"Mama" word taken from the Spanish dictionary meaning "Mother". Translating "Breast Cancer" to Spanish results
The Model has been trained on the proprietary data provided
The work flow for the whole project and the inner working pipeline has been provided and described as below
Refer to the Instruction Manual for better results when the model would be deployed.
- To get great results the user must follow the rules which enable the best image capture aka Data Acquisition for the model.
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.
Taking example
- 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.
- After taking 3 Folders into consideration. This is for sure that the images contained in one particular folder are of one single patient.
- Photometry is either RGB or YBR_FULL .
and the consecutive images listed in that folder are named by the following convention.
GE VSCAN Image
Use the file "data_aug.py" and the function "augment" for augmenting the data set.
t= "True/False") img_data seems to be the data attached to the images dataset available with the developer.
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%”}
- Status Code
- Status
- Output
- Color
- Kappa Score
- Cohen's Kappa (Similar to Kappa Score)
- Fleiss' Kappa
- Positive Predictive Value
- Jaccard Coefficient
- Probability Score
- Sensitivity
- Cut-off Values
Time Elapsed by v1.0
Parameters | Values |
---|---|
Cohen's Kappa Score | 0.89 |
Jaccard Coefficient | 0.90 |
Sensitivity | 0.958295 |
Specificity | 0.920495 |
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 |
Dataset Description
- mavd_1: "Dr. Berg Images", provided by Dr. Wendie Berg. MamaNetv1.0 is trained on this data.
- 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. )
- 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 |