Multi-level Quality Assessment of Retinal Fundus Images using Deep Convolution Neural Networks

Muddamsetty, Satya M.; Moeslund, Thomas B.

doi:10.5220/0010250506610668

Cited by 13 publications

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experts annotation experiments consist of two phases. In the first phase a total of 100 images are randomly drawn from the Retinal Fundus Image Quality Assessment (RFIQA) dataset [16]. Each expert subject (ophthalmologist) is then required to classify each image (stimuli) as a Good/Bad quality.…”

Section: Eye-tracking Experiments and Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

Expert Level Evaluations for Explainable AI (XAI) Methods in the Medical Domain

Muddamsetty

Jahromi

Moeslund

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The recently emerged field of explainable artificial intelligence (XAI) attempts to shed lights on 'black box' Machine Learning (ML) models in understandable terms for human. As several explanation methods are developed alongside different applications for a black box model, the need for expert-level evaluation in inspecting their effectiveness becomes inevitable. This is significantly important for sensitive domains such as medical applications where evaluation of experts is essential to better understand how accurate the results of complex ML are and debug the models if necessary. The aim of this study is to experimentally show how the expert-level evaluation of XAI methods in a medical application can be utilized and aligned with the actual explanations generated by the clinician. To this end, we collect annotations from expert subjects equipped with an eye-tracker while they classify medical images and devise an approach for comparing the results with those obtained from XAI methods. We demonstrate the effectiveness of our approach in several experiments.

show abstract

Section: Eye-tracking Experiments and Data Collectionmentioning

confidence: 99%

“…The dataset consists of 9,945 images with two levels of quality, 'Good' and 'Bad'. The retinal images were collected from a large number of patients with retinal diseases [16]. The dataset is split into 80% training, 10% validation and 10% testing.…”

Section: Training Cnn Modelsmentioning

confidence: 99%

Expert Level Evaluations for Explainable AI (XAI) Methods in the Medical Domain

Muddamsetty

Jahromi

Moeslund

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The dataset consists of 9,945 images with two levels of quality, 'Good' and 'Bad'. The retinal images were collected from a large number of patients with retinal diseases [33].…”

Section: Functionally Grounded Evaluationmentioning

confidence: 99%

“…We also conducted a second experiment on Medical Image dataset which has totally different characteristics. We trained the existing ResNet-50 [34] with an additional two FC layers and softmax layer on the RFIQA dataset [33].…”

Section: Functionally Grounded Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Introducing and assessing the explainable AI (XAI)method: SIDU

Muddamsetty¹,

Jahromi²,

Ciontos³

et al. 2021

Preprint

View full text Add to dashboard Cite

Explainable Artificial Intelligence (XAI) has in recent years become a well-suited framework to generate human understandable explanations of black box models. In this paper, we present a novel XAI visual explanation algorithm denoted SIDU that can effectively localize entire object regions responsible for prediction in a full extend. We analyze its robustness and effectiveness through various computational and human subject experiments. In particular, we assess the SIDU algorithm using three different types of evaluations (Application, Human and Functionally-Grounded) to demonstrate its superior performance. The robustness of SIDU is further studied in presence of adversarial attack on black box models to better understand its performance.

show abstract

A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment

Zou

Liu

2021

Pattern Recognition and Computer Vision

View full text Add to dashboard Cite

Multi-level Quality Assessment of Retinal Fundus Images using Deep Convolution Neural Networks

Cited by 13 publications

References 0 publications

Expert Level Evaluations for Explainable AI (XAI) Methods in the Medical Domain

Expert Level Evaluations for Explainable AI (XAI) Methods in the Medical Domain

Introducing and assessing the explainable AI (XAI)method: SIDU

A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment

Contact Info

Product

Resources

About