Detection Of Malignant Masses Research Articles

Detection of breast cancer presenting as a mass in women with dense breasts- digital breast tomosynthesis versus full-field digital mammography.

To evaluate the sensitivity and specificity of digital breast tomosynthesis compared with full-field digital mammography in detection of breast cancer presenting as a mass in women with dense breasts. Маterials and Methods: This study included 347asymptomatic and symptomatic patients with dense breasts who underwent full-field digital mammography, digital breast tomosynthesis and hand-held full breast ultrasound. 57core-needle biopsies were performed. Pathology included 31invasive cancers and 26non-cancerous lesions. Sensitivity of full-field digital mammography was 61.3%[0.422-0.789] and sensitivity of digital breast tomosynthesis was 77.4%[0.589-0.904]. Specificity of full-field digital mammography was 92.7%[0.893-0.953] that was 2.2% lower than the specificity of digital breast tomosynthesis- 94.9%[0.919-0.971]. Results of our study showed superior sensitivity and specificity of digital breast tomosynthesis compared to full-field digital mammography for detection of malignant masses in women with dense breasts.

Classifying symmetrical differences and temporal change for the detection of malignant masses in mammography using deep neural networks.

We investigate the addition of symmetry and temporal context information to a deep convolutional neural network (CNN) with the purpose of detecting malignant soft tissue lesions in mammography. We employ a simple linear mapping that takes the location of a mass candidate and maps it to either the contralateral or prior mammogram, and regions of interest (ROIs) are extracted around each location. Two different architectures are subsequently explored: (1)a fusion model employing two datastreams where both ROIs are fed to the network during training and testing and (2)a stagewise approach where a single ROI CNN is trained on the primary image and subsequently used as a feature extractor for both primary and contralateral or prior ROIs. A "shallow" gradient boosted tree classifier is then trained on the concatenation of these features and used to classify the joint representation. The baseline yielded an AUC of 0.87 with confidence interval [0.853, 0.893]. For the analysis of symmetrical differences, the first architecture where both primary and contralateral patches are presented during training obtained an AUC of 0.895 with confidence interval [0.877, 0.913], and the second architecture where a new classifier is retrained on the concatenation an AUC of 0.88 with confidence interval [0.859, 0.9]. We found a significant difference between the first architecture and the baseline at high specificity with [Formula: see text]. When using the same architectures to analyze temporal change, we yielded an AUC of 0.884 with confidence interval [0.865, 0.902] for the first architecture and an AUC of 0.879 with confidence interval [0.858, 0.898] in the second setting. Although improvements for temporal analysis were consistent, they were not found to be significant. The results show our proposed method is promising and we suspect performance can greatly be improved when more temporal data become available.

Diagnostic Performance of Split-Bolus Portal Venous Phase Dual-Energy CT Urography in Patients With Hematuria.

The purpose of this study is to evaluate the diagnostic performance of split-bolus portal venous phase dual-energy CT (DECT) urography in patients with hematuria. True unenhanced and split-bolus portal venous phase contrast-enhanced weighted-average images were obtained in 171 patients with hematuria. Virtual unenhanced and iodine-overlay images were reconstructed from contrast-enhanced 80-kVp and tin-filtered 140-kVp scans. Images were independently reviewed by two radiologists who were blinded to the final diagnoses in two separate reading sessions: virtual unenhanced and iodine-overlay images (single phase) in the first session and true unenhanced and contrast-enhanced weighted-average images (dual phase) in the second session (mean ± SD, 52 ± 8 days later). Sensitivity, specificity, and accuracy of mass detection were calculated from the data of both reading sessions. The number of calculi detected on virtual unenhanced images was compared with the number detected on true unenhanced images. The difference in radiation dose between the single- and dual-phase protocols was calculated. The statistical significance was determined by ANOVA. The sensitivity, specificity, and accuracy were 98.7%, 98.9%, and 98.8%, respectively, for the single-phase approach to malignant mass detection and 98.7%, 97.9%, and 98.3%, respectively, for the dual-phase approach (p > 0.05 for all comparisons). The overall sensitivity of stone detection was 86.7% (39/45) for virtual unenhanced images. Omitting the unenhanced scan reduced the mean radiation dose from 15.4 to 6.7 mSv. The diagnostic performance of both the single- and dual-phase approaches of portal venous phase split-bolus DECT urography is equally good in patients with hematuria, and single-phase acquisition has the added benefit of radiation reduction.

FAST DETECTION OF MASSES IN MAMMOGRAMS WITH DIFFICULT CASE EXCLUSION

Breast cancer is one of the most common forms of cancer among women. Currently mammography is the most efficient method for early detection. A simple and fast mammographic mass detection system and two different methods for difficult case exclusion are presented in this paper. The mass detection system uses a modified version of a known algorithm for small masses and a new algorithm for large masses. The first difficult case filtering method is based on tissue density estimation, the second one on mass candidate count. The system was tested with 600 mammographic cases, each containing 4 images. Case-level performance was measured for malignant mass detection first without and then with difficult case exclusion.

Computer-aided detection system for masses in automated whole breast ultrasonography: development and evaluation of the effectiveness

Purpose:The aim of this study was to evaluate the performance of a proposed computer-aided detection (CAD) system in automated breast ultrasonography (ABUS).Methods:Eighty-nine two-dimensional images (20 cysts, 42 benign lesions, and 27 malignant lesions) were obtained from 47 patients who underwent ABUS (ACUSON S2000). After boundary detection and removal, we detected mass candidates by using the proposed adjusted Otsu's threshold; the threshold was adaptive to the variations of pixel intensities in an image. Then, the detected candidates were segmented. Features of the segmented objects were extracted and used for training/testing in the classification. In our study, a support vector machine classifier was adopted. Eighteen features were used to determine whether the candidates were true lesions or not. A five-fold cross validation was repeated 20 times for the performance evaluation. The sensitivity and the false positive rate per image were calculated, and the classification accuracy was evaluated for each feature.Results:In the classification step, the sensitivity of the proposed CAD system was 82.67% (SD, 0.02%). The false positive rate was 0.26 per image. In the detection/segmentation step, the sensitivities for benign and malignant mass detection were 90.47% (38/42) and 92.59% (25/27), respectively. In the five-fold cross-validation, the standard deviation of pixel intensities for the mass candidates was the most frequently selected feature, followed by the vertical position of the centroids. In the univariate analysis, each feature had 50% or higher accuracy.Conclusion:The proposed CAD system can be used for lesion detection in ABUS and may be useful in improving the screening efficiency.

Computer-aided Detection of Masses at Mammography: Interactive Decision Support versus Prompts

To compare effectiveness of an interactive computer-aided detection (CAD) system, in which CAD marks and their associated suspiciousness scores remain hidden unless their location is queried by the reader, with the effect of traditional CAD prompts used in current clinical practice for the detection of malignant masses on full-field digital mammograms. The requirement for institutional review board approval was waived for this retrospective observer study. Nine certified screening radiologists and three residents who were trained in breast imaging read 200 studies (63 studies containing at least one screen-detected mass, 17 false-negative studies, 20 false-positive studies, and 100 normal studies) twice, once with CAD prompts and once with interactive CAD. Localized findings were reported and scored by the readers. In the prompted mode, findings were recorded before and after activation of CAD. The partial area under the location receiver operating characteristic (ROC) curve for an interval of low false-positive fractions typical for screening, from 0 to 0.2, was computed for each reader and each mode. Differences in reader performance were analyzed by using software. The average partial area under the location ROC curve with unaided reading was 0.57, and it increased to 0.62 with interactive CAD, while it remained unaffected by prompts. The difference in reader performance for unaided reading versus interactive CAD was statistically significant (P = .009). When used as decision support, interactive use of CAD for malignant masses on mammograms may be more effective than the current use of CAD, which is aimed at the prevention of perceptual oversights.

Standalone computer-aided detection compared to radiologists’ performance for the detection of mammographic masses

We developed a computer-aided detection (CAD) system aimed at decision support for detection of malignant masses and architectural distortions in mammograms. The effect of this system on radiologists' performance depends strongly on its standalone performance. The purpose of this study was to compare the standalone performance of this CAD system to that of radiologists. In a retrospective study, nine certified screening radiologists and three residents read 200 digital screening mammograms without the use of CAD. Performances of the individual readers and of CAD were computed as the true-positive fraction (TPF) at a false-positive fraction of 0.05 and 0.2. Differences were analysed using an independent one-sample t-test. At a false-positive fraction of 0.05, the performance of CAD (TPF = 0.487) was similar to that of the certified screening radiologists (TPF = 0.518, P = 0.17). At a false-positive fraction of 0.2, CAD performance (TPF = 0.620) was significantly lower than the radiologist performance (TPF = 0.736, P <0.001). Compared to the residents, CAD performance was similar for all false-positive fractions. The sensitivity of CAD at a high specificity was comparable to that of human readers. These results show potential for CAD to be used as an independent reader in breast cancer screening.

Exploring the potential of context‐sensitive CADe in screening mammography

Conventional computer-assisted detection (CADe) systems in screening mammography provide the same decision support to all users. The aim of this study was to investigate the potential of a context-sensitive CADe system which provides decision support guided by each user's focus of attention during visual search and reporting patterns for a specific case. An observer study for the detection of malignant masses in screening mammograms was conducted in which six radiologists evaluated 20 mammograms while wearing an eye-tracking device. Eye-position data and diagnostic decisions were collected for each radiologist and case they reviewed. These cases were subsequently analyzed with an in-house knowledge-based CADe system using two different modes: Conventional mode with a globally fixed decision threshold and context-sensitive mode with a location-variable decision threshold based on the radiologists' eye dwelling data and reporting information. The CADe system operating in conventional mode had 85.7% per-image malignant mass sensitivity at 3.15 false positives per image (FPsI). The same system operating in context-sensitive mode provided personalized decision support at 85.7%-100% sensitivity and 0.35-0.40 FPsI to all six radiologists. Furthermore, context-sensitive CADe system could improve the radiologists' sensitivity and reduce their performance gap more effectively than conventional CADe. Context-sensitive CADe support shows promise in delineating and reducing the radiologists' perceptual and cognitive errors in the diagnostic interpretation of screening mammograms more effectively than conventional CADe.

Does image quality matter? Impact of resolution and noise on mammographic task performance

The purpose of this study was to examine the effects of different resolution and noise levels on task performance in digital mammography. This study created an image set with images at three different resolution levels, corresponding to three digital display devices, and three different noise levels, with noise magnitudes similar to full clinical dose, half clinical dose, and quarter clinical dose. The images were read by five experienced breast imaging radiologists. The data were then analyzed to compute two accuracy statistics (overall classification accuracy and lesion detection accuracy) and performance at four diagnostic tasks (detection of microcalcifications, benign masses, malignant masses, and discrimination of benign and malignant masses). Human observer results showed decreasing display resolution had little effect on overall classification accuracy and individual diagnostic task performance, but increasing noise caused overall classification accuracy to decrease by a statistically significant 21% as the breast dose went to one quarter of its normal clinical value. The noise effects were most prominent for the tasks of microcalcification detection and mass discrimination. When the noise changed from full clinical dose to quarter clinical dose, the microcalcification detection performance fell from 89% to 67% and the mass discrimination performance decreased from 93% to 79%, while malignant mass detection performance remained relatively constant with values of 88% and 84%, respectively. As a secondary aim, the image set was also analyzed by two observer models to examine whether their performance was similar to humans. Observer models differed from human observers and each other in their sensitivity to resolution degradation and noise. The primary conclusions of this study suggest that quantum noise appears to be the dominant image quality factor in digital mammography, affecting radiologist performance much more profoundly than display resolution.

A Concentric Morphology Model for the Detection of Masses in Mammography

We propose a technique for the automated detection of malignant masses in screening mammography. The technique is based on the presence of concentric layers surrounding a focal area with suspicious morphological characteristics and low relative incidence in the breast region. Mammographic locations with high concentration of concentric layers with progressively lower average intensity are considered suspicious deviations from normal parenchyma. The multiple concentric layers (MCLs) technique was trained and tested using the craniocaudal views of 270 mammographic cases with biopsy proven malignant masses from the digital database of screening mammography. One-half of the available cases were used for optimizing the parameters of the detection algorithm. The remaining cases were used for testing. During testing, malignant masses were detected with 92%, 88%, and 81% sensitivity at 5.4, 2.4, and 0.6 false positive marks per image. Testing on 82 normal screening mammograms showed a false positive rate of 5.0, 1.7, and 0.2 marks per image at the previously reported operating points. Furthermore, additional evaluation on 135 benign cases produced a significantly lower detection rate for benign masses (61.6%, 58.3%, and 43.7% at 5.1, 2.8, and 1.2 false positives per image, respectively). Overall, MCL is a promising computer-assisted detection strategy for screening mammograms to identify malignant masses while maintaining the detection rate of benign masses considerably lower.

Digital Mammography: Effects of Reduced Radiation Dose on Diagnostic Performance

To experimentally determine the relationship between radiation dose and observer accuracy in the detection and discrimination of simulated lesions for digital mammography. This HIPAA-compliant study received institutional review board approval; the informed consent requirement was waived. Three hundred normal craniocaudal images were selected from an existing database of digital mammograms. Simulated mammographic lesions that mimicked benign and malignant masses and clusters of microcalcifications (3.3-7.4 cm in diameter) were then superimposed on images. Images were rendered without and with added radiographic noise to simulate effects of reducing the radiation dose to one half and one quarter of the clinical dose. Images were read by five experienced breast imaging radiologists. Results were analyzed to determine effects of reduced dose on overall interpretation accuracy, detection of microcalcifications and masses, discrimination between benign and malignant masses, and interpretation time. Overall accuracy decreased from 0.83 with full dose to 0.78 and 0.62 with half and quarter doses, respectively. The decrease associated with transition from full dose to quarter dose was significant (P < .01), primarily because of an effect on detection of microcalcifications (P < .01) and discrimination of masses (P < .05). The level of dose reduction did not significantly affect detection of malignant masses (P > .5). However, reduced dose resulted in an increased mean interpretation time per image by 28% (P < .0001). These findings suggest that dose reduction in digital mammography has a measurable but modest effect on diagnostic accuracy. The small magnitude of the effect in response to the drastic reduction of dose suggests potential for modest dose reductions in digital mammography.

FDG small animal PET permits early detection of malignant cells in a xenograft murine model

The administration of new anticancer drugs in animal models is the first step from in vitro to in vivo pre-clinical protocols. At this stage it is crucial to ensure that cells are in the logarithmic phase of growth and to avoid vascular impairment, which can cause inhomogeneous distribution of the drug within the tumour and thus lead to bias in the final analysis of efficacy. In subcutaneous xenograft murine models, positivity for cancer is visually recognisable 2-3 weeks after inoculation, when a certain amount of necrosis is usually already present. The aim of this study was to evaluate the accuracy of FDG small animal PET for the early detection of malignant masses in a xenograft murine model of human rhabdomyosarcoma. A second goal was to analyse the metabolic behaviour of this xenograft tumour over time. We studied 23 nude mice, in which 7 x 10(6) rhabdomyosarcoma cells (RH-30 cell line) were injected in the dorsal subcutaneous tissues. Each animal underwent four FDG PET scans (GE, eXplore Vista DR) under gas anaesthesia. The animals were studied 2, 5, 14 and 20 days after inoculation. We administered 20 MBq of FDG via the tail vein. Uptake time was 60 min, and acquisition time, 20 min. Images were reconstructed with OSEM 2D iterative reconstruction and the target to background ratio (TBR) was calculated for each tumour. Normal subcutaneous tissue had a TBR of 0.3. Necrosis was diagnosed when one or more cold areas were present within the mass. All the animals were sacrificed and histology was available to verify PET results. PET results were concordant with the findings of necropsy and histology in all cases. The incidence of the tumour was 69.6% (16/23 animals); seven animals did not develop a malignant mass. Ten of the 23 animals had a positive PET scan 2 days after inoculation. Nine of these ten animals developed a tumour; the remaining animal became negative, at the third scan. The positive predictive value of the early PET scan was 90% (9/10 animals) while the negative predictive value was 46% (6/13 animals). In the whole group of animals, mean TBR increased scan by scan. There was a statistically significant difference in TBR between 2 and 20 days after inoculation. Necrosis was present at the second scan in two animals, at the third scan in six animals and at the fourth scan in 11 animals. The high positive predictive value of FDG PET 2 days after inoculation means that an animal with a first positive scan has a very high likelihood of developing a mass and can be treated at an early stage with an experimental drug. Animals negative at this point in time will never develop a mass or will eventually do so at a late phase. As 2 of the 16 (12.5%) positive animals had necrosis at the second scan, indicating a vascular mismatch, it may be argued that animals should be treated 2 days after inoculation to guarantee homogeneous vascularisation (thereby ensuring a good drug supply within the tumour) in all subjects.

Interval change analysis to improve computer aided detection in mammography

We are developing computer aided diagnosis (CAD) techniques to study interval changes between two consecutive mammographic screening rounds. We have previously developed methods for the detection of malignant masses based on features extracted from single mammographic views. The goal of the present work was to improve our detection method by including temporal information in the CAD program. Toward this goal, we have developed a regional registration technique. This technique links a suspicious location on the current mammogram with a corresponding location on the prior mammogram. The novelty of our method is that the search for correspondence is done in feature space. This has the advantage that very small lesions and architectural distortions may be found as well. Following the linking process several features are calculated for the current and prior region. Temporal features are obtained by combining the feature values from both regions. We evaluated the detection performance with and without the use of temporal features on a data set containing 2873 temporal film pairs from 938 patients. There were 589 cases in which the current mammogram contained exactly one malignant mass. Cross validation was used to partition the data set into a train set and a test set. The train set was used for feature selection and classifier training, the test set for classifier evaluation. FROC (free response operating characteristic) analysis showed an improvement in detection performance with the use of temporal features.

Improvement of computerized mass detection on mammograms: fusion of two-view information.

Recent clinical studies have proved that computer-aided diagnosis (CAD) systems are helpful for improving lesion detection by radiologists in mammography. However, these systems would be more useful if the false-positive rate is reduced. Current CAD systems generally detect and characterize suspicious abnormal structures in individual mammographic images. Clinical experiences by radiologists indicate that screening with two mammographic views improves the detection accuracy of abnormalities in the breast. It is expected that the fusion of information from different mammographic views will improve the performance of CAD systems. We are developing a two-view matching method that utilizes the geometric locations, and morphological and textural features to correlate objects detected in two different views using a prescreening program. First, a geometrical model is used to predict the search region for an object in a second view from its location in the first view. The distance between the object and the nipple is used to define the search area. After pairing the objects in two views, textural and morphological characteristics of the paired objects are merged and similarity measures are defined. Linear discriminant analysis is then employed to classify each object pair as a true or false mass pair. The resulting object correspondence score is combined with its one-view detection score using a fusion scheme. The fusion information was found to improve the lesion detectability and reduce the number of FPs. In a preliminary study, we used a data set of 169 pairs of cranio-caudal (CC) and mediolateral oblique (MLO) view mammograms. For the detection of malignant masses on current mammograms, the film-based detection sensitivity was found to improve from 62% with a one-view detection scheme to 73% with the new two-view scheme, at a false-positive rate of 1 FP/image. The corresponding cased-based detection sensitivity improved from 77% to 91%.

Computer-aided diagnosis: automatic detection of malignant masses in digitized mammograms.

A computerized method to automatically detect malignant masses on digital mammograms based on bilateral subtraction to identify asymmetries between left and right breast images was developed. After the digitization, in order to align left and right mammograms the breast border and nipple were automatically detected. Images were corrected to avoid differences in brightness due to the recording procedure. Left and right mammograms were subtracted and a threshold was applied to obtain a binary image with the information of suspicious areas. The suspicious regions or asymmetries were delimited by a region growing algorithm. Size and eccentricity tests were used to eliminate false-positive responses and texture features were extracted from suspicious regions to reject normal tissue regions. The scheme, tested in 70 pairs of digital mammograms, achieved a true-positive rate of 71% with an average number of 0.67 false positives per image. Computerized detection was evaluated by using free-response operating characteristic analysis (FROC). An area under the AFROC (A1) of 0.667 was obtained. Our results show that the scheme may be helpful to the radiologists by serving as a second reader in mammographic screening. The low number of false positives indicates that our scheme would not confuse the radiologist by suggesting normal regions as suspicious.

Computer‐aided diagnosis: Automatic detection of malignant masses on digital mammograms

A computerized method to automatically detect malignant masses on digital mammograms based on bilateral subtraction to identify asymmetries between left and right breast images was developed. After the digitization, the breast border and nipple are automatically detected in order to align left and right mammograms. Images are corrected to avoid differences in brightness due to the recording procedure. Left and right mammograms are subtracted, and a threshold is applied to obtain a binary image with the information of suspicious areas. The asymmetries are extracted by region growing. Size and eccentricity tests are used to eliminate false‐positive responses and texture features are extracted from suspicious regions to reject normal tissue regions. The scheme was tested in 70 pairs of digital mammograms and a true‐positive rate of 71% with an average number of 0.67 false‐positives per image was achieved. Computerized detection was evaluated by free‐response operating characteristic analysis (FROC). An area under the AFROC (A1) of 0.667 was obtained. Our results show that the scheme could help radiologists as a second reader in mammographic screening. The low number of false‐positives indicates that our scheme would not add confusion to radiologists, detecting normal regions as suspicious.