After After
Before Before

10159 - H&E, Metastasis Detection, AI

DEVELOPED FOR METASTASIS DETECTION IN H&E STAINED LYMPH NODES

Finding metastases in H&E stained lymph node sections can be time consuming and challenging. The differences between small metastases, epithelial tissue and clusters of macrophages are often subtle, and would not be possible to distinguish using conventional image analysis techniques.

This APP utilizes AI/deep learning and has been trained to detect micro- and macro-metastases in lymph nodes associated with breast cancer, stained with H&E. The deep learning architecture allows it to recognize complex structures and interpret the tissue context when analyzing an image, making it an efficient tool for detecting even small metastases that are not easily noticed.

KEYWORDS
Lymph node, screening, metastasis, H&E, hematoxylin, eosin, deep learning, AI, image analysis, breast cancer, DeepLabv3+

METHODS
The APP was developed using the using the DeepLabv3+ neural network available with AuthorTM AI. The neural network uses a cascade of layers of nonlinear processing units for feature extraction and transformation, with each successive layer using the output from the previous layer as input. DeepLabv3+ uses an encoder-decoder structure with atrous spatial pyramid pooling (ASPP) that is able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective field-of-views. This means that instead of using step-wise upsampling blocks to incorporate features from different levels, this network only needs two upsampling steps, i.e. it is faster to train and analyze than e.g. the U-Net. All of this also means that the decoder module can refine the segmentation results along the object boundaries more precisely. For more information on the network architecture, see [1]

QUANTITATIVE OUTPUT VARIABLES
The output variables obtained from this protocol are:

  • Largest Tumor Area [mm2

  • Largest Tumor Diameter (estimate) [mm]

AUXILIARY APP
There are no auxiliary APPs available.

WORKFLOW
The APP contains four protocols:
01 Tissue Detect: Outlines tissue on the slide for further analysis.
02 Metastasis Detection: Identifies possible metastases using AI.
03 Post Processing: Post-processes the classification results, improving accuracy and visualization.
04 Find Largest: Locates the single largest metastasis and calculates the area or diameter.

The protocols can be run separately or as one using the APP sequence functionality in VIS.

STAINING PROTOCOL
There is no staining protocol available.

ADDITIONAL INFORMATION
To run the APP, a NVIDIA GPU with minimum 4 GB RAM is required.
The APP utilizes the Visiopharm EngineTM AI and Viewer software modules, where EngineTM AI offers an execution platform to expand processing capability and speed of image analysis. The Viewer allows a fast review together with several types of image adjustment properties e.g. outlining of regions, annotations and direct measures of distance, curve length, radius, etc.
By adding the AuthorTM AI module the APP can be customized to fit other purposes. AuthorTM AI offers a comprehensive and dedicated set of tools for creating new fit-for-purpose analysis APPs, and no programming experience is required.

REFERENCES

LITERATURE
1. Chen, L., et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European conference on computer vision (ECCV) 2018, 801-181, arXiv:1802.02611

RUO
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 – not present) and Low Probability (yellow).
FIGURE 3
FIGURE 3
The largest metastasis is highlighted, and its area is calculated.
FIGURE 4
FIGURE 4
Zooming in, the outlined metastasis is reviewed in detail.
FIGURE 5
FIGURE 5
The size of the metastasis is easily measured in the software.