Integration of convolutional neural networks for pulmonary nodule malignancy assessment in a lung cancer classification pipeline.

Comput Methods Programs Biomed

BCN Medtech, Dept. of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain; ICREA, Barcelona, Spain. Electronic address:

Published: March 2020

The early identification of malignant pulmonary nodules is critical for a better lung cancer prognosis and less invasive chemo or radio therapies. Nodule malignancy assessment done by radiologists is extremely useful for planning a preventive intervention but is, unfortunately, a complex, time-consuming and error-prone task. This explains the lack of large datasets containing radiologists malignancy characterization of nodules; METHODS: In this article, we propose to assess nodule malignancy through 3D convolutional neural networks and to integrate it in an automated end-to-end existing pipeline of lung cancer detection. For training and testing purposes we used independent subsets of the LIDC dataset; RESULTS: Adding the probabilities of nodules malignity in a baseline lung cancer pipeline improved its F1-weighted score by 14.7%, whereas integrating the malignancy model itself using transfer learning outperformed the baseline prediction by 11.8% of F1-weighted score; CONCLUSIONS: Despite the limited size of the lung cancer datasets, integrating predictive models of nodule malignancy improves prediction of lung cancer.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2019.105172DOI Listing

Publication Analysis

Top Keywords

lung cancer
24
nodule malignancy
16
convolutional neural
8
neural networks
8
malignancy assessment
8
f1-weighted score
8
malignancy
6
lung
6
cancer
6
integration convolutional
4

Similar Publications

Background: The sensitivity of reverse-transcription polymerase chain reaction (RT-PCR) is limited for diagnosis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Chest computed tomography (CT) is reported to have high sensitivity; however, given the limited availability of chest CT during a pandemic, the assessment of more readily available imaging, such as chest radiographs, augmented by artificial intelligence may substitute for the detection of the features of coronavirus disease 2019 (COVID-19) pneumonia.

Methods: We trained a deep convolutional neural network to detect SARS-CoV-2 pneumonia using publicly available chest radiography imaging data including 8,851 normal, 6,045 pneumonia, and 200 COVID-19 pneumonia radiographs.

View Article and Find Full Text PDF

Clinical utility and predictive value of cerebrospinal fluid cell-free DNA profiling in non-small cell lung cancer patients with leptomeningeal metastasis.

Neoplasia

December 2024

Department of Internal Medicine, National Taiwan University Hospital and College of Medicine, National Taiwan University, Taipei, Taiwan; Department of Internal Medicine, National Taiwan University Hospital Hsinchu Branch, Hsinchu, Taiwan.

Leptomeningeal metastasis (LM) is a challenging complication of non-small cell lung cancer (NSCLC). Cerebrospinal fluid (CSF) cell-free DNA (cfDNA) analysis using next-generation sequencing (NGS) offers insights into resistance mechanisms and potential treatment strategies. We conducted a study from February 2022 to April 2023 involving patients from five hospitals in Taiwan who had recurrent or advanced NSCLC with LM.

View Article and Find Full Text PDF

A 26-year-old male presented to a hospital with complaints of hemoptysis and right scrotal swelling. Computed tomography (CT) revealed right testicular swelling, multiple lung metastases, and small intestinal wall thickening. The patient's β-human chorionic gonadotropin, alpha-fetoprotein, lactate dehydrogenase, and hemoglobin levels were 103.

View Article and Find Full Text PDF

Background: Lung cancer is a form of cancer that is responsible for the largest incidence of deaths attributed to cancer worldwide. Non-small cell lung cancer (NSCLC) is the most prevalent of all the subtypes of the disease. Treatment with tyrosine kinase inhibitors (TKI) may help some people who have been diagnosed with non-small cell lung cancer.

View Article and Find Full Text PDF

Background: It has been proposed that risk model-based strategies could serve as viable alternatives to traditional risk factor-based approaches in lung cancer screening; however, there has been no systematic discussion. In this review, we provide an overview of the benefits, harms, and cost-effectiveness of these two strategies in lung cancer screening application, as well as discussing possible future research directions.

Methods: Following the PRISMA guidelines, a comprehensive literature search was conducted across PubMed, Web of Science, Cochrane libraries, and EMBASE from January 1994 to April 2024.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!