PDDD-PreTrain: A Series of Commonly Used Pre-Trained Models Support Image-Based Plant Disease Diagnosis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37213546", "kind": "science-record", "revision": 3, "content_hash": "sha256:afdd52c66a1c35470f5d2bd39c0d27c2b674fb22c3f0fd0108e1f2c986fc10ac", "created_at": "2026-11-01T19:01:54Z", "updated_at": "2026-11-01T22:09:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PDDD-PreTrain: A Series of Commonly Used Pre-Trained Models Support Image-Based Plant Disease Diagnosis.", "doi": "10.34133/plantphenomics.0054", "pmid": "37213546", "authors": ["Xinyu Dong", "Qi Wang", "Qianding Huang", "Qinglong Ge", "Kejun Zhao", "Xingcai Wu", "Xue Wu", "Liang Lei", "Gefei Hao"], "journal": "Plant phenomics (Washington, D.C.)", "year": 2023, "abstract": "Plant diseases threaten global food security by reducing crop yield; thus, diagnosing plant diseases is critical to agricultural production. Artificial intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming, costly, inefficient, and subjective disadvantages. As a mainstream AI method, deep learning has substantially improved plant disease detection and diagnosis for precision agriculture. In the meantime, most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased leaves. However, the commonly used pre-trained models are from the computer vision dataset, not the botany dataset, which barely provides the pre-trained models sufficient domain knowledge about plant disease. Furthermore, this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic precision. To address this issue, we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease diagnosis. In addition, we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification, plant disease detection, plant disease segmentation, and other subtasks. The extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time, thereby supporting the better diagnosis of plant diseases. In addition, our pre-trained models will be open-sourced at https://pd.samlab.cn/ and Zenodo platform https://doi.org/10.5281/zenodo.7856293.", "claims": [{"id": "claim-method", "statement": "For plant disease recognition, we adopt classification recognition accuracy as the evaluation criterion", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37213546", "locator": "sections[15] \"Evaluation metrics and validation dataset\" paragraph 2", "quote": "For plant disease recognition, we adopt classification recognition accuracy as the evaluation criterion"}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data and codes are available on the website https://pd.samlab.cn/ and Zenodo platform https://doi.org/10.5281/zenodo.7856293.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37213546", "locator": "sections[28] \"Data Availability\" paragraph 2", "quote": "All data and codes are available on the website https://pd.samlab.cn/ and Zenodo platform https://doi.org/10.5281/zenodo.7856293."}], "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:37213546"], "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:37213546", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.34133/plantphenomics.0054", "sha256": "sha256:9fd0bad7f3bec69d355a6a6c54e07bd55d00ca8411bf586e6c096eefdb815b80", "bytes": 62781, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.34133/plantphenomics.0054", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10194370", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "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": 0.7, "band": "medium", "quote": "segmentation"}}, {"id": "method-2", "family": null, "specific": null, "label": "Classification recognition accuracy, mean average precision, and mean intersection over union", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For plant disease recognition, we adopt classification recognition accuracy as the evaluation criterion"}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["All data and codes are available on the website https://pd.samlab.cn/ and Zenodo platform https://doi.org/10.5281/zenodo.7856293."], "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:37213546"], "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": "2026-11-01T18:40:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15565, "completion_tokens": 2483, "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:37213546", "type": "paper", "label": "pmid:37213546"}, {"id": "source:pmid:37213546", "type": "manuscript", "label": "PMID 37213546 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37213546", "type": "paper", "label": "pmid:37213546"}, {"id": "source:pmid:37213546", "type": "manuscript", "label": "PMID 37213546 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37213546", "type": "extraction", "used": ["source:pmid:37213546"], "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:37213546", "parent_hash": "sha256:c8f58ee836d7fd8324549094ea45d8215af9016835a947eb84d163fca8a2e5f5", "fork_of": null, "generation": 2}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "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": 0.7, "evidence": ["segmentation"], "order_basis": "analysis_only", "id": "assay:1"}]}