Skip to content

Latest commit

 

History

History
119 lines (90 loc) · 5 KB

mamanet.md

File metadata and controls

119 lines (90 loc) · 5 KB

MamaNet v1.0

Introduction

"Mama" word taken from the Spanish dictionary meaning "Mother". Translating "Breast Cancer" to Spanish results

Description

The Model has been trained on the proprietary data provided

Work Flow

The work flow for the whole project and the inner working pipeline has been provided and described as below

DSL Flow

Data Acquisition

Refer to the Instruction Manual for better results when the model would be deployed.

  1. To get great results the user must follow the rules which enable the best image capture aka Data Acquisition for the model.

ACRIN6666

Description

Contains 830 folders with .dcm (DICOM) files which further contains 25409 images in total. Few of the sample images have been provided below to give a glimpse of how the data looks like before any type of pre-processing.

Out of these multiple images only 386 contained the corresponding BI-RADS score.

Observations

Taking example

  1. 1.2.276.0.26.1.1.1.2.2006.165.66912.3832895.1 signifies the Folder Name and Study Instance ID . Both refer to the same.
  2. After taking 3 Folders into consideration. This is for sure that the images contained in one particular folder are of one single patient.
  3. Photometry is either RGB or YBR_FULL .

and the consecutive images listed in that folder are named by the following convention.

GE VSCAN Image

Sample ACRIN Image Sample ACRIN Image

Data Preparation

Data Augmentation

Use the file "data_aug.py" and the function "augment" for augmenting the data set.

augment(img_data, config, augmen

t= "True/False") img_data seems to be the data attached to the images dataset available with the developer.

move_file_type(folder, file_path)

Example Metrics

Metrics {"StatusCode":"200","Status":"Success","Output":”Benign”,”BiradsScore”:0, ”Color”:”Green”,”Kappa score”:0.5, “Cohen’s kappa”:0.5, “Fleiss’ kappa”:0.5, “Positive predictive Value”:0.5, “Jaccard coefficient”:0,4, “Probability Score”:0.5, “sensitivity”:0.5, “Cut-off values”:”66%”}

  1. Status Code
  2. Status
  3. Output
  4. Color
  5. Kappa Score
  6. Cohen's Kappa (Similar to Kappa Score)
  7. Fleiss' Kappa
  8. Positive Predictive Value
  9. Jaccard Coefficient
  10. Probability Score
  11. Sensitivity
  12. Cut-off Values

Excel File

Model Statistics

Model Statistics (v1.0)

Speed

Time Elapsed by v1.0

Parameters Values
Cohen's Kappa Score 0.89
Jaccard Coefficient 0.90
Sensitivity 0.958295
Specificity 0.920495

Confusion Marix

Confusion Matrix allows us to quantify the metrics which help in the evaluation of a Classification Model. For Medical use-cases we require the FN (False Negatives) to be the minimum. As mentioned in the example below, we see that a False Negative can have adverse affects on the situation (here: Pregnancy) of the individual.

In Cancer cases this cannot be taken lightly and the FN cases should be minimized and state-of-the-art tools cannot provide Diagnostics but can provide Triage .

BI-RADS 0 1 2 3 4 4a 4b 4c 5 6
0 3 0 0 0 0 0 0 0 1 0
1 0 7 1 0 0 0 0 0 0 0
2 0 0 325 5 6 0 2 4 10 0
3 0 0 10 170 7 1 2 4 8 0
4 0 0 7 5 230 0 0 10 9 0
4a 0 0 1 1 4 56 0 3 2 0
4b 0 0 1 0 1 0 64 2 3 0
4c 0 0 3 0 8 0 0 163 14 0
5 0 0 7 5 2 1 2 13 423 0
6 0 0 1 0 1 0 0 0 2 21

Appendix

Appendix 1

Dataset Description

  1. mavd_1: "Dr. Berg Images", provided by Dr. Wendie Berg. MamaNetv1.0 is trained on this data.
  2. mavd_2 "ACRIN6666", provided by ACRIN: American College of Radiology Imaging Network which is a collation of data from multiple devices(including devices made by GE(General Electric), Philips, etc. )
  3. mavd_3 "NIH_Images", which is a collection of Ultrasound Images provided by NIH(National Institute of Health)
Symbol Name Dataset Proprietary Sponsor/ Provider Devices Average Resolution Number of Images Size
mavd_1 Dr. Berg Images Yes Dr. Wendie Berg Philips Unknown 2267 1.35 GB
mavd_2 ACRIN6666 Yes American Cancer Radiology Imaging Network Philips, GE 1024 * 768 25409 5.35 GB
mavd_3 NIH_Images Yes National Institute of Health Philips Unknown 1227 450.07 MB
mavd_4 Mexico_Guadalraja Yes Dr. Susan Love Foundation GE VScan Variable 719 206.5 MB