fix README and zenodo

Author: rkhosrowshahi

.zenodo.json

@@ -1,6 +1,6 @@
 {
     "title": "Enhancing Image Retrieval Through Optimal Barcode Representation",
-    "description": "This repository contains the implementation of deep feature barcoding methods using Combinatorial Genetic Algorithm (CGA) for efficient medical image retrieval. The code includes multiple hashing and barcoding techniques evaluated on TCGA (The Cancer Genome Atlas) datasets and other image datasets. The main contribution is the optimization of feature ordering using CGA to improve barcoding performance for histopathological image retrieval.",
+    "description": "This repository contains the implementation of deep feature barcoding methods using Combinatorial Genetic Algorithm (CGA) for efficient medical image retrieval. The code includes multiple hashing and barcoding techniques evaluated on TCGA (The Cancer Genome Atlas) datasets and other image datasets. The main contribution is the optimization of feature ordering using CGA to improve barcoding performance for histopathological image retrieval. This implementation includes: 1) Combinatorial Genetic Algorithm for feature ordering optimization, 2) Multiple baseline hashing methods (aHash, dHash, DFT, etc.), 3) Neural network-based hashing approaches, 4) Comprehensive evaluation metrics (F1-score, Precision@k, mAP), 5) Support for multiple datasets including TCGA organ-specific subsets.",
     "creators": [
         {
             "name": "Khosrowshahli, Rasa",
@@ -57,30 +57,10 @@
             "identifier": "http://id.loc.gov/authorities/subjects/sh95008757"
         }
     ],
-    "related_identifiers": [
-        {
-            "identifier": "https://github.com/username/DeepFeatureBarcodingCGA",
-            "relation": "isSupplementTo",
-            "resource_type": "software"
-        }
-    ],
     "references": [
         "The Cancer Genome Atlas Research Network. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 455, 1061–1068 (2008).",
         "Kalra, S., Tizhoosh, H.R., Shah, S. et al. Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence. npj Digit. Med. 3, 31 (2020)."
     ],
     "notes": "This software accompanies the research paper on deep feature barcoding with combinatorial genetic algorithm. The code allows for reproducible experiments and comparison of various hashing methods on medical image datasets. TCGA data access requires appropriate permissions and data use agreements.",
-    "method": "This implementation includes: 1) Combinatorial Genetic Algorithm for feature ordering optimization, 2) Multiple baseline hashing methods (aHash, dHash, DFT, etc.), 3) Neural network-based hashing approaches, 4) Comprehensive evaluation metrics (F1-score, Precision@k, mAP), 5) Support for multiple datasets including TCGA organ-specific subsets.",
-    "funding": [
-        {
-            "award": {
-                "title": "Research Grant Title",
-                "number": "Grant-Number-123"
-            },
-            "funder": {
-                "name": "Funding Agency Name"
-            }
-        }
-    ],
-    "version": "1.0.0",
-    "publication_date": "2024-01-01"
+    "version": "1.0.0"
 } 

README.md

@@ -49,7 +49,7 @@ Download the datasets from the following links and extract them to the `./data`
 2. **CIFAR-100**: https://drive.google.com/uc?export=download&id=1V6vBIX-MW8LGAl7W8cGZHbI4D8FhcoeY
 3. **COVID-19**: https://drive.google.com/uc?export=download&id=1yUhCG__EJUKei4s5dtagldO0Blh6EFzt
 4. **Fashion-MNIST**: https://drive.google.com/uc?export=download&id=1zAgS9-fGtnRNKY8tVOqMkS8yZHnkDDGB
-5. **TCGA**: https://drive.google.com/file/d/1jZCslLLz_jJ6lctlfutvMN4ljfNn2PQU/view?usp=sharing
+5. **TCGA**: https://drive.google.com/uc?export=download&id=1jZCslLLz_jJ6lctlfutvMN4ljfNn2PQU
 
 After downloading (either automatically or manually), your data directory structure should look like:
 
@@ -205,11 +205,11 @@ To ensure reproducibility of results:
 If you use this code in your research, please cite our paper:
 
 ```bibtex
-@article{khosrowshahli2024enhancing,
+@article{khosrowshahli2025enhancing,
   title={Enhancing Image Retrieval Through Optimal Barcode Representation},
   author={Khosrowshahli, Rasa and Kheiri, Farnaz and Bidgoli, Azam Asilian and Tizhoosh, H.R. and Makrehchi, Masoud and Rahnamayan, Shahryar},
-  journal={[Journal Name]},
-  year={2024}
+  journal={Scientific Report},
+  year={2025}
 }
 ```
 

src/utils.py

@@ -369,7 +369,7 @@ def setup_seed(seed):
     'cifar100': 'https://drive.google.com/uc?export=download&id=1V6vBIX-MW8LGAl7W8cGZHbI4D8FhcoeY',
     'covid19': 'https://drive.google.com/uc?export=download&id=1yUhCG__EJUKei4s5dtagldO0Blh6EFzt',
     'fashion': 'https://drive.google.com/uc?export=download&id=1zAgS9-fGtnRNKY8tVOqMkS8yZHnkDDGB',
-    'tcga': 'https://drive.google.com/file/d/1jZCslLLz_jJ6lctlfutvMN4ljfNn2PQU/view?usp=sharing'
+    'tcga': 'https://drive.google.com/uc?export=download&id=1jZCslLLz_jJ6lctlfutvMN4ljfNn2PQU'
 }
 
 def check_dataset_exists(dataset_name: str, data_dir: str = './data') -> bool: