|
|
Illness Detection in Eye Retina Image
Aubrecht, Tomáš ; Drahanský, Martin (referee) ; Semerád, Lukáš (advisor)
Age-related macular degeneration is one of the most common retinal diseases of the human eye that leads at different rates to blindness. This disease occurs in two forms. While the wet can slow down its progression, for dry form there is no available treatment method so far, so prevention is the most important. For this reason, the aim of this work is to design and implement software that allows automatic detection of the symptoms of this disease from retinal images. The symptom detection algorithm is based on adaptive thresholding which obtains suspicious areas that are subsequently categorized. 407 retinal images were used for the evaluation and the software was highly successful. When used in conjunction with an optical retinal scanner, it helps ophthalmologists, for example, to diagnose more quickly.
|
|
|
Detection of Diseases of Diabetes on the Human Eye Retina
Sýkorová, Tereza ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This bachelor's thesis deals with the detection of the symptoms of diabetic retinopathy at retinal images taken by a digital fundus camera. Optic disc, fovea, and blood vessels are found before searching for exudates and hemorrhages. This step improves final detection. The detector uses morphological reconstruction of a candidate region for determination of specific lesions. An algorithm based on thresholding precises its edges. Found regions are classified according to shape and color. Evaluation of detection was done using 120 images selected from three databases. Adding automatic detection of signs of diabetic retinopathy into equipment for retinal screening can help medical doctors in diagnosis and prevent possible vision loss which the disease can cause.
|
|
|
Reconstruction of Extracted Bloodstream in Images of Retinas
Kozel, Vojtěch ; Drahanský, Martin (referee) ; Semerád, Lukáš (advisor)
Retinal bloodstream plays a significant role in many specializations. In medicine, retinal images are used for automatic disease diagnosis. The blood vessel tree is unique for each individual, and as such this feature is often used in biometric systems for person-recognition. Healthy individuals possess consistent retinas throughout their life, however, there are many reasons why retinal changes may occur. The most common reason for physical changes is disease. In such cases problems arise in automated processing of retina images. These problems may also lie with retinal scans errors or blood vessel extraction algorithm error. This thesis describes reasons why segmented blood vessels are interrupted. Main goal of this thesis is to create a program which can automatically locate interrupted vessel segments and reconstruct them. The program is implemented in Java with OpenCV library.
|
|
|
Detection and Recognition of ARMD Disease Impacts to the Human Eye Retina
Stančíková, Ivana ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This thesis aims to create a software able to detect symptoms of age-related macular degeneration in images of human eye retina. This condition is considered one of the leading causes of vision loss in older adults. Lesions of the macular area called drusen are the first and also the most distinctive sign of developing ARMD. The approach presented in this thesis utilizes methods of image processing and computer vision to recognize retinal structures, in particular the optical disk and blood vessels, and distinguish between these structures and actual symptoms of the disease. The evaluation of the program's success rate was performed on 692 images originating from four databases. The resulting solution has the potential to assist medical professionals with earlier diagnosis of the disease and thus contribute to prevention of severe vision loss.
|
|
|
Reconstruction of Extracted Bloodstream in Images of Retinas
Kozel, Vojtěch ; Drahanský, Martin (referee) ; Semerád, Lukáš (advisor)
Retinal bloodstream plays a significant role in many specializations. In medicine, retinal images are used for automatic disease diagnosis. The blood vessel tree is unique for each individual, and as such this feature is often used in biometric systems for person-recognition. Healthy individuals possess consistent retinas throughout their life, however, there are many reasons why retinal changes may occur. The most common reason for physical changes is disease. In such cases problems arise in automated processing of retina images. These problems may also lie with retinal scans errors or blood vessel extraction algorithm error. This thesis describes reasons why segmented blood vessels are interrupted. Main goal of this thesis is to create a program which can automatically locate interrupted vessel segments and reconstruct them. The program is implemented in Java with OpenCV library.
|
|
|
Detection and Recognition of ARMD Disease Impacts to the Human Eye Retina
Stančíková, Ivana ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This thesis aims to create a software able to detect symptoms of age-related macular degeneration in images of human eye retina. This condition is considered one of the leading causes of vision loss in older adults. Lesions of the macular area called drusen are the first and also the most distinctive sign of developing ARMD. The approach presented in this thesis utilizes methods of image processing and computer vision to recognize retinal structures, in particular the optical disk and blood vessels, and distinguish between these structures and actual symptoms of the disease. The evaluation of the program's success rate was performed on 692 images originating from four databases. The resulting solution has the potential to assist medical professionals with earlier diagnosis of the disease and thus contribute to prevention of severe vision loss.
|
|
|
Detection of Diseases of Diabetes on the Human Eye Retina
Sýkorová, Tereza ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
This bachelor's thesis deals with the detection of the symptoms of diabetic retinopathy at retinal images taken by a digital fundus camera. Optic disc, fovea, and blood vessels are found before searching for exudates and hemorrhages. This step improves final detection. The detector uses morphological reconstruction of a candidate region for determination of specific lesions. An algorithm based on thresholding precises its edges. Found regions are classified according to shape and color. Evaluation of detection was done using 120 images selected from three databases. Adding automatic detection of signs of diabetic retinopathy into equipment for retinal screening can help medical doctors in diagnosis and prevent possible vision loss which the disease can cause.
|
|
|
Illness Detection in Eye Retina Image
Aubrecht, Tomáš ; Drahanský, Martin (referee) ; Semerád, Lukáš (advisor)
Age-related macular degeneration is one of the most common retinal diseases of the human eye that leads at different rates to blindness. This disease occurs in two forms. While the wet can slow down its progression, for dry form there is no available treatment method so far, so prevention is the most important. For this reason, the aim of this work is to design and implement software that allows automatic detection of the symptoms of this disease from retinal images. The symptom detection algorithm is based on adaptive thresholding which obtains suspicious areas that are subsequently categorized. 407 retinal images were used for the evaluation and the software was highly successful. When used in conjunction with an optical retinal scanner, it helps ophthalmologists, for example, to diagnose more quickly.
|
guest ::
