TY - GEN
T1 - A Lightweight UNet with Inverted Residual Blocks for Diabetic Retinopathy Lesion Segmentation
AU - Bhati, Amit
AU - Choudhary, Karan
AU - Jain, Samir
AU - Gour, Neha
AU - Khanna, Pritee
AU - Ojha, Aparajita
AU - Werghi, Naoufel
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Diabetic Retinopathy (DR) is a progressive disease that significantly contributes to vision impairment and blindness. Its complex nature, characterized by subtle variations among different grades and the presence of numerous important small features, poses a considerable challenge for accurate recognition. Currently, the process of identifying DR relies heavily on the expertise of physicians, making it a time-consuming and labor-intensive task. However, automated detection of specific lesions plays a crucial role in visualizing, characterizing, and determining the severity of DR. Timely detection of DR in its early stages is vital for diagnosis and can potentially prevent blindness through appropriate treatment. Nonetheless, segmenting lesions in fundus imaging is a challenging task due to variations in lesion sizes, shapes, similarities, and limited contrast with other parts of the eye, leading to ambiguous results. In this work, a shallow UNet-based architecture with inverted residual skip connections is proposed to segment lesion parts of DR disease. Performance of the model is evaluated on Indian Diabetic Retinopathy Image Dataset (IDRiD) and DDR datasets. Results show that the proposed model is able to distinguish different kinds of DR lesion parts with a very less number of parameters (3.3 M).
AB - Diabetic Retinopathy (DR) is a progressive disease that significantly contributes to vision impairment and blindness. Its complex nature, characterized by subtle variations among different grades and the presence of numerous important small features, poses a considerable challenge for accurate recognition. Currently, the process of identifying DR relies heavily on the expertise of physicians, making it a time-consuming and labor-intensive task. However, automated detection of specific lesions plays a crucial role in visualizing, characterizing, and determining the severity of DR. Timely detection of DR in its early stages is vital for diagnosis and can potentially prevent blindness through appropriate treatment. Nonetheless, segmenting lesions in fundus imaging is a challenging task due to variations in lesion sizes, shapes, similarities, and limited contrast with other parts of the eye, leading to ambiguous results. In this work, a shallow UNet-based architecture with inverted residual skip connections is proposed to segment lesion parts of DR disease. Performance of the model is evaluated on Indian Diabetic Retinopathy Image Dataset (IDRiD) and DDR datasets. Results show that the proposed model is able to distinguish different kinds of DR lesion parts with a very less number of parameters (3.3 M).
KW - Diabetic Retinopathy
KW - Inverted Residual Block
KW - Lesion Segmentation
KW - Lightweight Model
KW - UNet
UR - https://www.scopus.com/pages/publications/85200663161
U2 - 10.1007/978-3-031-58174-8_6
DO - 10.1007/978-3-031-58174-8_6
M3 - Conference contribution
AN - SCOPUS:85200663161
SN - 9783031581731
T3 - Communications in Computer and Information Science
SP - 57
EP - 66
BT - Computer Vision and Image Processing - 8th International Conference, CVIP 2023, Revised Selected Papers
A2 - Kaur, Harkeerat
A2 - Jakhetiya, Vinit
A2 - Goyal, Puneet
A2 - Khanna, Pritee
A2 - Raman, Balasubramanian
A2 - Kumar, Sanjeev
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th International Conference on Computer Vision and Image Processing, CVIP 2023
Y2 - 3 November 2023 through 5 November 2023
ER -