate

SNDT Women's University

Goa University

King AbdulAziz University (KAU) Jeddah, Saudi Arabia

Tiwalade Usman

Augustine Nsang

SOMASUNDARAM S K

Uploads

Papers by Tamoor Aziz

Deep learning-based hemorrhage detection for diabetic retinopathy screening

Scientific Reports, Jan 27, 2023

Diabetic retinopathy is a retinal compilation that causes visual impairment. Hemorrhage is one of... more Diabetic retinopathy is a retinal compilation that causes visual impairment. Hemorrhage is one of the pathological symptoms of diabetic retinopathy that emerges during disease development. Therefore, hemorrhage detection reveals the presence of diabetic retinopathy in the early phase. Diagnosing the disease in its initial stage is crucial to adopt proper treatment so the repercussions can be prevented. The automatic deep learning-based hemorrhage detection method is proposed that can be used as the second interpreter for ophthalmologists to reduce the time and complexity of conventional screening methods. The quality of the images was enhanced, and the prospective hemorrhage locations were estimated in the preprocessing stage. Modified gamma correction adaptively illuminates fundus images by using gradient information to address the nonuniform brightness levels of images. The algorithm estimated the locations of potential candidates by using a Gaussian match filter, entropy thresholding, and mathematical morphology. The required objects were segmented using the regional diversity at estimated locations. The novel hemorrhage network is propounded for hemorrhage classification and compared with the renowned deep models. Two datasets benchmarked the model's performance using sensitivity, specificity, precision, and accuracy metrics. Despite being the shallowest network, the proposed network marked competitive results than LeNet-5, AlexNet, ResNet50, and VGG-16. The hemorrhage network was assessed using training time and classification accuracy through synthetic experimentation. Results showed promising accuracy in the classification stage while significantly reducing training time. The research concluded that increasing deep network layers does not guarantee good results but rather increases training time. The suitable architecture of a deep model and its appropriate parameters are critical for obtaining excellent outcomes. The International Diabetes Federation (IDF) estimated that 700 million people will be living with Diabetes mellitus (DM) by 2045 1. DM develops fat and cholesterol in blood vessels that obstruct the flow of blood and nutrients required by human organs. The physiologic autoregulatory response to this progression increases the intracranial pressure of blood vessels 2-This change in the retina yields rupture of small arteries that compiles Diabetic retinopathy (DR). DR is a retinal compilation that damages blood vessels, and DM is one of the causes of its development. DR cannot be cured permanently, but its progression rate can be reduced significantly by effective control of serum glucose, blood pressure and timely treatment. DR is broadly categorized into non-proliferative diabetic retinopathy (NPDR) and proliferative diabetic retinopathy (PDR). NPDR is classified by visible pathological features like microaneurysms (MAs), hemorrhages (HEs), exudates, and microvascular abnormalities. In comparison, PDR is diagnosed by the emergence of new blood vessels called neovascularization 3. Figure 1 depicts two stages of DR. MAs and HEs are grouped into red lesions. MAs are the earliest clinically manifest of DR and appear as small circular red dots in fundus images. Causes of MAs development are endothelial cell dysfunction, hypercoagulability, and atherosclerosis 4. When MAs are weakened enough to rupture and swell, they rise to HEs. These dot-HEs are indistinguishable from MAs. HEs are disastrous for eyesight, predominantly when emerging in the macular region. Therefore, they often lead to significant and perpetual ocular impairment 5. Fluorescein angiography (FA), optical coherence tomography (OCT), and ophthalmoscopy are eminent methods of DR diagnosis. FA is a standard gold method and is capable of assessing microvascular changes. It helps to determine the origin of the leakage. Conversely, FA is time-consuming, invasive, and requires injection of intravenous fluorescein dye that may cause adverse side effects 6. OCT is advanced for microvascular evaluation and captures a cross-section of the retina. OCT is non-invasive and does not require fluorescent dye injection.

Download

Comparing Conventional and Deep Feature Models for Classifying Fundus Photography of Hemorrhages

Journal of Healthcare Engineering

Diabetic retinopathy is an eye-related pathology creating abnormalities and causing visual impair... more Diabetic retinopathy is an eye-related pathology creating abnormalities and causing visual impairment, proper treatment of which requires identifying irregularities. This research uses a hemorrhage detection method and compares the classification of conventional and deep features. Especially, the method identifies hemorrhage connected with blood vessels or residing at the retinal border and was reported challenging. Initially, adaptive brightness adjustment and contrast enhancement rectify degraded images. Prospective locations of hemorrhages are estimated by a Gaussian matched filter, entropy thresholding, and morphological operation. Hemorrhages are segmented by a novel technique based on the regional variance of intensities. Features are then extracted by conventional methods and deep models for training support vector machines and the results are evaluated. Evaluation metrics for each model are promising, but findings suggest that comparatively, deep models are more effective th...

Download

Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features

Applied Sciences, 2021

Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumul... more Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in retinal fundus images. The proposed method first performs preprocessing on retinal fundus images. Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally, conventional and hand-crafted features are extracted from each candidate and classified by a support vector machine. Two datasets are used to evaluate the algorithms. Precision rate (P), recall rate (R), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error, peak signal to n...

Download

Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features

Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumul... more Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated
accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may
obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities
linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting
retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in
retinal fundus images. The proposed method first performs preprocessing on retinal fundus images.
Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally,
conventional and hand-crafted features are extracted from each candidate and classified by a support
vector machine. Two datasets are used to evaluate the algorithms. Precision rate (P), recall rate
(R), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error,
peak signal to noise ratio, information entropy, and contrast are also used to evaluate preprocessing
method. The proposed method achieves a high F1 score with 83.85% for the DIARETDB1 image
dataset and 72.25% for the DIARETDB0 image dataset. The proposed algorithm adequately adapts
when compared with conventional algorithms, hence will act as a tool for segmentation.

Download

Deep learning-based hemorrhage detection for diabetic retinopathy screening

Scientific Reports, Jan 27, 2023

Download

Comparing Conventional and Deep Feature Models for Classifying Fundus Photography of Hemorrhages

Journal of Healthcare Engineering

Download

Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features

Applied Sciences, 2021

Download

Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features

Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumul... more Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated
accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may
obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities
linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting
retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in
retinal fundus images. The proposed method first performs preprocessing on retinal fundus images.
Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally,
conventional and hand-crafted features are extracted from each candidate and classified by a support
vector machine. Two datasets are used to evaluate the algorithms. Precision rate (P), recall rate
(R), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error,
peak signal to noise ratio, information entropy, and contrast are also used to evaluate preprocessing
method. The proposed method achieves a high F1 score with 83.85% for the DIARETDB1 image
dataset and 72.25% for the DIARETDB0 image dataset. The proposed algorithm adequately adapts
when compared with conventional algorithms, hence will act as a tool for segmentation.

Download

Tamoor Aziz

Uploads

Papers by Tamoor Aziz

Log In