Normal Regions Of Interest Research Articles

Dynamic NIR Fluorescence Imaging and Machine Learning Framework for Stratifying High vs. Low Notch-Dll4 Expressing Host Microenvironment in Triple-Negative Breast Cancer.

Delta like canonical notch ligand 4 (Dll4) expression levels in tumors are known to affect the efficacy of cancer therapies. This study aimed to develop a model to predict Dll4 expression levels in tumors using dynamic enhanced near-infrared (NIR) imaging with indocyanine green (ICG). Two rat-based consomic xenograft (CXM) strains of breast cancer with different Dll4 expression levels and eight congenic xenograft strains were studied. Principal component analysis (PCA) was used to visualize and segment tumors, and modified PCA techniques identified and analyzed tumor and normal regions of interest (ROIs). The average NIR intensity for each ROI was calculated from pixel brightness at each time interval, yielding easily interpretable features including the slope of initial ICG uptake, time to peak perfusion, and rate of ICG intensity change after reaching half-maximum intensity. Machine learning algorithms were applied to select discriminative features for classification, and model performance was evaluated with a confusion matrix, receiver operating characteristic curve, and area under the curve. The selected machine learning methods accurately identified host Dll4 expression alterations with sensitivity and specificity above 90%. This may enable stratification of patients for Dll4 targeted therapies. NIR imaging with ICG can noninvasively assess Dll4 expression levels in tumors and aid in effective decision making for cancer therapy.

MAVRIC based T2 mapping assessment of infrapatellar fat pad scarring in patients with total knee arthroplasty.

The infrapatellar fat pad (IPFP) has been implicated as a source of postoperative knee pain. Imaging the IPFP is challenging in patients with total knee arthroplasty (TKA) due to metallic susceptibility artifact. Multi-Acquisition Variable-Resonance Image Combination (MAVRIC)-based T2 Mapping has been developed to mitigate this artifact and can generate quantitative T2 data. Objectives of this study were to (1) measure T2 values of the IPFP in patients with TKAs using a MAVRIC based T2 mapping technique and (2) determine if IPFP T2 values are related to the degree of fat pad scarring or clinical magnetic resonance imaging (MRI) findings. Twenty-eight subjects (10 males, 18 females, Age: 66 + 7.2 years [Mean ± standard deviations]) undergoing clinical MRIs were sequentially recruited. Morphological imaging and quantitative T2 mapping sequences were performed on a clinical 1.5 Tscanner. The morphologic images were graded for the presence and severity of fat pad scarring and clinical outcomes. T2 values were calculated in the total fat pad volume, a normal regions of interest (ROI), and an abnormal ROI. T2 values were shortened in the total IPFP volume (p = 0.001) and within abnormal regions (p = 0.003) in subjects with more severe IPFP scarring. The difference between T2 values in normal-abnormal regions was greater in subjects with severe versus no scarring (+1426.1%, p = 0.008). T2 values were elevated in patients with MRI findings of osteolysis (+32.3%, p = 0.02). These findings indicate that MAVRIC-based T2 Mapping may be used as a quantitative biomarker of postoperative IPFP scarring in individuals following TKA.

Prediction Model of Hemorrhage Transformation in Patient with Acute Ischemic Stroke Based on Multiparametric MRI Radiomics and Machine Learning.

Intravenous thrombolysis is the most commonly used drug therapy for patients with acute ischemic stroke, which is often accompanied by complications of intracerebral hemorrhage transformation (HT). This study proposed to build a reliable model for pretreatment prediction of HT. Specifically, 5400 radiomics features were extracted from 20 regions of interest (ROIs) of multiparametric MRI images of 71 patients. Furthermore, a minimal set of all-relevant features were selected by LASSO from all ROIs and used to build a radiomics model through the random forest (RF). To explore the significance of normal ROIs, we built a model only based on abnormal ROIs. In addition, a model combining clinical factors and radiomics features was further built. Finally, the models were tested on an independent validation cohort. The radiomics model with 14 All-ROIs features achieved pretreatment prediction of HT (AUC = 0.871, accuracy = 0.848), which significantly outperformed the model with only 14 Abnormal-ROIs features (AUC = 0.831, accuracy = 0.818). Besides, combining clinical factors with radiomics features further benefited the prediction performance (AUC = 0.911, accuracy = 0.894). So, we think that the combined model can greatly assist doctors in diagnosis. Furthermore, we find that even if there were no lesions in the normal ROIs, they also provide characteristic information for the prediction of HT.

Evaluation of HIF-1α Expression in a Rat Glioma Model Using Intravoxel Incoherent Motion and R2* Mapping.

Accurate evaluation of HIF-1α levels can facilitate the detection of hypoxia niches in glioma and treatment decisions. To investigate the feasibility of intravoxel incoherent motion (IVIM) and R2* Mapping for detecting HIF-1α expression levels, sixteen rats with intracranial C6 gliomas were subjected to IVIM and R2* Mapping using a 7 Tesla MRI scanner. For each model, the brain tissue on the HIF-1α-stained slices was subdivided into multiple square regions of interest (ROIs) with areas of 1 mm2, for which HIF-1α expression was assessed by HALO software to form a maps of HIF scores with a 0–300 range. The IVIM and R2* Mapping images were processed to create maps of the D, D*, f and R2* that were then paired with the corresponding HIF score maps. The average D, D*, f, perfusion (f × D*) and R2* values were calculated for the ROIs in the tumor and normal brain regions with different HIF-1α levels and used in further analysis. In this study, the average tumor size of sixteen C6 model rats was 458 ± 46.52 mm3, and the 482 included ROIs consisted of 280 tumoral and 202 normal ROIs. The average HIF score for the tumor regions was significantly higher than normal brain tissue (p < 0.001), and higher HIF scores were obtained for the central part of tumors than peripheral parts (p=0.03). Compared with normal brain tissues, elevated perfusion and f values were observed in tumor regions (p = 0.021, 0.004). In tumoral ROIs, the R2* values were higher in the group with high HIF-1α expression than in the group with low HIF-1α expression (p = 0.003). A correlation analysis revealed a positive correlation between the R2* value and HIF scores (r = 0.43, p < 0.001) and a negative correlation between D* and the HIF scores (r = -0.30, p = 0.001). Discrepancies in HIF-1α expression were found among different intratumoral areas, and IVIM and R2* Mapping were found to be promising means of noninvasive detection of the distribution and expression level of HIF-1α.

Multiparametric MRI as a Biomarker of Response to Neoadjuvant Therapy for Localized Prostate Cancer–A Pilot Study

To explore a role for multiparametric MRI (mpMRI) as a biomarker of response to neoadjuvant androgen deprivation therapy (ADT) for prostate cancer (PCa). This prospective study was approved by the institutional review board and was HIPAA compliant. Eight patients with localized PCa had a baseline mpMRI, repeated after 6-months of ADT, followed by prostatectomy. mpMRI indices were extracted from tumor and normal regions of interest (TROI/NROI). Residual cancer burden (RCB) was measured on mpMRI and on the prostatectomy specimen. Paired t-tests compared TROI/NROI mpMRI indices and pre/post-treatment TROI mpMRI indices. Spearman's rank tested for correlations between MRI/pathology-based RCB, and between pathological RCB and mpMRI indices. At baseline, TROI apparent diffusion coefficient (ADC) was lower and dynamic contrast enhanced (DCE) metrics were higher, compared to NROI (ADC: 806 ± 137 × 10-6 vs. 1277 ± 213 × 10-6 mm2/sec, p = 0.0005; Ktrans: 0.346 ± 0.16 vs. 0.144 ± 0.06 min-1, p = 0.002; AUC90: 0.213 ± 0.08 vs. 0.11 ± 0.03, p = 0.002). Post-treatment, there was no change in TROI ADC, but a decrease in TROI Ktrans (0.346 ± 0.16 to 0.188 ± 0.08 min-1; p = 0.02) and AUC90 (0.213 ± 0.08 to 0.13 ± 0.06; p = 0.02). Tumor volume decreased with ADT. There was no difference between mpMRI-based and pathology-based RCB, which positively correlated (⍴ = 0.74-0.81, p < 0.05). Pathology-based RCB positively correlated with post-treatment DCE metrics (⍴ = 0.76-0.70, p < 0.05) and negatively with ADC (⍴ = -0.79, p = 0.03). Given the heterogeneity of PCa, an individualized approach to ADT may maximize potential benefit. This pilot study suggests that mpMRI may serve as a biomarker of ADT response and as a surrogate for RCB at prostatectomy.

Supervised risk predictor of central gland lesions in prostate cancer using 1 H MR spectroscopic imaging with gradient offset-independent adiabaticity pulses.

Due to the histological heterogeneity of the central gland, accurate detection of central gland prostate cancer remains a challenge. To evaluate the efficacy of in vivo 3D 1 H MR spectroscopic imaging (3D 1 H MRSI) with a semi-localized adiabatic selective refocusing (sLASER) sequence and gradient-modulated offset-independent adiabatic (GOIA) pulses for detection of central gland prostate cancer. Additionally four risk models were developed to differentiate 1) normal vs. cancer, 2) low- vs. high-risk cancer, 3) low- vs. intermediate-risk cancer, and 4) intermediate- vs. high-risk cancer voxels. Prospective. Thirty-six patients with biopsy-proven central gland prostate cancer. 3T MRI / 3D 1 H MRSI using GOIA-sLASER. Cancer and normal regions of interest (ROIs) were selected by an experienced radiologist and 1 H MRSI voxels were placed within the ROIs to calculate seven metabolite signal ratios. Voxels were split into two subsets, 80% for model training and 20% for testing. Four support vector machine (SVM) models were built using the training dataset. The accuracy, sensitivity, and specificity for each model were calculated for the testing dataset. High-quality MR spectra were obtained for the whole central gland of the prostate. The normal vs. cancer diagnostic model achieved the highest predictive performance with an accuracy, sensitivity, and specificity of 96.2%, 95.8%, and 93.1%, respectively. The accuracy, sensitivity, and specificity of the low- vs. high-risk cancer and low- vs. intermediate-risk cancer models were 82.5%, 89.2%, 70.2%, and 73.0%, 84.7%, 60.8%, respectively. The intermediate- vs. high-risk cancer model yielded an accuracy, sensitivity, and specificity lower than 55%. The GOIA-sLASER sequence with an external phased-array coil allows for fast assessment of central gland prostate cancer. The classification offers a promising diagnostic tool for discriminating normal vs. cancer, low- vs. high-risk cancer, and low- vs. intermediate-risk cancer. 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1926-1936.

Breast cancer detection using synthetic mammograms from generative adversarial networks in convolutional neural networks.

The convolutional neural network (CNN) is a promising technique to detect breast cancer based on mammograms. Training the CNN from scratch, however, requires a large amount of labeled data. Such a requirement usually is infeasible for some kinds of medical image data such as mammographic tumor images. Because improvement of the performance of a CNN classifier requires more training data, the creation of new training images, image augmentation, is one solution to this problem. We applied the generative adversarial network (GAN) to generate synthetic mammographic images from the digital database for screening mammography (DDSM). From the DDSM, we cropped two sets of regions of interest (ROIs) from the images: normal and abnormal (cancer/tumor). Those ROIs were used to train the GAN, and the GAN then generated synthetic images. For comparison with the affine transformation augmentation methods, such as rotation, shifting, scaling, etc., we used six groups of ROIs [three simple groups: affine augmented, GAN synthetic, real (original), and three mixture groups of any two of the three simple groups] for each to train a CNN classifier from scratch. And, we used real ROIs that were not used in training to validate classification outcomes. Our results show that, to classify the normal ROIs and abnormal ROIs from DDSM, adding GAN-generated ROIs in the training data can help the classifier prevent overfitting, and on validation accuracy, the GAN performs about 3.6% better than affine transformations for image augmentation. Therefore, GAN could be an ideal augmentation approach. The images augmented by GAN or affine transformation cannot substitute for real images to train CNN classifiers because the absence of real images in the training set will cause over-fitting.

Improving Ultrasound Detection of Uterine Adenomyosis Through Computational Texture Analysis.

The purpose of our study was to determine if a textural analysis metric can be implemented to improve diagnosis of adenomyosis by ultrasound.We retrospectively identified 38 patients with a magnetic resonance imaging (MRI) diagnosis of uterine adenomyosis that also had a pelvic ultrasound within 6 months. We also identified 50 normal pelvic ultrasound examinations confirmed by a normal pelvic MRI within 6 months as a control group. A region of interest (ROI) was subsequently placed on the study population ultrasound image corresponding to the area of adenomyosis on MRI. An ROI was placed in the area of the junctional zone in the normal controls. The abnormal and normal ROIs were then compared against trained normal and abnormal distributions to determine the success rate, sensitivity, specificity, and negative and positive predictive values of our computer metric. The ultrasound reports performed before MRI were also reviewed to determine the radiologist correct/incorrect interpretation rate for comparison with our textural analysis metric.Using a training population of 50 normal ultrasound examinations (confirmed with a normal MRI) and 38 abnormal ultrasound examinations (MRI confirmed adenomyosis), we had an overall 75% (66/88 accurately diagnosed) success rate with a sensitivity, specificity, and negative and positive predictive values of 70%, 79%, 73%, and 76%, respectively (P < .0001). The sensitivity and false-negative rate of the initial ultrasound interpretation were 26% (10/38) and 74% (28/38), respectively.

Three phase bone scintigraphy with (99m)Tc-MDP and serological indices in detecting infection after internal fixation in malunion or nonunion traumatic fractures.

To evaluate the diagnostic efficacy of technetium-99m-methylene diphosphonate ((99m)Tc-MDP) three phase bone scintigraphy in detecting infection in malunion or nonunion traumatic fractures after internal fixation. One hundred and eighty four patients with malunion or nonunion fractures after internal fixation (130 men and 54 women; age range, 16-79 years) underwent (99m)Tc-MDP three phase bone scintigraphy (3PBS). They were divided into the infection group (n=96) and the control group without infection (n=88) based on the final diagnosis after operation. The sensitivity, specificity, accuracy, positive prediction value (PPV) and negative prediction value (NPV) were calculated and compared. All patients carried out other laboratory tests related to infection such as complete serum blood cells count, C-reactive protein (CRP), and erythrocyte sedimentation rate (ESR). The (99m)Tc-MDP 3PBS for the blood flow phase showed sensitivity, specificity, accuracy, positive predictive value and negative predictive value, 91.7% (88/96), 72.7% (64/88), 82.6% (152/184), 78.6% (88/112) and 88.9% (64/72), respectively and for the blood pool phase, 93.8% (90/96), 61.4% (54/88), 78.3% (144/184), 72.6% (90/124) and 90.0% (54/60) respectively. The semiquantitative indices of the ratio between the abnormal and the normal region of interest (ROI), called by us the A/N ratio, for both blood flow and blood pool phases as estimated between the infection group and the control group were statistically different. It is the opinion of the authors that (99m)Tc-MDP 3PBS provided high predictive values in diagnosing infection in patients with malunion or nonunion traumatic fractures after internal fixation. The diagnostic value of blood flow and blood pool phases estimated of the 3PBS was better than the laboratory indices: white blood cell counts, CRP, and ESR.

A Bayesian spatial temporal mixtures approach to kinetic parametric images in dynamic positron emission tomography.

Estimation of parametric maps is challenging for kinetic models in dynamic positron emission tomography. Since voxel kinetics tend to be spatially contiguous, the authors consider groups of homogeneous voxels together. The authors propose a novel algorithm to identify the groups and estimate kinetic parameters simultaneously. Uncertainty estimates for kinetic parameters are also obtained. Mixture models were used to fit the time activity curves. In order to borrow information from spatially nearby voxels, the Potts model was adopted. A spatial temporal model was built incorporating both spatial and temporal information in the data. Markov chain Monte Carlo was used to carry out parameter estimation. Evaluation and comparisons with existing methods were carried out on cardiac studies using both simulated data sets and a pig study data. One-compartment kinetic modeling was used, in which K1 is the parameter of interest, providing a measure of local perfusion. Based on simulation experiments, the median standard deviation across all image voxels, of K1 estimates were 0, 0.13, and 0.16 for the proposed spatial mixture models (SMMs), standard curve fitting, and spatial K-means methods, respectively. The corresponding median mean squared biases for K1 were 0.04, 0.06, and 0.06 for abnormal region of interest (ROI); 0.03, 0.03, and 0.04 for normal ROI; and 0.007, 0.02, and 0.05 for the noise region. SMM is a fully Bayesian algorithm which determines the optimal number of homogeneous voxel groups, voxel group membership, parameter estimation, and parameter uncertainty estimation simultaneously. The voxel membership can also be used for classification purposes. By borrowing information from spatially nearby voxels, SMM substantially reduces the variability of parameter estimates. In some ROIs, SMM also reduces mean squared bias.

SU‐E‐J‐248: Contributions of Tumor and Stroma Phenotyping in Computer‐Aided Diagnosis

Purpose:To gain insight into the role of parenchyma stroma in the characterization of breast tumors by incorporating computerized mammographic parenchyma assessment into breast CADx in the task of distinguishing between malignant and benign lesions.Methods:This study was performed on 182 biopsy‐proven breast mass lesions, including 76 benign and 106 malignant lesions. For each full‐field digital mammogram (FFDM) case, our quantitative imaging analysis was performed on both the tumor and a region‐of‐interest (ROI) from the normal contralateral breast. The lesion characterization includes automatic lesion segmentation and feature extraction. Radiographic texture analysis (RTA) was applied on the normal ROIs to assess the mammographic parenchymal patterns of these contralateral normal breasts. Classification performance of both individual computer extracted features and the output from a Bayesian artificial neural network (BANN) were evaluated with a leave‐one‐lesion‐out method using receiver operating characteristic (ROC) analysis with area under the curve (AUC) as the figure of merit.Results:Lesion characterization included computer‐extracted phenotypes of spiculation, size, shape, and margin. For parenchymal pattern characterization, five texture features were selected, including power law beta, contrast, and edge gradient. Merging of these computer‐selected features using BANN classifiers yielded AUC values of 0.79 (SE=0.03) and 0.67 (SE=0.04) in the task of distinguishing between malignant and benign lesions using only tumor phenotypes and texture features from the contralateral breasts, respectively. Incorporation of tumor phenotypes with parenchyma texture features into the BANN yielded improved classification performance with an AUC value of 0.83 (SE=0.03) in the task of differentiating malignant from benign lesions.Conclusion:Combining computerized tumor and parenchyma phenotyping was found to significantly improve breast cancer diagnostic accuracy highlighting the need to consider both tumor and stroma in decision making.Funding: University of Chicago Dean Bridge Fund, NCI U24‐CA143848‐05, P50‐CA58223 Breast SPORE program, and Breast Cancer Research Foundation. COI: MLG is a stockholder in R2 technology/Hologic and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi, and Toshiba. MLG is a cofounder and stockholder in Quantitative Insights.

Abstract P2-04-06: Demonstration of immune cell and pathway heterogeneity in Singapore DCIS samples using novel hyperplexing method (MultiOmyx®)

Abstract Breast cancer is the most common malignancy in Singapore women with rising incidence across all ethnic groups (Chinese, Malays and Indians). Ductal carcinoma in situ (DCIS) is the earliest non-invasive stage of disease and has been shown to account for approximately 26% of diagnoses in all women participating in the Breast-Screen Singapore program. Despite availability of breast screening, there are still Singapore women presenting with locally advanced breast cancer. The goal of the current study was to investigate pathway and immune cell heterogeneity in low, intermediate and high nuclear grade DCIS using a newly developed method for in situ hyperplexed analysis of multiple proteins in a single FFPE tissue (MultiOmyx). FFPE samples from patients (n= 15) diagnosed with DCIS were provided by Singapore General Hospital. Patients were of Chinese origin, ranged from 50-59 years, were all post-menopausal, and included low (n=5), intermediate (n=5) and high grade (n=5) samples. All histological diagnoses were reviewed by a single pathologist. Following a single antigen retrieval step, DAPI and cytokeratin staining was conducted and imaged at 10X. Based on DAPI, cytokeratin and autofluorescence, an H&amp;E-like image was generated for each sample. Using this image, approximately 30 regions of interest (ROI) were selected per slide/patient, including normal and DCIS regions with and without immune cells. In total, 15 biomarkers were imaged following an iterative process of IF staining and dye inactivation. These included CD4 (T-cells), CD8 (T-cells), CD20 (B-cells), CD68 (macrophages), CD10 (myoepithelial cells), CD44v6 (cancer stem cell), Her2, Her4, EGFR (ErbB family proteins), pmTOR (cell growth), SLC7A5 (Mammostrat) and epithelium and cell segmentation markers (pan-cadherin, pan-cytokeratin, S6 and Na+K+ATPase). Images were evaluated for quality and processed to generate single cell quantification data for each marker in the epithelium and stroma. Single cell data was compared with clinical and histological features (grade, DCIS/ low immune cells, DCIS/ high immune cells). Cell-based k-means clustering was then performed for biomarkers in both the epithelial cells (Her4, Her2, panCK, SLC7A5, EGFR, NaKATPase, pmTOR, and CD10) and stromal cells (CD4, CD8, CD20, CD68). Using consensus clustering, the optimum number of clusters was found to be six in both the epithelium and stroma. No distinct clusters were associated with histological grade. Normal ROIs tended to be associated with higher CD10 and EGFR, moderate CD20 and low or negative for other markers. DCIS with low immune cells tended to have higher Her4, pmTOR and moderate CD68 while DCIS with high immune cells tended to have high Her2 and moderate to high CD4, CD20 and CD68. A larger study is needed to associate the findings with outcome. This technology provides a way to elucidate mechanisms of early disease and illustrates the complex inter-play between grade, pathway activation and immune response. Citation Format: Nicole E LaPlante, Yunxia Sui, Michael J Gerdes, Sean Dinn, Rong Zhang, Sireesha Kaanumalle, Elizabeth McDonough, Christina Lowes, Craig Allred, Fiona Ginty, Thomas Foo, Puay-Hoon Tan. Demonstration of immune cell and pathway heterogeneity in Singapore DCIS samples using novel hyperplexing method (MultiOmyx®) [abstract]. In: Proceedings of the Thirty-Seventh Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2014 Dec 9-13; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2015;75(9 Suppl):Abstract nr P2-04-06.

Computer-aided diagnosis in hysteroscopic imaging.

The paper presents the development of a computer-aided diagnostic (CAD) system for the early detection of endometrial cancer. The proposed CAD system supports reproducibility through texture feature standardization, standardized multifeature selection, and provides physicians with comparative distributions of the extracted texture features. The CAD system was validated using 516 regions of interest (ROIs) extracted from 52 subjects. The ROIs were equally distributed among normal and abnormal cases. To support reproducibility, the RGB images were first gamma corrected and then converted into HSV and YCrCb. From each channel of the gamma-corrected YCrCb, HSV, and RGB color systems, we extracted the following texture features: 1) statistical features (SFs), 2) spatial gray-level dependence matrices (SGLDM), and 3) gray-level difference statistics (GLDS). The texture features were then used as inputs with support vector machines (SVMs) and the probabilistic neural network (PNN) classifiers. After accounting for multiple comparisons, texture features extracted from abnormal ROIs were found to be significantly different than texture features extracted from normal ROIs. Compared to texture features extracted from normal ROIs, abnormal ROIs were characterized by lower image intensity, while variance, entropy, and contrast gave higher values. In terms of ROI classification, the best results were achieved by using SF and GLDS features with an SVM classifier. For this combination, the proposed CAD system achieved an 81% correct classification rate.

Development of CAD based on ANN analysis of power spectra for pneumoconiosis in chest radiographs: effect of three new enhancement methods

We have been developing a computer-aided detection (CAD) scheme for pneumoconiosis based on a rule-based plus artificial neural network (ANN) analysis of power spectra. In this study, we have developed three enhancement methods for the abnormal patterns to reduce false-positive and false-negative values. The image database consisted of 2 normal and 15 abnormal chest radiographs. The International Labour Organization standard chest radiographs with pneumoconiosis were categorized as subcategory, size, and shape of pneumoconiosis. Regions of interest (ROIs) with a matrix size of 32 × 32 were selected from normal and abnormal lungs. Three new enhanced methods were obtained by window function, top-hat transformation, and gray-level co-occurrence matrix analysis. We calculated the power spectrum (PS) of all ROIs by Fourier transform. For the classification between normal and abnormal ROIs, we applied a combined analysis using the ruled-based plus the ANN method. To evaluate the overall performance of this CAD scheme, we employed ROC analysis for distinguishing between normal and abnormal ROIs. On the chest radiographs of the highest categories (severe pneumoconiosis) and the lowest categories (early pneumoconiosis), this CAD scheme achieved area under the curve (AUC) values of 0.93 ± 0.02 and 0.72 ± 0.03. The combined rule-based plus ANN method with the three new enhanced methods obtained the highest classification performance for distinguishing between abnormal and normal ROIs. Our CAD system based on the three new enhanced methods would be useful in assisting radiologists in the classification of pneumoconiosis.

Accuracy and saving of time using a new algorithm for quantitative measurement of infarct and edema size in patients with acute myocardial infarction

Background Cardiac magnetic resonance imaging (CMR) enables infarct and edema size measurement on LGEand T2wCMR, respectively. However, evaluation of infarct and edema size using a threshold method is time consuming and relies on accurate placement of normal regions of interest and manual delineation of the respective areas. The purpose of the study was to analyze the accuracy and expenditure of time of a new algorithm for infarct and edema size measurement using LGEand T2wCMR in comparison to a standard evaluation strategy.

영상처리와 SVM을 이용한 Billet의 스크래치 결함 분류

In the steel manufacturing area, researches for defect inspection receive a big attention for quality control. This paper proposes an algorithm to detect a scratch defect on steel billets. This algorithm takes ROIs (Regions of Interest), and extracts 11 features which represent properties of defect on a ROI. SVM (Support Vector Machine) is used to classify defect and normal ROIs. The algorithm classifies a frame image of a Billet as a defect image if there is one or more defect ROIs. In the experiments, the proposed algorithm had reliable classifying accuracy.

Quantitative Analysis of Multiparametric Prostate MR Images: Differentiation between Prostate Cancer and Normal Tissue and Correlation with Gleason Score—A Computer-aided Diagnosis Development Study

To evaluate the potential utility of a number of parameters obtained at T2-weighted, diffusion-weighted, and dynamic contrast material-enhanced multiparametric magnetic resonance (MR) imaging for computer-aided diagnosis (CAD) of prostate cancer and assessment of cancer aggressiveness. In this institutional review board-approved HIPAA-compliant study, multiparametric MR images were acquired with an endorectal coil in 48 patients with prostate cancer (median age, 62.5 years; age range, 44-73 years) who subsequently underwent prostatectomy. A radiologist and a pathologist identified 104 regions of interest (ROIs) (61 cancer ROIs, 43 normal ROIs) based on correlation of histologic and MR findings. The 10th percentile and average apparent diffusion coefficient (ADC) values, T2-weighted signal intensity histogram skewness, and Tofts K(trans) were analyzed, both individually and combined, via linear discriminant analysis, with receiver operating characteristic curve analysis with area under the curve (AUC) as figure of merit, to distinguish cancer foci from normal foci. Spearman rank-order correlation (ρ) was calculated between cancer foci Gleason score (GS) and image features. AUC (maximum likelihood estimate ± standard error) values in the differentiation of prostate cancer from normal foci of 10th percentile ADC, average ADC, T2-weighted skewness, and K(trans) were 0.92 ± 0.03, 0.89 ± 0.03, 0.86 ± 0.04, and 0.69 ± 0.04, respectively. The combination of 10th percentile ADC, average ADC, and T2-weighted skewness yielded an AUC value for the same task of 0.95 ± 0.02. GS correlated moderately with 10th percentile ADC (ρ = -0.34, P = .008), average ADC (ρ = -0.30, P = .02), and K(trans) (ρ = 0.38, P = .004). The combination of 10th percentile ADC, average ADC, and T2-weighted skewness with CAD is promising in the differentiation of prostate cancer from normal tissue. ADC image features and K(trans) moderately correlate with GS.

Quantitative Measurement Method for Possible Rib Fractures in Chest Radiographs

ObjectivesThis paper proposes a measurement method to quantify the abnormal characteristics of the broken parts of ribs using local texture and shape features in chest radiographs.MethodsOur measurement method comprises two steps: a measurement area assignment and sampling step using a spline curve and sampling lines orthogonal to the spline curve, and a fracture-ness measurement step with three measures, asymmetry and gray-level co-occurrence matrix based measures (contrast and homogeneity). They were designed to quantify the regional shape and texture features of ribs along the centerline. The discriminating ability of our method was evaluated through region of interest (ROI) analysis and rib fracture classification test using support vector machine.ResultsThe statistically significant difference was found between the measured values from fracture and normal ROIs; asymmetry (p < 0.0001), contrast (p < 0.001), and homogeneity (p = 0.022). The rib fracture classifier, trained with the measured values in ROI analysis, detected every rib fracture from chest radiographs used for ROI analysis, but it also classified some unbroken parts of ribs as abnormal parts (8 to 17 line sets; length of each line set, 2.998 ± 2.652 mm; length of centerlines, 131.067 ± 29.460 mm).ConclusionsOur measurement method, which includes a flexible measurement technique for the curved shape of ribs and the proposed shape and texture measures, could discriminate the suspicious regions of ribs for possible rib fractures in chest radiographs.

Evaluation of a new semi-automatic strategy for quantitative measurement of infarct size in patients with acute and chronic myocardial infarction using cardiac magnetic resonance imaging

Background Cardiac magnetic resonance imaging (CMR) with delayed gadolinium enhancement (DE) enables accurate infarct size measurement, however, the evaluation of infarct size using a threshold method is time consuming and relies on accurate placement of normal regions of interest and manual delineation of the infarct size. The purpose of the study was to analyze the accuracy and expenditure of time of a new evaluation strategy for infarct size measurement using delayed enhancement CMR in comparison to a standard evaluation.

Texture analysis of CT images in the characterization of oral cancers involving buccal mucosa

The aim of this study was to investigate the usefulness of texture analysis in the characterization of oral cancers involving the buccal mucosa and to assess its effectiveness in differentiating between the various grades of the tumour. Contrast enhanced CT examination was carried out in 21 patients with carcinoma of the buccal mucosa who had consented to retrospective analysis during a research study that was approved by the institutional review board. Two regions of interest (ROIs) were created, one at the site of the lesion and the other at the contralateral normal side. Texture analysis measures of fractal dimension (FD), lacunarity and grey level co-occurrence matrix (GLCM) were computed for each ROI. The numeric data from the two ROIs were compared and were correlated with the tumour grade as confirmed by biopsy. The difference between the mean FD and GLCM parameters of the lesion vs the normal ROI were statistically significant (p < 0.05); no significant difference was observed between the three grades of tumour for any of the parameters (p > 0.05). Texture analysis on CT images is a potential method in the characterization of oral cancers involving the buccal mucosa and deserves further investigation as a predictor of tumour aggression.