arXiv AI

Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection

arXiv AI
Aug 20

OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation

OptiModNet is a lightweight UNet‑Transformer hybrid designed for optic disc and cup segmentation. It incorporates grouped‑query and channel attention across multiple stages, along with an Aggregated Pyramid Loss to improve gradient flow and structural consistency. Evaluated on the REFUGE2 dataset, it surpasses existing methods by over 2.5 % while using only 3.73 GFLOPs and 1.93 M parameters.

By Soumili Ghosh, Debapriya Roy, Aryan Das, Bikash Santra
arXiv Machine Learning
Aug 11

Disentangling Co-Occurring Retinal Pathologies with Saliency-Guided Sparse Expert Routing

arXiv:2608. 09752v1 Announce Type: cross Abstract: Retinal fundus images frequently exhibit multiple co-occurring pathologies, yet standard deep learning classifiers apply static, identical computation to every image regardless of the underlying disease distribution.

By Nagur Shareef Shaik, Jeongwoo Park, Yeong-Jin Kim, Jaeuk Jung, Hyunjung Oh, Dong Hye Ye
arXiv Computer Vision
Sep 4

Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images

The paper presents a two‑pipeline framework for retinal fundus analysis that combines four‑class disease classification with vessel segmentation. It fine‑tunes eight ImageNet‑pretrained CNNs on the FIVES dataset, applies five gradient‑based explanation methods to assess model interpretability, and benchmarks ten U‑Net variants—including transformer‑based and attention‑enhanced architectures—on the FIVES and DRIVE datasets. The best classification results come from ResNet101 (94.17% accuracy), while the strongest segmentation performance is achieved by Attention U‑Net with a ResNet101V2 backbone, improving DRIVE IoU from 60.80% to 64.83%.

By Fatema Tuj Johora Faria, Mukaffi Bin Moin, Pronay Debnath, Asif Iftekher Fahim, Faisal Muhammad Shah
arXiv Machine Learning
Jul 24

Counterfactual Explainability Framework With CycleGAN And Counterfactual-Classifier Alignnment Score for Retinal Disease Classification

arXiv:2607. 21068v1 Announce Type: new Abstract: Automated detection of vision impairing retina-based ocular conditions from fundus images is important for early screening, timely referral and reducing dependency on specialist-only assessment, for which neural network-based deep learning (DL) models have been widely utilized.

By Kritanu Chattopadhyay, Sayanjit Singha Roy, Soumya Chatterjee
arXiv Computer Vision
Sep 7

An Attention-Guided Global and Local Fusion Framework for Lesion-Focused Image Classification

The paper introduces an attention‑guided fusion framework that combines global and lesion‑focused local information for image classification. Using a three‑branch architecture built on DenseNet‑121, the model generates attention maps with Grad‑CAM, refines local features with CBAM, and adaptively fuses the two representations. Experiments on synthetic and real datasets, including skin, guava leaf, and grape leaf images, show that the fusion branch outperforms individual branches, achieving up to 97.75% accuracy on skin lesions and 99.64% on guava leaves.

By Mst Shafia Tasnima, Md Samaun Elaheea, Tanjim Taharat Aurpab, Md Musfique Anwar
arXiv Machine Learning
Jul 7

GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment

arXiv:2607. 04673v1 Announce Type: cross Abstract: Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer little clinical interpretability.

By Cheng Huang, Jia Zhang, Yi Jiang, Yang Liu, Karanjit Kooner, Yadi Liu, Tsengdar Lee, Yang Xie, Wenqi Shi, Guanghua Xiao
arXiv Computer Vision
Sep 3

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection

The study evaluates fundus-specific foundation models (FM) for detecting diabetic macular edema (DME) in retinal images. It compares two popular FM—RETFound and FLAIR—against a lightweight EfficientNet-B0 backbone across multiple datasets (IDRiD, MESSIDOR-2, and OCT-and-Eye-FundusImages). Results indicate that FM do not consistently outperform fine‑tuned CNNs; EfficientNet-B0 often matches or exceeds FM performance, with FLAIR being the most competitive FM.

By Franco Javier Arellano, Jos\'e Ignacio Orlando
arXiv Machine Learning
Aug 17

XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas

arXiv:2602. 04819v5 Announce Type: replace-cross Abstract: Accurate risk stratification of precancerous polyps during routine colonoscopy screening is a key strategy to reduce the incidence of colorectal cancer (CRC).

By Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari