A comprehensive review on various preprocessing methods in detecting diabetic retinopathy

Ramasubramanian, B.; Selvaperumal, S.

doi:10.1109/iccsp.2016.7754220

Cited by 16 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Selain preprocessing tersebut terdapat preprocessing yang ditawarkan oleh Nakhon Ratchasima [26], yang merupakan notebook preprocessing dengan vote terbanyak pada Kaggle kompetisi dengan judul "APTOS 2019 Blindness Detection". Ramasubramanian [27] [25], Nakhon [26], Ramasubramanian [27], dan enhanced green. Hubungan preprocessing yang satu dengan yang lain dapat dilihat pada Gambar 7.…”

Section: Label Label One Hotunclassified

“…Gambar 11 menunjukan citra input dan citra output dari preprocessing Nakhon. Bisa dilihat pada citra output, bentuk retina dipotong dengan melingkar sempurna dan memiliki "boundary effect" Preprocessing Ramasubramanian Ramasubramanian dan Selvaperumal [27] mengusulkan teknik preprocessing dengan mengambil green channel dari citra RGB karena green channel memiliki informasi paling banyak dan menunjukkan diskriminasi antara gejala klinis dengan warna latar belakang. Mula-mula citra diambil channel hijau saja lalu margin hitam dipotong.…”

Section: Preprocessing Nakhonunclassified

“…CLAHE membagi citra input ke dalam beberapa wilayah kontekstual dengan kernel berukuran 8 × 8 lalu histogram equalization diterapkan pada wilayah tersebut. Menurut Ramasubramanian [27], CLAHE menonjolkan fitur tersembunyi seperti exudates, microaneurysms, fovea, blood vessel.…”

Section: Gambar 12 Preprocessing Ramasubramanian Dan Selvaperumalunclassified

“…dilanjutkan dengan empat preprocessing terpisah, yaitu preprocessing Ben Graham[25], Nakhon[26], Ramasubramanian[27], dan enhanced green.Setelah preprocessing, dilakukan training model dengan menggunakan teknik deep learning CNN.…”

unclassified

See 3 more Smart Citations

Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network

Widyaya

Budi

2021

JuTISI

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is eye diseases caused by diabetic mellitus or sugar diseases. If DR is detected in early stage, the blindness that follow can be prevented. Ophthalmologist or eye clinician usually decide the stage of DR from retinal fundus images. Careful examination of retinal fundus images is time consuming task and require experienced clinicians or ophthalmologist but a computer which has been trained to recognize the DR stages can diagnose and give result in real-time manner. One approach of algorithm to train a computer to recognize an image is deep learning Convolutional Neural Network (CNN). CNN allows a computer to learn the features of an image, in our case is retinal fundus image, automatically. Preprocessing is usually done before a CNN model is trained. In this study, four preprocessing were carried out. Of the four preprocessing tested, preprocessing with CLAHE and unsharp masking on the green channel of the retinal fundus image give the best results with an accuracy of 79.79%, 82.97% precision, 74.64% recall, and 95.81% AUC. The CNN architecture used is Inception v3.

show abstract