Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Sensitivity and Specificity”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

Patterns of Response After Preoperative Intensity-Modulated Radiation Therapy and Capecitabine/Oxaliplatin in Rectal Cancer: Is There Still a Place for Ecoendoscopic Ultrasound?

Purpose: The main goals of preoperative chemoradiotherapy (CHRT) in rectal cancer are to achieve pathological response and to ensure tumor control with functional surgery when possible. Assessment of the concordance between clinical and pathological responses is necessary to make decisions regarding alternative conservative procedures. The present study evaluates the patterns of response after a preoperative CHRT regimen, and the value of endoscopic ultrasound (EUS) in assessing response. Methods and Materials: A total of 51 EUS-staged T3 to T4 and/or N0 to N+ rectal cancer patients received preoperative CHRT (intensity-modulated radiation therapy and capecitabine/oxaliplatin (XELOX) followed by radical resection. Clinical response was assesed by EUS. Rates of pathological tumor regression grade (TRG) and lymph node (LN) involvement were determined in the surgical specimen. Clinical and pathological responses were compared, and the accuracy of EUS in assessing response was calculated. Results: Twenty-four patients (45%) achieved a major pathological response (complete or >95% pathological response (TRG 3+/4)). Sensitivity, specificity, negative predictive value, and positive predictive value of EUS in predicting pathological T response after preoperative CHRT were 77.8%, 37.5%, 60%, and 58%, respectively. The EUS sensitivity, specificity, negative predictive value, and positive predictive value for nodal staging were 44%, 88%, 88%, and 44%, respectively. Furthermore, EUS after CHRT accurately predicted the absence of LN involvement in 7 of 7 patients (100%) with major pathological response of the primary tumor. Conclusion: Preoperative IMRT with concomitant XELOX induces favorable rates of major pathological response. EUS has a limited ability to predict primary tumor response after preoperative CHRT, but it is useful for accurately determining LN status. EUS may have a potential value in identifying patients with a very low risk of LN involvement in association with a good pathological response as potential candidates for conservative local surgical protocols.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

WE-EF-210-05: Diagnosis and Quantification of Liver Steatosis with Quantitative Ultrasound Backscatter Technique

Purpose: Nonalcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease in the United States, affects 30% of adult Americans and may progress to more serious diseases. Liver biopsy is the standard method for diagnosing NAFLD. MRI can accurately diagnose and quantify hepatic steatosis but is expensive. Sonography with qualitative interpretation by radiologists is lower cost, more accessible but less sensitive for detection. The objective of this study, using MRI proton density fat fraction (PDFF) as reference, is to assess the accuracy for diagnosing and quantifying steatosis with two quantitative US parameters-- backscatter coefficient (BSC) and attenuation coefficient (AC)--derived from RF signals using the calibration phantom technique. Methods: We performed a prospective, cross-sectional analysis of a cohort of adults (n=204) with NAFLD (MRI-PDFF≥5%) and without NAFLD (controls). Subjects underwent MRI-PDFF and BSC and AC US analyses of the liver on the same day. Patients were randomly assigned to training (n=102, mean age 51±17 years, mean body mass index 31±7 kg/m{sup 2}) and validation (n=102, mean age 49±17 years, body mass index 30±6 kg/m{sup 2}) groups; 69% of patients in each group had NAFLD. Results: BSC provided AUC 0.98 (95% CI 0.95–1.00, p<0.0001) for diagnosis of NAFLD; the optimal BSC cut-off provided sensitivity, specificity, positive and negative predictive values (PPV, NPV) of 87%, 91%, 95%, and 76%, respectively. AC provided AUC 0.89 (95% CI 0.81–0.96, p<0.0001) for diagnosis of steatosis; the optimal AC cut-off provided sensitivity, specificity, PPV, NPV of 80%, 84%, 92%, and 66%, respectively. BSC and AC both correlated significantly with MRI-PDFF (P<0.0001). Conclusion: QUS BSC and AC can accurately diagnose and quantify hepatic steatosis, using MRI-PDFF as reference. With further validation, QUS may emerge as an inexpensive, widely available tool for NAFLD assessment. General support: NIH R01 CA111289, K23 -DK090303, AmerGastroAssoc Found, TF Williams Scholarship, S3000 scanner loaned by Siemens, Sucampo, JA Hartford Found, Atlantic Philanthropies Amer Gastroenterological Assoc. Agencies had no role in design/conduct of study, collection, management, analysis or interpretation of the data; preparation, review, or approval of the manuscript.

60 APPLIED LIFE SCIENCES↗

Can 18-FDG-PET During Radiotherapy Replace Post-Therapy Scanning for Detection/Demonstration of Tumor Response in Head-and-Neck Cancer?

Purpose: In routine practice, the tumor response in head-and-neck cancer (HNC) is assessed 3-4 months after radiotherapy (RT). We compared the results of fluorodeoxyglucose-positron emission tomography (FDG-PET) during (47 Gy) and 4 months after RT. Methods and Materials: In 40 patients with HNC, PET was performed before (PET1), at the end of Week 4 (47 Gy) (PET2), and 4 months after RT (PET3). Visual analysis classified patients as having a complete response (CR) or a non-CR (NCR). The sensitivity, specificity, accuracy, negative predictive value, and positive predictive value for PET2 and PET3 were determined. The 2-year overall survival (OS) rate for a CR and NCR was calculated for both response evaluation points. Results: After a median follow-up of 26 months, 10 patients had died, 6 had residual disease, and 24 remained disease free. The overall sensitivity, specificity, negative predictive value, positive predictive value, and accuracy of PET2 vs. PET3 for the detection of a CR was 28.6%, 81.8%, 31.0%, 80.0%, and 42.5% vs. 78.6%, 75.0%, 60.0%, 88.0%, and 77.5%, respectively. The 2-year OS rate determined at 47 Gy was 90.0% and 71.8% for a CR and NCR, respectively, and did not appear to be significantly different (p = .50). For the study, at 4 months, the OS was significantly better in the CR group (91.8%) than in the NCR group (49.9%; p = .0055). Conclusion: The high specificity and positive predictive value for the evaluation of tumor response with PET2 and PET3 might avoid unnecessary salvage surgery in patients with a CR. In contrast to PET3, the sensitivity of PET 2 was low, and the difference in OS between the CR and NCR groups was not significantly different. Therefore, the evaluation of the tumor response with FDG-PET at 4 months after RT completion cannot be replaced by FDG-PET during RT at 47 Gy.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Clinical Significance of Postradiotherapy [{sup 18}F]-Fluorodeoxyglucose Positron Emission Tomography Imaging in Management of Head-and-Neck Cancer-A Long-Term Outcome Report

Purpose: To determine the accuracy and prognostic significance of post-treatment [{sup 18}F]-fluorodeoxyglucose positron emission tomography (FDG-PET) in head-and-neck squamous cell carcinoma after radiotherapy (RT). Methods and Materials: This was a retrospective study of 188 patients with head-and-neck squamous cell carcinoma who had undergone FDG-PET within 12 months after completing RT. All living patients had {>=}1 year of follow-up after FDG-PET. All patients had undergone intensity-modulated RT, 128 with definitive and 60 with postoperative intensity-modulated RT. Results: For all patients, the median follow-up after RT completion was 32.6 months and after FDG-PET was 29.2 months. For the neck, 171 patients had negative FDG-PET findings. Of these results, two were falsely negative. Seventeen patients had positive FDG-PET findings, of which 12 were true-positive findings. The sensitivity, specificity, positive predictive value, and negative predictive value for FDG-PET in the assessment of the treatment response in the neck was 86%, 97%, 71%, and 99%, respectively. For the primary site, 151 patients had negative FDG-PET findings, of which two were falsely negative. Thirty-seven patients had positive FDG-PET findings, of which 12 were true-positive findings. The sensitivity, specificity, positive predictive value, and negative predictive value for FDG-PET in the assessment of the treatment response in the primary site was 86%, 86%, 32.4%, and 98.7%, respectively. Patients with positive post-RT PET findings had significantly worse 3-year overall survival and disease-free survival. Conclusion: The results of our study have shown that the findings of post-RT FDG-PET have a high negative predictive value and are a significant prognostic factor. It can provide guidance for the management of head-and-neck cancer after definitive treatment.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Pulmonary Masses: Initial Results of Cone-beam CT Guidance with Needle Planning Software for Percutaneous Lung Biopsy

Purpose: To evaluate the outcome of percutaneous lung biopsy (PLB) findings using cone-beam computed tomographic (CT) guidance (CBCT guidance) and compared to conventional biopsy guidance techniques. Methods: CBCT guidance is a stereotactic technique for needle interventions, combining 3D soft-tissue cone-beam CT, needle planning software, and real-time fluoroscopy. Between March 2007 and August 2010, we performed 84 Tru-Cut PLBs, where bronchoscopy did not provide histopathologic diagnosis. Mean patient age was 64.6 (range 24-85) years; 57 patients were men, and 25 were women. Records were prospectively collected for calculating sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. We also registered fluoroscopy time, room time, interventional time, dose-area product (DAP), and complications. Procedures were divided into subgroups (e.g., location, size, operator). Results: Mean lesion diameter was 32.5 (range 3.0-93.0) mm, and the mean number of samples per biopsy procedure was 3.2 (range 1-7). Mean fluoroscopy time was 161 (range 104-551) s, room time was 34 (range 15-79) min, mean DAP value was 25.9 (range 3.9-80.5) Gy{center_dot}cm{sup -2}, and interventional time was 18 (range 5-65) min. Of 84 lesions, 70 were malignant (83.3%) and 14 were benign (16.7%). Seven (8.3%) of the biopsy samples were nondiagnostic. All nondiagnostic biopsied lesions proved to be malignant during surgical resection. The outcome for sensitivity, specificity, positive predictive value, negative predictive value, and accuracy was 90% (95% confidence interval [CI] 86-96), 100% (95% CI 82-100), 100% (95% CI 96-100), 66.7% (95% CI 55-83), and 91.7% (95% CI 86-96), respectively. Sixteen patients (19%) had minor and 2 (2.4%) had major complications. Conclusion: CBCT guidance is an effective method for PLB, with results comparable to CT/CT fluoroscopy guidance.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Polymerase chain reaction for the in vitro detection of the pESI plasmid associated with the globally circulating Salmonella Infantis outbreak strain

Abstract A globally circulating strain of Salmonella enterica serotype Infantis containing the pESI plasmid has increased in prevalence in poultry meat samples and cases of human infections. In this study, a polymerase chain reaction (PCR) protocol was designed to detect the pESI plasmid and confirm the Infantis serotype of Salmonella isolates. Primers were tested bioinformatically to predict specificity, sensitivity, and precision. A total of 54 isolates of Salmonella serotypes Infantis, Senftenberg, and Alachua were tested, with and without the pESI plasmid carriage. Isolates of 31 additional serotypes were also screened to confirm specificity to Infantis. Specificity, sensitivity, and precision of each primer were >0.95. All isolates tested produced the expected band sizes. This PCR protocol provides a rapid and clear result for the detection of the pESI plasmid and serotype Infantis and will allow for the in vitro detection for epidemiological studies where whole-genome sequencing is not available.

McMillan, Elizabeth A. (ORCID:000000027503514X)↗

Analyzing the post-contrast attenuation of the esophageal wall on routine contrast-enhanced MDCT examination can improve the diagnostic accuracy in response evaluation of the squamous cell esophageal carcinoma to neoadjuvant chemoradiotherapy in comparison with the esophageal wall thickness

Purpose: To evaluate the accuracy of the multidetector computed tomography (MDCT) in the response evaluation of the esophageal squamous cell carcinoma (ESCC) to neoadjuvant chemoradiotherapy (nCRT) by analyzing the thickness and post-contrast attenuation of the esophageal wall after the nCRT. Methods: Contrast-enhanced (CE)-MDCT examinations in portal venous phase of one hundred patients with locally advanced ESCC who received nCRT and underwent esophageal resection and histopathology assessment of tumor regression grade (TRG) were retrospectively analyzed by measuring the maximal thickness and mean density of the esophageal wall in the segment involved by tumor and visually searching for hyperdense foci within it. Diagnostic performance was evaluated using the ROC analysis. Results: Average attenuation of the esophageal wall had stronger diagnostic performance for predicting pathologic complete regression (pCR) (AUC = 0.994; p < 0.001) in relation to maximal esophageal wall thickness (AUC = 0.731; p < 0.001). Maximal esophageal wall thickness ≤ 9 mm and average attenuation of the esophageal wall ≤ 64 HU predicted pCR with the sensitivity, specificity, and overall accuracy of 62.5%, 77.9%, and 73%, and 96.9%, 98.5%, and 98%, respectively. Combination of both cutoff values enabled correct assessment of pCR with the 100% accuracy. Visual detection of the hyperdense focus within the esophageal wall predicted pCR with the sensitivity, specificity, and overall accuracy values of 100%, 94.1%, and 96%, respectively. Conclusion: Visual analysis and measurement of post-contrast attenuation of the esophageal wall after the nCRT can improve diagnostic accuracy of MDCT in the response evaluation of the ESCC to nCRT in comparison with measuring the esophageal wall thickness.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Prediction of DVH parameter changes due to setup errors for breast cancer treatment based on 2D portal dosimetry

Electronic portal imaging devices (EPIDs) are increasingly used for portal dosimetry applications. In our department, EPIDs are clinically used for two-dimensional (2D) transit dosimetry. Predicted and measured portal dose images are compared to detect dose delivery errors caused for instance by setup errors or organ motion. The aim of this work is to develop a model to predict dose-volume histogram (DVH) changes due to setup errors during breast cancer treatment using 2D transit dosimetry. First, correlations between DVH parameter changes and 2D gamma parameters are investigated for different simulated setup errors, which are described by a binomial logistic regression model. The model calculates the probability that a DVH parameter changes more than a specific tolerance level and uses several gamma evaluation parameters for the planning target volume (PTV) projection in the EPID plane as input. Second, the predictive model is applied to clinically measured portal images. Predicted DVH parameter changes are compared to calculated DVH parameter changes using the measured setup error resulting from a dosimetric registration procedure. Statistical accuracy is investigated by using receiver operating characteristic (ROC) curves and values for the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values. Changes in the mean PTV dose larger than 5%, and changes in V{sub 90} and V{sub 95} larger than 10% are accurately predicted based on a set of 2D gamma parameters. Most pronounced changes in the three DVH parameters are found for setup errors in the lateral-medial direction. AUC, sensitivity, specificity, and negative predictive values were between 85% and 100% while the positive predictive values were lower but still higher than 54%. Clinical predictive value is decreased due to the occurrence of patient rotations or breast deformations during treatment, but the overall reliability of the predictive model remains high. Based on our predictive model, 2D transit dosimetry measurements can now directly be translated in clinically more relevant DVH parameter changes for the PTV during conventional breast treatment. In this way, the possibility to design decision protocols based on extracted DVH changes is created instead of undertaking elaborate actions such as repeated treatment planning or 3D dose reconstruction for a large group of patients.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Catalytically inactive, purified RNase H1: A specific and sensitive probe for RNA–DNA hybrid imaging

R-loops are three-stranded nucleic acid structures with both physiological and pathological roles in cells. R-loop imaging generally relies on detection of the RNA–DNA hybrid component of these structures using the S9.6 antibody. We show that the use of this antibody for imaging can be problematic because it readily binds to double-stranded RNA (dsRNA) in vitro and in vivo, giving rise to nonspecific signal. In contrast, purified, catalytically inactive human RNase H1 tagged with GFP (GFP-dRNH1) is a more specific reagent for imaging RNA–DNA hybrids. GFP-dRNH1 binds strongly to RNA–DNA hybrids but not to dsRNA oligonucleotides in fixed human cells and is not susceptible to binding endogenous RNA. Furthermore, we demonstrate that purified GFP-dRNH1 can be applied to fixed cells to detect hybrids after their induction, thereby bypassing the need for cell line engineering. GFP-dRNH1 therefore promises to be a versatile tool for imaging and quantifying RNA–DNA hybrids under a wide range of conditions.

59 BASIC BIOLOGICAL SCIENCES↗

Development of a Colorimetric Loop-Mediated Isothermal Amplification Assay for the Detection of Trypanosoma cruzi in Low-Resource Settings

Chagas disease is an inflammatory parasitic infection caused by Trypanosoma cruzi (T. cruzi). Early diagnosis is crucial in guiding treatment and slowing disease progression; however, current diagnostic methods have insufficient detection limits and often require skilled technicians. Molecular tests, especially isothermal nucleic acid assays, are advantageous due to their excellent sensitivity, specificity, speed, and simplicity. Here, we optimized a colorimetric loop-mediated isothermal amplification (LAMP) assay for T. cruzi. We can detect as few as 2 genomic copies/reaction using three different T. cruzi strains. We examined selectivity using other parasitic protozoans and successfully detected T. cruzi DNA extracted from parasites in human whole blood down to 1.2 parasite equivalents/reaction. We also performed a blinded study using canine blood samples and established a 100% sensitivity, specificity, and accuracy for the colorimetric LAMP assay. Finally, we used a heated 3D printer bed and an insulated thermos cup to demonstrate that the LAMP incubation step could be performed with accessible, low-cost materials. Altogether, we have developed a high-performing assay for T. cruzi with a simple colorimetric output that would be ideal for rapid, low-cost screening at the point of use.

60 APPLIED LIFE SCIENCES↗

Functional Gene Array-Based Ultrasensitive and Quantitative Detection of Microbial Populations in Complex Communities

ABSTRACT While functional gene arrays (FGAs) have greatly expanded our understanding of complex microbial systems, specificity, sensitivity, and quantitation challenges remain. We developed a new generation of FGA, GeoChip 5.0, using the Agilent platform. Two formats were created, a smaller format (GeoChip 5.0S), primarily covering carbon-, nitrogen-, sulfur-, and phosphorus-cycling genes and others providing ecological services, and a larger format (GeoChip 5.0M) containing the functional categories involved in biogeochemical cycling of C, N, S, and P and various metals, stress response, microbial defense, electron transport, plant growth promotion, virulence, gyrB , and fungus-, protozoan-, and virus-specific genes. GeoChip 5.0M contains 161,961 oligonucleotide probes covering >365,000 genes of 1,447 gene families from broad, functionally divergent taxonomic groups, including bacteria (2,721 genera), archaea (101 genera), fungi (297 genera), protists (219 genera), and viruses (167 genera), mainly phages. Computational and experimental evaluation indicated that designed probes were highly specific and could detect as little as 0.05 ng of pure culture DNAs within a background of 1 μg community DNA (equivalent to 0.005% of the population). Additionally, strong quantitative linear relationships were observed between signal intensity and amount of pure genomic (∼99% of probes detected; r > 0.9) or soil (∼97%; r > 0.9) DNAs. Application of the GeoChip to a contaminated groundwater microbial community indicated that environmental contaminants (primarily heavy metals) had significant impacts on the biodiversity of the communities. This is the most comprehensive FGA to date, capable of directly linking microbial genes/populations to ecosystem functions. IMPORTANCE The rapid development of metagenomic technologies, including microarrays, over the past decade has greatly expanded our understanding of complex microbial systems. However, because of the ever-expanding number of novel microbial sequences discovered each year, developing a microarray that is representative of real microbial communities, is specific and sensitive, and provides quantitative information remains a challenge. The newly developed GeoChip 5.0 is the most comprehensive microarray available to date for examining the functional capabilities of microbial communities important to biogeochemistry, ecology, environmental sciences, and human health. The GeoChip 5 is highly specific, sensitive, and quantitative based on both computational and experimental assays. Use of the array on a contaminated groundwater sample provided novel insights on the impacts of environmental contaminants on groundwater microbial communities.

59 BASIC BIOLOGICAL SCIENCES↗

Dual-energy cone-beam CT with a flat-panel detector: Effect of reconstruction algorithm on material classification

Purpose: Cone-beam CT (CBCT) with a flat-panel detector (FPD) is finding application in areas such as breast and musculoskeletal imaging, where dual-energy (DE) capabilities offer potential benefit. The authors investigate the accuracy of material classification in DE CBCT using filtered backprojection (FBP) and penalized likelihood (PL) reconstruction and optimize contrast-enhanced DE CBCT of the joints as a function of dose, material concentration, and detail size. Methods: Phantoms consisting of a 15 cm diameter water cylinder with solid calcium inserts (50–200 mg/ml, 3–28.4 mm diameter) and solid iodine inserts (2–10 mg/ml, 3–28.4 mm diameter), as well as a cadaveric knee with intra-articular injection of iodine were imaged on a CBCT bench with a Varian 4343 FPD. The low energy (LE) beam was 70 kVp (+0.2 mm Cu), and the high energy (HE) beam was 120 kVp (+0.2 mm Cu, +0.5 mm Ag). Total dose (LE+HE) was varied from 3.1 to 15.6 mGy with equal dose allocation. Image-based DE classification involved a nearest distance classifier in the space of LE versus HE attenuation values. Recognizing the differences in noise between LE and HE beams, the LE and HE data were differentially filtered (in FBP) or regularized (in PL). Both a quadratic (PLQ) and a total-variation penalty (PLTV) were investigated for PL. The performance of DE CBCT material discrimination was quantified in terms of voxelwise specificity, sensitivity, and accuracy. Results: Noise in the HE image was primarily responsible for classification errors within the contrast inserts, whereas noise in the LE image mainly influenced classification in the surrounding water. For inserts of diameter 28.4 mm, DE CBCT reconstructions were optimized to maximize the total combined accuracy across the range of calcium and iodine concentrations, yielding values of ∼88% for FBP and PLQ, and ∼95% for PLTV at 3.1 mGy total dose, increasing to ∼95% for FBP and PLQ, and ∼98% for PLTV at 15.6 mGy total dose. For a fixed iodine concentration of 5 mg/ml and reconstructions maximizing overall accuracy across the range of insert diameters, the minimum diameter classified with accuracy >80% was ∼15 mm for FBP and PLQ and ∼10 mm for PLTV, improving to ∼7 mm for FBP and PLQ and ∼3 mm for PLTV at 15.6 mGy. The results indicate similar performance for FBP and PLQ and showed improved classification accuracy with edge-preserving PLTV. A slight preference for increased smoothing of the HE data was found. DE CBCT discrimination of iodine and bone in the knee was demonstrated with FBP and PLTV at 6.2 mGy total dose. Conclusions: For iodine concentrations >5 mg/ml and detail size ∼20 mm, material classification accuracy of >90% was achieved in DE CBCT with both FBP and PL at total doses <10 mGy. Optimal performance was attained by selection of reconstruction parameters based on the differences in noise between HE and LE data, typically favoring stronger smoothing of the HE data, and by using penalties matched to the imaging task (e.g., edge-preserving PLTV in areas of uniform enhancement)

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Sensitive and Specific Peak Detection for SELDI-TOF Mass Spectrometry Using a Wavelet/Neural-Network Based Approach

SELDI-TOF mass spectrometer’s compact size and automated, high throughput design have been attractive to clinical researchers, and the platform has seen steady-use in biomarker studies. Despite new algorithms and preprocessing pipelines that have been developed to address reproducibility issues, visual inspection of the results of SELDI spectra preprocessing by the best algorithms still shows miscalled peaks and systematic sources of error. This suggests that there continues to be problems with SELDI preprocessing. In this work, we study the preprocessing of SELDI in detail and introduce improvements. While many algorithms, including the vendor supplied software, can identify peak clusters of specific mass (or m/z) in groups of spectra with high specificity and low false discover rate (FDR), the algorithms tend to underperform estimating the exact prevalence and intensity of peaks in those clusters. Thus group differences that at first appear very strong are shown, after careful and laborious hand inspection of the spectra, to be less than significant. Here we introduce a wavelet/neural network based algorithm which mimics what a team of expert, human users would call for peaks in each of several hundred spectra in a typical SELDI clinical study. The wavelet denoising part of the algorithm optimally smoothes the signal in each spectrum according to an improved suite of signal processing algorithms previously reported (the LibSELDI toolbox under development). The neural network part of the algorithm combines those results with the raw signal and a training dataset of expertly called peaks, to call peaks in a test set of spectra with approximately 95% accuracy. The new method was applied to data collected from a study of cervical mucus for the early detection of cervical cancer in HPV infected women. The method shows promise in addressing the ongoing SELDI reproducibility issues.

59 BASIC BIOLOGICAL SCIENCES↗