Koios DS for Breast

by Koios Medical  · Based in United States →AI-based Clinical Decision Support for Radiologists
General Surgery Oncology Radiology

Subscription
Regulatory Status Disclosed

Overview

Koios DS for Breast is an AI/machine learning-based computer-aided diagnosis (CADx) software device developed by Koios Medical. It is intended for use as an adjunct to diagnostic ultrasound examinations of lesions or nodules suspicious for breast cancer in adult female patients (>= 22 years) with soft tissue breast lesions. The software aids trained interpreting physicians in analyzing breast ultrasound images by automatically classifying lesions into ACR BI-RADS or European U1-U5 Classification System-aligned categories.

Built on an ensemble of algorithms trained with a proprietary dataset of over 2 million ultrasound images and analyzing over 17,000 features per image, Koios DS provides an AI/ML-derived cancer risk assessment. It also generates applicable lexicon-based descriptors to improve overall diagnostic accuracy and reduce interpreting physician variability. The software can also function as an image viewer for multi-modality digital images, including ultrasound and mammography, offering tools to adjust, measure, and document images, and output structured reports.

Koios DS for Breast integrates seamlessly into most PACS workstations, offering rapid deployment and an automated workflow that reduces manual data entry and physician fatigue. Clinical studies have demonstrated that Koios DS improves diagnostic accuracy, increases sensitivity and specificity, and can significantly reduce benign biopsy rates without missing cancers. It is also designed to be a reimbursement-eligible technology.

Reviewed by Pouyan Golshani, MD — Interventional Radiologist

Key Features

  • AI/ML-based clinical decision support
  • Aids in analysis of ultrasound images
  • Classifies breast lesions into ACR BI-RADS or European U1-U5 categories
  • Generates AI/ML-derived cancer risk assessment
  • Provides lexicon-based descriptors
  • Image viewer for multi-modality digital images (ultrasound, mammography)
  • Tools for adjusting, measuring, documenting images, and structured reporting
  • Seamless PACS integration
  • Automated workflow, reduces manual data entry
  • Real-time malignancy risk assessment

Use Cases

  • Early and accurate breast cancer diagnosis
  • Improving diagnostic accuracy for radiologists
  • Reducing benign biopsy rates
  • Reducing inter- and intraobserver variability in breast lesion assessment
  • Automating reporting
  • Enhancing workflow efficiency

What Physicians Need to Know

Evidence Base
Koios DS for Breast aligns its malignancy risk assessment with established guidelines, specifically the ACR BI-RADSu00ae Atlas and the European U1-U5 Classification System. The underlying algorithms are trained on a vast proprietary dataset of over 2 million ultrasound images, analyzing more than 17,000 features per image to classify lesions.
Clinical Validation Studies
The software is FDA-cleared and CE-marked. A multicenter retrospective study published in AJR involving 15 physicians and 900 breast lesions demonstrated improved diagnostic accuracy, detecting up to 6 more cancers per 100 interpreted and potentially reducing benign biopsies by up to 31%. This study also showed a statistically significant improvement in mean AUC (from 0.83 to 0.87) and reduced inter- and intra-observer variability. Other studies indicate 100% accuracy in identifying suspicious lesions for invasive lobular carcinoma and up to 97% for triple-negative breast cancers. A study on triaging BI-RADS 3 lesions reported 100% sensitivity and negative predictive value.
Override Rate Data
Specific override rate data is not explicitly provided in the available information. However, clinical studies indicate improved consistency of interpretation and reduced variability among physicians when using Koios DS, suggesting a high level of agreement with the AI's assessments.
Differential Diagnosis Support
The tool automatically classifies user-selected regions of interest (ROIs) containing breast lesions into four BI-RADS-aligned categories: Benign, Probably Benign, Suspicious, and Probably Malignant. It also displays a continuous graphical confidence level indicator and automatically classifies lesion shape and orientation according to BI-RADS descriptors, aiding in differential diagnosis.
Guideline Update Frequency
The frequency of guideline updates for Koios DS is not explicitly stated. However, Koios Medical is committed to ongoing product development, improvement, and regulatory compliance.
Clinical Workflow Integration
Koios DS integrates seamlessly into most PACS workstations and can be deployed directly on compatible ultrasound scanners (e.g., GE Healthcare's LOGIQ E10 Series, LOGIQ P-Series, and Invenia ABUS 2.0). It automatically captures nodule descriptors, aligns them to BI-RADS, and exports findings to reporting systems, including automatic prepopulation of diagnostic reports. The system offers rapid deployment with no coding required, providing results in 2 seconds or less, and supports a viewer-agnostic workflow.
Physician Tip

Koios DS for Breast serves as an AI-powered 'second opinion' to enhance diagnostic accuracy and reduce variability in breast ultrasound lesion assessment. Leverage its automated lesion classification and BI-RADS alignment to streamline reporting and improve consistency. The system's ability to reduce benign biopsies and potentially detect more cancers can significantly impact patient care and reduce unnecessary procedures. It is particularly beneficial for improving performance among less experienced readers and standardizing interpretations across different levels of expertise.

Koios DS is designed for broad compatibility, integrating with most major PACS platforms and directly with GE Healthcare's LOGIQ E10 Series, LOGIQ P-Series, and Invenia ABUS 2.0 ultrasound systems. This allows for flexible deployment at the point of care or connected to image viewers, facilitating seamless workflow integration and export of results to third-party reporting software.

Details

Category Clinical Decision Support & Reference, Oncology AI, Radiology & Imaging AI
Pricing Subscription
  • Annual subscription pricing tailored to customer size; based on number of analyses and/or number of users
DeploymentOn-premise (PACS integrated), Cloud (via partners)
Compliance
BAA AvailableUnknown AI-estimated
HIPAA CompliantUnknown AI-estimated
FDA Status 1 AI-estimated

Koios DS for Breast received 510(k) clearance (K190442) from the U.S. Food and Drug Administration on July 3, 2019, as a computer-assisted diagnostic software for lesions suspicious for cancer, intended as an adjunct to diagnostic ultrasound for breast cancer.

Integrations
EHR Not specified
Specialties General Surgery, Oncology, Radiology

What the Web Says

Koios DS for Breast is an AI-powered decision support tool designed to assist radiologists in breast cancer diagnosis. Reviews highlight its potential to improve diagnostic accuracy, reduce unnecessary biopsies, and standardize reporting, particularly for less experienced radiologists. While generally well-received, some discussions touch upon the integration challenges and the need for robust validation studies.

Overall: Positive

Strengths

  • Aids in early and accurate breast cancer detection.
  • Reduces false positives and unnecessary biopsies.
  • Standardizes reporting and reduces inter-reader variability.
  • Potentially improves efficiency in radiology workflows.
  • Provides decision support for less experienced radiologists.
  • Non-invasive and integrates with existing imaging modalities.

Limitations

  • Integration challenges with existing PACS and EMR systems.
  • Requires validation and trust from radiologists.
  • Potential for over-reliance on AI by less experienced users.
  • Cost of implementation and ongoing maintenance.
  • Limited long-term outcome data in real-world settings.
  • Data privacy and security concerns with AI platforms.

Based on reviews from: Koios Medical Website, Healthcare IT News, Radiology Today, AuntMinnie.com, PubMed (research articles), LinkedIn (professional discussions)

Last updated: 2026-07-18

Ratings & Reviews

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

Rate Koios DS for Breast

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

Press & Coverage

AJR Online
Should We Ignore, Follow, or Biopsy? Impact of Artificial Intelligence Decision Support on Breast Ultrasound Lesion Assessment
This peer-reviewed article from February 2024 evaluates the impact of Koios DS for Breast on breast ultrasound lesion assessment, finding that AI-based decision support improves accuracy and reduces inter- and intraobserver variability. The study involved a multicenter retrospective review of 900 breast lesions interpreted by 15 physicians with and without the AI system.
2024-02
PMC (via Ultrasonography)
Artificial intelligence in breast ultrasound: application in clinical practice
Published in January 2024, this article discusses the application of AI in breast ultrasound, highlighting Koios DS for Breast as a decision support system that assists physicians in analyzing breast US images by generating a likelihood of malignancy. It references a multicenter retrospective study of 900 breast lesions.
2024-01
PMC
Validating racial and ethnic non-bias of artificial intelligence decision support for diagnostic breast ultrasound evaluation
This December 2023 peer-reviewed publication assesses whether the Koios DS for Breast AI decision support system demonstrates bias based on race or ethnicity, evaluating its performance on 1810 biopsy-proven cases. The study aims to ensure equitable healthcare outcomes with AI integration.
2023-12
HealthImaging
Can AI Rein in Follow-Up Exams and Benign Lesion Biopsies After Breast Ultrasound?
A December 2023 news article reports on a study comparing radiologist assessment and stand-alone AI interpretation using Koios DS for Breast, suggesting that AI could significantly reduce unnecessary follow-up exams. The AI system showed high sensitivity and negative predictive value for detecting breast cancer lesions.
2023-12
Koios Medical
Koios Medical Announces CE Marking for Smart Ultrasound ...
This press release from December 2022 announces that Koios Medical received CE Marking for Koios DS for Breast and thyroid ultrasound, indicating its compliance with European health, safety, and environmental protection standards.
2022-12
Journal of Breast Imaging
Artificial Intelligence for Breast US
This December 2022 article discusses AI for breast ultrasound, featuring Koios DS for Breast as an AI-based clinical decision support software that determines the probability of malignancy for breast lesions on static US images. It highlights a retrospective reader study involving 15 readers and 900 breast US lesions.
2022-12
Hardian Health
How Hardian helped Koios convert their FDA approval to CE marking
A March 2021 article details Hardian Health's collaboration with Koios Medical to convert their FDA regulatory technical files to MDR format, successfully gaining a Class IIa CE mark for Koios DS for Breast. This allowed Koios to expand into the EU market.
2021-03
AuntMinnie
AI can help classify masses found on breast ultrasound
This May 2021 news article reports on research from Yale University indicating that Koios DS for Breast AI software can improve diagnostic accuracy in characterizing masses on screening breast ultrasound exams. The study found the software correctly classified all malignant cases and downgraded many suspicious lesions.
2021-05

Videos

Product demos, reviews, and walkthroughs for Koios DS for Breast.

View all on YouTube

Frequently Asked Questions

Koios DS for Breast is designed to seamlessly integrate with most Picture Archiving and Communication Systems (PACS) workstations, allowing physicians to analyze ultrasound images directly within their current reading environment. It can also be directly installed on GE Healthcare's LOGIQ E10 ultrasound system. Physicians select a region of interest, and the software provides an AI-generated assessment and BI-RADS alignment within seconds, which can then be exported into patient records or reporting systems.
Yes, Koios DS Breast 2.0 received 510(k) clearance from the U.S. Food and Drug Administration (FDA) in 2019, indicating it is considered safe and effective for assisting physicians in analyzing breast ultrasound images. While specific data privacy protocols like HIPAA compliance are not detailed in every search result, Koios Medical's partners, such as RamSoft, emphasize maintaining the highest level of data security and compliance, including HIPAA.
Koios DS for Breast is an assistive artificial intelligence tool intended to support, not replace, the diagnostic judgment of trained interpreting physicians. It requires the user to select the region of interest for analysis and provides a probability of malignancy and BI-RADS alignment. The software functions as a decision support system, enhancing accuracy and consistency rather than making autonomous diagnoses.
Koios DS for Breast has demonstrated improved diagnostic accuracy in breast ultrasound lesion assessment, with studies showing it can significantly enhance a physician's ability to detect cancer and reduce inter- and intraobserver variability. Research indicates it can help detect more cancers and potentially reduce unnecessary biopsies of benign tissue by up to 31%.
Koios DS for Breast is highlighted as an FDA-cleared AI/ML-based computer-aided diagnosis software specifically for breast ultrasound evaluation of suspicious lesions, a distinction not all other AI tools for breast ultrasound currently hold. It aims to improve upon traditional methods by providing an AI-generated cancer risk assessment and aligning with BI-RADS categories, which can enhance diagnostic performance and efficiency. While other AI solutions exist or are in development, Koios DS has a proven track record of FDA clearance for this specific indication.
Koios DS for Breast operates on a subscription-based pricing model, which may be based on the number of analyses or users. New CPT Category III codes, released in early 2022, are now available for practices to use when Koios DS software is utilized in conjunction with traditional breast ultrasound exams. Reimbursement rates from private payers have been reported to range from $50 to over $150 per case, varying by location, payer, and patient health plan.

Related Tools

OCTA
OCTA
Clinical Decision Support & Reference
OCTA Flow is an AI-powered platform that assists ophthalmologists in analyzing Optical Coherence Tomography Angiography (OCTA) scans to enhance diagnostic accuracy and efficiency.
Elsevier
Elsevier
Clinical Decision Support & Reference
ClinicalKey AI is a clinical decision support tool that uses artificial intelligence to provide physicians with rapid access to evidence-based medical information.
EvidenceMD
EvidenceMD
Clinical Decision Support & Reference
EvidenceMD is an AI-powered clinical decision support platform that provides physicians with rapid access to current and relevant medical evidence for informed decision-making.
FAITH project
AI Agent
Clinical Decision Support & Reference
The FAITH project focuses on Federated Artificial Intelligence for Trusted Healthcare, aiming to develop secure and privacy-preserving AI solutions for healthcare, including potential applications for physician directories.
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.
Prof. Valmed
Prof. Valmed - validated medical information GmbH
Clinical Decision Support & Reference
Prof. Valmed is Europe's first CE Class IIb certified AI-supported medical co-pilot, providing healthcare professionals with validated, evidence-based medical information through an innovative AI platform.

See all Clinical Decision Support & Reference tools →

More from Koios Medical

Koios DS
Koios Medical
Oncology AI
Koios DS is an AI-powered clinical decision support software by Koios Medical, assisting physicians in analyzing breast and thyroid ultrasound images for cancer diagnosis, improving accuracy, and streamlining workflows.

View company profile →

Suggest an Edit → | Last Verified: 2026-04-18 | First Added: 2026-04-18
AI Tool Finder
AI-powered search. Results may not be comprehensive.