{"doi":"10.1016/j.xpro.2025.104221","title":"Protocol to annotate and automate single-cell instance segmentation on stimulated Raman histology using deep learning","abstract":"Stimulated Raman histology (SRH) is a label-free optical imaging technique that can discern molecular components such as lipids and proteins at subcellular spatial resolution without histologic staining. Here, we present a protocol for labeling cells and training AI models for automated cell segmentation on SRH images acquired intra-operatively from neurosurgical cases. We describe steps to enable single-cell spatial analysis on SRH using ELUCIDATE, a web-based SRH cell annotation tool, and DetectSRH Python library. • Step-by-step workflow from manual labeling to automated cell detection and analysis • Instructions for annotating stimulated Raman histology (SRH) images with ELUCIDATE • Guidance on training deep learning cell segmentation models with DetectSRH library • Steps for model evaluation and iterative refinement via prediction correction and retraining Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. Stimulated Raman histology (SRH) is a label-free optical imaging technique that can discern molecular components such as lipids and proteins at subcellular spatial resolution without histologic staining. Here, we present a protocol for labeling cells and training AI models for automated cell segmentation on SRH images acquired intra-operatively from neurosurgical cases. We describe steps to enable single-cell spatial analysis on SRH using ELUCIDATE, a web-based SRH cell annotation tool, and DetectSRH Python library.","journal":"STAR Protocols","year":2025,"id":549078,"datarank":0.10397207708399181,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.0,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9392,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1338300,"name":"Eric Landgraf","orcid":null,"position":1,"is_corresponding":false},{"id":470264,"name":"Cheng Jiang","orcid":"0000-0003-1759-4960","position":2,"is_corresponding":false},{"id":921806,"name":"Asadur Chowdury","orcid":"0000-0002-5653-9721","position":3,"is_corresponding":false},{"id":921807,"name":"Akhil Kondepudi","orcid":"0000-0002-2643-7580","position":4,"is_corresponding":false},{"id":379429,"name":"Lin Wang","orcid":"0000-0002-6449-4930","position":5,"is_corresponding":false},{"id":1330571,"name":"Edward Harake","orcid":"0000-0002-8865-1267","position":6,"is_corresponding":false},{"id":571734,"name":"Xinhai Hou","orcid":null,"position":7,"is_corresponding":false},{"id":1442744,"name":"Lisa L. Walsh","orcid":"0000-0003-0311-5455","position":8,"is_corresponding":false},{"id":345541,"name":"Todd Hollon","orcid":"0000-0001-5987-6531","position":9,"is_corresponding":false},{"id":1442743,"name":"Abhishek Bhattacharya","orcid":"0000-0003-1600-4308","position":0,"is_corresponding":true}],"reference_count":4,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:54:03.053965Z","pmid":"41317327","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}