{"doi":"10.1117/12.3047273","title":"Scalable, reproducible, and cost-effective processing of large-scale medical imaging datasets","abstract":"Curating, processing, and combining large-scale medical imaging datasets from national studies is a non-trivial task due to the intense computation and data throughput required, variability of acquired data, and associated financial overhead. Existing platforms or tools for large-scale data curation, processing, and storage have difficulty achieving a viable cost-to-scale ratio of computation speed for research purposes, either being too slow or too expensive. Additionally, management and consistency of processing large data in a team-driven manner is a non-trivial task. We design a BIDS-compliant method for an efficient and robust data processing pipeline of large-scale diffusion-weighted and T1-weighted MRI data compatible with low-cost, high-efficiency computing systems. Our method accomplishes automated querying of data available for processing and process running in a consistent and reproducible manner that has long-term stability, while using heterogenous low-cost computational resources and storage systems for efficient processing and data transfer. We demonstrate how our organizational structure permits efficiency in a semi-automated data processing pipeline and show how our method is comparable in processing time to cloud-based computation while being almost 20 times more cost-effective. Our design allows for fast data throughput speeds and low latency to reduce the time for data transfer between storage servers and computation servers, achieving an average of 0.60 Gb/s compared to 0.33 Gb/s for using cloud-based processing methods. The design of our workflow engine permits quick process running while maintaining flexibility to adapt to newly acquired data.","journal":"PubMed","year":2025,"id":554764,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":8,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9454,"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":528831,"name":"Karthik Ramadass","orcid":"0000-0002-4610-3860","position":1,"is_corresponding":false},{"id":1337792,"name":"Chenyu Gao","orcid":"0000-0001-6689-7293","position":2,"is_corresponding":false},{"id":517672,"name":"Praitayini Kanakaraj","orcid":"0000-0002-9979-217X","position":3,"is_corresponding":false},{"id":1079871,"name":"Nancy R. Newlin","orcid":"0000-0003-3714-4684","position":4,"is_corresponding":false},{"id":1297373,"name":"Gaurav Rudravaram","orcid":null,"position":5,"is_corresponding":false},{"id":251252,"name":"Kurt G. Schilling","orcid":"0000-0003-3686-7645","position":6,"is_corresponding":false},{"id":420040,"name":"Blake E. Dewey","orcid":"0000-0003-4554-5058","position":7,"is_corresponding":false},{"id":463985,"name":"Derek B. Archer","orcid":"0000-0001-8638-0785","position":8,"is_corresponding":false},{"id":254761,"name":"Timothy J. Hohman","orcid":"0000-0002-3377-7014","position":9,"is_corresponding":false},{"id":1337793,"name":"Z. Li","orcid":"0000-0001-7096-2158","position":10,"is_corresponding":false},{"id":425888,"name":"Shunxing Bao","orcid":"0000-0001-6376-4292","position":11,"is_corresponding":false},{"id":104551,"name":"Bennett A. Landman","orcid":"0000-0001-5733-2127","position":12,"is_corresponding":false},{"id":1190992,"name":"Nazirah Mohd Khairi","orcid":"0000-0003-2180-3200","position":13,"is_corresponding":false},{"id":1167009,"name":"Michael E. Kim","orcid":"0009-0006-3562-2688","position":0,"is_corresponding":true}],"reference_count":70,"raw_metadata":null,"created_at":"2026-07-19T02:54:54.542303Z","pmid":"41450588","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":[]}