Shan Li

Ph.D

Zephex Technology

Co-founder

PLCO (Learn more about this study)

PLCO-289

Jul 24, 2017

Detection and Diagnosis of Lung & Breast Cancer with Deep Learning

The cases of lung and breast cancer are growing exponentially in China in recent decades. In this project, we aim to develop deep learning algorithms for the detection, feature extraction and characterization of malignant lung nodules and breast cancer in chest X-rays and mammograms respectively to assist radiologists to identify cancer at earlier stage with higher accuracy.

In the first phase, we want to use the images from PLCO to develop an image recognition AI to differentiate between cancer and cancer free patients with both high efficiency and accuracy. We need more data points for our training data and the images from PLCO would definitely be crucial for our research.

After we develop the algorithm, a portion of the images from PLCO will be held out for validation tests. We will evaluate the robustness of the model by leveraging the images from PLCO. We will continue to accumulate our training images database in order to build a generalizable, robust model that can be implemented to assist radiologists on their work.

Firstly, we want to develop deep learning algorithms to detect lung cancer nodules and breast cancer from X-rays and mammograms. Hence, we would like to have access to all patients’ images who were diagnosed with cancer as well as those from cancer free patients.

Furthermore we want to characterize malignant and benign nodules based on information extracted from images combined with other patient-specific clinical results.

Ultimately, we want to develop automated diagnosis tools integrated with EMR to assist radiologists and doctors in evaluation of X-rays and mammograms as well as treatment decisions.