Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation.
Συγγραφείς:	Jaiswal A; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Rinneburger M; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Meyer F; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Arjune S; Department II of Internal Medicine, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Center for Rare Diseases Cologne, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), Cologne, Germany., Oberlinkels L; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Wawer Matos Reimer PA; Department of Ophthalmology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany., Lotter-Becker L; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Akünal Ü; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany., Bujotzek M; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany.; Medical Faculty Heidelberg, University of Heidelberg, Heidelberg, Germany., Denner S; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany.; Faculty of Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany., Maier-Hein K; Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany.; Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital, Heidelberg, Germany.; German Cancer Consortium (DKTK), Partner Site Heidelberg, Heidelberg, Germany.; National Center for Tumor Diseases (NCT), NCT Heidelberg, A Partnership Between DKFZ and The University Medical Center Heidelberg, Heidelberg, Germany., Stepansky L; Department of Radiology, Universitätsklinikum Erlangen, Erlangen, Germany., May MS; Department of Radiology, Universitätsklinikum Erlangen, Erlangen, Germany., Habert M; ImFusion GmbH, Munich, Germany., Köhn A; Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany., Schöneck M; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Wawer Matos Reimer RP; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Müller RU; Department II of Internal Medicine, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Center for Rare Diseases Cologne, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.; Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases (CECAD), Cologne, Germany., Lennartz S; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Große Hokamp N; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Bucher AM; Institute for Diagnostic and Interventional Radiology, Frankfurt University Hospital, Frankfurt, Germany., Persigehl T; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany., Caldeira LL; Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Str 62, 50937 Cologne, Germany.
Πηγή:	Radiology. Artificial intelligence [Radiol Artif Intell] 2026 Jul; Vol. 8 (4), pp. e250200.
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Radiological Society of North America, Inc Country of Publication: United States NLM ID: 101746556 Publication Model: Print Cited Medium: Internet ISSN: 2638-6100 (Electronic) Linking ISSN: 26386100 NLM ISO Abbreviation: Radiol Artif Intell Subsets: MEDLINE
Imprint Name(s):	Original Publication: Oak Brook, IL : Radiological Society of North America, Inc., [2019]-
Ιατρικοί όροι (MeSH):	Deep Learning/economics , Magnetic Resonance Imaging/economics , Tomography, X-Ray Computed/economics , Image Processing, Computer-Assisted/methods , Image Processing, Computer-Assisted*/economics, Lung Neoplasms/diagnostic imaging ; Prostatic Neoplasms/diagnostic imaging ; Melanoma/diagnostic imaging ; Humans ; Retrospective Studies ; Male ; Time Factors ; Uveal Melanoma
Περίληψη:	Purpose To develop and systematically evaluate an iterative training approach, termed the expert-guided annotation loop, for efficient reference standard segmentation generation, including assessment of two sample selection strategies and real-world clinical implementation. Materials and Methods This retrospective study included 10 datasets comprising 1941 CT and MRI scans from patients with autosomal dominant polycystic kidney disease, prostate cancer, uveal melanoma, thyroid eye disease, or non-small cell lung cancer. nnU-Net segmentation models were iteratively trained using an expert-guided annotation loop with random or active learning-based sample selection. In each iteration, additional samples were added to the training set, and model-generated presegmentations were corrected by expert radiologists to create reference standard annotations. Expert time required for manual segmentation versus presegmentations correction was measured. Model performance and efficiency were assessed using nonparametric tests, and cost savings were estimated for kidney and tumor segmentation using probabilistic sensitivity analysis. Feasibility of end-to-end no-code implementation was evaluated. Results Fifty-seven segmentation models were trained and evaluated. Final model mean Dice scores ranged from 0.67 to 0.97 for organ segmentation and from 0.64 to 0.69 for lung tumor segmentation across internal and external test sets. Maximum expert time savings were 90.3% for kidney and 48.2% for tumor segmentation (P < .001 and P = .003, respectively), corresponding to estimated per-examination cost savings of $14.30 (95% CI: 5.94, 26.87) and $5.63 (95% CI: -7.26, 26.09), respectively. No-code execution of the expert-guided annotation loop was feasible. Conclusion The expert-guided annotation loop reduced expert annotation time and enabled estimated cost savings while producing high-quality reference standard segmentations. The no-code workflow was implemented in a clinical environment. Keywords: Artificial Intelligence, CT, Human-in-the-Loop Machine Learning, Medical Image Segmentation, MRI Supplemental material is available for this article. © RSNA, 2026.
Contributed Indexing:	Keywords: Artificial Intelligence; CT; Human-in-the-Loop Machine Learning; MRI; Medical Image Segmentation
Entry Date(s):	Date Created: 20260624 Date Completed: 20260715 Latest Revision: 20260715
Update Code:	20260716
DOI:	10.1148/ryai.250200
PMID:	42340187
Βάση Δεδομένων:	MEDLINE

Περιγραφή
ISSN:	2638-6100
DOI:	10.1148/ryai.250200