Machine Learning and Feature Selection Methods for Disease Classification With Application to Lung Cancer Screening Image Data

As awareness of the habits and risks associated with lung cancer has increased, so has the interest in promoting and improving upon lung cancer screening procedures. Recent research demonstrates the benefits of lung cancer screening; the National Lung Screening Trial (NLST) found as its primary result that preventative screening significantly decreases the death rate for patients battling lung cancer. However, it was also noted that the false positive rate was very high (>94%).In this work, we investigated the ability of various machine learning classifiers to accurately predict lung cancer nodule status while also considering the associated false positive rate. We utilized 416 quantitative imaging biomarkers taken from CT scans of lung nodules from 200 patients, where the nodules had been verified as cancerous or benign. These imaging biomarkers were created from both nodule and parenchymal tissue. A variety of linear, nonlinear, and ensemble predictive classifying models, along with several feature selection methods, were used to classify the binary outcome of malignant or benign status. Elastic net and support vector machine, combined with either a linear combination or correlation feature selection method, were some of the best-performing classifiers (average cross-validation AUC near 0.72 for these models), while random forest and bagged trees were the worst performing classifiers (AUC near 0.60). For the best performing models, the false positive rate was near 30%, n...
Source: Frontiers in Oncology - Category: Cancer & Oncology Source Type: research

Related Links:

ConclusionThe present study found that pretreatment PET parameters were of not predictive value for PFS and OS in patients with SCLC.
Source: Revista Espanola de Medicina Nuclear e Imagen Molecular - Category: Nuclear Medicine Source Type: research
Immune checkpoint inhibitors that block the programmed death 1/programmed death ligand 1 pathways are widely used to treat advanced lung cancers. There are seldom cases of histologic transformation reported after treatment with immunotherapy. Here, we report the case of a 69 ‐year‐old man with stage IV lung squamous cell carcinoma. He received pembrolizumab monotherapy and had a partial response. After 22 cycles of pembrolizumab, chest computed tomography (CT) showed a left hilar tumor, bilateral pleural effusion and lymphadenopathy. The cytology of pleural effusion and bronchoscopic biopsy of an intraluminal lesion re...
Source: Thoracic Cancer - Category: Cancer & Oncology Authors: Tags: CASE REPORT Source Type: research
This study investigated the risk of occupational asbestos exposure for lung cancer development, utilizing a hospital-based case-control study. Subjects were patients who received a thoracic CT scan at Persahabatan Hospital, Jakarta. The cases had primary lung cancer confirmed by histology, the controls were negative for lung cancer. The cumulative occupational asbestos exposure was calculated by multiplying the exposure intensity by the years of exposure. The exposure intensity was obtained by adopting the weighted arithmetic mean value of asbestos exposure from a job-exposure matrix developed in Korea. The primary data an...
Source: International Journal of Environmental Research and Public Health - Category: Environmental Health Authors: Tags: Article Source Type: research
Conclusions: EBUS-TBNA combined with PET/CT could effectively reduce false-positive and false-negative rates in the diagnosis of hilar and mediastinal lymphadenopathy, which might provide accurate staging, determine optimum therapeutic strategy and improve survival in patients with lung cancer.
Source: Journal of Cancer Research and Therapeutics - Category: Cancer & Oncology Authors: Source Type: research
The association between gut microbiota and the lung immune system has been attracting increasing interest. Here, we report a case of pancreatic cancer in which the dipeptidyl peptidase ‐4 inhibitor vildagliptin induced unusual manifestations of interstitial pneumonia, possibly under the influence ofLactobacillus paraplantarum probiotic supplementation. Chest computed tomography and positron emission tomography showed multiple ground ‐glass nodules (GGNs) mimicking metastatic lung cancer. Transbronchial biopsy specimens showed mild fibrosis and infiltration of lymphocytes consisting of more CD4+ than CD8+ cells. The CD4...
Source: Thoracic Cancer - Category: Cancer & Oncology Authors: Tags: CASE REPORT Source Type: research
CONCLUSION: A survey of trial candidates provides useful information regarding personal motivation, media use, and lifestyle. Unpaid media events appear superior in generating recruitment, while print media may be superior to radio and television in selecting eligible recruits. The utility of individual print media characteristics appears to differ from the commercial advertising literature. Further research on marketing in clinical trials is encouraged to improve recruitment ( registration: NCT00751660, ). PMID: 31894702 [PubMed - as supplied by publisher]
Source: Clinical Trials - Category: Research Authors: Tags: Clin Trials Source Type: research
We present the case of an asymptomatic woman, a chronic heavy smoker, who presented with an incidental lung mass and mediastinal lymphadenopathy. Bronchoscopy with transbronchial biopsy and endobronchial ultrasound-guided transbronchial needle aspiration did not show malignancy. A positron emission tomography/computed tomography scan showed increased uptake with a standardized uptake value of 26.4 in the mediastinal lymph node and an additional hypermetabolic right supraclavicular lymph node. Surgical biopsy of the supraclavicular node revealed non-necrotizing granuloma. Discussion of the clinical dilemma is provided. ...
Source: Respiratory Care - Category: Respiratory Medicine Authors: Tags: Respir Med Case Rep Source Type: research
While there has been controversy over when and how often women should be screened for breast cancer using mammograms, studies consistently show that screening can lead to earlier detection of the disease, when it’s more treatable. So improving how effectively mammograms can detect abnormal growths that could be cancerous is a priority in the field. AI could play a role in accomplishing that—computer-based machine learning might help doctors to read mammograms more accurately. In a study published Jan. 1 in Nature, researchers from Google Health, and from universities in the U.S. and U.K., report on an AI model ...
Source: TIME: Health - Category: Consumer Health News Authors: Tags: Uncategorized Artifical Intelligence Breast Cancer embargoed study MSFTAI2019 Source Type: news
The analysis of multi-modality positron emission tomography and computed tomography (PET-CT) images for computer-aided diagnosis applications (e.g., detection and segmentation) requires combining the sensitivity of PET to detect abnormal regions with anatomical localization from CT. Current methods for PET-CT image analysis either process the modalities separately or fuse information from each modality based on knowledge about the image analysis task. These methods generally do not consider the spatially varying visual characteristics that encode different information across different modalities, which have different prior...
Source: IEE Transactions on Medical Imaging - Category: Biomedical Engineering Source Type: research
ConclusionsSegment location, ground glass opacity proportion and absence of hilar lymph nodes involvement are reliable predictors of node-negative status in specific mediastinal regions. Based on these findings, we propose a new selective mediastinal lymph node dissection strategy for NSCLC.
Source: The Annals of Thoracic Surgery - Category: Cardiovascular & Thoracic Surgery Source Type: research
More News: Cancer | Cancer & Oncology | CT Scan | Learning | Lung Cancer | PET Scan | Universities & Medical Training