scholarly journals Deep Learning on MRI Images for Diagnosis of Lung Cancer Spinal Bone Metastasis

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Xiaojie Fan ◽  
Xiaoyu Zhang ◽  
Zibo Zhang ◽  
Yifang Jiang
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Bone Metastasis ◽  
False Negative ◽  
Region Growing ◽  
Jaccard Coefficient ◽  
Adaboost Algorithm ◽  
Diagnosis Of Lung Cancer ◽  
Preliminary Classification ◽  
Dice Index

This paper aimed to explore the adoption of deep learning algorithms in lung cancer spinal bone metastasis diagnosis. Comprehensive analysis was carried out with the aid of AdaBoost algorithm and Chan-Vese (CV) algorithm. 87 patients with lung cancer spinal bone metastasis were taken as research subjects, and comprehensive evaluation was made in terms of preliminary classification of images, segmentation results, Dice index, and Jaccard coefficient. After the case of misjudgment on whether there was hot spot was excluded, the initial classification accuracy of the AdaBoost algorithm can reach 96.55%. True positive rate (TPR) was 2.3%, and false negative rate (FNR) was 1.15%. 45 MRI images with hot spots were utilized as test set to detect the segmentation accuracy of CV, maximum between-cluster variance method (OTSU), and region growing algorithm. The results showed that the Dice index and Jaccard coefficient of the CV algorithm were 0.8591 and 0.8002, respectively, which were considerably superior to OTSU (0.6125 and 0.5541) and region growing algorithm (0.7293 and 0.6598). In summary, the AdaBoost algorithm was adopted for image preliminary classification, and CV algorithm for image segmentation was ideal for the diagnosis of lung cancer spinal bone metastasis and it was worthy of clinical promotion.

scholarly journals CAD System for Lung Cancer and its Stages Detection using Image Processing Techniques

2020 ◽  
Vol 9 (4) ◽  
pp. 1612-1615
Keyword(s):  
Lung Cancer ◽  
Image Processing ◽  
False Positive ◽  
False Negative ◽  
Region Growing ◽  
High Rate ◽  
Support Vector ◽  
Image Region ◽  
Image Processing Techniques ◽  
Processing Techniques

The Lung Cancer is a most common cancer which causes of death to people. Early detection of this cancer will increase the survival rate. Usually, cancer detection is done manually by radiologists that had resulted in high rate of False Positive (FP) and False Negative (FN) test results. Currently Computed Tomography (CT) scan is used to scan the lung, which is much efficient than X-ray. In this proposed system a Computer Aided Detection (CADe) system for detecting lung cancer is used. This proposed system uses various image processing techniques to detect the lung cancer and also to classify the stages of lung cancer. Thus the rates of human errors are reduced in this system. As the result, the rate of obtaining False positive and (FP) False Negative (FN) has reduced. In this system, MATLAB have been used to process the image. Region growing algorithm is used to segment the ROI (Region of Interest). The SVM (Support Vector Machine) classifier is used to detect lung cancer and to identify the stages of lung cancer for the segmented ROI region. This proposed system produced 98.5 % accuracy when compared to other existing system

scholarly journals Diagnostic role of bronchoalveolar lavage: A cytohistopathological correlation

2019 ◽  
Vol 9 (1) ◽  
pp. 1441-144
Author(s):  
Prabesh Kumar Choudhary ◽  
Niraj Nepal ◽  
Nirajan Mainali ◽  
Ram Hari Ghimire
Keyword(s):  
Lung Cancer ◽  
Predictive Value ◽  
Malignant Tumors ◽  
False Negative ◽  
Bronchial Biopsy ◽  
Medical College ◽  
Diagnostic Role ◽  
Risk Of Malignancy ◽  
Diagnosis Of Lung Cancer ◽  
Sensitivity Specificity

Background: Tumors of lung are common in Nepal. The risk of malignancy has to be judged prior to surgery for which bronchoscopy is often done. Brocho-alveolar lavage and bronchial biopsy are routine procedure done for diagnosis of lung cancer during bronchoscopy. This study was done to correlate the cytology of broncho-alveolar lavage specimen with histopathology in malignant tumors of the lug in our setup. Materials and methods: This study was conducted at department of pathology, Nobel Medical College from August 2017 to December 2018. Histopathology reports with malignancy were compared to their cytological diagnosis. Results: A total of 141 cases were included in the study. Among the study population,  Bronchogenic carcinoma was found more prevalent in female. The sensitivity, specificity, positive predictive value, negative predictive value and overall accuracy of broncho-alveolar lavage in the diagnosis of lung cancer were 88.1%, 97.98%, 94.7%, 95.1% and 95.03% respectively. Conclusions: Brochoalveolar lavage cytology has a greater accuracy for the diagnosis of lung cancer; however, benign cases need regular follow up as there are false negative cases.

scholarly journals Fine-Grained Lung Cancer Classification from PET and CT Images Based on Multidimensional Attention Mechanism

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
RuoXi Qin ◽  
Zhenzhen Wang ◽  
LingYun Jiang ◽  
Kai Qiao ◽  
Jinjin Hai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Feature Fusion ◽  
Imaging Modality ◽  
Ct Images ◽  
Attention Mechanism ◽  
Rapid Screening ◽  
Clinical Images ◽  
Fine Grained ◽  
Diagnosis Of Lung Cancer

Lung cancer ranks among the most common types of cancer. Noninvasive computer-aided diagnosis can enable large-scale rapid screening of potential patients with lung cancer. Deep learning methods have already been applied for the automatic diagnosis of lung cancer in the past. Due to restrictions caused by single modality images of dataset as well as the lack of approaches that allow for a reliable extraction of fine-grained features from different imaging modalities, research regarding the automated diagnosis of lung cancer based on noninvasive clinical images requires further study. In this paper, we present a deep learning architecture that combines the fine-grained feature from PET and CT images that allow for the noninvasive diagnosis of lung cancer. The multidimensional (regarding the channel as well as spatial dimensions) attention mechanism is used to effectively reduce feature noise when extracting fine-grained features from each imaging modality. We conduct a comparative analysis of the two aspects of feature fusion and attention mechanism through quantitative evaluation metrics and the visualization of deep learning process. In our experiments, we obtained an area under the ROC curve of 0.92 (balanced accuracy = 0.72) and a more focused network attention which shows the effective extraction of the fine-grained feature from each imaging modality.

scholarly journals Clinical Implications of “Atypia” on Biopsy: Possible Precursor to Lung Cancer?

2021 ◽  
Vol 28 (4) ◽  
pp. 2516-2522
Author(s):  
Denise Albano ◽  
Lee Ann Santore ◽  
Thomas Bilfinger ◽  
Melissa Feraca ◽  
Samantha Novotny ◽  
...  
Keyword(s):  
Lung Cancer ◽  
False Negative ◽  
Lung Nodule ◽  
Pulmonary Nodules ◽  
Negative Finding ◽  
Time Period ◽  
Increased Risk ◽  
High Conversion Rate ◽  
Mixed Ground ◽  
Diagnosis Of Lung Cancer

Background: It is common for biopsies of concerning pulmonary nodules to result in cytologic “atypia” on biopsy, which may represent a benign response or a false negative finding. This investigation evaluated time to diagnosis and factors which may predict an ultimate diagnosis of lung cancer in these patients with atypia cytology on lung nodule biopsy. Methods: This retrospective study included patients of the Stony Brook Lung Cancer Evaluation Center who had a biopsy baseline diagnosis of atypia between 2010 and 2020 and were either diagnosed with cancer or remained disease free by the end of the observation period. Cox Proportional Hazard (CPH) Models were used to assess factor effects on outcomes. Results: Among 106 patients with an initial diagnosis of atypia, 80 (75%) were diagnosed with lung cancer. Of those, over three-quarters were diagnosed within 6 months. The CPH models indicated that PET positivity (SUV ≥ 2.5) (HR = 1.74 (1.03, 2.94)), nodule size > 3.5 cm (HR = 2.83, 95% CI (1.47, 5.45)) and the presence of mixed ground glass opacities (HR = 2.15 (1.05, 4.43)) significantly increased risk of lung cancer. Conclusion: Given the high conversion rate to cancer within 6 months, at least tight monitoring, if not repeat biopsy may be warranted during this time period for patients diagnosed with atypia.

scholarly journals Lung Cancer Detection in Radiology Images using CNN

2021 ◽  
Vol 9 (VII) ◽  
pp. 2471-2475
Author(s):  
Sheetal P
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Deep Learning ◽  
Cancer Detection ◽  
Deep Neural Network ◽  
Initial Stage ◽  
Detection And Diagnosis ◽  
Diagnosis Of Lung Cancer ◽  
Lung Cancer Detection

A risk factor is anything that increases chances of getting a disease, such as cancer. Thus diagnosing the cancer at the earliest stage is very important. Nowadays any cancer affects the human and may lead to death and lung cancer is one of its kind.to decrease the mortality rate and give a good treatment for the affected ones we need a better technique to diagnosis the lung cancer in initial stage itself. Early prediction of Lung Cancer will help with the survival of cancer patients. Machine Learning and Deep Learning have been widely used in the diagnosis of Lung Cancer and on the early detection. The main aim of the research is to review the role of deep learning in Lung Cancer detection and diagnosis. So we have used the convolutional neural network (CNN) which is a class of deep neural network which presents lung cancer detection using Radiology Images.

Blockade of C5aR impairs tumor-induced osteoclastogenesis preventing bone metastasis colonization in lung cancer

2016 ◽  
Author(s):  
Daniel Ajona ◽  
Carolina Zandueta ◽  
Leticia Corrales ◽  
Maria J. Pajares ◽  
Elena Martinez-Terroba ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Bone Metastasis
Sign in / Sign up

Export Citation Format

Share Document