Image dataset of ten durian diseases captured in real-field conditions from a family orchard in Vinh Long, Vietnam.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41342007", "kind": "science-record", "revision": 3, "content_hash": "sha256:db47adfe6ab905cdf6e304cc4dbbbe1ee382e4bd35c73b65f1fafe84a97e9d91", "created_at": "2026-11-01T20:31:21Z", "updated_at": "2026-11-01T22:15:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Image dataset of ten durian diseases captured in real-field conditions from a family orchard in Vinh Long, Vietnam.", "doi": "10.1016/j.dib.2025.112244", "pmid": "41342007", "authors": ["Tan Nguyen"], "journal": "Data in brief", "year": 2025, "abstract": "This dataset comprises 5452 images of durian plant parts-including leaves, flowers, branches, stems, and roots-affected by ten common disease classes. The images were captured from one family-owned durian orchard and four nearby orchards in Vinh Long Province, Vietnam. Each class contains approximately 405-427 raw images, photographed using an iPhone 14 under natural field conditions. These conditions simulate typical farmer photography practices, featuring varied angles, inconsistent lighting, and complex environmental backgrounds, resulting in significant visual noise. All raw JPEG images were manually reviewed and cropped on macOS systems using MacBook devices equipped with Apple M4 chips to focus on disease-affected regions, reduce file size, and minimize background noise. The processed, cropped images are provided in PNG format with variable dimensions. Images were resized to 224×224 pixels only during model training for machine learning experiments. Disease symptoms were verified in collaboration with plant pathologists to ensure accurate classification. This dataset is publicly available on Mendeley Data and is suitable for developing and evaluating machine learning models in plant disease classification. It is particularly valuable for testing model performance under real-world, noisy conditions and for supporting the creation of mobile or edge-based diagnostic tools in agriculture.", "claims": [{"id": "claim-data-access", "statement": "Mendeley DataImage Dataset of Ten Durian Diseases Captured in Real-Field Conditions from a Family Orchard in Vinh Long, Vietnam (Original data).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41342007", "locator": "sections[11] \"Data Availability\" paragraph 2", "quote": "Mendeley DataImage Dataset of Ten Durian Diseases Captured in Real-Field Conditions from a Family Orchard in Vinh Long, Vietnam (Original data)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41342007"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:accession_absent", "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41342007", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2025.112244", "sha256": "sha256:8c6f7460d655d7668b06286fa00c3698d070b644cd6d0c2652908bd337e0cde0", "bytes": 21822, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2025.112244", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12670932", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "image_quantification", "specific": "segmentation", "label": "Image analysis / quantification", "dsl_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["image_stack"], "evidence": {"score": 0.8, "band": "high", "quote": "segmentation"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["segment_objects", "quantify_intensity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: segmentation."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Mendeley DataImage Dataset of Ten Durian Diseases Captured in Real-Field Conditions from a Family Orchard in Vinh Long, Vietnam (Original data)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["segment_objects", "quantify_intensity"], "assets": ["source:pmid:41342007"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:07:06Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6204, "completion_tokens": 872, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41342007", "type": "paper", "label": "pmid:41342007"}, {"id": "source:pmid:41342007", "type": "manuscript", "label": "PMID 41342007 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41342007", "type": "paper", "label": "pmid:41342007"}, {"id": "source:pmid:41342007", "type": "manuscript", "label": "PMID 41342007 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41342007", "type": "extraction", "used": ["source:pmid:41342007"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41342007", "parent_hash": "sha256:bd894c8d40225980cc2ebf6ff9fa6cb3a48713f745dcadb58b827be035faf457", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "image_quantification", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["segment_objects", "quantify_intensity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["segmentation"], "order_basis": "analysis_only", "id": "assay:1"}]}