A use of a neural network to evaluate contrast enhancement curves in breast magnetic resonance images

For the diagnosis of breast cancer using magnetic resonance imaging (MRI), one of the most important parameters is the analysis of contrast enhancement. A threedimensional MR sequence is applied before and five times after bolus injection of paramagnetic contrast medium (Gd-DTPA). The dynamics of absorption are described by a time/intensity enhancement curve, which reports the mean intensity of the MR signal in a small region of interest (ROI) for about 8 minutes after contrast injection. The aim of our study was to use an artificial neural network to automatically classify the enhancement curves as “benign” or “malignant.” We used a classic feed-forward back-propagation neural network, with three layers: five input nodes, two hidden nodes, and one output node. The network has been trained with 26 pathologic curves (10 invasive carcinoma [K], two carcinoma-in-situ [DCIS], and 14 benign lesion [B]). The trained network has been tested with 58 curves (36 K, one DCIS, 21 B). The network was able to correctly identify the test curves with a sensitivity of 76% and a specificity of 90%. For comparison, the same set of curves was analyzed separately by two radiologists (a breast MR expert and a resident radiologist). The first correctly interpreted the curves with a sensitivity of 76% and a specificity of 90%, while the second scored 59% for sensitivity and 90% for specificity. These results demonstrate that a trained neural network recognizes the pathologic curves at least as well as an expert radiologist. This algorithm can help the radiologist attain rapid and affordable screening of a large number of ROIs. A complete automatic computer-aided diagnosis support system should find a number of potentially interesting ROIs and automatically analyze the enhancement curves for each ROI by neural networks, reporting to the radiologist only the potentially pathologic ROIs for a more accurate, manual, repeated evaluation.     

Computerized detection of breast lesions in multi-centre and multi-instrument DCE-MR data using 3D principal component maps and template matching

In this study, we introduce a novel, robust and accurate computerized algorithm based on volumetric principal component maps and template matching that facilitates lesion detection on dynamic contrast-enhanced MR. The study dataset comprises 24,204 contrast-enhanced breast MR images corresponding to 4034 axial slices from 47 women in the UK multi-centre study of MRI screening for breast cancer and categorized as high risk. The scans analysed here were performed on six different models of scanner from three commercial vendors, sited in 13 clinics around the UK. 1952 slices from this dataset, containing 15 benign and 13 malignant lesions, were used for training. The remaining 2082 slices, with 14 benign and 12 malignant lesions, were used for test purposes. To prevent false positives being detected from other tissues and regions of the body, breast volumes are segmented from pre-contrast images using a fast semi-automated algorithm. Principal component analysis is applied to the centred intensity vectors formed from the dynamic contrast-enhanced T1-weighted images of the segmented breasts, followed by automatic thresholding to eliminate fatty tissues and slowly enhancing normal parenchyma and a convolution and filtering process to minimize artefacts from moderately enhanced normal parenchyma and blood vessels. Finally, suspicious lesions are identified through a volumetric sixfold neighbourhood connectivity search and calculation of two morphological features: volume and volumetric eccentricity, to exclude highly enhanced blood vessels, nipples and normal parenchyma and to localize lesions. This provides satisfactory lesion localization. For a detection sensitivity of 100%, the overall false-positive detection rate of the system is 1.02/lesion, 1.17/case and 0.08/slice, comparing favourably with previous studies. This approach may facilitate detection of lesions in multi-centre and multi-instrument dynamic contrast-enhanced breast MR data.     

Diagnosis of breast lesions: fine-needle aspiration cytology or core needle biopsy? A review

Diagnosis of breast lesions is routinely performed by the triple assessment of a specialised surgeon, radiologist and pathologist. In this setting, fine-needle aspiration cytology (FNAC) and core needle biopsy (CNB) are the current methods of choice for pathological diagnosis, both with their specific advantages and limitations. Evidence-based literature discussing which of both modalities is preferable in breast lesion diagnosis is sparse and there is no consensus among different specialised breast cancer centres. This study reviews FNAC and CNB for diagnosing breast lesions, comparing methodological issues, diagnostic performance indices, possibilities for additional prognostic and predictive tests and cost effectiveness. Overall, CNB achieved better sensitivity and specificity especially in those lesions that were not definitively benign or malignant, non-palpable and/or calcified lesions. Although FNAC is easier to perform, interpretation requires vast experience and even then, it is more often inconclusive requiring additional CNB. The authors conclude that overall CNB is to be preferred as a diagnostic method.     

Application of artificial neural networks for quantitative analysis of image data in chest radiographs for detection of interstitial lung disease

The authors have developed an automated computeraided diagnostic (CAD) scheme by using artificial neural networks (ANNs) on quantitative analysis of image data. Three separate ANNs were applied for detection of interstitial disease on digitized chest images. The first ANN was trained with horizontal profiles in regions of interest (ROIs) selected from normal and abnormal chest radiographs for distinguishing between normal and abnormal patterns. For training and testing of the second ANN, the vertical output patterns obtained from the 1st ANN were used for each ROI. The output value of the second ANN was used to distinguish between normal and abnormal ROIs with interstitial infiltrates. If the ratio of the number of abnormal ROIs to the total number of all ROIs in a chest image was greater than a specified threshold level, the image was classified as abnormal. In addition, the third ANN was applied to distinguish between normal and abnormal chest images. The combination of the rule-based method and the third ANN also was applied to the classification between normal and abnormal chest images. The performance of the ANNs was evaluated by means of receiver operating characteristic (ROC) analysis. The average A_z value (area under the ROC curve) for distinguishing between normal and abnormal cases was 0.976±0.012 for 100 chest radiographs that were not used in training of ANNs. The results indicate that the ANN trained with image data can learn some statistical properties associated with interstitial infiltrates in chest radiographs.     

Classification of normal and abnormal lungs with interstitial diseases by rule-based method and artificial neural networks

We devised an automated classification scheme by using the rule-based method plus artificial neural networks (ANN) for distinction between normal and abnormal lungs with interstitial disease in digital chest radiographs. Four measures used in the classification scheme are determined from the texture and geometric-pattern feature analyses. The rms variation and the first moment of the power spectrum of lung patterns aredetermined as measures for the texture analysis. In addition, the total area of nodular opacities and the total length of linear opacities are determined as measures for the geometric-pattern feature analysis. In our classification scheme with these measures, we identify obviously normal and abnormal cases first by the rule-based method and then ANN is applied for the remaining difficult cases. The rulebased plus ANN method provided a sensitivity of 0.926 at the specificity of 0.900, which was considerably improved compared to performance of either the rule-based method alone or ANNs alone.     

Advanced integrated technique in breast cancer thermography

Thermography is a passive and non-contact imaging technique used extensively in the medical arena, but in relation to breast care, it has not been accepted as being on a par with mammography. This paper proposes the analysis of thermograms with the use of artificial neural networks (ANN) and bio-statistical methods, including regression and receiver operating characteristics (ROC). It is desired that through these approaches, highly accurate diagnosis using thermography techniques can be achieved. The suggested method is a multi-pronged approach comprising of linear regression, radial basis function network (RBFN) and ROC analysis. It is a novel, integrative and powerful technique that can be used to analyse large amounts of complicated measured data such as temperature values extracted from abnormal and healthy breast thermograms. The use of regression allows the correlation between the variables and the actual health status of the subject, which is decided by other traditional means such as the gold standard of mammography for breast cancer detection. This is important as it helps to select the appropriate variables to be used as inputs for building the neural network. RBFN is next trained to produce the desired outcome that is either positive or negative. When this is done, the RBFN possess the ability to predict the outcome when there are new input variables. The advantages of using RBFN include fast training of superior classification and decision-making abilities as compared to other networks such as backpropagation. Lastly, ROC is applied to evaluate the sensitivity, specificity and accuracy of the outcome for the RBFN test files. The proposed technique has an accuracy rate of 80.95%, with 100% sensitivity and 70.6% specificity in identifying breast cancer. The results are promising as compared to clinical examination by experienced radiologists, which has an accuracy rate of approximately 60-70%. To sum up, technological advances in the field of infrared thermography over the last 20 years warrant a re-evaluation of the use of high-resolution digital thermographic camera systems in the diagnosis and management of breast cancer. Thermography seeks to identify the presence of a tumour by the elevated temperature associated with increase blood flow and cellular activity. Of particular interest would be investigation in younger women and men, for whom mammography is either unsuitable or of limited effectiveness. The paper evaluated the high-definition digital infrared thermographic technology and knowledge base; and supports the development of future diagnostic and therapeutic services in breast cancer imaging. Through the use of integrative ANN and bio-statistical methods, advances are made in thermography application with regard to achieving a higher level of consistency. For breast cancer care, it has become possible to use thermography as a powerful adjunct and biomarker tool, together with mammography for diagnosis purposes.     

Advanced integrated technique in breast cancer thermography

Thermography is a passive and non-contact imaging technique used extensively in the medical arena, but in relation to breast care, it has not been accepted as being on a par with mammography. This paper proposes the analysis of thermograms with the use of artificial neural networks (ANN) and bio-statistical methods, including regression and receiver operating characteristics (ROC). It is desired that through these approaches, highly accurate diagnosis using thermography techniques can be achieved. The suggested method is a multi-pronged approach comprising of linear regression, radial basis function network (RBFN) and ROC analysis. It is a novel, integrative and powerful technique that can be used to analyse large amounts of complicated measured data such as temperature values extracted from abnormal and healthy breast thermograms. The use of regression allows the correlation between the variables and the actual health status of the subject, which is decided by other traditional means such as the gold standard of mammography for breast cancer detection. This is important as it helps to select the appropriate variables to be used as inputs for building the neural network. RBFN is next trained to produce the desired outcome that is either positive or negative. When this is done, the RBFN possess the ability to predict the outcome when there are new input variables. The advantages of using RBFN include fast training of superior classification and decision-making abilities as compared to other networks such as backpropagation. Lastly, ROC is applied to evaluate the sensitivity, specificity and accuracy of the outcome for the RBFN test files. The proposed technique has an accuracy rate of 80.95%, with 100% sensitivity and 70.6% specificity in identifying breast cancer. The results are promising as compared to clinical examination by experienced radiologists, which has an accuracy rate of approximately 60 – 70%. To sum up, technological advances in the field of infrared thermography over the last 20 years warrant a re-evaluation of the use of high-resolution digital thermographic camera systems in the diagnosis and management of breast cancer. Thermography seeks to identify the presence of a tumour by the elevated temperature associated with increase blood flow and cellular activity. Of particular interest would be investigation in younger women and men, for whom mammography is either unsuitable or of limited effectiveness. The paper evaluated the high-definition digital infrared thermographic technology and knowledge base; and supports the development of future diagnostic and therapeutic services in breast cancer imaging. Through the use of integrative ANN and bio-statistical methods, advances are made in thermography application with regard to achieving a higher level of consistency. For breast cancer care, it has become possible to use thermography as a powerful adjunct and biomarker tool, together with mammography for diagnosis purposes.     

The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors

BACKGROUND: The limitations of current prognostic models in identifying postoperative cardiac patients at risk of experiencing morbidity and subsequently an extended intensive care unit length of stay (ICU LOS) is well recognized. This coupled with the desire for risk stratification in order to prioritize medical intervention has lead to the need for the development of a system that can accurately predict individual patient outcome based on both preoperative and immediate postoperative clinical factors. The usefulness of artificial neural networks (ANNs) as an outcome prediction tool in the critical care environment has been previously demonstrated for medical intensive care unit (ICU) patients and it is the aim of this study to apply this methodology to postoperative cardiac patients. METHODS: A review of contemporary literature revealed 15 preoperative risk factors and 17 operative and postoperative variables that have a determining effect on LOS. An integrated, multi-functional software package was developed to automate the ANN development process. The efficacy of the resultant individual ANNs as well as groupings or ensembles of ANNs were measured by calculating sensitivity and specificity estimates as well as the area under the receiver operating curve (AUC) when the ANN is applied to an independent test dataset. RESULTS: The individual ANN with the highest discriminating ability produced an AUC of 0.819. The use of the ensembles of networks technique significantly improved the classification accuracy. Consolidating the output of three ANNs improved the AUC to 0.90. CONCLUSIONS: This study demonstrates the suitability of ANNs, in particular ensembles of ANNs, to outcome prediction tasks in postoperative cardiac patients.     

Artificial neural network in breast lesions from fine‐needle aspiration cytology smear

Artificial neural networks (ANNs) are applied in engineering and certain medical fields. ANN has immense potential and is rarely been used in breast lesions. In this present study, we attempted to build up a complete robust back propagation ANN model based on cytomorphological data, morphometric data, nuclear densitometric data, and gray level co‐occurrence matrix (GLCM) of ductal carcinoma and fibroadenomas of breast cases diagnosed on fine‐needle aspiration cytology (FNAC). We selected 52 cases of fibroadenomas and 60 cases of infiltrating ductal carcinoma of breast diagnosed on FNAC by two cytologists. Essential cytological data was quantitated by two independent cytologists (SRM, PD). With the help of Image J software, nuclear morphomeric, densitometric, and GLCM features were measured in all the cases on hematoxylin and eosin‐stained smears. With the available data, an ANN model was built up with the help of Neurointelligence software. The network was designed as 41‐20‐1 (41 input nodes, 20 hidden nodes, 1 output node). The network was trained by the online back propagation algorithm and 500 iterations were done. Learning was adjusted after every iteration. ANN model correctly identified all cases of fibroadenomas and infiltrating carcinomas in the test set. This is one of the first successful composite ANN models of breast carcinomas. This basic model can be used to diagnose the gray zone area of the breast lesions on FNAC. We assume that this model may have far‐reaching implications in future. Diagn. Cytopathol. 2014;42:218–224. © 2013 Wiley Periodicals, Inc.     

Mortality assessment in intensive care units via adverse events using artificial neural networks

OBJECTIVE: This work presents a novel approach for the prediction of mortality in intensive care units (ICUs) based on the use of adverse events, which are defined from four bedside alarms, and artificial neural networks (ANNs). This approach is compared with two logistic regression (LR) models: the prognostic model used in most of the European ICUs, based on the simplified acute physiology score (SAPS II), and a LR that uses the same input variables of the ANN model. MATERIALS AND METHODS: A large dataset was considered, encompassing forty two ICUs of nine European countries. The recorded features of each patient include the final outcome, the case mix (e.g. age) and the intermediate outcomes, defined as the daily averages of the out of range values of four biometrics (e.g. heart rate). The SAPS II score requires 17 static variables (e.g. serum sodium), which are collected within the first day of the patient's admission. A nonlinear least squares method was used to calibrate the LR models while the ANNs are made up of multilayer perceptrons trained by the RPROP algorithm. A total of 13,164 adult patients were randomly divided into training (66%) and test (33%) sets. The two methods were evaluated in terms of receiver operator characteristic (ROC) curves. RESULTS: The event based models predicted the outcome more accurately than the currently used SAPS II model (P<0.05), with ROC areas within the ranges 83.9-87.1% (ANN) and 82.6-85.2% (LR) versus 80% (LR SAPS II). When using the same inputs, the ANNs outperform the LR (improvement of 1.3-2%). CONCLUSION: Better prognostic models can be achieved by adopting low cost and real-time intermediate outcomes rather than static data.     

The IFAST model, a novel parallel nonlinear EEG analysis technique, distinguishes mild cognitive impairment and Alzheimer's disease patients with high degree of accuracy

OBJECTIVE: This paper presents the results obtained with the innovative use of special types of artificial neural networks (ANNs) assembled in a novel methodology named IFAST (implicit function as squashing time) capable of compressing the temporal sequence of electroencephalographic (EEG) data into spatial invariants. The aim of this study is to assess the potential of this parallel and nonlinear EEG analysis technique in distinguishing between subjects with mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients with a high degree of accuracy in comparison with standard and advanced nonlinear techniques. The principal aim of the study was testing the hypothesis that automatic classification of MCI and AD subjects can be reasonably correct when the spatial content of the EEG voltage is properly extracted by ANNs. METHODS AND MATERIAL: Resting eyes-closed EEG data were recorded in 180 AD patients and in 115 MCI subjects. The spatial content of the EEG voltage was extracted by IFAST step-wise procedure using ANNs. The data input for the classification operated by ANNs were not the EEG data, but the connections weights of a nonlinear auto-associative ANN trained to reproduce the recorded EEG tracks. These weights represented a good model of the peculiar spatial features of the EEG patterns at scalp surface. The classification based on these parameters was binary (MCI versus AD) and was performed by a supervised ANN. Half of the EEG database was used for the ANN training and the remaining half was utilised for the automatic classification phase (testing). RESULTS: The best results distinguishing between AD and MCI reached to 92.33%. The comparative results obtained with the best method so far described in the literature, based on blind source separation and Wavelet pre-processing, were 80.43% (p<0.001). CONCLUSION: The results confirmed the working hypothesis that a correct automatic classification of MCI and AD subjects can be obtained extracting spatial information content of the resting EEG voltage by ANNs and represent the basis for research aimed at integrating spatial and temporal information content of the EEG.     

An automatic method for the identification and interpretation of clustered microcalcifications in mammograms.

We investigated a method for a fully automatic identification and interpretation process for clustered microcalcifications in mammograms. Mammographic films of 100 patients containing microcalcifications with known histology were digitized and preprocessed using standard techniques. Microcalcifications detected by an artificial neural network (ANN) were clustered and some cluster features served as the input of another ANN trained to differentiate between typical and atypical clusters, while others were fed into an ANN trained on typical clusters to evaluate these lesions. The measured sensitivity for the detection of grouped microcalcifications was 0.98. For the task of differentiation between typical and atypical clusters an Az value of 0.87 was computed, while for the diagnosis an Az value of 0.87 with a sensitivity of 0.97 and a specificity of 0.47 was obtained. The results show that a fully automatic computer system was developed for the identification and interpretation of clustered microcalcitications in mammograms with the ability to differentiate most benign lesions from malignant ones in an automatically selected subset of cases.     

Automatic recognition of alertness and drowsiness from EEG by an artificial neural network

We present a novel method for classifying alert vs drowsy states from 1 s long sequences of full spectrum EEG recordings in an arbitrary subject. This novel method uses time series of interhemispheric and intrahemispheric cross spectral densities of full spectrum EEG as the input to an artificial neural network (ANN) with two discrete outputs: drowsy and alert. The experimental data were collected from 17 subjects. Two experts in EEG interpretation visually inspected the data and provided the necessary expertise for the training of an ANN. We selected the following three ANNs as potential candidates: (1) the linear network with Widrow-Hoff (WH) algorithm; (2) the non-linear ANN with the Levenberg-Marquardt (LM) rule; and (3) the Learning Vector Quantization (LVQ) neural network. We showed that the LVQ neural network gives the best classification compared with the linear network that uses WH algorithm (the worst), and the non-linear network trained with the LM rule. Classification properties of LVQ were validated using the data recorded in 12 healthy volunteer subjects, yet whose EEG recordings have not been used for the training of the ANN. The statistics were used as a measure of potential applicability of the LVQ: the t-distribution showed that matching between the human assessment and the network output was 94.37+/-1.95%. This result suggests that the automatic recognition algorithm is applicable for distinguishing between alert and drowsy state in recordings that have not been used for the training.     

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses on Breast DCE-MRI Images Using Deep Convolutional Neural Network with Bayesian Optimization

Although magnetic resonance imaging (MRI) has a higher sensitivity of early breast cancer than mammography, the specificity is lower. The purpose of this study was to develop a computer-aided diagnosis (CAD) scheme for distinguishing between benign and malignant breast masses on dynamic contrast material-enhanced MRI (DCE-MRI) by using a deep convolutional neural network (DCNN) with Bayesian optimization. Our database consisted of 56 DCE-MRI examinations for 56 patients, each of which contained five sequential phase images. It included 26 benign and 30 malignant masses. In this study, we first determined a baseline DCNN model from well-known DCNN models in terms of classification performance. The optimum architecture of the DCNN model was determined by changing the hyperparameters of the baseline DCNN model such as the number of layers, the filter size, and the number of filters using Bayesian optimization. As the input of the proposed DCNN model, rectangular regions of interest which include an entire mass were selected from each of DCE-MRI images by an experienced radiologist. Three-fold cross validation method was used for training and testing of the proposed DCNN model. The classification accuracy, the sensitivity, the specificity, the positive predictive value, and the negative predictive value were 92.9% (52/56), 93.3% (28/30), 92.3% (24/26), 93.3% (28/30), and 92.3% (24/26), respectively. These results were substantially greater than those with the conventional method based on handcrafted features and a classifier. The proposed DCNN model achieved high classification performance and would be useful in differential diagnoses of masses in breast DCE-MRI images as a diagnostic aid.     

A system of microcalcifications detection and evaluation of the radiologist: comparative study of the three main races in Malaysia

This paper uses wavelets in the detection comparison of breast cancer among the three main races in Malaysia: Chinese, Malays, and Indians followed by a system that evaluates the radiologist's findings over a period of time to gauge the radiologist's skills in confirming breast cancer cases. The db4 wavelet has been utilized to detect microcalcifications in mammogram-digitized images obtained from Malaysian women sample. The wavelet filter's detection evaluation was done by visual inspection by an expert radiologist to confirm the detection results of those pixels that corresponded to microcalcifications. Detection was counted if the wavelet-detected pixels corresponded to the radiologist's identified microcalcification pixels. After the radiologist's detection confirmation a new client–server radiologist recording and evaluation system is designed to evaluate the findings of the radiologist over some period of cancer detection working time. It is a system that records the findings of the Malaysian radiologist for the presence of breast cancer in Malaysian patients and provides a way of registering the progress of detecting breast cancer of the radiologist by tracking certain metric values such as the sensitivity, specificity, and receiver operator curve (ROC). The initial findings suggest that no single race mammograms are easier for wavelets' detections of microcalcifications and for the radiologist confirmation even though for this study the Chinese race samples detection average were a few percentages less than the other two races, namely the Malay and Indian races.     

Infrared spectroscopy: A new diagnostic tool in Alzheimer disease

Biological markers play an evolving role in the diagnosis of Alzheimer disease (AD). We compare conventional measurements of cerebrospinal fluid (CSF) tau and β-amyloid_1–42 proteins to a novel approach – Fourier transformed infrared (FT-IR) spectroscopy – a simple technique derived from chemical and physical sciences that characterizes intramolecular bonds. For automatic diagnostic analysis, we developed an artificial neural network (ANN). We examined 71 patients with a clinical diagnosis of AD and 66 controls. β-Amyloid_1–42 was decreased (sensitivity 80% and specificity 78%); tau was elevated (sensitivity 76% and specificity 88%) in CSF of AD patients. The combined tau/β-amyloid_1–42 quotient was able to distinguish healthy from diseased subjects with 99% sensitivity and 86% specificity. The ANN could separate FT-IR spectroscopy data with 88.5% sensitivity and 80% specificity. FT-IR spectroscopy proved to be cost-effective and simple to perform. Diagnostic sensitivity and specificity is in the range of CSF tau and β-amyloid_1–42 protein analysis. Larger sample numbers for ANN training and validation could increase diagnostic accuracy and thus prove to be a useful screening tool.     

液基细胞学联合DNA定量细胞学在筛查宫颈病变中的应用价值

目的探讨宫颈液基细胞学和DNA定量细胞学在宫颈癌前病变及宫颈癌诊断中的应用价值。方法对2156例患者进行宫颈液基细胞学和DNA定量细胞学检查,对其中221例液基细胞学和（或）DNA定量分析阳性者行宫颈活检,以活检结果为金标准,比较两种方法的检测结果及DNA定量细胞学对ASCUS患者的分流作用。结果1．液基细胞学以≥ASCUS,DNA定量细胞学以可见DNA倍体异常细胞作为活检标准及联合两种方法检测,活检结果以CINI及以上病理改变作为阳性结果,其敏感度、特异度、阳性预测值、阴性预测值分别为69．77％、77．52％和89．15％,38．04％、48．91％和84．09％,61．22％、63．69％和86．47％,47．30％、60．81％和84．09％。2．TCT与DNA定量细胞学检测方法灵敏度及特异度对比,均无统计学意义（P〉0．05）;TCT联合应用DNA定量细胞学与单独应用TCT检测方法灵敏度及特异度对比,均有统计学意义（P〈0．01）;TCT联合应用DNA定量细胞学与单独应用DNA定量细胞学检测方法灵敏度对比,无统计学意义（P〉0．05）,特异度对比,有统计学意义（P〈0．01）。3．ASCUS患者宫颈病变的检出率为56．25％。ASCUS患者以DNA定量细胞学作为分流方法：阳性组检出率为74．00％,阴性组检出率为26．67％,两组检出率对比,有高度统计学差异（P〈0．01）;DNA定量细胞学阳性组与ASCUS患者未分流前检出率对比,有统计学意义（P〈0．05）。结论DNA定量分析方法与液基薄层细胞学联合筛查,可提高宫颈癌前病变及宫颈癌筛查的敏感度和特异度,对于细胞学检测为ASCUS的人群有分流作用。     

乳腺计算机辅助诊断中DCE-MRI图像特征的选择与分析

目的比较动态对比度增强磁共振成像（dynamic contrast—enhanced magnetic resonance imaging,DCE—MRI）图像的形态、纹理和时间强度曲线（time intensity curve,TIC）特征对乳腺病灶良恶性的诊断效果,讨论DCE—MRI图像特征的计算机辅助诊断价值。方法测量224个乳腺病灶样本（良性样本82个,恶性样本142个）的12个形态学特征、56个基于灰度共生矩阵（gray level co—occurrencematrix,GLCM）的纹理特征以及11个TIC特征,采用平均平方距离准则和SVM分类器评估这三类特征的良恶性分辨能力。结果反映病灶血流动力学特性的TIC特征的分类性能最优（SE0．9366,SP0．8293,AUC0．9495）;纹理特征次之（SE0．9225,SP0．7195,AUC0．8835）;形态学特征效果最差（SE0．8451,SP0．6951,AUC0．8079）。研究发现,在上述基础上融合三类特征可优化分类性能。最终结合平滑度、紧致度、熵等9个特征参数进行诊断,对乳腺病灶良恶性的分辨效果最好,AUC达0．9642。结论DCE—MRI的TIC特征对恶性乳腺病灶具有较高的灵敏度,可以提高乳腺计算机辅助诊断的恶性病灶检出率。综合分析形态、纹理和TIC特征可以提高病灶的诊断特异度,降低良性病灶的误诊率。