After After
Before Before

90159 - Metastasis Detection, AI

AI-ASSISTED METASTASIS DETECTION IN LYMPH NODES – SIMPLIFYING LYMPH NODE ASSESSMENT
Metastases in the lymph nodes are a significant indicator of cancer progression, which makes detection critical for treatment decisions. For lymph node assessment pathologists must review many slides per patient which amounts to a significant workload.

Visiopharm has developed a CE IVD certified AI deep learning application that has been trained to detect metastases in H&E stained lymph nodes associated with breast and colorectal adenocarcinoma.

This highly accurate APP enables pathologists to not only detect areas of metastases in lymph nodes. It also orders, identifies, and assesses metastases based on relevant features for either breast or colorectal cancer metastasis (largest metastasis diameter or total area of metastasis).

Verified with clinical samples, the Metastasis Detection APP improves a tedious workflow, and results in improved sensitivity and specificity of metastasis detection in lymph nodes from colorectal and breast adenocarcinoma.

BENEFITS FROM AI-ASSISTED METASTASIS DETECTION IN YOUR DIAGNOSIS WORKFLOW

  • Multi-indication:
    Verified on breast and colorectal data from 3 clinical sites for CE IVD certification

  • Improved results:
    Increased detection sensitivity compared to manual methods

  • Efficient:
    Automated slide sorting based on indication specific output

 

EFFICIENT WORKFLOW
Visiopharm’s Metastasis Detection APP for whole slide images can easily be integrated into your workflow to become a potential time saver in your review process.

AI Deep Learning Brochure Metastasis Figure JPEG

After biopsies are processed, Visiopharm’s powerful software identifies metastatic regions. Slides with metastatic regions are then ordered and presented based on the area or diameter of the tumor regions identified. This allows for a metric-based review.

AI-SUPPORTED ASSESSMENT OF METASTASIS IMPROVES SENSITIVITY
Verification study on 296 breast cancer and 302 colorectal cancer lymph node samples from 3 clinical sites shows comparable performance for specificity and improved sensitivity compared to manual assessment.

TableModified2

In US: For Research Use Only, not for use in diagnostic procedures.
In EU: CE IVD.

CE IVD
FIGURE 1
FIGURE 1
All relevant lymph node tissue is automatically outlined (in purple) for further analysis.
FIGURE 2
FIGURE 2
Metastases are identified as High Probability (red), Medium Probability (orange), Low Probability (yellow) and the largest is highlighted and measured.
FIGURE 3
FIGURE 3
Zooming in, the largest metastasis is reviewed in detail.
FIGURE 4
FIGURE 4
The remaining metastases in the image are reviewed as necessary, showing High Probability (red), Medium Probability (orange) and Low Probability (yellow).
FIGURE 5
FIGURE 5
The APP also identifies metastases in lymph nodes associated with colon adenocarcinoma and is robust against H&E stain variations.
FIGURE 6
FIGURE 6
The metastases are outlined showing High Probability (red), Medium Probability (orange) and Low Probability (yellow).