Page 55 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

Journal Conference Conference Journal Journal Journal Journal Journal Conference Continued

[88] [89] [90] [91] [92] [93] [94] [95] [96]
consisted retinopathy 9653 11,347 the and used eye, per images which used, images set data patient's the on (BCDR) randomly taken taken was

used of and DRIVE was color image 1748 was 850 cancer film 736 available was archive, Center, segmented was set

was images diabetic consisted the that retinal diabetes, set BI-RADS benchmarking of Repository MRIs Medical views data purpose
that a images were set digital fovea-centered data approximately of breast total was scientific Netherlands manually INbreast
set fundus from initiative retinal used data the with terms 344 a that Digital breast the University 40 oblique
data patient acquired images sets Messidor-2 of one subjects hospital of in biopsy-proven from containing Cancer 66 of from The with available experimental

DRISHTI-GS 50 of set Data screening ungradable gradable data Two STARE The consisted images, 874 of Multicenter consisted distributed new A built was cases mammography Breast set data A selected Radboud Nijmegen, set data A mediolateral Publicly the for

fundus imaging image image retinal images Mammography Mammography Mammography Mammography

Color Retinal Fundus Digital color MRI

Ensemble-based CNN five with CNN convolution named layers CNN5 as FCNN CNN Faster-R-CNN and CNN2 CNN3 U-Net CNN

optic as of of and of of framework
automated well as assessment segmentation diabetic classification breast diagnosis representation segmentation tissue a into tissues breast malignant

the glaucoma the quality improved of in the for for fibroglandular create coherent classify or
for segmentation for for vessel for detection for tumors using framework to classification to benign
designed disc of developed image developed retinal designed automated retinopathy designed of mammograms developed cancer developed and designed region semantically designed as

Model cup, detection Model retinal Model the Model System detection System breast learning System breast System for Model masses

2016

Breast