scholarly journals A novel technology to integrate imaging and clinical markers for non-invasive diagnosis of lung cancer

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ahmed Shaffie ◽  
Ahmed Soliman ◽  
Xiao-An Fu ◽  
Michael Nantz ◽  
Guruprasad Giridharan ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Sample Size ◽  
Pulmonary Nodules ◽  
Small Sample ◽  
Appearance Model ◽  
Exhaled Breath ◽  
Clinical Markers ◽  
Imaging Data ◽  
Non Invasive ◽  
Diagnosis Of Lung Cancer

AbstractThis study presents a non-invasive, automated, clinical diagnostic system for early diagnosis of lung cancer that integrates imaging data from a single computed tomography scan and breath bio-markers obtained from a single exhaled breath to quickly and accurately classify lung nodules. CT imaging and breath volatile organic compounds data were collected from 47 patients. Spherical Harmonics-based shape features to quantify the shape complexity of the pulmonary nodules, 7th-Order Markov Gibbs Random Field based appearance model to describe the spatial non-homogeneities in the pulmonary nodule, and volumetric features (size) of pulmonary nodules were calculated from CT images. 27 VOCs in exhaled breath were captured by a micro-reactor approach and quantied using mass spectrometry. CT and breath markers were input into a deep-learning autoencoder classifier with a leave-one-subject-out cross validation for nodule classification. To mitigate the limitation of a small sample size and validate the methodology for individual markers, retrospective CT scans from 467 patients with 727 pulmonary nodules, and breath samples from 504 patients were analyzed. The CAD system achieved 97.8% accuracy, 97.3% sensitivity, 100% specificity, and 99.1% area under curve in classifying pulmonary nodules.

scholarly journals Reducing False-Positives in Lung Nodules Detection Using Balanced Datasets

2021 ◽  
Vol 9 ◽  
Author(s):  
Jinglun Liang ◽  
Guoliang Ye ◽  
Jianwen Guo ◽  
Qifan Huang ◽  
Shaohui Zhang
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
False Positives ◽  
Classification Systems ◽  
Cad System ◽  
Nodule Detection ◽  
Diagnosis Of Lung Cancer ◽  
Lung Ct

Malignant pulmonary nodules are one of the main manifestations of lung cancer in early CT image screening. Since lung cancer may have no early obvious symptoms, it is important to develop a computer-aided detection (CAD) system to assist doctors to detect the malignant pulmonary nodules in the early stage of lung cancer CT diagnosis. Due to the recent successful applications of deep learning in image processing, more and more researchers have been trying to apply it to the diagnosis of pulmonary nodules. However, due to the ratio of nodules and non-nodules samples used in the training and testing datasets usually being different from the practical ratio of lung cancer, the CAD classification systems may easily produce higher false-positives while using this imbalanced dataset. This work introduces a filtering step to remove the irrelevant images from the dataset, and the results show that the false-positives can be reduced and the accuracy can be above 98%. There are two steps in nodule detection. Firstly, the images with pulmonary nodules are screened from the whole lung CT images of the patients. Secondly, the exact locations of pulmonary nodules will be detected using Faster R-CNN. Final results show that this method can effectively detect the pulmonary nodules in the CT images and hence potentially assist doctors in the early diagnosis of lung cancer.

Deep Random Forests for Small Sample Size Prediction with Medical Imaging Data

2020 ◽  
Author(s):  
Alexander Katzmann ◽  
Alexander Muehlberg ◽  
Michael Suehling ◽  
Dominik Norenberg ◽  
Julian Walter Holch ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Sample Size ◽  
Random Forests ◽  
Small Sample Size ◽  
Small Sample ◽  
Imaging Data ◽  
Medical Imaging Data

Early diagnosis of lung cancer based on proteome analysis of exhaled breath condensate

2016 ◽  
Vol 71 (2) ◽  
pp. 134-139 ◽  
Author(s):  
K. U. Fedorchenko ◽  
A. M. Ryabokon ◽  
A. S. Kononikhin ◽  
S. I. Mitrofanov ◽  
V. V. Barmin ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Early Diagnosis ◽  
Exhaled Breath Condensate ◽  
Proteome Analysis ◽  
Exhaled Breath ◽  
Diagnosis Of Lung Cancer ◽  
Breath Condensate

Xanthine oxidoreductase and chemosensitivity in non-small cell lung cancer

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. 11077-11077
Author(s):  
R. Myint ◽  
M. Batus ◽  
P. Bonomi ◽  
P. Gattuso ◽  
W. H. Warren ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Median Survival ◽  
Cell Lung Cancer ◽  
Small Sample Size ◽  
Small Cell ◽  
Small Sample ◽  
Xanthine Oxidoreductase ◽  
Small Cell Lung ◽  
Clin Pathol

11077 Background: Xanthine oxidoreductase (XOR) is an enzyme involved in the degradation of purines into uric acid and reactive oxygen species and activation of the MAP kinase pathway involved in apoptosis. Decreased XOR expression was shown in recent studies to be associated with more aggressive disease in breast (Linder et al. Clin Cancer Res. 2005;11:4372–4381) and gastric cancers (Linder et al. J Clin Pathol. 2006;59:965–971). The goal of our study was to show that decreased XOR expression was associated with decreased survival in non-small cell lung cancer (NSCLC). Methods: Tissue specimens from 82 patients (pts) were stained using a XOR specific antibody (36 male and 46 female, age range from 40 to 92 years). These included 41 adenocarcinoma, 31 squamous cell, 8 poorly/moderately differentiated, and 2 bronchioloalveolar. XOR staining intensity was measured on a scale of 0 through 4 (0 being no staining). XOR intensity was correlated with clinical characteristics and outcomes using log rank and COX PH regression analysis. Results: Of the 82 pts, 34 received adjuvant chemo, and of these, 15 specimens had low XOR intensity (0–1). These 15 pts received adjuvant chemo and had a median survival of 543 days. In comparison, 19 of the 34 pts receiving adjuvant chemo had specimens with high XOR intensity (2–4). Their median survival was significantly longer at 2,023 days (p=0.007, hazard ratio=0.33). Conclusions: Although we had a small sample size, in our retrospective study, we found that pts who received adjuvant chemo had a longer survival if their tumors expressed high levels of XOR. XOR could be a potential predictor for responsiveness to adjuvant chemo in patients with NSCLC. Pts with decreased XOR may be less responsive to chemo and thus be able to avoid a toxic treatment if it is not significantly beneficial. [Table: see text] No significant financial relationships to disclose.

Radiotherapy to augment pembrolizumab responses and outcomes in metastatic non-small cell lung cancer: Pooled analysis of two randomized trials.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 9548-9548
Author(s):  
James William Welsh ◽  
Dawei Chen ◽  
Paul Baas ◽  
Joe Y. Chang ◽  
Vivek Verma ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Randomized Trials ◽  
Small Sample Size ◽  
Response Rates ◽  
Pooled Analysis ◽  
Small Cell ◽  
Small Sample ◽  
Small Cell Lung

9548 Background: In metastatic non-small cell lung cancer (mNSCLC), the clinical trials NCT02492568 and NCT02444741 are the only known randomized comparisons of pembrolizumab alone versus pembrolizumab combined with radiation therapy (RT). When the trials were analyzed individually, some potential benefit was observed in the combination therapy group, but the relatively small sample size of each trial limited the detection of potential differences in response rates and outcomes. Hence, we perform a pooled analysis of these two randomized trials to validate and explore whether RT improves mNSCLC patient responses to immunotherapy. Methods: This was a pooled analysis of two randomized trials (NCT02492568 and NCT02444741) of pembrolizumab with or without RT for mNSCLC. Endpoints included the out-of-field overall response rate (ORR) and disease control rate (DCR), progression-free survival (PFS), overall survival (OS), and subgroup analysis of the different RT schemes. Results: In all, 131 patients were analyzed (n = 66 pembrolizumab; n = 65 pembrolizumab/RT (iRT)). ORR was 21% in the pembrolizumab arm vs. 38% in the iRT arm (p = 0.01); DCR was 53% in the pembrolizumab arm vs. 67% in the iRT arm (p = 0.0009); PFS was 4.4 m vs 8.3 m (p = 0.046); and OS was 9.2 m vs 19.2 m (HR 0.66; p = 0.040). Ablative RT (24Gy/3 fractions and 50Gy/4 fractions) had better ORRs of 48% and 54%, respectively, compared to 18% for non-ablative RT (45Gy/15 fractions) and 20% for pembrolizumab alone (p < 0.05, respectively). Conclusions: The addition of RT to immunotherapy significantly increased the ORR of unirradiated lesions and was additionally associated with significant improvements in PFS and OS. Ablative RT was associated with response rates significantly higher than those of non-ablative RT, possibly due to a detrimental effect of non-ablative RT on ALC. These hypothesis-generating findings require dedicated, large-volume, and randomized studies for corroboration. Clinical trial information: NCT02492568 and NCT02444741 .

scholarly journals The value of circulating tumor cells with positive centromere probe 8 in the diagnosis of small pulmonary nodules.

2020 ◽  
Author(s):  
Caidong Liu ◽  
Hongling Chen ◽  
Tong Sun ◽  
Haibo Wang ◽  
Baoan Chen ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Roc Analysis ◽  
Pulmonary Nodules ◽  
Diagnostic Specificity ◽  
Non Invasive ◽  
Ct Examination ◽  
Combined Use ◽  
Small Pulmonary Nodules ◽  
Advanced Development ◽  
Triple Staining

Abstract Background: Circulating cancer cells (CTCs) provide opportunities for early diagnosis and evaluation of cancer stage as a more acceptable non-invasive liquid biopsy. The advanced development and use of CTCs for diagnosis or prognosis just started in recent years.Methods: Fifty three patients, diagnosed as SPNs with a diameter less than 30 mm by CT examination, was enrolled for statistical analysis based on their CTCs level, CT examination features, serum tumor marker concentrations, and histopathological characteristics. Centromere probe 8 (CEP8) was utilized as a marker for CTCs determination. Results: The CTCs level was significantly different between malignant and benign SPNs, as well as between early (0/Ⅰa) and advanced (Ⅰb/Ⅱ/Ⅲ) stages of lung cancer. ROC analysis showed that the CTCs level had diagnostic effect on malignant SNPs. Combined use of CTCs and density feature of CT morphology further improve the overall diagnostic effect on the pTNM stage of these SPNs determined as lung cancer (≤Ia vs. >Ia stage) compared to use of these two markers solely, especially increased the diagnostic specificity. Moreover, in bigger, single, and solid SPNs based on CT morphology, the CTCs level significantly correlated with the malignant histopathology. Additionally, triple staining (CEP8, EpCAM and CKs) results using samples from 22 out of 53 patients showed that more CTCs was detected when CEP8 was used as a marker. Conclusions: The CTCs determined by CEP8 positive would be a potential adjuvant diagnostic marker for the malignance and stage of lung cancer for patients with SPNs.

Sign in / Sign up

Export Citation Format

Share Document