Automated Diagnosis of Lymphoma with Digital Pathology Images Using Deep Learning.
Hanadi El Achi, Tatiana Belousova, Lei Chen, Amer Wahed, Iris Wang, Zhihong Hu, Zeyad Kanaan, Adan Rios, Andy N D Nguyen
Author Information
Hanadi El Achi: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Tatiana Belousova: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Lei Chen: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Amer Wahed: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Iris Wang: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Zhihong Hu: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Zeyad Kanaan: Department of Internal Medicine, Hematologic Oncology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Adan Rios: Department of Internal Medicine, Hematologic Oncology Section, University of Texas Health Science Center at Houston, Texas, TX, USA.
Andy N D Nguyen: Department of Pathology and Laboratory Medicine, Hematopathology Section, University of Texas Health Science Center at Houston, Texas, TX, USA Nghia.D.Nguyen@uth.tmc.edu.
Recent studies have shown promising results in using Deep Learning to detect malignancy in whole slide imaging, however, they were limited to just predicting a positive or negative finding for a specific neoplasm. We attempted to use Deep Learning with a convolutional neural network (CNN) algorithm to build a Lymphoma diagnostic model for four diagnostic categories: (1) benign lymph node, (2) diffuse large B-cell Lymphoma, (3) Burkitt Lymphoma, and (4) small lymphocytic Lymphoma. Our software was written in Python language. We obtained digital whole-slide images of Hematoxylin and Eosin stained slides of 128 cases including 32 cases for each diagnostic category. Four sets of 5 representative images, 40x40 pixels in dimension, were taken for each case. A total of 2,560 images were obtained from which 1,856 were used for training, 464 for validation, and 240 for testing. For each test set of 5 images, the predicted diagnosis was combined from the prediction of five images. The test results showed excellent diagnostic accuracy at 95% for image-by-image prediction and at 100% for set-by-set prediction. This preliminary study provided a proof of concept for incorporating automated Lymphoma diagnostic screen into future pathology work-flow to augment the pathologists' productivity.
