doi:10.1007/s12559-021-09880-3

Details

Publication Date

Wed Jun 16 2021

Journal Name

Cognitive Computation

Volume

14

DOI

10.1007/s12559-021-09880-3

Choose Citation Style

Statistics

View publication

1

View original publication

1

Statistics

(23)

(20)

Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps

Ali H.

Nebras H.

Zahraa M.

Javier

...Show More Authors

Abstract Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.

View Publication

Publication Date

Tue Jan 18 2022

Journal Name

Materials Science Forum

The Effect of Gamma Radiation on the Manufactured HgBa2Ca2Cu2.4Ag0.6O8+δ Compound

Gamma doses radiation

crystal size

strain

degree of crystallinity

Scherrer

crystallinity and Williamson equations.

zainab j

Balqees A.

Mohammed A.

Kareem A.

Auday H.

...Show More Authors

In this article four samples of HgBa₂Ca₂Cu_2.4Ag_0.6O_8+δ were prepared and irradiated with different doses of gamma radiation 6, 8 and 10 Mrad. The effects of gamma irradiation on structure of HgBa₂Ca₂Cu_2.4Ag_0.6O_8+δ samples were characterized using X-ray diffraction. It was concluded that there effect on structure by gamma irradiation. Scherrer, crystallization, and Williamson equations were applied based on the X-ray diffraction diagram and for all gamma doses, to calculate crystal size, strain, and degree of crystallinity. I

View Publication

(2)

1 2 3 4 ... 3045 3046 3047 3048