Improving Augmented Human Intelligence to Distinguish Burkitt Lymphoma From Diffuse Large B-Cell Lymphoma Cases

Abstract

Objectives To assess and improve the assistive role of a deep, densely connected convolutional neural network (CNN) to hematopathologists in differentiating histologic images of Burkitt lymphoma (BL) from diffuse large B-cell lymphoma (DLBCL). Methods A total of 10,818 images from BL (n = 34) and DLBCL (n = 36) cases were used to either train or apply different CNNs. Networks differed by number of training images and pixels of images, absence of color, pixel and staining augmentation, and depth of the network, among other parameters. Results Cases classified correctly were 17 of 18 (94%), nine with 100% of images correct by the best performing network showing a receiver operating characteristic curve analysis area under the curve 0.92 for both DLBCL and BL. The best performing CNN used all available training images, two random subcrops per image of 448 × 448 pixels, random H&E staining image augmentation, random horizontal flipping of images, random alteration of contrast, reduction on validation error plateau of 15 epochs, block size of six, batch size of 32, and depth of 22. Other networks and decreasing training images had poorer performance. Conclusions CNNs are promising augmented human intelligence tools for differentiating a subset of BL and DLBCL cases.

Deep Learning for the Classification of Non-Hodgkin Lymphoma on Histopathological Images

“…We used models from the EfficientNet family [ 22 ] for our analysis. The EfficientNet family is composed of multiple models (from B0 to B7), which are each scaled versions of the baseline model B0.…”

“…The EfficientNet family is composed of multiple models (from B0 to B7), which are each scaled versions of the baseline model B0. The models were scaled by the compound scaling method introduced in [ 22 ]. With compound scaling, each consecutive model increased in network width, depth, and image resolution by a set of fixed scaling coefficients.…”

“…With compound scaling, each consecutive model increased in network width, depth, and image resolution by a set of fixed scaling coefficients. This form of scaling utilizes the idea that network width, depth, and image resolution seem to exhibit a certain relationship [ 22 ]. A model with fewer trainable weights can be trained using fewer resources, and its inference is faster [ 22 ].…”

Machine learning and artificial intelligence in haematology

“…Deep learning techniques increasingly drive diagnosis‐supporting tools based on image analysis 9,10 . For instance, Mohlman et al presented an algorithm that accurately distinguishes between diffuse large B‐cell lymphoma and Burkitt lymphoma samples, based on raw images of H&E stained tissue slides fed into convolutional neural networks (a deep learning technique) 31 . Similar algorithms have also been used to identify neoplastic cells from bone marrow aspirates 32 .…”

“…9,10 For instance, Mohlman et al presented an algorithm that accurately distinguishes between diffuse large B-cell lymphoma and Burkitt lymphoma samples, based on raw images of H&E stained tissue slides fed into convolutional neural networks (a deep learning technique). 31 Similar algorithms have also been used to identify neoplastic cells from bone marrow aspirates. 32 Using unsupervised learning techniques, Gandelman et al detected patterns of organ involvement in chronic GVHD.…”