ULTRASOUND BREAST CANCER

PROBLEM STATEMENT

Breast cancer is one of the most common causes of the death among women worldwide. Early detection helps in reducing the number of deaths. Despite many significant efforts and promising outcomes in this domain, accurate segmentation and classification remain a challenging task. Historically, it was a difficult and time consuming process to review the medical images of breast cancer using ultrasound scan and identify the tumor in the breast . The objective of this case study is to use evaluate and classify the type of tumor using ultra sound breast images. After a detailed analysis and research, Ai labs developed and implemented a Proof of Concept (POC) using its proprietary engine Minsky™ to automatically evaluate and classify the type of Breast tumor to aid in early treatment.

KEY BENEFITS (MINSKY™)

• User-Friendly cloud based AI platform
• Scalable across various domains/data.
• Provides you a list of % dependency features that can be used to optimize the outcomes.
• Ability to fine tune or optimize the models by trying different algorithms / prediction attributes
• Easy integration with other third party solutions such as TABLEAU for data visualization

RESULTS/BENEFITS

• Assisting clinicians in the early diagnosis of a variety of conditions and diseases from ultra-sound imagery.
• Reduce the rates of misdiagnosis and missed diagnosis.
• Patients can get more safer and effective treatment.
• Reduce time and cost involved in the process.
• Effectively improve the quality of medical services.

SOLUTION OVERVIEW:

After comprehensively evaluating the Client’s historical ultra-sound image data, we classified the tumor type into the following three categories
A. Normal
B. Benign
C. Malignant
We analyzed these images using Deep learning algorithms by classifying the tumor types into the above mentioned three categories. Historical labelled image data was used for modelling using selected deep learning Algorithms. Real time image data was then fed to the trained Minsky™ models to predict and classify the images as Normal or Benign or Malignant tumor.

Minsky™ DL Results for Normal Class

Based on the data from Fig 1 above, our analysis shows that CNN (87.0%) highest model accuracy. The above image shows the result of Normal class (99%) with the best matching image.

Minsky™ DL Results for Benign Tumor

Based on the data from Fig 2 above, our analysis shows that CNN (87.0%) highest model accuracy. The above image shows the result of Benign class (99%) with the best matching image.

Minsky™ DL Results for MALIGNANT TUMOR

Based on the data from Fig 3 above, our analysis shows that CNN (87.0%) highest model accuracy. The above image shows the result of Malignant class (99%) along with the best matching image.