radiology-skills

Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.

Design/audit imaging truth, readers, ROI geometry, reproducibility and label noise; not model training.

Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews.

Verify claim-level sources and DOI/PMID; export checked citations. Not discovery or evidence synthesis.

Set disease pathways, endpoints, reference standards and treatment timelines; not patient care.

Design/audit consensus and evidence-to-recommendation products; not review synthesis or endorsement.

Plan/audit imaging provenance, DICOM de-identification, sharing, repositories and retention; not ethics approval.

Design/train/audit imaging DL pipelines, splits, tuning and validation; not deployment studies.

Lock study feasibility, population, estimand, imaging task and validation; not novelty scanning or execution. CN: 可行性、课题设计、样本量、外部验证

Create traceable posters, conference abstracts, summaries and media; not papers, decks or figures.

Audit IRB, consent, privacy, IACUC/IBC, biosafety and dual use; not logistics or lab execution.

Design/audit tissue, cell, organoid, animal, perturbation and rescue validation; not physical SOP execution.

Create/audit publication plots, visual abstracts and imaging panels with render QA; not tables or decks. CN: 统计图、ROC、森林图、影像图版

Identify evidence-grounded imaging frontiers and gaps; not design lock or journal choice.

Develop/review radiology grants against a live call, including current NSFC rules, code/call routing, funder criteria and imaging feasibility; not papers or decks. CN: 标书、国自然、基金评审

Plan/audit imaging economic evaluation, decision models, budget impact, uncertainty and HTA reporting.

Assess disclosure, prior-art handoff, rights and transfer readiness; not patentability, FTO or legal advice.

Match a near-finished imaging paper to live journal scope and tier; not scientific review or file audit.

Audit parameter provenance, metric fit, fair comparisons and robustness; not execution or paper review.

Plan/create/audit evidence-led research decks for defenses, meetings and talks, with render QA. CN: PPT、答辩、组会汇报

Mentor and route ambiguous, multistage or resumed radiology research; tutoring defaults to read-only. CN: 总控、课题导航、下一步

Polish existing research prose while preserving facts and claims; not drafting or scientific repair.

Run author, peer or editorial scientific review with traceable findings; not checklists or upload audits. CN: 模拟审稿、预审、大修风险

Design/audit qualitative and mixed-methods sampling, reflexivity, integration and claim limits.

Interpret mechanisms and imaging-mechanism bridges with competing explanations and causal ceilings.

Design/audit radiomics preprocessing, IBSI extraction, stability, leakage-safe selection and validation.

Create bilingual figure-aware readers from supplied papers; not reader-study or MRMC design.

Select/audit reporting guidelines across imaging AI, diagnosis, reviews, guidelines and economics.

Audit/package computational replay with manifests, environments, provenance and evidence levels.

Audit authorship, COI, AI use, selective reporting and artifact integrity; not misconduct adjudication.

Plan/audit sites, RACI, milestones, dependencies, resources, risks and closeout; not scientific design.

Adjudicate reviews, draft point-by-point responses and verify closure; not initial prereview.

Search/deduplicate imaging papers or datasets into reproducible corpora; not claim checks or review synthesis. CN: 文献检索、公共数据集

Plan/compute/audit inference on defined data/effect rows: CI, AUC, MRMC, survival, meta-analysis and power. CN: 统计、样本量、AUC比较、校准

Audit journal or conference packages against current exact-venue fields/files; not scientific review. CN: 投稿材料、投稿包、文件检查

Design/audit systematic or scoping reviews from protocol through synthesis, certainty and living updates.

Create/audit editable publication tables with source reconciliation; not figures or statistical inference.

Build/run/audit bulk RNA, sc/snRNA and spatial workflows with traceable QC; not mechanism claims.

Design clinical use, reader/impact studies, human factors, deployment and lifecycle evidence.

Draft/restructure manuscripts or theses from fixed evidence; not polishing, review or rebuttal. CN: 论文写作、英文稿、结构化摘要