CLAT
importedsoftware/clat
[TMI 2024] Code for "Concept-based Lesion Aware Transformer for Interpretable Retinal Disease Diagnosis"
Machine-generated from the listed sources and not yet reviewed by a human.
- Category
- Software & Systems
- Subcategory
- unknown
- License
- Apache-2.0(osi)
- Status
- maintained
- Maturity
- deployed
- Organization
- unknown
- Country
- unknown
- Homepage
- unknown
- Repository
- github.com/Sorades/CLAT
- Documentation
- unknown
- Tags
- concept-based-models · diabetic-retinopathy · fundus-image-classification · interpretability · medical-imaging
- Regulatory
- unknown
Computed from shared tags, weighted so a rare tag counts for more than a common one. These are suggestions, not curated relationships.
- Diabetic-Retinopathy-Detection-Retinal-Vessel-Segmentationdiabetic-retinopathy · fundus-image-classification · medical-imaging
Classification of Fundus Images into 5 stages of Diabetic Retinopathy, and segmentation of blood vessels in fundus images
- eye-diagnosis-attention-cnndiabetic-retinopathy
A deep learning framework for automated diagnosis of Diabetic Retinopathy, AMD, and Glaucoma using a Hybrid Attention-CNN model. Combines ResNet50 with self-attention for enhanced accuracy and…
- MONETinterpretability · medical-imaging
Transparent medical image AI via an image–text foundation model grounded in medical literature
- autoprognosisinterpretability
A system for automating the design of predictive modeling pipelines tailored for clinical prognosis.
- clinical-self-verificationinterpretability
Self-verification for LLMs.
- cnn-interpretabilityinterpretability
🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
- api.github.com/repos/Sorades/CLATretrieved 2026-08-25 · via github-api
Machine-imported from GitHub search. Last push 2025-10-30, 31 stars, license reported as Apache-2.0. Category and schematic were assigned by keyword heuristics and are unreviewed.
Not yet verified by a human. Correct this record →
/v1/entries/15.json→ .entries["clat"]
Entries are sharded 64 ways by a stable hash of the id, so a consumer can find any record without an index.