Fovea and diabetic retinopathy: Understanding the relationship using a deep interpretable classifier

Listyalina, Latifah; Utari, Evrita Lusiana; Puspaningtyas, Desty Ervira

doi:10.1016/j.cmpbup.2022.100059

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Selanjutnya, citra hasil akuisisi telah dibagi menjadi dua set, yaitu set pelatihan dan pengujian [8] [9]. Set pelatihan berisikan citra ban yang telah digunakan pada tahap pelatihan beberapa arsitektur convolutional neural network agar mampu dan mengklasifikasikannya ke tingkat kelayakan yang sesuai.…”

Section: Metodeunclassified

Identifikasi Kelayakan Karet Ban Dengan Model CNN Resnet-50

Listyalina

2022

bptkspk

View full text Add to dashboard Cite

In this study, the authors designed an algorithm based on a convolutional neural network that is capable of automatically classifying tire rubber eligibility according to the appearance of the tire on the tire image. The proposed algorithm will be built through several stages as follows. In the first stage, tire image acquisition will be carried out which will be the input of the designed algorithm. Furthermore, the acquired image will be divided into two sets, namely training and testing sets. The training set contains tire images that will be used at the training stage of several convolutional neural network architectures to be able to and classify them to the appropriate level of feasibility. The training phase will be carried out in a number of epohs, and at each epoh, the cross entropy loss function value will be calculated which expresses the performance of the convolutional neural network architecture in classifying tire images. In this study, the author has designed an algorithm based on deep learning that is capable of automatically classifying tire eligibility. The proposed algorithm has been built through several stages such as tire image acquisition, training of several CNN models, especially ResNet-50. The CNN architecture test is trained to classify tire images from the test set. In addition, the accuracy value has also been calculated which shows the percentage of the number of tire images that are successfully classified correctly to the total number of tire images in the test set, which is an accuracy of 88.31%.

show abstract

Section: Metodeunclassified

Identifikasi Kelayakan Karet Ban Dengan Model CNN Resnet-50

Listyalina

2022

bptkspk

View full text Add to dashboard Cite

show abstract

“…Pencitraan medis juga dapat didefinisikan dengan serangkaian teknik yang secara noninvasif dan menghasilkan gambar dari aspek internal tubuh. Pencitraan medis menggunsksn teknologi pencitraan radiografi Sinar-X, pencitraan resonansi magnetik, ultrasonografi medis, endoskopi, dan teknik pencitraan fungsional kedokteran nuklir sebagai PET (Positron Emission Tomography) dan SPECT (Single Photon Emission Tomography) [9].…”

Section: Iunclassified

Sistem Identifikasi Citra Rontgen Paru Menggunakan Filter Median Filter Maksimum-Minimum Dan Filter Rerata

Utari

Munir

Mustiadi

et al. 2022

SINTaKS

View full text Add to dashboard Cite

Citra merupakan sinyal dua dimensi yang dapat diamati menggunakan sistem visual manusia. Pencitraan medismerupakan citra yang mengandung informasi medis seperti representasivisual dari tubuh pasien. Terdapat kendala yang dapat ditemukan dalampengolahan citra medis salah satunya yaitu terdapatnya noise/ derau padacitra. Derau dapat disebabkan karena posisi saat pengambilan citra,gangguan fisik dari alat penangkap citra atau saat proses digitalisasi padacitra. Derau ini dapat diminimalisir dengan melakukan proses filteringpada citra. Sebelum melakukan proses filtering, citra diolah pada tahappre-processing. Tahapan pre-processing terdiri dari tahap cropping citradan reesize citra. Setelah tahap ini selesai, kemudian citra disisipkan derau,setelah itu mengalami proses filtering. Pada penelitian ini digunakansembilan citra dengan tiga kondisi paru-paru yang berbeda. Kondisitersebut berupa paru normal, kanker paru dan paru efusi. Tahap preprocessing melewati proses cropping dan resize 50% dari ukuran citraawal. Derau yang digunakan berjenis Gaussian dengan perbandinganempat jenis filter berupa filter median, filter maksimum, filter minimumdan filter rerata. Kinerja filter terbaik mengacu pada nilai error terkecildengan perhitungan menggunakan metode MSE (Mean Square Error).Filter median dengan nilai error terkecil 162.418, filter maksimum dengannilai error terkecil 2,260, filter minimum dengan nilai error terkecil 3,880dan filter rerata dengan nilai error terkecil yaitu 199.438.

show abstract

Deep learning of fundus images and optical coherence tomography images for ocular disease detection – a review

Narayanan

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Fovea and diabetic retinopathy: Understanding the relationship using a deep interpretable classifier

Cited by 3 publications

References 22 publications

Identifikasi Kelayakan Karet Ban Dengan Model CNN Resnet-50

Identifikasi Kelayakan Karet Ban Dengan Model CNN Resnet-50

Sistem Identifikasi Citra Rontgen Paru Menggunakan Filter Median Filter Maksimum-Minimum Dan Filter Rerata

Deep learning of fundus images and optical coherence tomography images for ocular disease detection – a review

Contact Info

Product

Resources

About