Koios DS for Breast

by Koios Medical  · Based in United States → — Confident diagnosis in seconds. Smart Ultrasound® Software.
General Surgery Oncology Radiology

Subscription model
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 utilizes algorithms trained on a proprietary dataset of over 2 million ultrasound images, analyzing over 17,000 features per image to classify and assess breast cancer risk. The software aligns its output with BI-RADS categories.
Clinical Validation Studies
Multiple studies have validated Koios DS for Breast. A multicenter retrospective study involving 900 breast lesions and 15 physicians (11 radiologists, two surgeons, two obstetrician/gynecologists) showed that AI-based decision support improved the accuracy of sonographic breast lesion assessment and reduced inter- and intraobserver variability. In this study, the mean reader AUC for cases reviewed with US only was 0.83, which improved to 0.87 with Koios DS. The system's standalone sensitivity was 98%, higher than the average reader sensitivity of 94%. Another study demonstrated that Koios DS could significantly reduce unnecessary biopsies, particularly for less experienced radiologists, and improved diagnostic performance. A quality assurance review over 18 months showed that radiologists using Koios DS increased cancer detection rates while significantly reducing benign biopsies. Koios DS has been shown to reduce benign biopsies by up to 31% and potentially detect up to 6 more cancers per 100 interpreted cases. It also improved consistency of interpretation.
Alert Fatigue Management
Koios DS is designed to battle physician fatigue, stress, and burnout by automating workflows and eliminating manual data entry. It provides an automated workflow that aims to give physicians more time to focus on critical tasks.
Override Rate Data
While specific override rate data is not explicitly provided, studies indicate that physicians' diagnostic performance improved with the use of Koios DS. The system provides a 'second opinion' to assist physicians in classifying suspicious lesions and aligning to BI-RADS categories. The software's output is displayed graphically, showing the DS-generated classification and confidence of assessment.
Differential Diagnosis Support
Koios DS for Breast assists in differential diagnosis by generating a likelihood of malignancy for user-selected regions of interest (ROIs) containing breast lesions. It classifies lesions into categories such as benign, probably benign, suspicious, and probably malignant, aligning with BI-RADS categories. The software automatically characterizes selected image data to generate an AI/ML-derived cancer risk assessment and selects applicable lexicon-based descriptors.
Clinical Workflow Integration
Koios DS software integrates into most PACS workstations and can be deployed directly on ultrasound scanners or connected to any PACS. It allows users to select ROIs for analysis without exiting their image viewing software. The system analyzes and captures nodule descriptors automatically, aligning to BI-RADS, and allows for exporting findings to reporting systems and saving them as a secondary capture to PACS. Koios DS is ultrasound hardware manufacturer agnostic and accepts DICOM compliant digital medical files.
Decision Audit Trail
The software supports the generation of structured outputs for inclusion in clinical reports. This functionality implies a record of the decision support provided, which can contribute to an audit trail.
Physician Tip

Koios DS for Breast acts as an on-demand second opinion, providing AI-powered analysis of breast ultrasound images to assist in classifying lesions and assessing malignancy risk. It can help improve diagnostic accuracy, reduce inter- and intraobserver variability, and potentially decrease unnecessary biopsies. Physicians should be trained in its use to identify breast lesions or thyroid nodules for analysis. The system's output, including the likelihood of malignancy and alignment to BI-RADS categories, can be reviewed alongside clinical details to formulate the best management plan. Koios DS can be particularly beneficial for less experienced radiologists in improving their diagnostic performance.

Koios DS for Breast integrates seamlessly with most major PACS workstations and can be directly available on ultrasound scanners like the GE Healthcare LOGIQ™ E10. It is ultrasound hardware manufacturer agnostic and can process DICOM compliant digital medical files from various devices. The software facilitates a flexible, viewer-agnostic workflow, allowing users to select images and regions of interest through their own image viewers. It also supports exporting findings to reporting systems and saving them as a secondary capture to PACS. Koios DS is also integrated into RamSoft's cloud-native RIS/PACS platforms.

Details

Category Clinical Decision Support & Reference, Oncology AI, Radiology & Imaging AI
Pricing Subscription model
DeploymentOn-premise (PACS integration, direct download), embedded in ultrasound scanners
Data Export Yes
Training Yes
Compliance
BAA AvailableUnknown
HIPAA Compliant Yes AI-estimated
FDA Status Cleared AI-estimated
GDPR Yes AI-estimated
Integrations
EHR Not specified
Specialties General Surgery, Oncology, Radiology

Support & Reliability

Training Provided Yes

FDA clearance history

This product’s FDA authorization. From FDA’s list of AI-enabled medical devices; each number links to FDA’s record.

Decision dateNumberName as listed by FDA
2019-07-03K190442 510(k)Koios DS for Breast

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
No press coverage or publications on file yet. Know of some? Suggest an edit →

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 integrate seamlessly into most PACS workstations. Physicians can select a region of interest for analysis, and the software automatically analyzes nodule descriptors, aligns them to BI-RADS, and dynamically calculates ratings. The findings can then be exported to a reporting system and saved as a secondary capture to PACS.
Koios DS for Breast is FDA-cleared and CE-marked, indicating it is deemed safe and effective for assisting physicians in analyzing breast ultrasound images. It aligns with BI-RADS classifications from the American College of Radiology.
Koios DS for Breast is intended as an adjunct to diagnostic ultrasound examinations and not for primary interpretation of mammography images. It should not be used on images with Doppler, elastography, or other overlays, or on sites of post-surgical excision. Patient management decisions should not be made solely based on Koios DS analysis.
While Koios DS for Breast is an FDA-cleared AI solution for breast ultrasound image analysis, other AI-powered systems exist for breast lesion analysis, such as S-Detect for Breast US and QVCAD. Koios DS focuses specifically on ultrasound images for breast and thyroid, not MRI, CT, or mammography.
Studies have shown that Koios DS for Breast improves radiologists' diagnostic performance, particularly for less experienced practitioners, and can potentially reduce unnecessary biopsies. It has demonstrated improved accuracy in assessing sonographic breast lesions and reduced inter- and intra-observer variability among physicians.
Clinical studies indicate that using Koios DS for Breast can lead to a significant reduction in unnecessary benign breast biopsies. This is achieved by improving the accuracy of malignancy risk assessment, helping physicians to better differentiate between benign and malignant lesions.
Yes, Koios Medical has indicated that new CPT Category 3 codes from the American Medical Association can be used by clinicians to bill for the use of Koios DS software in interpreting, classifying, and reporting findings from traditional ultrasound examinations.

Related Tools

Stanford University
Stanford University
Clinical Decision Support & Reference
Stanford Online's "AI in Healthcare" program provides a comprehensive overview of artificial intelligence's applications and implications within the medical field.
RADIN Health
RADIN Health
Clinical Decision Support & Reference
RADINA is an AI-powered platform by RADIN Health designed to optimize radiology workflows, enhance diagnostic accuracy, and streamline reporting.
Med-PaLM 2
Google
Clinical Decision Support & Reference
Med-PaLM 2 is a large language model from Google, fine-tuned for healthcare to provide high-quality answers to medical questions and support clinical decision-making.
Pacmed Critical Discharge
Pacmed
Clinical Decision Support & Reference
Pacmed Critical Discharge is an AI tool that predicts the probability of death or readmission within seven days of ICU discharge, providing explainable insights for physicians.
AiZtech Labs
AiZtech Labs
Clinical Decision Support & Reference
AiZtech Labs provides enterprise-grade AI solutions for healthcare, focusing on operational efficiency, diagnostic accuracy, and patient care workflows for providers and health systems.
Stethophone Pro
Sparrow Acoustics
Cardiology AI
Stethophone Pro transforms smartphones into advanced cardiac screening tools, enabling clinicians to capture, interpret, and visualize heart sounds for early detection of cardiovascular diseases.

See all Clinical Decision Support & Reference tools →

More in the Koios DS line

Koios DS Koios DS for Breast (this page)

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 → | Report an issue | Last Verified: 2026-11-08 | First Added: 2026-04-18
AI Tool Finder
AI-powered search. Results may not be comprehensive.