Explainable Artificial Intelligence in Retinal Imaging for the detection of Systemic Diseases

Bhatt, Ayushi Raj; Vaghashiya, Rajkumar; Kulkarni, Meghna; Kamaraj, Dr Prakash

doi:10.48550/arxiv.2212.07058

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the available models inevitably focus on thick vessels rather than thin vessels. To address this problem, our research will include a comprehensive analysis of preprocessing techniques to highlight thin vessels in order to learn the discriminative features, while also making explicit its explainable model structure [18]. GRAD-CAM is used for the visualization of features and improve the explainability of the model.…”

Section: Introductionmentioning

confidence: 99%

Exploring the Impact of Preprocessing Techniques on Retinal Blood Vessel Segmentation Using a Study Group Learning Scheme

Bashir,

Rohail,

Sadak

et al. 2023

2023 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

View full text Add to dashboard Cite

The segmentation of retinal vessels in retinal images is vital for automated diagnosis of retinal diseases. This is a challenging task because it requires accurate manual labeling of the vessels by expert clinicians and the detection of tiny vessels is difficult due to limited samples, low contrast, and noise. In this study, we explore the use of pre-processing techniques such as contrast-limited adaptive histogram equalization (CLAHE), grad-cam analysis and min-max contrast stretching to improve the performance of a study-group learning (SGL) segmentation model. We evaluate the impact of these pre-processing techniques on the accuracy, sensitivity, specificity, AUC, IoU, and Dice scores using four publicly available datasets, DRIVE, CHASE, HRF and IOSTAR. Our findings indicate that the utilization of the Min-Max technique resulted in a notable enhancement in the accuracy of both the DRIVE and CHASE datasets, with an approximate increase of 3% and 2% respectively. Conversely, the impact of the CLAHE method was discernible solely in the DRIVE dataset, demonstrating an improvement in accuracy of 1%. In addition, our results demonstrated superior accuracy performance for both the DRIVE and CHASE datasets compared to the findings of the reviewed studies. The GitHub repo for this project is available at Link.

show abstract

Section: Introductionmentioning

confidence: 99%