DB-ATRG: The Density and BI-RADS-Aware Triage and Automatic Report Generation System for Mammography
- 1Georgia State University
Abstract
Background: The growing volume of mammography screenings has created severe radiologist shortages, while standard First-In, First-Out (FIFO) reading queues fail to prioritize urgent or complex cases, delaying critical diagnoses. Objective: This study introduces the Density and BI-RADS--Aware Triage and Report Generation (DB-ATRG) framework to fundamentally restructure mammography workflows by automating diagnostic text generation and enabling risk-based case prioritization. Methods: Utilizing the Digital Mammography Dataset for Breast Cancer Diagnosis Research (DMID), we fine-tuned the 4-billion parameter MedGemma 1.5 vision-language model using Quantization and Low-Rank Adaptation (QLoRA). The extracted biomarkers drive a dual-phase triage algorithm that flags extremely dense breasts (ACR Category D) for supplemental screening and dynamically ranks remaining cases using a calculated Cumulative Urgency Score. The clinical impact of this triage workflow was evaluated against a standard FIFO queue using a simulated cohort of 100 mammography cases. Results: DB-ATRG achieved significant improvements over the AMRG baseline in clinical text generation and classification, securing a ROUGE-L score of 0.8012, a METEOR score of 0.8358, and an ACR Density Accuracy of 0.6810. In clinical simulations, the optimized prioritization queue captured 100.0% of high-risk malignancies (BI-RADS 4 and 5) within the first 20% of the reading workload, compared to just 19.2% in the random FIFO queue. This framework effectively accelerated the mean rank position of severe cases from 42.0 down to 7.5. Conclusion: By accurately automating report generation and aggressively prioritizing severe cases, the DB-ATRG framework can drastically optimize clinical resource allocation and accelerate the time-to-diagnosis for the most vulnerable patients.
Related
- Capillary hemangioma of the breast presenting as a new mass on screening mammography: A case report with imaging-pathology correlation
- AI-assisted Decision-support Framework for Breast Density and Background Parenchymal Enhancement Assessment in Contrast-enhanced Mammography
- The impact of 5‐alpha reductase inhibitors on multiparametric MRI diagnostic performance and prostate‐specific antigen density triage: A systematic review
- Case Report: Necrotizing fasciitis caused by Vibrio vulnificus without recalled seafood or seawater exposure diagnosed by metagenomic next-generation sequencing
- Laron syndrome presenting with severe low bone density for age in a 28-year-old woman: a case report
BibTeX
@misc{phan2026dbatrg,
title = {{DB-ATRG: The Density and BI-RADS-Aware Triage and Automatic Report Generation System for Mammography}},
author = {V. Phan and N. N. C. Tran and N. T. D. Bui and R. Jeter},
howpublished = {medRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.22.26358655},
url = {https://www.medrxiv.org/content/10.64898/2026.07.22.26358655v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - DB-ATRG: The Density and BI-RADS-Aware Triage and Automatic Report Generation System for Mammography
AU - V. Phan
AU - N. N. C. Tran
AU - N. T. D. Bui
AU - R. Jeter
PY - 2026
DA - 2026/07/22
PB - medRxiv
DO - 10.64898/2026.07.22.26358655
UR - https://www.medrxiv.org/content/10.64898/2026.07.22.26358655v2
AB - Background: The growing volume of mammography screenings has created severe radiologist shortages, while standard First-In, First-Out (FIFO) reading queues fail to prioritize urgent or complex cases, delaying critical diagnoses. Objective: This study introduces the Density and BI-RADS--Aware Triage and Report Generation (DB-ATRG) framework to fundamentally restructure mammography workflows by automating diagnostic text generation and enabling risk-based case prioritization. Methods: Utilizing the Digital Mammography Dataset for Breast Cancer Diagnosis Research (DMID), we fine-tuned the 4-billion parameter MedGemma 1.5 vision-language model using Quantization and Low-Rank Adaptation (QLoRA). The extracted biomarkers drive a dual-phase triage algorithm that flags extremely dense breasts (ACR Category D) for supplemental screening and dynamically ranks remaining cases using a calculated Cumulative Urgency Score. The clinical impact of this triage workflow was evaluated against a standard FIFO queue using a simulated cohort of 100 mammography cases. Results: DB-ATRG achieved significant improvements over the AMRG baseline in clinical text generation and classification, securing a ROUGE-L score of 0.8012, a METEOR score of 0.8358, and an ACR Density Accuracy of 0.6810. In clinical simulations, the optimized prioritization queue captured 100.0% of high-risk malignancies (BI-RADS 4 and 5) within the first 20% of the reading workload, compared to just 19.2% in the random FIFO queue. This framework effectively accelerated the mean rank position of severe cases from 42.0 down to 7.5. Conclusion: By accurately automating report generation and aggressively prioritizing severe cases, the DB-ATRG framework can drastically optimize clinical resource allocation and accelerate the time-to-diagnosis for the most vulnerable patients.
ER -