Multi-Region Detection of eye Conjunctiva Images Using DNCNN and YOLOv8 Algorithms

Emine Cengil

Makale detayları

Multi-Region Detection of eye Conjunctiva Images Using DNCNN and YOLOv8 Algorithms

Yazarlar:

Emine Cengil

Yayıncı:

Bitlis Eren University

Ana Başlıklar:

Artificial Intelligence (Other)

Dergi:

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 4, pp.1181-1193

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001336491

pISSN:

2147-3129

Anahtar kelimeler:

Özet:

 Artificial intelligence is encountered in many areas today. It makes our lives easier with its use in our daily lives. With the advancement of medical big data and artificial intelligence, eye images have begun to be used in the detection of endocrine, cardiovascular, neurological, renal, hematological and many other diseases. It is possible to find more connections between systemic disorders and eye disorders and apply them to increase the effectiveness of artificial intelligence. The eye is an anatomically complex organ. Detection of the conjunctiva regions of the eye generally plays an important role in the diagnosis of eye diseases and applications related to eye health. The conjunctiva is a thin membrane tissue that covers the inner surface of the eyelids and the white part of the eye. Detection and analysis of this region is used in the examination of inflammation, redness, dryness and other disorders in the eye. The relevant regions were found using conjunctiva images in the study. Conjunctiva region detection Images were taken from a public database and enhanced with the image enhancement method DNCNN. The YOLO algorithm is applied to raw images and DNCNN enhanced images separately using the same parameters. As a result, the effect of the deep learning based method on finding the truth in images is presented with F1-confidence curve, precision-confidence curve, recall-confidence curve, precision-recall curve and confusion matrix metrics. In the proposed method, the mAP value is given as 0.984 in all classes.

 Artificial intelligence is encountered in many areas today. It makes our lives easier with its use in our daily lives. With the advancement of medical big data and artificial intelligence, eye images have begun to be used in the detection of endocrine, cardiovascular, neurological, renal, hematological and many other diseases. It is possible to find more connections between systemic disorders and eye disorders and apply them to increase the effectiveness of artificial intelligence. The eye is an anatomically complex organ. Detection of the conjunctiva regions of the eye generally plays an important role in the diagnosis of eye diseases and applications related to eye health. The conjunctiva is a thin membrane tissue that covers the inner surface of the eyelids and the white part of the eye. Detection and analysis of this region is used in the examination of inflammation, redness, dryness and other disorders in the eye. The relevant regions were found using conjunctiva images in the study. Conjunctiva region detection Images were taken from a public database and enhanced with the image enhancement method DNCNN. The YOLO algorithm is applied to raw images and DNCNN enhanced images separately using the same parameters. As a result, the effect of the deep learning based method on finding the truth in images is presented with F1-confidence curve, precision-confidence curve, recall-confidence curve, precision-recall curve and confusion matrix metrics. In the proposed method, the mAP value is given as 0.984 in all classes.

 Artificial intelligence is encountered in many areas today. It makes our lives easier with its use in our daily lives. With the advancement of medical big data and artificial intelligence, eye images have begun to be used in the detection of endocrine, cardiovascular, neurological, renal, hematological and many other diseases. It is possible to find more connections between systemic disorders and eye disorders and apply them to increase the effectiveness of artificial intelligence. The eye is an anatomically complex organ. Detection of the conjunctiva regions of the eye generally plays an important role in the diagnosis of eye diseases and applications related to eye health. The conjunctiva is a thin membrane tissue that covers the inner surface of the eyelids and the white part of the eye. Detection and analysis of this region is used in the examination of inflammation, redness, dryness and other disorders in the eye. The relevant regions were found using conjunctiva images in the study. Conjunctiva region detection Images were taken from a public database and enhanced with the image enhancement method DNCNN. The YOLO algorithm is applied to raw images and DNCNN enhanced images separately using the same parameters. As a result, the effect of the deep learning based method on finding the truth in images is presented with F1-confidence curve, precision-confidence curve, recall-confidence curve, precision-recall curve and confusion matrix metrics. In the proposed method, the mAP value is given as 0.984 in all classes.

 Artificial intelligence is encountered in many areas today. It makes our lives easier with its use in our daily lives. With the advancement of medical big data and artificial intelligence, eye images have begun to be used in the detection of endocrine, cardiovascular, neurological, renal, hematological and many other diseases. It is possible to find more connections between systemic disorders and eye disorders and apply them to increase the effectiveness of artificial intelligence. The eye is an anatomically complex organ. Detection of the conjunctiva regions of the eye generally plays an important role in the diagnosis of eye diseases and applications related to eye health. The conjunctiva is a thin membrane tissue that covers the inner surface of the eyelids and the white part of the eye. Detection and analysis of this region is used in the examination of inflammation, redness, dryness and other disorders in the eye. The relevant regions were found using conjunctiva images in the study. Conjunctiva region detection Images were taken from a public database and enhanced with the image enhancement method DNCNN. The YOLO algorithm is applied to raw images and DNCNN enhanced images separately using the same parameters. As a result, the effect of the deep learning based method on finding the truth in images is presented with F1-confidence curve, precision-confidence curve, recall-confidence curve, precision-recall curve and confusion matrix metrics. In the proposed method, the mAP value is given as 0.984 in all classes.

Makale detayları

Multi-Region Detection of eye Conjunctiva Images Using DNCNN and YOLOv8 Algorithms

Yazarlar:

Emine Cengil

Yayıncı:

Bitlis Eren University

Ana Başlıklar:

Artificial Intelligence (Other)

Dergi:

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 4, pp.1181-1193

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001336491

pISSN:

2147-3129

Convolutional Neural Network (CNN)

Artificial Intelligence

YOLOv8

Image Enhancement

Object Detection

Sayı

Makale detayları

Multi-Region Detection of eye Conjunctiva Images Using DNCNN and YOLOv8 Algorithms

Yazarlar: Emine Cengil

Yayıncı: Bitlis Eren University

Ana Başlıklar: Artificial Intelligence (Other)

Dergi: Bitlis Eren Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 4, pp.1181-1193

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001336491

pISSN: 2147-3129

Convolutional Neural Network (CNN)

Artificial Intelligence

YOLOv8

Image Enhancement

Object Detection

Sayı

Yazarlar:

Emine Cengil

Yayıncı:

Bitlis Eren University

Ana Başlıklar:

Artificial Intelligence (Other)

Dergi:

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi Vol.13 Issue 4, pp.1181-1193

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001336491

pISSN:

2147-3129