Article

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

Arkadiusz GertychDepartment of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, California, USA. [email protected]Żaneta Świderska-ChadajFaculty of Electrical Engineering, Warsaw University of Technology, Warsaw, PolandZhaoxuan MaDepartment of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USANathan IngDepartment of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USATomasz MarkiewiczDepartment of Pathology, Military Institute of Medicine, Warsaw, PolandSzczepan CierniakDepartment of Pathology, Military Institute of Medicine, Warsaw, PolandHootan SalemiDepartment of Surgery, Cedars-Sinai Medical Center, Los Angeles, California, USASamuel GuzmanDepartment of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, California, USAAnn E. WaltsDepartment of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles, California, USABeatrice S. KnudsenDepartment of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA

2019en

ABI

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.

Identifiers

DOI: 10.1038/s41598-018-37638-9

Citations and references

Cited by 20 references

Metrics — AkademScholar