Literature DB >> 33774339

Benign-malignant pulmonary nodule classification in low-dose CT with convolutional features.

Mehdi Astaraki1, Yousuf Zakko2, Iuliana Toma Dasu3, Örjan Smedby4, Chunliang Wang4.   

Abstract

PURPOSE: Low-Dose Computed Tomography (LDCT) is the most common imaging modality for lung cancer diagnosis. The presence of nodules in the scans does not necessarily portend lung cancer, as there is an intricate relationship between nodule characteristics and lung cancer. Therefore, benign-malignant pulmonary nodule classification at early detection is a crucial step to improve diagnosis and prolong patient survival. The aim of this study is to propose a method for predicting nodule malignancy based on deep abstract features.
METHODS: To efficiently capture both intra-nodule heterogeneities and contextual information of the pulmonary nodules, a dual pathway model was developed to integrate the intra-nodule characteristics with contextual attributes. The proposed approach was implemented with both supervised and unsupervised learning schemes. A random forest model was added as a second component on top of the networks to generate the classification results. The discrimination power of the model was evaluated by calculating the Area Under the Receiver Operating Characteristic Curve (AUROC) metric.
RESULTS: Experiments on 1297 manually segmented nodules show that the integration of context and target supervised deep features have a great potential for accurate prediction, resulting in a discrimination power of 0.936 in terms of AUROC, which outperformed the classification performance of the Kaggle 2017 challenge winner.
CONCLUSION: Empirical results demonstrate that integrating nodule target and context images into a unified network improves the discrimination power, outperforming the conventional single pathway convolutional neural networks.
Copyright © 2021 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  Benign-malignant classification; Deep features; Pulmonary nodule

Mesh:

Year:  2021        PMID: 33774339     DOI: 10.1016/j.ejmp.2021.03.013

Source DB:  PubMed          Journal:  Phys Med        ISSN: 1120-1797            Impact factor:   2.685


  6 in total

1.  APU-Net: An Attention Mechanism Parallel U-Net for Lung Tumor Segmentation.

Authors:  Tao Zhou; YaLi Dong; HuiLing Lu; XiaoMin Zheng; Shi Qiu; SenBao Hou
Journal:  Biomed Res Int       Date:  2022-05-09       Impact factor: 3.246

2.  Form Factors as Potential Imaging Biomarkers to Differentiate Benign vs. Malignant Lung Lesions on CT Scans.

Authors:  Francesco Bianconi; Isabella Palumbo; Mario Luca Fravolini; Maria Rondini; Matteo Minestrini; Giulia Pascoletti; Susanna Nuvoli; Angela Spanu; Michele Scialpi; Cynthia Aristei; Barbara Palumbo
Journal:  Sensors (Basel)       Date:  2022-07-04       Impact factor: 3.847

3.  Spherical Convolutional Neural Networks for Survival Rate Prediction in Cancer Patients.

Authors:  Fabian Sinzinger; Mehdi Astaraki; Örjan Smedby; Rodrigo Moreno
Journal:  Front Oncol       Date:  2022-04-27       Impact factor: 5.738

Review 4.  Radiomics in Early Lung Cancer Diagnosis: From Diagnosis to Clinical Decision Support and Education.

Authors:  Yun-Ju Wu; Fu-Zong Wu; Shu-Ching Yang; En-Kuei Tang; Chia-Hao Liang
Journal:  Diagnostics (Basel)       Date:  2022-04-24

5.  A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images.

Authors:  Mehdi Astaraki; Guang Yang; Yousuf Zakko; Iuliana Toma-Dasu; Örjan Smedby; Chunliang Wang
Journal:  Front Oncol       Date:  2021-12-17       Impact factor: 6.244

Review 6.  The Role of Artificial Intelligence in Early Cancer Diagnosis.

Authors:  Benjamin Hunter; Sumeet Hindocha; Richard W Lee
Journal:  Cancers (Basel)       Date:  2022-03-16       Impact factor: 6.639

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.