Chip-scale optical detection of lung cancer with engineered photodetector based on distributed semiconductor heterojunctions

As medical imaging technologies advance, a large number of medical images are produced which physicians/radiologists must interpret. Consequently, computer aids are becoming indispensable in physicians’ decision-making based on medical images. Computer-aided diagnosis (CAD) has been investigated and becomes an active research area in medical imaging. CAD is defined as detection and/or diagnosis made by a radiologist/physician who takes into account the computer output as a “second opinion.” In CAD research, detection of lung cancer in thoracic imaging constitutes a major research area, because lung cancer is the leading cause of cancer death worldwide, including the United States, Japan, and other countries. In this chapter, CAD for the detection of lung cancer in thoracic computed tomography (CT) is overviewed with emphasis on machine learning that plays an essential role in CAD systems. Massive training artificial neural network (MTANN) technology is one of the most promising machine learning techniques in image analysis. The MTANNs have substantially improved the sensitivity and specificity of CAD systems in detection and diagnosis of lung cancer. MTANN CAD systems offer high performance in detection and diagnosis of lung cancer in CT. Thus, MTANN CAD systems would be useful for improving the diagnostic performance of radiologists/physicians in early detection of lung cancer.

Lung Cancer Screening Results: Easily Misunderstood

The purpose of this study was to compare the diagnostic value of 11C-choline positron emission tomography (PET) and [18F]fluorodeoxyglucose (FDG) PET imaging in the detection of primary lung cancer and mediastinal lymph node metastases. Seventeen patients with histologically proven primary lung cancer were examined with both 11C-choline and FDG PET within a week of each study. Lung cancers were analysed visually and semiquantitatively using the ratio of tumour-to-normal radioactivity (T/N ratio) and standardized uptake value (SUV). Mediastinal lymph node metastases were analysed visually. Although both techniques delineated focal lesions with an increase in tracer accumulation in 13 patients, FDG PET identified three additional patients in whom 11C-choline PET did not visualize any lesion. In the detection of lung cancer <2 cm in size, FDG PET provided higher sensitivity (six of seven, 85.7%) than 11C-choline PET (four of seven, 57.1%). The T/N ratio and SUV were significantly higher with FDG PET (T/N ratio, 7.43+/-6.22; SUV, 4.05+/-3.05) than these were with 11C-choline PET (T/N ratio, 2.93+/-1.19; SUV, 2.93+/-0.79) (P<0.001). There was a significant positive correlation between the T/N ratios and SUVs of FDG and 11C-choline. In the assessment of mediastinal lymph node involvement, FDG PET detected lymph node metastases in two patients who were negative on 11C-choline PET, whereas both techniques could not detect tumour involvement in one patient. Both techniques have clinical value for the non-invasive detection of primary lung cancer that is 2 cm or greater in size. However, FDG PET is superior to 11C-choline PET in the detection of lung cancer that is less than 2 cm in diameter and in mediastinal lymph node metastases.

Lung cancer is the leading cause of cancer deaths in developed countries. The poor prognosis associated with this disease is closely related to the fact that most lung cancer patients are not identified until their malignancy has reached an advanced stage. Recent advances have added to the understanding of the morphological and molecular characteristics of preinvasive bronchial lesions and early lung cancers. Such information is being used to provide new tests for the detection of lung cancer at early or preinvasive stages, and for identifying targets for therapeutic intervention that can prevent progression to advanced disease. Laser induced fluorescence endoscope bronchoscopy has improved the sensitivity with which preinvasive dysplastic bronchial lesions and early invasive malignancies can be detected. Morphological features of such lesions have been described and can be monitored by follow-up bronchoscopies in order to validate potential chemoprevention treatments. Distinct morphological characteristics such as angiogenic squamous dysplasia also suggest that processes like angiogenesis are present early in the development of lung cancer. Furthermore, tissue obtained from these early lesions has been used to describe alterations in the expression of a number of factors that distinguish these early lesions from normal bronchial epithelium. This could provide molecular markers and targets for the detection and treatment of early lung cancer. Studies to detect these alterations by polymerase chain reaction and/or immunhistochemical analyses of easily obtained specimens such as sputa are helping identifing molecular markers that could be utilized in effective screening programmes. The current article reviews new findings regarding the molecular biology of preinvasive bronchial lesions and early lung cancers, and describes new developments regarding their application in the early detection and chemoprevention of lung cancer.

INTRODUCTION: Cancer is a life-threatening condition triggered by metabolic irregularities or the convergence of hereditary disorders. Cancerous cells in lung and colon leads more death rate count in the human race today. The histological diagnosis of malignant cancers is critical in establishing the most appropriate treatment for patients. Detecting cancer in its early stages, before it has a chance to advance within the body, greatly reduces the risk of death in both cases.&#x0D; OBJECTIVES: In order to examine a larger patient group more efficiently and quickly, researchers can utilize different methods of machine learning approach and different models of deep learning used to speed up the detection of cancer.&#x0D; METHODS: In this work, we provide a new ensemble transfer learning model for the rapid detection of lung and colon cancer. By ingtegrating various models of transfer learning approach and combining these methods in an ensemble, we aim to enhance the overall performance of the diagnosis process.&#x0D; RESULTS: The outcomes of this research indicate that our suggested approach performs better than current models, making it a valuable tool for clinics to support medical personnel in more efficiently detecting lung and colon cancer.&#x0D; CONCLUSION: The average ensemble is able to reach an accuracy of 98.66%, while the weighted-average ensemble with an accuracy of 99.80%, which is good with analysis of existing approaches.

BackgroundCurrently, no satisfactory biomarkers are available to screen for lung cancer. Surface-Enhanced Laser Desorption/ionization Time-of- Flight Mass Spectrometry ProteinChip system (SELDI-TOF-MS) is one of the currently used techniques to identify biomarkers for cancers. The aim of this study is to explore the application of serum SELDI proteomic patterns to distinguish lung cancer patients from healthy individuals.MethodsA total of 208 serum samples, including 158 lung cancer patients and 50 healthy individuals, were randomly divided into a training set (including 11 sera from patients with stages I/II lung cancer, 63 from patients with stages III/IV lung cancer and 20 from healthy controls) and a blinded test set (including 43 sera from patients with stages I/II lung cancer, 41 from patients with stages III/IV lung cancer and 30 from healthy controls). All samples were analyzed by SELDI technology. The spectra were generated on weak cation exchange (WCX2) chips, and protein peaks clustering and classification analyses were made using Ciphergen Biomarker Wizard and Biomarker Pattern software, respectively. We additionally determined Cyfra21-1 and NSE in the 208 serum samples included in this study using an electrochemiluminescent immunoassay.ResultsFive protein peaks at 11493, 6429, 8245, 5335 and 2538 Da were automatically chosen as a biomarker pattern in the training set. When the SELDI marker pattern was tested with the blinded test set, it yielded a sensitivity of 86.9%, a specificity of 80.0% and a positive predictive value of 92.4%. The sensitivities provided by Cyfra21-1 and NSE used individually or in combination were significantly lower than that of the SELDI marker pattern (P < 0.005 or 0.05, respectively). Based on the results of the test set, we found that the SELDI marker pattern showed a sensitivity of 91.4% in the detection of non-small cell lung cancers (NSCLC), which was significantly higher than that in the detection of small cell lung cancers (P < 0.05); The pattern also had a sensitivity of 79.1% in the detection of lung cancers in stages I/II.ConclusionThese results suggest that serum SELDI protein profiling can distinguish lung cancer patients, especially NSCLC patients, from normal subjects with relatively high sensitivity and specificity, and the SELDI-TOF-MS is a potential tool for the screening of lung cancer.

Objectives: The objective of this research paper is study the different methods related to artificial neural network used for prediction and detection of the lung cancer in its early stages so that survival rate of lung cancer patients can be increased. Methods: Lung cancer is the leading cause of death in India so early detection of lung cancer is very important. The detection and prediction of lung cancer was determined with image prepossessing method where segmentation, smoothing and enhancement steps were processed and features were extracted from images and stages of lung cancer were identified with suitable artificial neural network model and also survival rate of lung cancer patients was determined. Findings: Artificial neural network has a significant role in medical area. In these days most of the disease cure methods are process with the help of artificial intelligence to increase the performance of output. In lung cancer disease the artificial neural network model is very useful because detection of lung cancer in its early stages can be determine and it is very important to cure this disease initially because with the increasing stages of lung cancer it is very difficult to cure this disease and also the survival rate of lung cancer patients in higher stages is very low Improvements: The ultimate goal of this paper is to study different methods of Artificial Neural Networks model that can help for detection, prediction and find the survival rate of lung cancer patients.

Serological biomarkers for detection of cancer are often based upon measuring the ectopic expression of particular proteins that are otherwise only expressed during embryonic development. Perhaps the oldest and best known cancer biomarker in this class is carcinoembryonic antigen (CEA), which despite having some limitations, has been very popular in its longstanding use. We have compared CEA with HAAH (Human Aspartyl (Asparaginyl) beta hydroxylase), an emerging biomarker protein that like CEA has an onco-developmental re-expression pattern in a number of cancers including lung cancer. One of the limitations of CEA that precludes its routine utility for early serological screening and detection of lung cancer is that cigarette smokers, a lung cancer high risk group, frequently have elevated and variable CEA levels compared to normal non-smoking individuals. We compared serum CEA by ELISA (using a commercial kit) with serum HAAH (using Panacea's technology) in 26 individuals each who were either normal, cigarette smokers, or a population of patients with either stage I or II lung cancer. Both assays used a double monoclonal antibody sandwich format, and a peroxidase /TMB detection system with suitable calibration standards . The CEA assay had a simultaneous format, differing from the HAAH ELISA which had a sequential homolgous antibody format. The mean CEA level of smokers (2.7 ng/ mL, range 0.84-6.4) was double that of normal (1.3 ng/ mL range 0.77- 2.4) as expected. Several individuals clustered near or exceeded the cut off of 5ng /mL. More striking was the significant overlap of CEA levels between smokers and the lung cancer patients (&amp;gt;80 %) (whereas &amp;gt; 53% overlap between normals and lung cancer). It is even more striking to observe a 100% overlap between smokers and stage I lung cancer. It's interesting that a similar pattern of HAAH expression was seen between normals and smokers (two times higher). However, both of these groups mostly clustered below a pre-established cutoff of 2 ng/ mL and were scored negative and non-detectable by our acceptance parameters. Comparison of HAAH levels between normals/smokers and lung cancer patients clearly shows a distinction between these groups with 0 % overlap between normals/smokers and cancer patients. The concept of ELISA based serological screening for lung cancer is generally very well received as a cost effective non-invasive potential means for detection. Our early assessment of HAAH levels in smokers indicates that such testing performs favorably when compared to CEA testing in the effective detection of early stage lung cancer. Since cigarette smokers contribute to an overall 87% association with lung cancer, it's more likely that these individuals would be selected for voluntary screening and would therefore benefit from the superior performance of the HAAH ELISA. Citation Format: Mark A. Semenuk, Hossein A. Ghanbari. Serum biomarkers Carcinoembryonic Antigen (CEA) and Human Aspartyl (Asparaginyl) Beta Hydroxylase (HAAH) compared in normal volunteers, smokers, and stage I/II lung cancer patients. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr 2358. doi:10.1158/1538-7445.AM2013-2358

Computer-aided Diagnosis for the Detection and Classification of Lung Cancers on Chest Radiographs: ROC Analysis of Radiologists’ Performance

Lung cancer continues to be the foremost cause of death in both women and men. Worldwide, lung cancer kills over 1 million peoples a year. The major cause of lung cancer is smoking. In India each year it is estimated that about 80% of male lung cancer deaths and 70% of lung cancer deaths are caused by smoking. Undoubtedly, lung cancer is a major threat to human beings and also a widespread disease which constitutes a major public health problem. Other possible factors for lung cancer are increased air pollution by dusts and gases released by industry, automobile traffic etc. Hence, lung cancer detection is one of the major needs of the day. Several researchers developed Image Processing Techniques (IPT) for the detection of Lung Cancer [, , , , , , , ]. Earlier researchers employed the methods like Discrete Cosine Transform (DCT), Auto Enhancement Algorithm (AEA), Fast Fourier Transform (FFT), for image enhancement. These approaches are time consuming and less accurate. Some of the researchers are also used Kalman Filters, Hessian Based Filters (HBF), but these filters have drawbacks like, varying contrast; poor and non-uniform response for images of varying sizes [, ]. Some of other researchers used interpolation techniques, which is complex and time consuming []. So, to overcome the drawbacks of these earlier approaches, a new image enhancement technique is proposed with modifications in Gabor Filters which will help in early and efficient detection of lung cancer. This Modified Gabor Filter (MGF) approach has been validated using CT (Computer Tomography) and X-ray lung images which are collected from a hospital and they are analysed. The results obtained are comparable with real time analysis of medical practitioners. Hence, this new technique for Image Enhancement using MGF Approach can be employed for early detection of lung cancer and this technique is also suitable for development of new medical equipment’s for better detection of lung cancer.

Effect of temporal subtraction images on radiologists’ detection of lung cancer on CT: Results of the observer performance study with use of film computed tomography images 1

Cancer diagnosis by breath analysis: what is the future?

The global increase in population has simultaneously raised the awareness to maintain good health in most of the people. The poor quality of food taken and environmental pollution leads to occurrence of lung cancer in most of the people. It is highly important to detect the lung cancer in earlier stages with minimum time delay and provide a better solution to reduce the lung cancer. Early detection of lung cancer is also desirable for efficient analysis and it helps ophthalmologist to provide the treatment in early stages. Earlier researchers employed methods like Fast Fourier Transform (FFT) for image enhancement, thresholding approach for segmentation and Binarization approach for Extraction etc.,. Research work aiming at computerizing these selections, passing the available lung cancer images and its database in basic three stages like enhancement, segmentation and feature Extraction stage to achieve more quality and accuracy in detection of lung cancer. Approaches developed by the earlier researchers fail to produce accuracy in real time applications. Hence, to overcome the drawbacks of these approaches a new method to detect lung cancer using Gabor filters and watershed segmentation techniques is proposed in this work. The CT (Computed Tomography) images captured from lung cancer patients are analyzed by developing Digital Image processing technique. The results obtained are comparable with standard values obtained from the hospital for real time analysis. Hence, this new technique with Gabor filters and watershed segmentation approach can be used for quick detection of lung cancer. This approach is beneficial to the Medical Equipment's manufacturing industries and also helps the medical practitioners for early detection of lung cancer.

Lung cancer is the most often diagnosed cancer and the main cause of cancer deaths in the world compared with other tumor entities. To date, the only screening method for high‐risk lung cancer patients is low‐dosed computed tomography which still suffers from high false‐positive rates and overdiagnosis. Therefore, there is an obvious need to identify biomarkers for the detection of lung cancer that could be used to guide the use of low‐dosed computed tomography or other imaging procedures. We aimed to assess the performance of the protein cysteine‐rich angiogenic inducer 61 (CYR61) as a circulating biomarker for the detection of lung cancer. CYR61 concentrations in plasma were significantly elevated in 87 lung cancer patients (13.7 ± 18.6 ng·mL−1) compared with 150 healthy controls (0.29 ± 0.22 ng·mL−1). Subset analysis stratified by sex revealed increased CYR61 concentrations for adenocarcinoma and squamous cell carcinoma in men compared with women. For male lung cancer patients versus male healthy controls, the sensitivity was 84% at a specificity of 100%, whereas for females, the sensitivity was 27% at a specificity of 99%. The determination of circulating CYR61 protein in plasma might improve the detection of lung cancer in men. The findings of this pilot study support further verification of CYR61 as a biomarker for lung cancer detection in men. Additionally, CYR61 is significantly elevated in women but sensitivity and specificity for CYR61 are too low for the improvement of the detection of lung cancer in women.

Detection of lung cancer on the chest radiograph: a study on observer performance