An Investigation into the Consistency in Mammographic Density Identification by Radiologists: Effect of Radiologist Expertise and Mammographic Appearance

The aim of this work is to investigate how radiologist expertise and image appearance may have an impact on inter-reader variability of mammographic density (MD) identification. Seventeen radiologists, divided into three expertise groups, were asked to manually segment the areas they consider to be MD in 40 clinical images. The variation in identification of MD for each image was quantified by finding the range of segmentation areas. The impact of radiologist expertise and image appearance on this variation was explored. The range of areas chosen by participating radiologists varied from 7 to 73 % across the 40 images, with a mean range of 35 ± 13 %. Participants with high expertise were more likely to choose similar areas to one another, compared to participants with medium and low expertise levels (mean range were 19 ± 10 %, 29 ± 13 % and 25 ± 14 %, respectively, p < 0.0001). There was a significantly higher average grey level for the area segmented by all radiologists as MD compared to the area of variation, with mean grey level value for 8-bit images being 146 ± 19 vs. 99 ± 14, respectively. MD segmentation borders were consistent in areas where there was a sharp intensity change within a short distance. In conclusion, radiologists with high expertise tend to have a higher agreement when identifying MD. Tissues which have a lower contrast and a less visually sharp gradient change at the interface between high density tissue and adipose background lead to inter-reader variation in choosing mammographic density.     

Comparing Performance of the CADstream and the DynaCAD Breast MRI CAD Systems

Computer-aided diagnosis (CAD) systems are software programs that use algorithms to find patterns associated with breast cancer on breast magnetic resonance imaging (MRI). The most commonly used CAD systems in the USA are CADstream (CS) (Merge Healthcare Inc., Chicago, IL) and DynaCAD for Breast (DC) (Invivo, Gainesville, FL). Our primary objective in this study was to compare the CS and DC breast MRI CAD systems for diagnostic accuracy and postprocessed image quality. Our secondary objective was to compare the evaluation times of radiologists using each system. Three radiologists evaluated 30 biopsy-proven malignant lesions and 29 benign lesions on CS and DC and rated the lesions’ malignancy status using the Breast Imaging Reporting and Data System. Image quality was ranked on a 0–5 scale, and mean reading times were also recorded. CS detected 70 % of the malignant and 32 % of the benign lesions while DC detected 81 % of the malignant lesions and 34 % of the benign lesions. Analysis of the area under the receiver operating characteristic curve revealed that the difference in diagnostic performance was not statistically significant. On image quality scores, CS had significantly higher volume rendering (VR) (p < 0.0001) and motion correction (MC) scores (p < 0.0001). There were no statistically significant differences in the remaining image quality scores. Differences in evaluation times between DC and CS were also not statistically significant. We conclude that both CS and DC perform similarly in aiding detection of breast cancer on MRI. MRI CAD selection will likely be based on other factors, such as user interface and image quality preferences, including MC and VR.     

An Interactive System for Computer-Aided Diagnosis of Breast Masses

Although mammography is the only clinically accepted imaging modality for screening the general population to detect breast cancer, interpreting mammograms is difficult with lower sensitivity and specificity. To provide radiologists “a visual aid” in interpreting mammograms, we developed and tested an interactive system for computer-aided detection and diagnosis (CAD) of mass-like cancers. Using this system, an observer can view CAD-cued mass regions depicted on one image and then query any suspicious regions (either cued or not cued by CAD). CAD scheme automatically segments the suspicious region or accepts manually defined region and computes a set of image features. Using content-based image retrieval (CBIR) algorithm, CAD searches for a set of reference images depicting “abnormalities” similar to the queried region. Based on image retrieval results and a decision algorithm, a classification score is assigned to the queried region. In this study, a reference database with 1,800 malignant mass regions and 1,800 benign and CAD-generated false-positive regions was used. A modified CBIR algorithm with a new function of stretching the attributes in the multi-dimensional space and decision scheme was optimized using a genetic algorithm. Using a leave-one-out testing method to classify suspicious mass regions, we compared the classification performance using two CBIR algorithms with either equally weighted or optimally stretched attributes. Using the modified CBIR algorithm, the area under receiver operating characteristic curve was significantly increased from 0.865 ± 0.006 to 0.897 ± 0.005 (p < 0.001). This study demonstrated the feasibility of developing an interactive CAD system with a large reference database and achieving improved performance.     

Effect of Dose Reduction on the Ability of Digital Mammography to Detect Simulated Microcalcifications

The purpose of this article was to report the relationship between radiation dose and the ability of sentence digital mammography to detect microcalcifications. All images were acquired by computed radiography and an anthropomorphic breast phantom. The tube voltage and anode/filter combination used were 28 kVp and Mo/Mo. Simulated microcalcifications with an approximate diameter of 250–350 μm were positioned on the phantom. Groups of six microcalcifications were arranged in one of two patterns, a line cluster 1 cm long or a hexagonal cluster 4 mm wide. One of the six microcalcifications was removed to create a negative control. Each cluster was placed on 25 different points. Four levels of milliampere-second (mAs) values were applied: 100%, 50%, 25%, and 12.5%. Five staff radiologists participated in an observer performance test. All observers used a workstation with a 3-megapixel monochrome LCD monitor. The areas under the receiver-operating characteristics curves (AUC) were used to compare diagnostic performance among the four doses. The overall AUC scores were 0.97 with 100% mAs, 0.93 (n.s.) with 50%, 0.90 (p < 0.05) with 25%, and 0.81 (p < 0.01) with 12.5% mAs. Among the negative series, the percentage of images on which observers were able to identify the removed microcalcification point decreased from 88.8% with 100% mAs to 83.6% (n.s.) with 50%, 74.8% (p < 0.001) with 25%, and 67.2% (p < 0.001) with 12.5% mAs. A certain level of dose reduction in digital mammography may be an option.Key words: Digital mammography, computed radiography, observer performance, radiation dose, ROC-based analysis, phantoms, imaging     

Impact of a Computer-Aided Detection (CAD) System Integrated into a Picture Archiving and Communication System (PACS) on Reader Sensitivity and Efficiency for the Detection of Lung Nodules in Thoracic CT Exams

The objective of this study is to assess the impact on nodule detection and efficiency using a computer-aided detection (CAD) device seamlessly integrated into a commercially available picture archiving and communication system (PACS). Forty-eight consecutive low-dose thoracic computed tomography studies were retrospectively included from an ongoing multi-institutional screening study. CAD results were sent to PACS as a separate image series for each study. Five fellowship-trained thoracic radiologists interpreted each case first on contiguous 5 mm sections, then evaluated the CAD output series (with CAD marks on corresponding axial sections). The standard of reference was based on three-reader agreement with expert adjudication. The time to interpret CAD marking was automatically recorded. A total of 134 true-positive nodules, measuring 3 mm and larger were included in our study; with 85 ≥ 4 and 50 ≥ 5 mm in size. Readers detection improved significantly in each size category when using CAD, respectively, from 44 to 57 % for ≥3 mm, 48 to 61 % for ≥4 mm, and 44 to 60 % for ≥5 mm. CAD stand-alone sensitivity was 65, 68, and 66 % for nodules ≥3, ≥4, and ≥5 mm, respectively, with CAD significantly increasing the false positives for two readers only. The average time to interpret and annotate a CAD mark was 15.1 s, after localizing it in the original image series. The integration of CAD into PACS increases reader sensitivity with minimal impact on interpretation time and supports such implementation into daily clinical practice.     

The Enhanced Workflow and Efficiency of the Wireless Local Area Network (WLAN)-Based Direct Digital Radiography (DDR) Portable Radiography

With the implementation of the PACS in the hospital, there is an increasing demand from the clinicians for immediate access and display of radiological images. Recently, our hospital has installed the first wireless local area network (WLAN)-based direct digital radiography (DDR) portable radiography system. The DDR portable radiography system allows wireless retrieval of modality worklist and wireless transmission of portable X-ray image on the console to the Picture Archiving and Communication System (PACS), via WLAN connection of wireless fidelity (Wi-Fi). The aim of this study was to analyze the workflow and performance between the WLAN-based DDR portable radiography system and the old practice using conventional portable X-ray machine with computed radiography (CR) system. A total of 190 portable chest X-ray examinations were evaluated and timed, using the conventional portable X-ray machine with CR from March to April of 2012 and using the new DDR portable radiography system on December of 2012 (n = 97 for old system and n = 93 for DDR portable system). The time interval of image becoming available to the PACS using the WLAN-based DDR portable radiography system was significantly shorter than that of the old practice using the conventional portable X-ray machine with CR (6.8 ± 2.6 min for DDR portable system; 23 ± 10.2 min for old system; p < 0.0001), with the efficiency improved by 70 %. The implementation of the WLAN-based DDR portable radiography system can enhance the workflow of portable radiography by reduction of procedural steps.     

Mammographic Artifacts on Full-Field Digital Mammography

This study investigates the incidence of full-field digital mammographic (FFDM) artifacts with three systems at two institutions and compares the artifacts between two detector types and two grid types. A total of 4,440 direct and 4,142 indirect FFDM images were reviewed by two radiologists, and artifacts were classified as patient related, hardware related, and software processing. The overall incidence of FFDM artifacts was 3.4 % (292/8,582). Patient related artifacts (motion artifacts and skin line artifacts) were the most commonly detected types (1.7 %). Underexposure among hardware related artifacts and high-density artifacts among software processing artifacts also were common (0.7 and 0.5 %, respectively). These artifacts, specific to digital mammography, were more common with the direct detector type and the crossed air grid type than with the indirect type and linear grid type (p < 0.05). The most common mammographic artifacts on FFDM were patient related, which might be controlled by the instruction of a patient and technologist. Underexposure and high-density artifacts were more common with direct detector and crossed air type of grid.     

Observer Performance Using Virtual Pathology Slides: Impact of LCD Color Reproduction Accuracy

The use of color LCDs in medical imaging is growing as more clinical specialties use digital images as a resource in diagnosis and treatment decisions. Telemedicine applications such as telepathology, teledermatology, and teleophthalmology rely heavily on color images. However, standard methods for calibrating, characterizing, and profiling color displays do not exist, resulting in inconsistent presentation. To address this, we developed a calibration, characterization, and profiling protocol for color-critical medical imaging applications. Physical characterization of displays calibrated with and without the protocol revealed high color reproduction accuracy with the protocol. The present study assessed the impact of this protocol on observer performance. A set of 250 breast biopsy virtual slide regions of interest (half malignant, half benign) were shown to six pathologists, once using the calibration protocol and once using the same display in its “native” off-the-shelf uncalibrated state. Diagnostic accuracy and time to render a decision were measured. In terms of ROC performance, Az (area under the curve) calibrated = 0.8570 and Az uncalibrated = 0.8488. No statistically significant difference (p = 0.4112) was observed. In terms of interpretation speed, mean calibrated = 4.895 s; mean uncalibrated = 6.304 s which is statistically significant (p = 0.0460). Early results suggest a slight advantage diagnostically for a properly calibrated and color-managed display and a significant potential advantage in terms of improved workflow. Future work should be conducted using different types of color images that may be more dependent on accurate color rendering and a wider range of LCDs with varying characteristics.     

Automated 3D Ιnterstitial Lung Disease Εxtent Quantification: Performance Evaluation and Correlation to PFTs

In this study, the performance of a recently proposed computer-aided diagnosis (CAD) scheme in detection and 3D quantification of reticular and ground glass pattern extent in chest computed tomography of interstitial lung disease (ILD) patients is evaluated. CAD scheme performance was evaluated on a dataset of 37 volumetric chest scans, considering five representative axial anatomical levels per scan. CAD scheme reliability analysis was performed by estimating agreement (intraclass correlation coefficient, ICC) of automatically derived ILD pattern extent to semi-quantitative disease extent assessment in terms of 29-point rating scale provided by two expert radiologists. Receiver operating characteristic (ROC) analysis was employed to assess CAD scheme accuracy in ILD pattern detection in terms of area under ROC curve (A_z). Correlation of reticular and ground glass volumetric pattern extent to pulmonary function tests (PFTs) was also investigated. CAD scheme reliability was substantial for ILD extent (ICC = 0.809) and distinct reticular pattern extent (0.806) and moderate for distinct ground glass pattern extent (0.543), performing within inter-observer agreement. CAD scheme demonstrated high accuracy in detecting total ILD (A_z = 0.950 ± 0.018), while accuracy in detecting distinct reticular and ground glass patterns was 0.920 ± 0.023 and 0.883 ± 0.024, respectively. Moderate and statistically significant negative correlation was found between reticular volumetric pattern extent and diffusing capacity, forced expiratory volume in 1 s, forced vital capacity, and total lung capacity (R = −0.581, −0.513, −0.494, and −0.446, respectively), similar to correlations found between radiologists’ semi-quantitative ratings with PFTs. CAD-based quantification of disease extent is in agreement with radiologists’ semi-quantitative assessment and correlates to specific PFTs, suggesting a potential imaging biomarker for ILD staging and management.     

iPad-Based Patient Briefing for Radiological Examinations—a Clinical Trial

To analyze if an iPad-based patient briefing can serve as a digital alternative to conventional documentations prior to radiological examinations. One hundred one patients referred for routine MRI were randomized into two groups, who underwent iPad-based and classic written briefing in opposite order. For each briefing completion time, completeness and correctness were noted. Patient’s knowledge about the content of either briefing modality was subsequently tested. The influence of patient-related factors on the performance of the electronic briefing (EB) was analyzed. Finally, the patient’s subjective impression of the EB was assessed. The mean durations were 4.4 ± 2.2 min for EB and 1.7 ± 1.3 min for the classic briefing (p < 0.01). All iPad briefings were returned entirely filled out, whereas 11 % of the classic forms were returned with missing data. No significant differences in memorization of the briefing’s information were objectified. There was a positive correlation between the duration of EB and age (r = 0.53; p < 0.01), whereas a negative correlation was found between computer skills and patient’s age (r = −0.55; p < 0.01) or duration of EB (r = −0.62; p < 0.01). More than half of the study patients would prefer EB in the future; another 29 % had no preference at all. Patient briefing on iPads transfers the information for the patients equally well compared to the classic written approach. Although iPad briefing took patients longer to perform, the majority would prefer it to written consent briefings in the future. Nevertheless, measures have to be undertaken to improve the overall acceptance and performance.     

The Effect of Slice Thickness on the Assessment of Bone Defect Volumes by the Cavalieri Principle Using Cone Beam Computed Tomography

The purpose of this study was to investigate the possible effects of section thickness on volume estimations obtained by cone beam computed tomography. Intraosseal cavities representing bone defects on vestibular sides of the two dry sheep mandibles were scanned by a cone beam computed tomography system. Consecutive sections at 0.2, 0.6, 1, 1.4, and 2.2 mm thickness were used to estimate the volumes of the cavities using the Cavalieri principle of stereological methods. Estimated volumes are then compared with the volumes obtained by the Archimedean principle. In 0.2-, 0.6-, and 1-mm-thick slices, the volumes estimated by the Cavalieri principle did not differ from the volumes by the Archimedean principle (p > 0.05). The 0.2 mm slice-thickness group had the highest asymptotic significance value (p = 0.6). Although the thinnest slice appears to provide the most accurate values, slice thickness up to 1 mm can be chosen for volume calculations on CBCT images.     

Sigma Level Performance of the Innovated Process in the Imaging Department at a Mexican Health Institute

The National Institute of Respiratory Diseases is a third level public hospital in Mexico City, which in 2007 acquired an RIS-PACS to be implemented at its Imaging Department (ID), with the objective to enhance its service. This department attends an average of 3,500 patients per month developing different image modalities. The objective of this work was to determine the overall sigma level performance of four processes of the ID: reception, X-ray, computed tomography, and radiologist diagnosis, considering process analysis and innovation through Six Sigma methodology, measuring the innovation effectiveness by means of indicators and learning curves. Initially, a first measurement (M₁) of the original processes was determined; once 13 innovations were implemented in a pilot program, two more measurements were done, 15 days after (M₂) and 30 days after (M₃), in order to know the impact of the innovations in the ID processes. The initial sigma level of the ID before innovations was σ₁ = 2.0, which means that there were 36 patients per day with a process defect during their stay at the ID. In the two following measurements, σ₂ = 2.2 which means that there were 28 patients per day with a process defect, and σ₃ = 2.3 with 24 patients per day with a process defect. These results demonstrate that the percentage of performance enhancement between the original process and 15 days later was 23 % and 30 days later an enhancement of 15 %. In total, an overall enhancement of 38 % was obtained at the ID of the institute.     

Breast Density Analysis Using an Automatic Density Segmentation Algorithm

Breast density is a strong risk factor for breast cancer. In this paper, we present an automated approach for breast density segmentation in mammographic images based on a supervised pixel-based classification and using textural and morphological features. The objective of the paper is not only to show the feasibility of an automatic algorithm for breast density segmentation but also to prove its potential application to the study of breast density evolution in longitudinal studies. The database used here contains three complete screening examinations, acquired 2 years apart, of 130 different patients. The approach was validated by comparing manual expert annotations with automatically obtained estimations. Transversal analysis of the breast density analysis of craniocaudal (CC) and mediolateral oblique (MLO) views of both breasts acquired in the same study showed a correlation coefficient of ρ = 0.96 between the mammographic density percentage for left and right breasts, whereas a comparison of both mammographic views showed a correlation of ρ = 0.95. A longitudinal study of breast density confirmed the trend that dense tissue percentage decreases over time, although we noticed that the decrease in the ratio depends on the initial amount of breast density.     

Retrospective Review of the Drop in Observer Detection Performance Over Time in Lesion-enriched Experimental Studies

The vigilance decrement describes a decrease in sensitivity or increase in specificity with time on task. It has been observed in a variety of repetitive visual tasks, but little is known about these patterns in radiologists. We investigated whether there is systematic variation in performance over the course of a radiology reading session. We re-analyzed data from six previous lesion-enriched radiology studies. Studies featured 8–22 participants assessing 27–100 cases (including mammograms, chest CT, chest x-ray, and bone x-ray) in a reading session. Changes in performance and speed as the reading session progressed were analyzed using mixed effects models. Time taken per case decreased 9–23 % as the reading session progressed (p < 0.005 for every study). There was a sensitivity decrease or specificity increase over the course of reading 100 chest x-rays (p = 0.005), 60 bone fracture x-rays (p = 0.03), and 100 chest CT scans (p < 0.0001). This effect was not found in the shorter mammography sessions with 27 or 50 cases. We found evidence supporting the hypothesis that behavior and performance may change over the course of reading an enriched test set. Further research is required to ascertain whether this effect is present in radiological practice.     

Extracting Fuzzy Classification Rules from Texture Segmented HRCT Lung Images

Automatic tools for detection and identification of lung and lesion from high-resolution CT (HRCT) are becoming increasingly important both for diagnosis and for delivering high-precision radiation therapy. However, development of robust and interpretable classifiers still presents a challenge especially in case of non-small cell lung carcinoma (NSCLC) patients. In this paper, we have attempted to devise such a classifier by extracting fuzzy rules from texture segmented regions from HRCT images of NSCLC patients. A fuzzy inference system (FIS) has been constructed starting from a feature extraction procedure applied on overlapping regions from the same organs and deriving simple if–then rules so that more linguistically interpretable decisions can be implemented. The proposed method has been tested on 138 regions extracted from CT scan images acquired from patients with lung cancer. Assuming two classes of tissues C1 (healthy tissues) and C2 (lesion) as negative and positive, respectively; preliminary results report an AUC = 0.98 for lesions and AUC = 0.93 for healthy tissue, with an optimal operating condition related to sensitivity = 0.96, and specificity = 0.98 for lesions and sensitivity 0.99, and specificity = 0.94 for healthy tissue. Finally, the following results have been obtained: false-negative rate (FNR) = 6 % (C1), FNR = 2 % (C2), false-positive rate (FPR) = 4 % (C1), FPR = 3 % (C2), true-positive rate (TPR) = 94 %, (C1) and TPR = 98 % (C2).     

Creation and Implementation of Department-Wide Structured Reports: An Analysis of the Impact on Error Rate in Radiology Reports

The purpose of this study was to evaluate and compare textual error rates and subtypes in radiology reports before and after implementation of department-wide structured reports. Randomly selected radiology reports that were generated following the implementation of department-wide structured reports were evaluated for textual errors by two radiologists. For each report, the text was compared to the corresponding audio file. Errors in each report were tabulated and classified. Error rates were compared to results from a prior study performed prior to implementation of structured reports. Calculated error rates included the average number of errors per report, average number of nongrammatical errors per report, the percentage of reports with an error, and the percentage of reports with a nongrammatical error. Identical versions of voice-recognition software were used for both studies. A total of 644 radiology reports were randomly evaluated as part of this study. There was a statistically significant reduction in the percentage of reports with nongrammatical errors (33 to 26 %; p = 0.024). The likelihood of at least one missense omission error (omission errors that changed the meaning of a phrase or sentence) occurring in a report was significantly reduced from 3.5 to 1.2 % (p = 0.0175). A statistically significant reduction in the likelihood of at least one comission error (retained statements from a standardized report that contradict the dictated findings or impression) occurring in a report was also observed (3.9 to 0.8 %; p = 0.0007). Carefully constructed structured reports can help to reduce certain error types in radiology reports.     

Breast Ultrasound Image Classification Based on Multiple-Instance Learning

Breast ultrasound (BUS) image segmentation is a very difficult task due to poor image quality and speckle noise. In this paper, local features extracted from roughly segmented regions of interest (ROIs) are used to describe breast tumors. The roughly segmented ROI is viewed as a bag. And subregions of the ROI are considered as the instances of the bag. Multiple-instance learning (MIL) method is more suitable for classifying breast tumors using BUS images. However, due to the complexity of BUS images, traditional MIL method is not applicable. In this paper, a novel MIL method is proposed for solving such task. First, a self-organizing map is used to map the instance space to the concept space. Then, we use the distribution of the instances of each bag in the concept space to construct the bag feature vector. Finally, a support vector machine is employed for classifying the tumors. The experimental results show that the proposed method can achieve better performance: the accuracy is 0.9107 and the area under receiver operator characteristic curve is 0.96 (p < 0.005).     

Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts

Dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) of breasts is an important imaging modality in breast cancer diagnosis with higher sensitivity but relatively lower specificity. The objective of this study is to investigate a new approach to help improve diagnostic performance of DCE-MRI examinations based on the automated detection and analysis of bilateral asymmetry of characteristic kinetic features between the left and right breast. An image dataset involving 130 DCE-MRI examinations was assembled and used in which 80 were biopsy-proved malignant and 50 were benign. A computer-aided diagnosis (CAD) scheme was developed to segment breast areas depicted on each MR image, register images acquired from the sequential MR image scan series, compute average contrast enhancement of all pixels in one breast, and a set of kinetic features related to the difference of contrast enhancement between the left and right breast, and then use a multi-feature based Bayesian belief network to classify between malignant and benign cases. A leave-one-case-out validation method was applied to test CAD performance. The computed area under a receiver operating characteristic (ROC) curve is 0.78 ± 0.04. The positive and negative predictive values are 0.77 and 0.64, respectively. The study indicates that bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy. It also demonstrates the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations based on this new image biomarker.     

A Comparison of Computer-Aided Detection (CAD) Effectiveness in Pulmonary Nodule Identification Using Different Methods of Bone Suppression in Chest Radiographs

This study aimed to compare the diagnostic effectiveness of computer-aided detection (CAD) software (OnGuard™ 5.2) in combination with hardware-based bone suppression (dual-energy subtraction radiography (DESR)), software-based bone suppression (SoftView™, version 2.4), and standard posteroanterior images with no bone suppression. A retrospective pilot study compared the diagnostic performance of two commercially available methods of bone suppression when used with commercially available CAD software. Chest images from 27 patients with computed tomography (CT) and pathology-proven malignant pulmonary nodules (8–34 mm) and 25 CT-negative patient controls were used for analysis. The Friedman, McNemar, and chi-square tests were used to compare diagnostic performance and the kappa statistic was used to evaluate method agreement. The average number of regions of interest and false-positives per image identified by CAD were not found to be significantly different regardless of the bone suppression methods evaluated. Similarly, the sensitivity, specificity, and test efficiency were not found to be significantly different. Agreement between the methods was between poor and excellent. The accuracy of CAD (OnGuard™, version 5.2) is not statistically different with either DESR or SoftView™ (version 2.4) bone suppression technology in digital chest images for pulmonary nodule identification. Low values for sensitivity (<80 %) and specificity (<50 %) may limit their utility for clinical radiology.     

Enhanced CT Images by the Wavelet Transform Improving Diagnostic Accuracy of Chest Nodules

The objective of this study was to compare the diagnostic accuracy in the interpretation of chest nodules using original CT images versus enhanced CT images based on the wavelet transform. The CT images of 118 patients with cancers and 60 with benign nodules were used in this study. All images were enhanced through an algorithm based on the wavelet transform. Two experienced radiologists interpreted all the images in two reading sessions. The reading sessions were separated by a minimum of 1 month in order to minimize the effect of observer’s recall. The Mann–Whitney U nonparametric test was used to analyze the interpretation results between original and enhanced images. The Kruskal–Wallis H nonparametric test of K independent samples was used to investigate the related factors which could affect the diagnostic accuracy of observers. The area under the ROC curves for the original and enhanced images was 0.681 and 0.736, respectively. There is significant difference in diagnosing the malignant nodules between the original and enhanced images (z = 7.122, P < 0.001), whereas there is no significant difference in diagnosing the benign nodules (z = 0.894, P = 0.371). The results showed that there is significant difference between original and enhancement images when the size of nodules was larger than 2 cm (Z = −2.509, P = 0.012, indicating the size of the nodules is a critical evaluating factor of the diagnostic accuracy of observers). This study indicated that the image enhancement based on wavelet transform could improve the diagnostic accuracy of radiologists for the malignant chest nodules.Key words: Wavelet transform, chest nodules, enhanced CT