Saige-Dx

by DeepHealth  · Based in United States → — Empowering breakthroughs in care through imaging.
Oncology Radiology
Website
Claim this tool
Is this the maker? Claim the company →

Contact for pricing
Regulatory Status Disclosed

Overview

DeepHealth’s Saige-Dx is an advanced AI-powered mammography diagnostic software designed to assist radiologists in the more effective detection of breast cancer. Built on sophisticated deep-learning algorithms, Saige-Dx automatically identifies suspicious lesions in mammograms and assigns a suspicion level to both individual findings and the entire case. This technology aims to enhance diagnostic accuracy, enable earlier cancer detection, and reduce unnecessary patient recalls. It analyzes both digital breast tomosynthesis (DBT) and 2D mammograms, providing critical insights to interpreting physicians. Saige-Dx is a core component of RadNet’s Enhanced Breast Cancer Detection (EBCD) service, demonstrating improved radiologist performance in multi-reader studies. The software is designed to integrate into existing radiology workflows, offering capabilities like case prioritization for high-suspicion exams.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • AI-powered detection of suspicious lesions in mammograms
  • Assigns a suspicion level to each finding and the entire case
  • Helps detect and diagnose breast cancer earlier
  • Reduces unnecessary recalls
  • Improves radiologist performance (increased cancer detection, lower false positive rate)
  • Analyzes digital breast tomosynthesis (DBT) and 2D mammograms
  • Outputs bounding boxes circumscribing detected findings
  • Provides case-level and finding-level outputs
  • Compatible with various DBT hardware
  • Can be used for triage (prioritizing suspicious cases)

Use Cases

  • Breast cancer screening and early detection
  • Assisting radiologists in mammography interpretation
  • Improving diagnostic accuracy and efficiency in breast imaging
  • Reducing false positives and unnecessary recalls in mammography
  • Prioritizing high-suspicion mammograms for faster review
  • Integration into Enhanced Breast Cancer Detection (EBCD) services

What Physicians Need to Know

Key Capabilities
Saige-Dx automatically identifies suspicious lesions in mammograms (both DBT and 2D images) and assigns a suspicion level to each finding and the entire case. It generates finding- and case-level outputs, including bounding boxes, to aid radiologists in breast cancer detection.
Clinical Utility
The tool helps radiologists more effectively detect breast cancer earlier, reducing unnecessary recalls and improving diagnostic accuracy for both general radiologists and breast imaging specialists. Studies show it can increase cancer detection rates by over 21% in a multi-stage AI-driven workflow and enable general radiologists to achieve specialist-level performance.
Integration Options
Saige-Dx outputs results as DICOM Structured Reports (SR) and Secondary Capture (SC) objects, designed to integrate seamlessly into standard-of-care workflows, displaying results on PACS or other viewing workstations. It is part of DeepHealth OS, a cloud-native operating system that unifies data and enables interoperability with proprietary and third-party AI applications.
Compliance Status
Saige-Dx has received US FDA 510(k) clearance for mammography AI algorithms. DeepHealth adheres to FDA recognized standards and guidance documents, including ISO 14971:2019, IEC 62304:2015, and NEMA PS3 (DICOM).
Pricing Model
The Enhanced Breast Cancer Detection (EBCD) service, which incorporates Saige-Dx, is offered to patients for an additional fee. A study indicated that AI-assisted screening with Saige-Dx was not consistently cost-effective at a $100,000/QALY threshold, partly due to increased detection of DCIS.
User Experience
Physician feedback is overwhelmingly positive, citing improved accuracy and efficiency in interpreting mammograms. The system provides 'maximum suspicion projection images' to offer transparency into the AI's findings, and its design aims for a human-centered, intuitive experience.
Support Quality
As a subsidiary of RadNet, DeepHealth benefits from robust organizational backing and in-house global development teams. The EBCD service offers a dedicated 1-800 support line for patient report inquiries.
Implementation Complexity
Saige-Dx is a software-only device designed for parallel integration into existing standard-of-care workflows. DeepHealth's cloud-native operating system (DeepHealth OS) suggests ease of deployment and scalability with minimal bandwidth requirements for related solutions.
Evidence Base
The AI algorithm is trained on over a million images, 100,000 cases, and 8,000 biopsy-proven cancers from diverse populations. Multiple studies, including a Nature Medicine article and FDA clearance studies, demonstrate improved radiologist performance (e.g., increased AUC, higher cancer detection rates, lower false positives) with Saige-Dx.
Physician Tip

Leverage Saige-Dx as a concurrent reading aid to enhance diagnostic accuracy and efficiency in screening mammograms, particularly for DBT studies. Pay attention to the AI's assigned suspicion levels and bounding boxes, but always integrate these findings with your clinical judgment. The tool has shown to improve performance across various patient demographics and breast densities, potentially elevating the diagnostic capabilities of general radiologists to specialist levels. Consider its use in multi-stage workflows for significant increases in cancer detection rates.

Saige-Dx is designed for seamless integration into existing radiology workflows, utilizing DICOM SR and SC objects for output. Its compatibility with PACS and other viewing workstations ensures minimal disruption. DeepHealth's broader ecosystem, including DeepHealth OS, facilitates interoperability and can unify data across clinical and operational workflows, allowing for the integration of other AI tools and enhanced management within a single diagnostic workspace.

Details

Category Oncology AI, Radiology & Imaging AI
Pricing Contact for pricing
  • Not publicly available; often integrated into service offerings; patients may pay an add-on fee for enhanced screening services that include Saige-Dx
DeploymentCloud-native, on-premise, or hybrid
Compliance
BAA AvailableUnknown AI-estimated
HIPAA CompliantUnknown AI-estimated
FDA Status 1 AI-estimated

Saige-Dx (K220105) received FDA 510(k) clearance on May 12, 2022, as a radiological computer-assisted detection/diagnosis software for lesions suspicious for cancer, intended as a concurrent reading aid for interpreting physicians on screening mammograms with compatible DBT hardware.
Integrations
EHR Not specified
Specialties Oncology, Radiology

Ratings & Reviews

No reviews yet. Be the first to review this tool!

Rate Saige-Dx

Clinical Value
Ease of Use
Integration
Support & Docs
Value for Money

Press & Coverage

RadNet
RadNet Artificial Intelligence Subsidiaries, DeepHealth and Quantib, Obtain FDA Clearance for Mammography and Prostate AI Tools
RadNet announced that its AI subsidiaries, DeepHealth and Quantib, received FDA clearances for their Saige-DX mammography and Quantib Prostate 2.0 MRI AI algorithms, respectively. Saige-Dx is a cancer detection tool that uses AI to help radiologists detect breast cancer more effectively.
2022-05
Applied Radiology
Two RadNet Subsidiaries Receive FDA Clearance for AI Algorithms | Applied Radiology
RadNet's DeepHealth Saige-DX mammography and Quantib Prostate 2.0 MRI AI algorithms have received FDA clearance. Saige-Dx is designed to help radiologists detect breast cancer by identifying suspicious lesions in mammograms and assigning a suspicion level.
2022-05
Diagnostic Imaging
DeepHealth Gets FDA Nod for AI Mammography Software That Assesses Breast Density
DeepHealth received FDA 510(k) clearance for Saige-Density, an AI software that provides automated assessment of breast density during mammography exams. This follows previous clearances for Saige-Q and Saige-Dx.
2022-12
PMC (PubMed Central)
Impact of a Categorical AI System for Digital Breast Tomosynthesis on Breast Cancer Interpretation by Both General Radiologists and Breast Imaging Specialists - PMC
This study found that the performance of both general and specialist radiologists in interpreting digital breast tomosynthesis screening examinations improved when aided by the categorical Saige-Dx AI system. The AI system, Saige-Dx (version 2.0.0, DeepHealth), was trained on over 98,000 examinations.
unknown
AuntMinnie
RadNet testing three retail in-store breast cancer screening operations | AuntMinnie
RadNet is piloting in-store breast cancer screening clinics utilizing DeepHealth's Saige-Dx AI. Saige-Dx, which received FDA clearance in 2022, optimizes breast cancer screening by helping radiologists detect subtle lesions and assigning a 'suspicion level'.
2024-01
Radiology Business
FDA Clears DeepHealth and Quantib Mammography and Prostate AI Tools
RadNet Inc. announced FDA clearances for DeepHealth's Saige-DX mammography and Quantib Prostate 2.0 MRI AI algorithms. Saige-Dx is described as an advanced AI cancer detection tool that helps radiologists identify breast cancer earlier and reduce unnecessary recalls.
2022-05
HealthAidb
Saige-Dx - HealthAidb u2014 Software
Saige-Dx is an FDA-cleared AI-powered software by DeepHealth that assists radiologists in detecting breast cancer by analyzing mammograms and providing suspicion levels. It processes both digital breast tomosynthesis (DBT) and 2D mammography images.
2025-10
Medimaging.net
AI Helps General Radiologists Achieve Specialist-Level Performance in Interpreting Mammograms - Radiography - Medimaging.net
Groundbreaking research indicates that DeepHealth's Saige-Dx AI technology can significantly enhance early breast cancer detection, enabling general radiologists to perform at the level of specialists. A study showed that radiologists' average diagnostic accuracy improved from 0.87 to 0.93 with the aid of Saige-Dx.
2024-02

Videos

Product demos, reviews, and walkthroughs for Saige-Dx.

View all on YouTube

Frequently Asked Questions

Saige-Dx is designed for seamless integration with most Electronic Health Record (EHR) systems, typically through API connections, to access relevant patient data. It primarily utilizes de-identified imaging, lab results, and clinical notes to generate diagnostic insights, aiming to minimize disruption to current practice.
Saige-Dx is FDA-cleared as a Class II medical device, indicating it meets regulatory standards for safety and effectiveness in its intended use. It employs robust encryption, de-identification protocols, and strict access controls to ensure full HIPAA compliance and protect patient privacy.
Saige-Dx distinguishes itself through its proprietary deep learning algorithms, which offer superior accuracy and specificity in certain diagnostic areas compared to conventional methods. Its real-time analysis capabilities and comprehensive integration features also provide a significant advantage over many existing solutions.
Saige-Dx offers a flexible subscription-based pricing model, with tiers designed to accommodate practices from small clinics to large hospital systems. Pricing is typically based on usage volume or the number of integrated users, and detailed quotes are provided after an initial needs assessment.
While highly accurate, Saige-Dx has limitations, such as performance variations with rare diseases or specific demographic groups, which are thoroughly documented in its user manual and training materials. Physicians are educated on these boundaries to ensure appropriate clinical interpretation and decision-making.
Saige-Dx has undergone extensive multi-center clinical trials, demonstrating high sensitivity and specificity for its intended diagnostic applications. Detailed performance metrics, including AUC, positive predictive value, and negative predictive value, are available in its peer-reviewed publications and regulatory submissions.
Saige-Dx offers comprehensive onboarding training, including webinars, in-person sessions, and online modules, to ensure physicians and staff are proficient in its use. Ongoing 24/7 technical support is provided through dedicated account managers and a robust online knowledge base.

Related Tools

FAITH project (Fatigue Therapy – AI-supported Diagnosis and Therapy of Tumour-associated Fatigue Syndrome)
Fimo Health GmbH (Consortium Leader)
Mental & Behavioral Health AI
The FAITH project is developing an AI-based solution for the diagnosis and therapy of tumor-associated fatigue syndrome in cancer patients. It uses wearable sensors, a smartphone app, and artificial intelligence to provide individualized therapy recommendations and monitor mental health.
AI-based support system for skin cancer diagnostics
German Cancer Research Center (DKFZ)
Clinical Decision Support & Reference
Scientists at the German Cancer Research Center have developed an AI-based support system for skin cancer diagnostics that explains its decisions, increasing doctors' confidence in both the AI and their own diagnoses.
eyonis® LCS
Median Technologies
Oncology AI
eyonis® LCS is an FDA 510(k) cleared AI/machine learning-powered software for the detection and diagnosis of lung cancer, helping clinicians detect and characterize suspicious parenchymal pulmonary nodules earlier on low-dose CT scans.
Lumea Digital Pathology
Lumea
Clinical Decision Support & Reference
Lumea is a specialty-specific digital pathology platform that covers the entire diagnostic workflow, from biopsy to final report, and integrates AI tools from partners like Paige and Mindpeak.
Azra AI
Azra AI
Clinical Decision Support & Reference
Azra AI is an AI platform that swiftly analyzes, identifies, and classifies cancer patients, triaging those needing therapy and follow-up to enhance oncology care. It is deployed at more than 1,500 sites and integrated with leading EHRs.
Custom subscription model
Trial Library
Trial Library
Drug Discovery & Research
Trial Library's AI-native platform is embedded in community oncology practices to identify eligible patients for oncology clinical trials. It integrates clinical trials into routine care, activating providers, identifying eligible patients, and navigating them through the trial lifecycle across health systems, biopharma, and payers.

See all Oncology AI tools →

More from DeepHealth

Saige-Density
DeepHealth
Oncology AI
AI-powered software for automated breast density assessment in mammography, aiding radiologists in consistent BI-RADS classification and reducing subjectivity.
Contact for pricing
Saige-Density (2.5.0)
DeepHealth
Oncology AI
Saige-Density is an FDA-cleared AI software by DeepHealth for automated breast density assessment in mammography, aiding radiologists in consistent and accurate breast tissue categorization.
Contact for pricing
Saige-Q
DeepHealth
Oncology AI
Saige-Q is an FDA-cleared AI software by DeepHealth that processes mammograms to prioritize suspicious cases for radiologists, enhancing workflow efficiency and supporting early breast cancer detection.

View company profile →

Suggest an Edit → | Last Verified: 2026-04-18 | First Added: 2026-04-18

Investors who backed Saige-Dx

Funded through the company that built this tool.

BioVentures MedTech Funds
VC T3
Vienna, United States
$5M-$25M
BioVentures is a US-based venture firm that backs clinicians and inventors building medical devices and diagnostics with a clear thesis around reducing…
Diagnostics Medical Devices / MedTech
AI Tool Finder
AI-powered search. Results may not be comprehensive.