Evaluation of a wavelet-based computer-assisted detection system for identifying microcalcifications in digital full-field mammography

PURPOSE: To evaluate a new wavelet-based computer-assisted detection (CAD) system for detecting and enhancing microcalcifications. MATERIAL AND METHODS: A total of 280 mammograms acquired by full-field digital mammography (Senographe 2000D; G.E. Medical Systems Milwaukee, Wisc., USA) were analyzed with and without a new wavelet-based CAD system for detecting and enhancing microcalcifications. The mammograms comprised roughly equal numbers of cases from each of the BIRADS (Breast Imaging, Reporting and Data System, according to the American College of Roentgenology) categories 1-5. Histologic confirmation was available for all of the 180 cases assigned BIRADS categories 3-5. Four readers interpreted all 280 images for suspicious microcalcifications using a scale of 1-5. The readers alternately assessed 5 images with and 5 without CAD. In a second reading immediately following the first, the readers had to reassess the 280 mammograms. The images that had already been interpreted without CAD were now presented with CAD and vice versa. The images were interpreted as soft copies on a diagnostic mammography workstation (Image Diagnost GmbH, Neufahrn/Munich, Germany). All images interpreted with CAD were presented with enhancement of microcalcifications by wavelet algorithms and prompting of microcalcifications. ROC (receiver operating characteristic) analyses were performed, and image interpretation time with and without CAD was measured. RESULTS: The overall time for interpretation required by all 4 readers together was 483 min with CAD compared to 580 min without CAD. ROC analysis revealed no significant advantage of CAD for the individual readers. Readers 3 (0.811/0.817) and 4 (0.799/0.843) had a slightly improved AUC (area under the curve) with CAD. Readers 1 and 2 had a slightly lower AUC with CAD (0.832 versus 0.861 and 0.818 versus 0.849). CONCLUSION: The CAD system significantly (P<0.05, t test) speeded up image interpretation with respect to the identification of microcalcifications, while the diagnostic quality remained almost identical under the study conditions.     

Reproducibility of Computer-Aided Detection Marks in Digital Mammography

Objective

To evaluate the performance and reproducibility of a computer-aided detection (CAD) system in mediolateral oblique (MLO) digital mammograms taken serially, without release of breast compression.

Materials and Methods

A CAD system was applied preoperatively to the full-field digital mammograms of two MLO views taken without release of breast compression in 82 patients (age range: 33 - 83 years; mean age: 49 years) with previously diagnosed breast cancers. The total number of visible lesion components in 82 patients was 101: 66 masses and 35 microcalcifications. We analyzed the sensitivity and reproducibility of the CAD marks.

Results

The sensitivity of the CAD system for first MLO views was 71% (47/66) for masses and 80% (28/35) for microcalcifications. The sensitivity of the CAD system for second MLO views was 68% (45/66) for masses and 17% (6/35) for microcalcifications. In 84 ipsilateral serial MLO image sets (two patients had bilateral cancers), identical images, regardless of the existence of CAD marks, were obtained for 35% (29/84) and identical images with CAD marks were obtained for 29% (23/78). Identical images, regardless of the existence of CAD marks, for contralateral MLO images were 65% (52/80) and identical images with CAD marks were obtained for 28% (11/39). The reproducibility of CAD marks for the true positive masses in serial MLO views was 84% (42/50) and that for the true positive microcalcifications was 0% (0/34).

Conclusion

The CAD system in digital mammograms showed a high sensitivity for detecting masses and microcalcifications. However, reproducibility of microcalcification marks was very low in MLO views taken serially without release of breast compression. Minute positional change and patient movement can alter the images and result in a significant effect on the algorithm utilized by the CAD for detecting microcalcifications.     

Detection of masses and calcifications by soft-copy reading: comparison of two postprocessing algorithms for full-field digital mammography

Purpose  The purpose of this study was to determine the effects of a commercially available postprocessing algorithm on the detection of masses and microcalcifications of breast cancer by soft-copy reading. Materials and methods  The study included 64 digital mammograms with 16 histologically proven abnormal findings (eight masses and eight microcalcifications) and 48 normal breasts. Two image-processing algorithms were applied to the digital images, which were acquired using General Electric units. The commercially available advanced and standard postprocessed digital mammograms were evaluated in a localization receiver operating characteristic (ROC) curve experiment involving seven mammography radiographers. Results  The mean area under the ROC curve was 0.921 ± 0.022 for the commercially available advanced postprocessed digital mammograms session and 0.904 ± 0.026 for the standard postprocessed digital mammograms session (P = 0.1953). Observer agreement among the readers was better for the advanced postprocessed digital mammograms than for the standard postprocessed digital mammograms. Conclusion  During soft-copy reading, the interpretation accuracy might be influenced by the postprocessing algorithm.     

The performance of computer-aided detection when analyzing prior mammograms of newly detected breast cancers with special focus on the time interval from initial imaging to detection

Purpose

The clinical role of CAD systems to detect breast cancer, which have not been on cancer containing mammograms not detected by the radiologist was proven retrospectively.

Methods

All patients from 1992 to 2005 with a histologically verified malignant breast lesion and a mammogram at our department, were analyzed in retrospect focussing on the time of detection of the malignant lesion. All prior mammograms were analyzed by CAD (CADx, USA). The resulting CAD printout was matched with the cancer containing images yielding to the radiological diagnosis of breast cancer. CAD performance, sensitivity as well as the association of CAD and radiological features were analyzed.

Results

278 mammograms fulfilled the inclusion criteria. 111 cases showed a retrospectively visible lesion (71 masses, 23 single microcalcification clusters, 16 masses with microcalcifications, in one case two microcalcification clusters). 54/87 masses and 34/41 microcalcifications were detected by CAD.Detection rates varied from 9/20 (ACR 1) to 5/7 (ACR 4) (45% vs. 71%). The detection of microcalcifications was not influenced by breast tissue density.

Conclusion

CAD might be useful in an earlier detection of subtle breast cancer cases, which might remain otherwise undetected.     

Tumour detection rate of a new commercially available computer-aided detection system

The aim of this study was to determine the tumour detection rate and false positive rate of a new mammographic computer-aided detection system (CAD) in order to assess its clinical usefulness. The craniocaudal and oblique images of 150 suspicious mammograms from 150 patients that were histologically proven to be malignant were analysed using the Second Look CAD (CADx Medical Systems, Quebec, Canada). Cases were selected randomly using the clinic's internal tumour case sampler. Correct marking of the malignant lesion in at least one view was scored as a true positive. Marks not at the location of the malignant lesion were scored as false positives. In addition, mammograms with histologically proven benign masses ( n=50) and microcalcifications ( n=50), as well as 100 non-suspicious mammograms, were scanned in order to determine the value of false-positive marks per image. The 150 mammograms included 94 lesions that were suspicious due to masses, 26 due to microcalcifications and 30 showed both signs of malignancy. The overall sensitivity was 90.0% (135 of 150). Sensitivity on subsets of the data was 88.7% (110 of 124) for suspicious masses (MA) and 98.2% (55 of 56) for microcalcifications. Eight of 14 false-negative cases were large lesions. The overall false-positive rate was observed as 0.28 and 0.97 marks per image of microcalcifications and masses, respectively. The lowest false-positive rates for microcalcifications and MA were observed in the cancer subgroup, whereas the highest false-positive rates were scored in the benign but mammographically suspicious subgroups, respectively. The new CAD system shows a high tumour detection rate, with approximately 1.3 false positive marks per image. These results suggest that this system might be clinically useful as a second reader of mammograms. The system performance was particularly useful for detecting microcalcifications.     

Computer-aided detection in mammography: an assessment of performance on current and prior images

RATIONALE AND OBJECTIVES: The authors assessed and compared the performance of a computer-aided detection (CAD) scheme for the detection of masses and microcalcification clusters on a set of images collected from two consecutive ("current" and "prior") mammographic examinations. MATERIALS AND METHODS: A previously developed CAD scheme was used to assess two consecutive screening mammograms from 200 cases in which the current mammogram showed a mass or cluster of microcalcifications that resulted in breast biopsy. The latest prior examinations had been initially interpreted as negative or definitely benign findings (Breast Imaging Reporting and Data System rating, 1 or 2). The study involved images of 400 examinations acquired in 200 patients. Radiologists identified 172 masses and 128 clusters of microcalcifications on the current images. The performance of the CAD scheme was analyzed and compared for the current and latest prior images. RESULTS: There were significant differences (P < .01) between current and prior images in many feature values. The performance of the CAD scheme was significantly lower for prior than for current images (P < .01). At 0.5 and 0.2 false-positive mass and cluster cues per image, the scheme detected 78 malignant masses (78%) and 63 malignant clusters (80%) on current images. Only 42% of malignant cases were detected on prior images, including 40 masses (40%) and 36 microcalcification clusters (46%). CONCLUSION: CAD schemes can detect a substantial fraction of masses and microcalcification clusters depicted on prior images. To improve performance with prior images, the scheme may have to be adaptively reoptimized with increasingly more subtle abnormalities.     

Malignant lesions on mammography: accuracy of two different computer-aided detection systems

We retrospectively compared the accuracy of two computer-aided detection (CAD) systems for the detection of malignant breast lesions on full-field digital mammograms. Mammograms of 326 patients were analyzed (117 patients with breast cancer, 209 negative cases), and each set of cases was read by two CAD systems (Second Look versus AccuDetect Galileo). True-positive fractions per image and case for soft densities, microcalcifications, and total cancers were assessed. Study results showed better overall performance of AccuDetect Galileo (when compared to Second Look) in detecting masses, microcalcifications, and all cancer types, especially in extremely dense breast parenchyma.     

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

Objectives

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.

Methods

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.

Results

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.

Conclusions

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.

Key points

? Computer-aided detection (CAD) systems are used to detect malignant masses in mammograms ? Current CAD systems operate at low specificity to avoid perceptual oversight ? A CAD system has been developed that operates at high specificity ? The performance of the CAD system is approaching that of trained radiologists ? CAD has the potential to be an independent reader in screening     

Computer-aided diagnosis in full digital mammography

RATIONALE AND OBJECTIVES: The authors clarify the detection rates for breast cancerous tumors and clustered microcalcifications with computer-aided diagnosis (CAD) based on Fuji Computed Radiography. The authors also determine whether mammographic reading with CAD contributes to the discovery of breast cancer. METHODS: Data acquired by Fuji Computed Radiography 9000, which consisted of 4148 digital mammograms including 267 cases of breast cancer, was transferred directly to an analysis workstation where an original software program determined extraction rates for breast tumors and clustered microcalcifications. Furthermore, using another 344 mammograms from 86 women, observer performance studies were conducted on five doctors for receiver operating characteristic (ROC) analysis. RESULTS: Sensitivity to breast cancerous tumors and clustered microcalcifications were 89.9% and 92.8%, respectively false-positive rates were 1.35 and 0.40 per image, respectively. The observer performance studies indicate that an average Az value for the five doctors was greater with the CAD system than with a film-only reading without CAD, and that a reading with CAD was significantly superior at P < 0.022. CONCLUSIONS: It has been shown that CAD based on Fuji Computed Radiography offers good detection rates for both breast cancerous tumors and clustered microcalcifications, and that the reading of mammograms with this CAD system would provide potential improvement in diagnostic accuracy for breast cancer.     

Impact of breast density on computer-aided detection for breast cancer

OBJECTIVE: Our aim was to determine whether breast density affects the performance of a computer-aided detection (CAD) system for the detection of breast cancer. MATERIALS AND METHODS: Nine hundred six sequential mammographically detected breast cancers and 147 normal screening mammograms from 18 facilities were classified by mammographic density. BI-RADS 1 and 2 density cases were classified as nondense breasts; BI-RADS 3 and 4 density cases were classified as dense breasts. Cancers were classified as either masses or microcalcifications. All mammograms from the cancer and normal cases were evaluated by the CAD system. The sensitivity and false-positive rates from CAD in dense and nondense breasts were evaluated and compared. RESULTS: Overall, 809 (89%) of 906 cancer cases were detected by CAD; 455/505 (90%) cancers in nondense breasts and 354/401 (88%) cancers in dense breasts were detected. CAD sensitivity was not affected by breast density (p=0.38). Across both breast density categories, 280/296 (95%) microcalcification cases and 529/610 (87%) mass cases were detected. One hundred fourteen (93%) of the 122 microcalcifications in nondense breasts and 166 (95%) of 174 microcalcifications in dense breasts were detected, showing that CAD sensitivity to microcalcifications is not dependent on breast density (p=0.46). Three hundred forty-one (89%) of 383 masses in nondense breasts, and 188 (83%) of 227 masses in dense breasts were detected-that is, CAD sensitivity to masses is affected by breast density (p=0.03). There were more false-positive marks on dense versus nondense mammograms (p=0.04). CONCLUSION: Breast density does not impact overall CAD detection of breast cancer. There is no statistically significant difference in breast cancer detection in dense and nondense breasts. However, the detection of breast cancer manifesting as masses is impacted by breast density. The false-positive rate is lower in nondense versus dense breasts. CAD may be particularly advantageous in patients with dense breasts, in which mammography is most challenging.     

Digital mammography. ROC studies of the effects of pixel size and unsharp-mask filtering on the detection of subtle microcalcifications

We investigated the spatial resolution requirement and the effect of unsharp-mask filtering on the detectability of subtle microcalcifications in digital mammography. Digital images were obtained by digitizing conventional screen-film mammograms with a 0.1 X 0.1 mm2 pixel size, processed with unsharp masking, and then reconstituted on film with a Fuji image processing/simulation system (Fuji Photo Film Co., Tokyo, Japan). Twenty normal cases and 12 cases with subtle microcalcifications were included. Observer performance experiments were conducted to assess the detectability of subtle microcalcifications in the conventional, the unprocessed digital, and the unsharp-masked mammograms. The observer response data were evaluated using receiver operating characteristic (ROC) and LROC (ROC with localization) analyses. Our results indicate that digital mammograms obtained with 0.1 X 0.1 mm2 pixels provide lower detectability than the conventional screen-film mammograms. The detectability of microcalcifications in the digital mammograms is improved by unsharp-mask filtering; the processed mammograms still provide lower accuracy than the conventional mammograms, however, chiefly because of increased false-positive detection rates for the processed images at each subjective confidence level. Viewing unprocessed digital and unsharp-masked images in pairs resulted in approximately the same detectability as that obtained with the unsharp-masked images alone. However, this result may be influenced by the fact that the same limited viewing time was necessarily divided between the two images.     

Detection of simulated lesions on data-compressed digital mammograms

PURPOSE: To evaluate retrospectively the effect of a wavelet-based compression method on the detection of simulated masses of various sizes and clustered microcalcifications on data-compressed digital mammograms. MATERIALS AND METHODS: The images used in this study were acquired with institutional review board approval and patient informed consent, both of which allowed subsequent image data analysis. Patient identification was removed from images, and the study complied with requirements of the Health Insurance Portability and Accountability Act. Masses 3, 6, and 8 mm in diameter were analytically simulated and added to clinical mammographic backgrounds. In addition, microcalcifications were extracted from a clinical mammogram and hybridized with simulated microcalcifications for use in this study. Image compression conditions of 1:1, 15:1, and 30:1 were investigated. Observer responses were recorded with a six-point rating scale, and receiver operating characteristic (ROC) analysis was performed. In addition, two well-established numeric observer models were used to study the effect of image compression under the same compression conditions as were used with human observers. Analysis of variance was performed after observer adjustment to compare the mean values for area under the ROC curve (A(z)) across the three compression levels for the masses and microcalcification clusters. RESULTS: The results of the study indicated no significant differences in the A(z) values for masses with the compression conditions investigated. For images of microcalcifications, there were significant differences in A(z) values between compression ratios of 1:1 and 30:1 (P = .0005) and of 15:1 and 30:1 (P = .004); the difference between compression ratios of 1:1 and 15:1 was nonsignificant (P = .053). The observer models and human observers exhibited similar trends in detection of the masses investigated in this study. CONCLUSION: Detection of simulated masses was not affected by the compression method with the conditions used in this study, while the detection of microcalcifications was significantly reduced with a compression ratio of more than 15:1.     

Improvement in radiologists' detection of clustered microcalcifications on mammograms. The potential of computer-aided diagnosis

Relatively simple, but important, detection tasks in radiology are nearing accessibility to computer-aided diagnostic (CAD) methods. The authors have studied one such task, the detection of clustered microcalcifications on mammograms, to determine whether CAD can improve radiologists' performance under controlled but generally realistic circumstances. The results of their receiver operating characteristic (ROC) study show that CAD, as implemented by their computer code in its present state of development, does significantly improve radiologists' accuracy in detecting clustered microcalcifications under conditions that simulate the rapid interpretation of screening mammograms. The results suggest also that a reduction in the computer's false-positive rate will further improve radiologists' diagnostic accuracy, although the improvement falls short of statistical significance in this study.     

Computer-aided detection of breast masses depicted on full-field digital mammograms: a performance assessment

Objectives

To investigate the feasibility of converting a computer–aided detection (CAD) scheme for digitised screen–film mammograms to full-field digital mammograms (FFDMs) and assessing CAD performance on a large database.

Methods

The database included 6478 FFDM images acquired on 1120 females, with 525 cancer cases and 595 negative cases. The database was divided into five case groups: (1) cancer detected during screening, (2) interval cancers, (3) “high-risk” recommended for surgical excision, (4) recalled but negative and (5) negative (not recalled). A previously developed CAD scheme for masses depicted on digitised images was converted and re-optimised for FFDM images while keeping the same image-processing structure. CAD performance was analysed on the entire database.

Results

The case-based sensitivity was 75.6% (397/525) for the current mammograms and 40.8% (42/103) for the prior mammograms deemed negative during clinical interpretation but “visible” during retrospective review. The region-based sensitivity was 58.1% (618/1064) for the current mammograms and 28.4% (57/201) for the prior mammograms. The CAD scheme marked 55.7% (221/397) and 35.7% (15/42) of the masses on both views of the current and the prior examinations, respectively. The overall CAD-cued false-positive rate was 0.32 per image, ranging from 0.29 to 0.51 for the five case groups.

Conclusion

This study indicated that (1) digitised image-based CAD can be converted for FFDMs while performing at a comparable, or better, level; (2) CAD detects a substantial fraction of cancers depicted on prior examinations, albeit most having been marked only on one view; and (3) CAD tends to mark more false-positive results on “difficult” negative cases that are more visually difficult for radiologists to interpret.During the last decade, commercialised computer-aided detection (CAD) systems were widely tested and used clinically as a “second reader” to assist radiologists in interpreting mammograms. These CAD systems process digitised or digital images and cue (mark) suspicious regions that may depict specific abnormalities (i.e. masses and/or microcalcification clusters). The second reader approach emphasises that radiologists should first read and interpret mammograms without CAD followed by the viewing of the CAD results to help highlight the regions that were missed and/or underestimated in their importance prior to making a final recommendation. A number of studies have assessed the impact of using CAD on radiologists'' performances when interpreting mammograms [1-6]. Some studies have shown that radiologists detected more cancers associated with microcalcifications when using CAD for both screen–film mammograms (SFMs) [1] and full-field digital mammograms (FFDMs) [6], while other studies have shown that the use of CAD had little impact on both cancer detection and recall rates of the radiologists [2], or even reduced radiologists'' performances as measured by the areas under the receiver operating characteristic (ROC) curves [5]. Although there is no universal agreement of the actual benefit, if any, when using CAD, in terms of performance improvement [7], the objective assessment of CAD performance alone is important and has scientific merit. Our own previous study demonstrated an improvement in radiologists'' performances when using “highly performing” CAD, whereas radiologists'' performances actually reduced when using “poorly performing” CAD with high false-positive cueing rates [8].A number of previous studies have assessed the performances of commercialised CAD systems alone using different image databases [9-15]. Among these, several studies assessed the performances of CAD systems for FFDM images. One study reported an 89% (32/36) case-based sensitivity at 0.29 false-positive mass cues per image using the ImageChecker M1000-DM system (v.3.1; Hologic Inc., Bedford, MA) [13], and another study reported a 92% (57/62) case-based sensitivity at an overall false-positive rate of 0.58 per image (including both false-positive mass and microcalcification cluster cues) using the SecondLook system (v.7.2; iCAD Inc., Nashua, NH) [14]. Recently, Sadaf et al [15] reported the largest retrospective study to evaluate CAD performance using FFDM images to date. The database included 127 verified cancer cases associated with 5 different types of abnormalities. The CAD scheme (SecondLook v.7.2) achieved overall a 91% (115/127) cancer detection sensitivity, or an 88% (44/51) sensitivity on malignant masses.As the majority of previously reported CAD schemes in mammography were developed for digitised SFM images, researchers have also investigated the feasibility of converting the CAD schemes developed for digitised SFM images to new CAD schemes for FFDM images and comparing the performance difference between the CAD schemes for these two types of images [16,17]. For example, one study reported that two CAD schemes with similar architecture achieved comparable performance levels for the FFDM and SFM images (e.g. 70% sensitivity at 0.9 and 1.0 false-positive marks per image) by using a database of 229 SFM and FFDM examinations depicting 27 malignant and 104 benign masses [16]. Another study investigated the feasibility of converting an SFM-based CAD scheme to classify between malignant and benign masses depicted on FFDM images without changing the structure of the CAD scheme. Using a data set depicting 148 malignant and 139 benign masses, the study reported that there was no significant difference from the result of a previous study using SFM images (with an area under the ROC curve of 0.81 and p=0.83) [17].Despite these research efforts and the reported high performances, the databases used in the previous studies [13-17] were limited. In the assessment of CAD performance using digitised SFM images, studies have shown that the higher sensitivity reported in a study using a limited database (i.e. 89% [9]) was often not achievable in large-scale assessment studies [1,11,12]. Therefore, owing to the large variation of breast abnormalities and normal tissue structures, assembling a large database that can relatively sufficiently represent the general screening population is important to effectively assess or predict CAD performance in clinical practice. In this study, we assembled a large and unique FFDM image database that included a series of mammographic examinations on the same females belonging to one of five categories (groups) and converted our in-house developed CAD scheme for SFM images into a new scheme for FFDM images. An assessment of the CAD performance levels on the entire FFDM image database and each of the five case groups, at an operating level similar to that previously used to assess commercial CAD schemes for SFM images [12], is described herein.     

CAD in full-field digital mammography-influence of reader experience and application of CAD on interpretation of time

AimTo assess time expenditure using the influence of computer-assisted detection (CAD) system in the interpretation of the dependence of early research and benign and malignant mammograms on readers' experience.Materials and MethodsCAD (Image Checker V2.3; R2 Technology, Los Altos, CA, USA) was prospectively applied on digital mammograms of 303 patients [early research (n=103), benign (n=102), and malignant group (n=98)]. Mammograms were analyzed by three readers with varying experience in evaluating mammograms (medical student, resident and attending) according to the BI-RADS classification. Time was stopped and recorded. All images were presented randomly with and without the influence of CAD and from the different patient groups. To evaluate the statistical significance, the corresponding P value for time to read the mammograms in addition to different patient groups, application of CAD, readers' experience, and interaction of reader was calculated.ResultsThe attending needs, independent of CAD application, the least time, followed by the medical assistant and the student. In all three patient groups, CAD adoption elongates reading time of the student and the resident. The medical specialist needs with and without CAD median the same time. In the early research group, no significant differences were registered (P=.1343). Concerning readers' experience, there is an explicit significant difference (P<.0001). The application of CAD correlates with the corresponding readers' experience and also provides a not significant result. In comparison, the P value for the malignant and benign groups shows significant interactions between the readers' experiences as well as CAD application.ConclusionThe future role of CAD application depends on whether sensitivity can be increased and time expenditure caused by false-positive marks can be decreased. In the future, second reading could be substituted by a CAD system if the reader has a wide professional experience.     

Effect of soft-copy display supported by CAD on mammography screening performance

Diagnostic performance and reading speed for conventional mammography film reading is compared to reading digitized mammograms on a dedicated workstation. A series of mammograms judged negative at screening and corresponding priors were collected. Half were diagnosed as cancer at the next screening, or earlier for interval cancers. The others were normal. Original films were read by fifteen experienced screening radiologists. The readers annotated potential abnormalities and estimated their likelihood of malignancy. More than 1 year later, five radiologists reread a subset of 271 cases (88 cancer cases having visible signs in retrospect and 183 normals) on a mammography workstation after film digitization. Markers from a computer-aided detection (CAD) system for microcalcifications were available to the readers. Performance was evaluated by comparison of A_z-scores based on ROC and multiple-Reader multiple-case (MRMC) analysis, and localized receiver operating characteristic (LROC) analysis for the 271 cases. Reading speed was also determined. No significant difference in diagnostic performance was observed between conventional and soft-copy reading. Average A_z-scores were 0.83 and 0.84 respectively. Soft-copy reading was only slightly slower than conventional reading. Using a mammography workstation including CAD for detection of microcalcifications, soft-copy reading is possible without loss of quality or efficiency.     

Spectral phase based medical image processing

RATIONALE AND OBJECTIVES: To exploit the spectral phase characteristics of digital or digitized mammograms for early detection of microcalcifications, shape, and sizes of suspected lesions and to demonstrate its use for training radiologists to discriminate signal features in different spatially varying backgrounds. MATERIALS AND METHODS: We propose two algorithms: in the phase-only image (POI) reconstruction algorithm the spectral phase of the digital mammogram is extracted from its Fourier spectrum. This is coupled with unit magnitude and inverse Fourier transformed to reconstruct the POI thus enhancing the features of interest such as microcalcifications, shape, and sizes of suspected lesions. In the algorithm for image reconstruction from a priori phase-only information, spectral phase is used to extract signal features of the digital mammogram and then this is combined with spectral magnitude that is extracted and averaged over an ensemble of unrelated digital mammograms. RESULTS: The results for several digital phantoms and mammograms show that POI reconstructs only high spatial frequencies related to the features such as microcalcifications, shape, and size of masses like cysts and tumors. The results on image reconstruction from a priori phase-only information demonstrate the changes in the visibility of signal features when buried in a wide variety of real world mammogram backgrounds with different densities. CONCLUSION: The POI can aid radiologists in early detection of microcalcifications, lesions, and other masses of interest in digital mammograms. This reconstruction method is self-adaptive to changes in the background. The image reconstruction from a priori phase-only information can help the radiologist as a training tool in his decision-making process. Preliminary experiments indicate the potential of the techniques for early diagnosis of breast cancer. Clinical studies on these algorithm procedures are in progress for application as a diagnostic CAD tool in digital mammography. These methods can in general be applied to other medical images such as CT and MRI images.     

Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study.

PURPOSE: To evaluate the effects of computer-aided diagnosis (CAD) on radiologists' classification of malignant and benign masses seen on mammograms. MATERIALS AND METHODS: The authors previously developed an automated computer program for estimation of the relative malignancy rating of masses. In the present study, the authors conducted observer performance experiments with receiver operating characteristic (ROC) methodology to evaluate the effects of computer estimates on radiologists' confidence ratings. Six radiologists assessed biopsy-proved masses with and without CAD. Two experiments, one with a single view and the other with two views, were conducted. The classification accuracy was quantified by using the area under the ROC curve, Az. RESULTS: For the reading of 238 images, the Az value for the computer classifier was 0.92. The radiologists' Az values ranged from 0.79 to 0.92 without CAD and improved to 0.87-0.96 with CAD. For the reading of a subset of 76 paired views, the radiologists' Az values ranged from 0.88 to 0.95 without CAD and improved to 0.93-0.97 with CAD. Improvements in the reading of the two sets of images were statistically significant (P = .022 and .007, respectively). An improved positive predictive value as a function of the false-negative fraction was predicted from the improved ROC curves. CONCLUSION: CAD may be useful for assisting radiologists in classification of masses and thereby potentially help reduce unnecessary biopsies.     

Detection of masses and microcalcifications of breast cancer on digital mammograms: comparison among hard-copy film, 3-megapixel liquid crystal display (LCD) monitors and 5-megapixel LCD monitors: an observer performance study

The purpose of the study was to compare observer performance in the detection of masses and microcalcifications of breast cancer among hard-copy reading and soft-copy readings using 3-megapixel (3M) and 5-megapixel (5M) liquid crystal display (LCD) monitors. For the microcalcification detection test, we prepared 100 mammograms: 40 surgically verified cancer cases and 60 normal cases. For the mass detection test, we prepared 100 mammograms: 50 cancer cases and 50 normal cases. After six readers assessed both microcalcifications and masses set for each modality, receiver operating characteristic (ROC) analysis was performed. The average A_zs for mass detection using a hard copy and 3M and 5M LCD monitors were 0.923, 0.927 and 0.920, respectively; there were no significant differences. The average A_z for microcalcification detection using hard copy, 3M and 5M LCD monitors was 0.977, 0.954 and 0.972, respectively. There were no significant differences, but the P-values between the hard copy and 3M LCD monitor and that between the 3M and 5M LCD monitor were 0.08 and 0.09, respectively. In conclusion, the observer performances for detecting masses of breast cancers were comparable among the hard copy and two LCD monitors; however, soft-copy reading with a 3M LCD monitor showed slightly lower observer performance for detecting microcalcifications of breast cancers than hard-copy or 5M LCD monitor reading.     

计算机辅助检测对检出乳腺X线片中成簇微钙化灶的价值

目的:探讨计算机辅助检测系统(CAD)对检出乳腺X线钼靶摄影片中成簇微钙化灶的临床应用价值。方法:将22例乳腺X线钼靶片上疑有簇状钙化灶患者和13例正常对照者的140张乳腺钼靶X线片,经专业扫描仪数字化处理后,应用CAD软件标记其中的微钙化灶,由6位放射科医师分别单独阅片,再结合CAD阅片,结果采用受试者操作特性(ROC)曲线法进行分析。结果:6位放射科医师结合CAD阅片后,评价效果均优于未结合CAD时,其中3位低年资医师(有1年临床经验)和1位中年资医师(有5年以上临床经验)的两次评价结果有显著性差异(P<0.05)。结论:CAD有助于提高乳腺X线片中成簇微钙化灶的检出率,尤其对缺少诊断经验医师的作用更大。