Scalable Clinical Annotation with Location Evidence (SCALE)

Deep learning can mitigate the global radiologist shortage but its development requires large-scale annotated datasets. This study introduces SCALE (Scalable Clinical Annotation with Location Evidence), a fully automated method for generating voxel-level annotations. It uses location priors that are automatically extracted from medical reports, tracked biopsy coordinates, or provided anatomical sectors. We annotated a large-scale dataset comprising 17 896 cases from 16 562 patients across 24 hospitals in 10 countries and 2 continents, using both SCALE and a count-based weakly semisupervised learning (CWSSL) method. An optimized algorithm was developed and trained on these datasets. Evaluation with 1561 cases from 1561 patients across 19 hospitals in 3 countries and 1 continent showed the superiority of the model trained on the dataset with SCALE annotations, achieving a case-level area under the receiver operating characteristic curve of 0.856. This is ＋0.012 compared to supervised learning (p=0.02), ＋0.007 compared to training with CWSSL (p=0.12), and ＋0.006 compared to the Prostate Imaging: Cancer AI (PI-CAI) Ensemble AI System. These results demonstrate that automated, location-guided annotation enables scalable development of AI for clinically significant prostate cancer detection on MRI, surpassing previous methods, and paving the way for broader clinical deployment.

Authors

Institutions

Publication Details

Journal
Computers in Biology and Medicine
Published
2025-11-21
DOI
https://doi.org/10.1016/j.compbiomed.2025.111321
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Scalable Clinical Annotation with Location Evidence (SCALE)

Joeran S. Bosma, Kostas Marias, Anindo Saha, Jasper J. Twilt et al.
Computers in Biology and Medicine
AI in cancer detection
article

Scalable Clinical Annotation with Location Evidence (SCALE)

Joeran S. Bosma, Kostas Marias, Anindo Saha, Jasper J. Twilt, Nickolas Papanikolaou, HenkJan J. Huisman, Luc Builtjes, Mattias P. Heinrich‬, Daniele Regge, Derya Yakar, Ivo G. Schoots, Alessa Hering, Jeroen Veltman, Mattijs Elschot, Maarten de Rooij, Nancy A. Obuchowski, Manolis Tsiknakis
article en

Abstract

Deep learning can mitigate the global radiologist shortage but its development requires large-scale annotated datasets. This study introduces SCALE (Scalable Clinical Annotation with Location Evidence), a fully automated method for generating voxel-level annotations. It uses location priors that are automatically extracted from medical reports, tracked biopsy coordinates, or provided anatomical sectors. We annotated a large-scale dataset comprising 17 896 cases from 16 562 patients across 24 hospitals in 10 countries and 2 continents, using both SCALE and a count-based weakly semisupervised learning (CWSSL) method. An optimized algorithm was developed and trained on these datasets. Evaluation with 1561 cases from 1561 patients across 19 hospitals in 3 countries and 1 continent showed the superiority of the model trained on the dataset with SCALE annotations, achieving a case-level area under the receiver operating characteristic curve of 0.856. This is ＋0.012 compared to supervised learning (p=0.02), ＋0.007 compared to training with CWSSL (p=0.12), and ＋0.006 compared to the Prostate Imaging: Cancer AI (PI-CAI) Ensemble AI System. These results demonstrate that automated, location-guided annotation enables scalable development of AI for clinically significant prostate cancer detection on MRI, surpassing previous methods, and paving the way for broader clinical deployment.

Computers in Biology and MedicineVol. 199
Champalimaud Foundation (PT), Cleveland Clinic (US), Royal Marsden NHS Foundation Trust (GB), University Medical Center Groningen (NL), Radboud University Nijmegen (NL), Norwegian University of Science and Technology (NO), Radboud University Medical Center (NL), St Olav's University Hospital (NO), Ziekenhuis Groep Twente (NL), Erasmus MC Cancer Institute (NL), Candiolo Cancer Institute (IT), Foundation for Research and Technology Hellas (GR), University of Lübeck (DE), University of Twente (NL)
European Commission
Openalex Percentile: Top 81%
AI in cancer detection
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.