scholarly journals An Efficient DA-Net Architecture for Lung Nodule Segmentation

Mathematics ◽  
2021 ◽  
Vol 9 (13) ◽  
pp. 1457
Author(s):  
Muazzam Maqsood ◽  
Sadaf Yasmin ◽  
Irfan Mehmood ◽  
Maryam Bukhari ◽  
Mucheol Kim
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Ct Scan ◽  
Cancer Diagnosis ◽  
Lung Nodule ◽  
Search Space ◽  
Lung Nodules ◽  
Suggested Model ◽  
Lung Cancer Diagnosis ◽  
Segmentation Framework

A typical growth of cells inside tissue is normally known as a nodular entity. Lung nodule segmentation from computed tomography (CT) images becomes crucial for early lung cancer diagnosis. An issue that pertains to the segmentation of lung nodules is homogenous modular variants. The resemblance among nodules as well as among neighboring regions is very challenging to deal with. Here, we propose an end-to-end U-Net-based segmentation framework named DA-Net for efficient lung nodule segmentation. This method extracts rich features by integrating compactly and densely linked rich convolutional blocks merged with Atrous convolutions blocks to broaden the view of filters without dropping loss and coverage data. We first extract the lung’s ROI images from the whole CT scan slices using standard image processing operations and k-means clustering. This reduces the search space of the model to only lungs where the nodules are present instead of the whole CT scan slice. The evaluation of the suggested model was performed through utilizing the LIDC-IDRI dataset. According to the results, we found that DA-Net showed good performance, achieving an 81% Dice score value and 71.6% IOU score.

scholarly journals RADIOLOGICAL AND PATHOLOGICAL CORRELATION OF LUNG NODULES IN A BACKGROUND OF METASTATIC DISEASE

2015 ◽  
Vol 1 (1) ◽  
Author(s):  
Azra Akhtar ◽  
Noreen Akhtar ◽  
Sajid Mushtaq ◽  
Usman Hassan ◽  
Ali Raza Khan
Keyword(s):  
Computed Tomography ◽  
Ct Scan ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Lung Nodule ◽  
Age Groups ◽  
Lung Nodules ◽  
Diagnostic Challenge ◽  
Radiographic Appearance ◽  
Histopathological Findings

Background: Computed tomography (CT) imaging has improved the chances of detecting small indeterminate (<1 cm) lung nodules. The determination of the underlying malignant or benign nature of a lung nodule poses a great diagnostic challenge and depends on a number of factors, including the radiographic appearance of nodule, the presence of non-pulmonary metastases, characteristics of growth and histological criteria. Methods: The medical records of 89 patients admitted to our specialist cancer centre between 2008 and 2013 were reviewed. Patients of all age groups and tumour category were included in the study. Clinical data of these patients were collected and the following parameters were analysed: Radiographic diagnosis, location, size, laterality and number of nodules and histological impression. The radiological findings were then correlated with histopathological findings. The nodules were sub-classified into groups on the basis of size (A = 0–0.5 cm; B = 0.5–0.9 cm; C = 1.0–1.5 cm and D = >1.5 cm). Results: CT scan reports of 89 patients with lung nodules were reviewed. On radiology, 73/89 (82%) were reported to be malignant nodule. Histopathological review of the biopsies of these 89 nodules confirmed malignancy in 50/89 (56.2%) patients. CT scan was found to be highly sensitive (94%, 95% confidence interval [CI]: 83.43–98.68%) but with a very low specificity (33.3%, 95% CI: 19.10–50.22%). CT scan was found to have a higher negative predictive value (81.2%, 95% CI: 54.34–95.73%) and a lower positive predictive value 64.4% (95% CI: 52.31–75.25%) when correlated with histopathological findings. Pathology of these nodules included metastatic sarcoma (27/89; 30.3%) and carcinoma (18/89; 20.2%). The frequency of the biopsy-proven malignant nodules on the right side was 26/45 (57.8%) and on the left side was 24/44 (54.5%) (P = 0.832). Malignant nodules were more frequent in lower lobes (28/43, 65.1%) than in upper lobes (14/32, 43.8%). These two sites combined accounted for 84% of all malignant nodules. There was a significant correlation between nodule size and likelihood of underlying malignancy. The overall prevalence of malignancy in the larger nodules (C and D) was much higher (23/30 and 76.7%) compared to the smaller sized (A and B) nodules (27/58 and 46.8%), P < 0.05.Conclusion: CT scan is a useful tool in the initial clinical assessment of indeterminate lung nodules with high sensitivity (94%) and a high negative predictive value (81.2%).Key words: Computed tomography, fibrosis, indeterminate lung nodule, infection, lung nodule, malignancy, metastases

P62.05 Identifying Risk-Factors for Lung Cancer Diagnosis After Detection of Incidental Lung Nodules

2021 ◽  
Vol 16 (10) ◽  
pp. S1178-S1179
Author(s):  
W. Liao ◽  
M. Smeltzer ◽  
N. Faris ◽  
C. Fehnel ◽  
J. Goss ◽  
...  
Keyword(s):  
Risk Factors ◽  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Lung Nodules ◽  
Lung Cancer Diagnosis

Machine Learning with Data Science-Enabled Lung Cancer Diagnosis and Classification Using Computed Tomography Images

2021 ◽  
Author(s):  
S. Vishwa Kiran ◽  
Inderjeet Kaur ◽  
K. Thangaraj ◽  
V. Saveetha ◽  
R. Kingsy Grace ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Data Science ◽  
Processing Technique ◽  
Ct Images ◽  
Lung Cancer Diagnosis ◽  
Computed Tomography Images ◽  
Diagnosis And Classification

In recent times, the healthcare industry has been generating a significant amount of data in distinct formats, such as electronic health records (EHR), clinical trials, genetic data, payments, scientific articles, wearables, and care management databases. Data science is useful for analysis (pattern recognition, hypothesis testing, risk valuation) and prediction. The major, primary usage of data science in the healthcare domain is in medical imaging. At the same time, lung cancer diagnosis has become a hot research topic, as automated disease detection poses numerous benefits. Although numerous approaches have existed in the literature for lung cancer diagnosis, the design of a novel model to automatically identify lung cancer is a challenging task. In this view, this paper designs an automated machine learning (ML) with data science-enabled lung cancer diagnosis and classification (MLDS-LCDC) using computed tomography (CT) images. The presented model initially employs Gaussian filtering (GF)-based pre-processing technique on the CT images collected from the lung cancer database. Besides, they are fed into the normalized cuts (Ncuts) technique where the nodule in the pre-processed image can be determined. Moreover, the oriented FAST and rotated BRIEF (ORB) technique is applied as a feature extractor. At last, sunflower optimization-based wavelet neural network (SFO-WNN) model is employed for the classification of lung cancer. In order to examine the diagnostic outcome of the MLDS-LCDC model, a set of experiments were carried out and the results are investigated in terms of different aspects. The resultant values demonstrated the effectiveness of the MLDS-LCDC model over the other state-of-the-art methods with the maximum sensitivity of 97.01%, specificity of 98.64%, and accuracy of 98.11%.

scholarly journals Analysis of MicroRNAs in Sputum to Improve Computed Tomography for Lung Cancer Diagnosis

2014 ◽  
Vol 9 (1) ◽  
pp. 33-40 ◽  
Author(s):  
Jun Shen ◽  
Jipei Liao ◽  
Maria A. Guarnera ◽  
HongBin Fang ◽  
Ling Cai ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Lung Cancer Diagnosis

scholarly journals Feasibility and efficacy of early lung cancer diagnosis with chest computed tomography in HIV-infected smokers

AIDS ◽  
2016 ◽  
Vol 30 (4) ◽  
pp. 573-582 ◽  
Author(s):  
Alain Makinson ◽  
Sabrina Eymard-Duvernay ◽  
François Raffi ◽  
Sophie Abgrall ◽  
Sébastien Bommart ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Chest Computed Tomography ◽  
Lung Cancer Diagnosis ◽  
Early Lung Cancer

scholarly journals End-to-End Lung Cancer Diagnosis on Computed Tomography Scans using 3D CNN and Explainable AI

2020 ◽  
Vol 176 (15) ◽  
pp. 1-6
Author(s):  
Chaitanya Rahalkar ◽  
Anushka Virgaonkar ◽  
Dhaval Gujar ◽  
Sumedh Patkar
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Lung Cancer Diagnosis ◽  
Computed Tomography Scans ◽  
Explainable Ai ◽  
End To End ◽  
3D Cnn

scholarly journals Lung Cancer Diagnosis by Fine Needle Aspiration Is Associated With Reduction in Resection of Nonmalignant Lung Nodules

2017 ◽  
Vol 103 (6) ◽  
pp. 1795-1801 ◽  
Author(s):  
Julie A. Barta ◽  
Claudia I. Henschke ◽  
Raja M. Flores ◽  
Rowena Yip ◽  
David F. Yankelevitz ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Diagnosis ◽  
Fine Needle Aspiration ◽  
Needle Aspiration ◽  
Lung Nodules ◽  
Fine Needle ◽  
Lung Cancer Diagnosis
Sign in / Sign up

Export Citation Format

Share Document