Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides

Abstract

During the diagnostic workup of lung adenocarcinomas (LAC), pathologists evaluate distinct histological tumor growth patterns. The percentage of each pattern on multiple slides bears prognostic significance. To assist with the quantification of growth patterns, we constructed a pipeline equipped with a convolutional neural network (CNN) and soft-voting as the decision function to recognize solid, micropapillary, acinar, and cribriform growth patterns, and non-tumor areas. Slides of primary LAC were obtained from Cedars-Sinai Medical Center (CSMC), the Military Institute of Medicine in Warsaw and the TCGA portal. Several CNN models trained with 19,924 image tiles extracted from 78 slides (MIMW and CSMC) were evaluated on 128 test slides from the three sites by F1-score and accuracy using manual tumor annotations by pathologist. The best CNN yielded F1-scores of 0.91 (solid), 0.76 (micropapillary), 0.74 (acinar), 0.6 (cribriform), and 0.96 (non-tumor) respectively. The overall accuracy of distinguishing the five tissue classes was 89.24%. Slide-based accuracy in the CSMC set (88.5%) was significantly better (p < 2.3E-4) than the accuracy in the MIMW (84.2%) and TCGA (84%) sets due to superior slide quality. Our model can work side-by-side with a pathologist to accurately quantify the percentages of growth patterns in tumors with mixed LAC patterns.

Emerging role of deep learning‐based artificial intelligence in tumor pathology

“…Considering different growth patterns of invasive lung adenocarcinoma cells are related with the clinical outcomes of patients, Gertych et al. [32] and Wei et al. [33] developed CNN algorithms to sort each image tile into individual growth pattern and generate a probability map for a WSI, facilitating pathologists to quantitatively report the major and more malignant components of lung adenocarcinoma, such as micropapillary and solid components.…”

“…Current AI algorithms are mainly established on small‐scale data and images from single‐center. The data from single center were still deviation, although researchers have developed methods to augment the dataset, including but not limited to random rotation and flipping, color jittering, and Gaussian blur [32, 35, 38, 39]. Variations exist in slide preparation, scanner models and digitization among different centers.…”

Deep Learning Models for Histopathological Classification of Gastric and Colonic Epithelial Tumours

“…In particular, deep convolutional neural networks (CNNs) have shown state-of-the-art results in a large number of computer vision 3,4 and medical image analysis applications 5 . Promising and successful computational pathology applications include tumour classification and segmentation, mutation classification, and outcome prediction [6][7][8][9][10][11][12][13][14][15][16][17] . These results highlight the potential large benefits that could be obtained when deploying deep learning-based tools and workflow systems to aid surgical pathologists and support histopathological diagnosis, especially for increasing primary screening efficiency and diagnostic double-reading.…”

Peer Review #1 of "Resolution-agnostic tissue segmentation in whole-slide histopathology images with convolutional neural networks (v0.1)"

“…The masks were used to select the positions of image patches in the WSIs to sample for training of the CNNs. (Gertych et al, 2019). The i threshold was determined by calculating the tissue masks of the validation subset of the development set and selecting the threshold value that achieved the highest average Dice score (Dice, 1945).…”