Publication

Prognostic impact of deep learning-based quantification in clinical stage 0-I lung adenocarcinoma

Abstract

Objectives To evaluate the performance of automatic deep learning (DL) algorithm for size, mass, and volume measurements in predicting prognosis of lung adenocarcinoma (LUAD) and compared with manual measurements. Methods A total of 542 patients with clinical stage 0-I peripheral LUAD and with preoperative CT data of 1-mm slice thickness were included. Maximal solid size on axial image (MSSA) was evaluated by two chest radiologists. MSSA, volume of solid component (SV), and mass of solid component (SM) were evaluated by DL. Consolidation-to-tumor ratios (CTRs) were calculated. For ground glass nodules (GGNs), solid parts were extracted with different density level thresholds. The prognosis prediction efficacy of DL was compared with that of manual measurements. Multivariate Cox proportional hazards model was used to find independent risk factors. Results The prognosis prediction efficacy of T-staging (TS) measured by radiologists was inferior to that of DL. For GGNs, MSSA-based CTR measured by radiologists ((R)MSSA%) could not stratify RFS and OS risk, whereas measured by DL using 0 HU ((2D-AI)MSSA(0HU)%) could by using different cutoffs. SM and SV measured by DL using 0 HU ((SM0HU)-S-AI% and (SV0HU)-S-AI%) could effectively stratify the survival risk regardless of different cutoffs and were superior to (2D-AI)MSSA(0HU)%. (SM0HU)-S-AI% and (SV0HU)-S-AI% were independent risk factors. Conclusion DL algorithm can replace human for more accurate T-staging of LUAD. For GGNs, (2D-AI)MSSA(0HU)% could predict prognosis rather than (R)MSSA%. The prediction efficacy of (SM0HU)-S-AI% and (SV0HU)-S-AI% was more accurate than of (2D-AI)MSSA(0HU)% and both were independent risk factors. Clinical relevance statement Deep learning algorithm could replace human for size measurements and could better stratify prognosis than manual measurements in patients with lung adenocarcinoma.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Ontological neighbourhood
Related concepts (31)
Cancer staging
Cancer staging is the process of determining the extent to which a cancer has grown and spread. A number from I to IV is assigned, with I being an isolated cancer and IV being a cancer that has metastasized and spread from its origin. The stage generally takes into account the size of a tumor, whether it has invaded adjacent organs, how many regional (nearby) lymph nodes it has spread to (if any), and whether it has appeared in more distant locations (metastasized).
Deep learning
Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Breast cancer classification
Breast cancer classification divides breast cancer into categories according to different schemes criteria and serving a different purpose. The major categories are the histopathological type, the grade of the tumor, the stage of the tumor, and the expression of proteins and genes. As knowledge of cancer cell biology develops these classifications are updated. The purpose of classification is to select the best treatment. The effectiveness of a specific treatment is demonstrated for a specific breast cancer (usually by randomized, controlled trials).
Show more
Related publications (33)

Multimodal fusion of liquid biopsy and CT enhances differential diagnosis of early-stage lung adenocarcinoma

Jiancheng Yang, Li Zhang, Jun Lu, Hua Zhong, Yunhua Zhang

This research explores the potential of multimodal fusion for the differential diagnosis of early-stage lung adenocarcinoma (LUAD) (tumor sizes < 2 cm). It combines liquid biopsy biomarkers, specifically extracellular vesicle long RNA (evlRNA) and the comp ...
Berlin2024

Multi-site, Multi-domain Airway Tree Modeling

Jiancheng Yang, Yi Wu, Ying Zhu, Boyu Zhang

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolut ...
Amsterdam2023

Self-Supervised Learning for Patient Stratification and Survival Analysis in Computational Pathology: An Application to Colorectal Cancer

Christian Robert Abbet

Over the years, clinical institutes accumulated large amounts of digital slides from resected tissue specimens. These digital images, called whole slide images (WSIs), are high-resolution tissue snapshots that depict the complex interaction of cells at the ...
EPFL2023
Show more