Radiologists' preferences for digital mammographic display. The International Digital Mammography Development Group

PURPOSE: To determine the preferences of radiologists among eight different image processing algorithms applied to digital mammograms obtained for screening and diagnostic imaging tasks. MATERIALS AND METHODS: Twenty-eight images representing histologically proved masses or calcifications were obtained by using three clinically available digital mammographic units. Images were processed and printed on film by using manual intensity windowing, histogram-based intensity windowing, mixture model intensity windowing, peripheral equalization, multiscale image contrast amplification (MUSICA), contrast-limited adaptive histogram equalization, Trex processing, and unsharp masking. Twelve radiologists compared the processed digital images with screen-film mammograms obtained in the same patient for breast cancer screening and breast lesion diagnosis. RESULTS: For the screening task, screen-film mammograms were preferred to all digital presentations, but the acceptability of images processed with Trex and MUSICA algorithms were not significantly different. All printed digital images were preferred to screen-film radiographs in the diagnosis of masses; mammograms processed with unsharp masking were significantly preferred. For the diagnosis of calcifications, no processed digital mammogram was preferred to screen-film mammograms. CONCLUSION: When digital mammograms were preferred to screen-film mammograms, radiologists selected different digital processing algorithms for each of three mammographic reading tasks and for different lesion types. Soft-copy display will eventually allow radiologists to select among these options more easily.     

Investigation of reduction of exposure dose in digital mammography: relationship between exposure dose and image processing

In digital mammograms, granularity is an important image property for the detection of microcalcifications and masses. Therefore, we investigated the relationship between the conditions of various exposure doses and the detectability of RMI156 phantom images with and without image processing for the reduction of exposure dose. The images are processed with Gaussian filter and unsharp-masking filters to evaluate the effects on image properties by using the digital Wiener spectrum (WS) presampled modulation transfer function (MTF). In addition, observer performance tests for the detectability of microcalcifications and masses are performed. With Gaussian filtering, the WS value decreased to 50% at 2.0 cycles/mm and the detectability score of masses increased 80% and 12%, on 1.34 mGy and 2.62 mGy, respectively (p<0.05). With unsharp-masking (7 x 7 pixels), the MTF value increased to 126% at 2.0 cycles/mm, and the detectability of microcalcification to 32% and 5%, on 1.34 mGy and 5.28 mGy, respectively (p<0.05) compared with the original image. The optimal dose of simulated lesions with unsharp masking became 5.25 mGy. The unsharp masking could reduce 37% of the exposure dose without a loss of detectability of microcalcifications and masses.     

Mammographic microcalcifications: detection with xerography, screen- film, and digitized film display

Pulverized bone specks and aluminum oxide specks were measured by hand into sizes ranging from 0.2 mm to 1.0 mm and then arranged in clusters. These clusters were superimposed on a human breast tissue phantom, and xeromammograms and screen-film mammograms of the clusters were made. The screen-film mammograms were digitized using a high-resolution laser scanner and then displayed on cathode ray tube (CRT) monitors. Six radiologists independently counted the microcalcifications on the xeromammograms, the screen-film mammograms, and the digitized-film mammograms. The xeromammograms were examined with a magnifying glass; the screen-film images were examined with a magnifying glass and by hot light; and the digitized-film images were examined by electronic magnification and image processing. The bone speck size that corresponded to a mean 50% detectability level for each technique was as follows: xeromammography, 0.550 mm; digitized film, 0.573 mm; and screen-film, 0.661 mm. We postulate that electronic magnification and image processing with edge enhancement can improve the capability of screen-film mammography to enhance the detection of microcalcifications.     

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.     

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.     

Image processing algorithms for digital mammography: a pictorial essay.

Digital mammography systems allow manipulation of fine differences in image contrast by means of image processing algorithms. Different display algorithms have advantages and disadvantages for the specific tasks required in breast imaging-diagnosis and screening. Manual intensity windowing can produce digital mammograms very similar to standard screen-film mammograms but is limited by its operator dependence. Histogram-based intensity windowing improves the conspicuity of the lesion edge, but there is loss of detail outside the dense parts of the image. Mixture-model intensity windowing enhances the visibility of lesion borders against the fatty background, but the mixed parenchymal densities abutting the lesion may be lost. Contrast-limited adaptive histogram equalization can also provide subtle edge information but might degrade performance in the screening setting by enhancing the visibility of nuisance information. Unsharp masking enhances the sharpness of the borders of mass lesions, but this algorithm may make even an indistinct mass appear more circumscribed. Peripheral equalization displays lesion details well and preserves the peripheral information in the surrounding breast, but there may be flattening of image contrast in the nonperipheral portions of the image. Trex processing allows visualization of both lesion detail and breast edge information but reduces image contrast.     

Improving the Detection of Simulated Masses in Mammograms through Two Different Image-Processing Techniques

RATIONALE AND OBJECTIVES: The purpose of this study was to determine whether contrast-limited adaptive histogram equalization (CLAHE) or histogram-based intensity windowing (HIW) improves the detection of simulated masses in dense mammograms. MATERIALS AND METHODS: Simulated masses were embedded in portions of mammograms of patients with dense breasts; the mammograms were digitized at 50 microm per pixel, 12 bits deep. In two different experiments, images were printed both with no processing applied and with related parameter settings of two image-processing methods. A simulated mass was embedded in a realistic background of dense breast tissue, with its position varied. The key variables in each trial included the position of the mass, the contrast levels of the mass relative to the background, and the selected parameter settings for the image-processing method. RESULTS: The success in detecting simulated masses on mammograms with dense backgrounds depended on the parameter settings of the algorithms used. The best HIW setting performed better than the best fixed-intensity window setting and better than no processing. Performance with the best CLAHE settings was no different from that with no processing. In the HIW experiment, there were no significant differences in observer performance between processing conditions for radiologists and nonradiologists. CONCLUSION: HIW should be tested in clinical images to determine whether the detection of masses by radiologists can be improved. CLAHE processing will probably not improve the detection of masses on clinical mammograms.     

Image segmentation in digital mammography: comparison of local thresholding and region growing algorithms.

Local thresholding and region-growing algorithms are developed and applied to digitized mammograms to quantify the parenchymal densities. The algorithms are first evaluated and optimized on phantom images reflecting varying image contrast, X-ray exposure conditions, and time-related changes. The difference between the segmentation results of the two techniques is less than 6% on the phantom images and 11% on the mammograms. The agreement between the computerized procedures and a manual one is in the range of 74-98%, depending on the breast parenchymal pattern and segmentation algorithm. The results show that computerized parenchymal classification of digitized mammograms is possible and independent of exposure.     

Radiographic image enhancement. Part I: spatial domain techniques

Digital image enhancement techniques provide a multitude of choices for improving the visual quality of diagnostic images. Appropriate choice of such techniques is greatly influenced by the imaging modality, task at hand and viewing conditions. This sequence of two articles will provide an overview of underlying concepts, along with algorithms commonly used for radiographic image enhancement. The first article focuses on spatial domain techniques for radiographic image enhancement, with particular reference to point processing methods, histogram modification and unsharp masking.     

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.     

腰椎数字X线摄影后处理参数的体模研究

目的 探讨腰椎数字X线摄影的后处理参数对影像质量的影响,从而在保证影像质量的同时降低有效辐射剂量.方法 通过调节Philips DR系统工作站提供的后处理参数,对CDRAD2.0体模成像,在医用显示器上评价腰椎体模影像质量.运用析因实验设计,通过ANOVA方法总结出细节对比度增强(DCE)、噪声补偿(NC)、反锐化掩膜(UM)、反锐化掩膜核(UMK)等后处理参数的优化方案.根据Solidose剂量仪测量出的体模表面入射剂量(ESD),对方案的优化效果进行体模验证.结果 通过析因实验显示,临床所用的管电压为70 kVp时,对影像质量影响较大的是DCE、UM和UMK(F值分别为91.45、373.79、429.88,P值均＜0.05).随着UM的增加(由0到5),图像质量因子(IQF)增加(约20个单位),而DCE和UMK增加导致IQF降低(分别约10和21个单位).增加管电压,IQF提高(如同样参数的设置下,管电压分别为63、85 kVp,IQF提高了14个单位),影像质量差异有统计学意义(t=5.31,P＜0.05).结论合理使用后处理参数的优化方案,可以在保证图像质量的前提下,通过增加管电压大大降低对患者的有效辐射剂量.     

Pneumothorax and other lung diseases: effect of altered resolution and edge enhancement on diagnosis with digitized radiographs

Prior studies have shown that pneumothorax is one of the more difficult entities to diagnose with digitized radiography. This study was designed to test whether increasing resolution from 1.25 to 2.5 line pairs per millimeter (lp/mm) and image processing (edge enhancement from unsharp masking) would increase accuracy and confidence in the diagnosis of pneumothorax, as well as normal cases and other forms of lung disease. Conventional radiographs were digitized with use of a laser reader and then reformatted as film hard copy. Eleven observers read 35 cases reformatted in three different ways (1.25 lp/mm, 2.5 lp/mm, 1.25 lp/mm unsharp mask). The images with finer resolution (2.5 lp/mm) and unsharp mask images were superior to those with coarser resolution (1.25 lp/mm) for the diagnosis of pneumothorax. There was no difference in diagnostic accuracy for normal patients. For abnormalities other than pneumothorax, the unsharp mask images were significantly worse. Confidence in the diagnosis of pneumothorax and other abnormalities was highest with the finest resolution (2.5 lp/mm).     

Film-screen magnification versus electronic magnification and enhancement of digitized contact mammograms in the assessment of subtle microcalcifications.

RATIONALE AND OBJECTIVES: To compare information drawn from magnification mammography with that extracted from electronic magnification, processing, and display of the digitized contact images. METHODS: Contact and magnification images of a mammographic statistical phantom were obtained. The magnification films versus the computer-enhanced, digitized images of the corresponding contact mammograms were separately presented to three observers. Receiver operating characteristic analysis was used to compare lesion detectability. The contact and magnification mammograms of 86 patients with subtle microcalcifications were also studied. The breast imaging reporting and data system (BI-RADS) scheme was used to compare the magnification patient films versus the corresponding digitized contact images. Differences in mammographic assessment were evaluated by using the kappa statistic. The dose to breast tissue from contact and magnification mammography was measured to evaluate dose reduction in instances where magnification mammography was to be avoided. RESULTS: Lesion detectability was found to be similar when either the digitized film image or the magnification hard-copy film was inspected. Interpretation of patient images by inspection of the contact and magnification screen-film mammograms on a view-box was in excellent agreement with that yielded by inspection of the contact image on a view-box and the computer-enhanced, digitized contact image on a display monitor. CONCLUSIONS: Electronic magnification and processing of the digitized contact image may provide valuable information concerning subtle microcalcifications, rendering magnification mammography unnecessary for many patients with such lesions.     

Free-response receiver operating characteristic evaluation of lossy JPEG2000 and object-based set partitioning in hierarchical trees compression of digitized mammograms

PURPOSE: To assess the effects of two irreversible wavelet-based compression algorithms--Joint Photographic Experts Group (JPEG) 2000 and object-based set partitioning in hierarchical trees (SPIHT)--on the detection of clusters of microcalcifications and masses on digitized mammograms. MATERIALS AND METHODS: The use of the images in this retrospective image-collection study was approved by the institutional review board, and patient informed consent was not required. One hundred twelve mammographic images (28 with one or two clusters of microcalcifications, 19 with one mass, 17 with both abnormal findings, and 48 with normal findings) obtained in 60 women who ranged in age from 25 to 79 years were digitized and compressed at 40:1 and 80:1 by using the JPEG2000 and object-based SPIHT methods. Five experienced radiologists were asked to locate and rate clusters of microcalcifications and masses on the original and compressed images in a free-response receiver operating characteristic (FROC) data acquisition paradigm. Observer performance was evaluated with the jackknife FROC method. RESULTS: The mean FROC figures of merit for detecting clusters of microcalcifications, masses, and both radiographic findings on uncompressed images were 0.80, 0.81, and 0.72, respectively. With object-based SPIHT 80:1 compression, the corresponding values were larger than the values for uncompressed images by 0.005, 0.009, and -0.005, respectively. The 95% confidence interval for the differences in figures of merit between compressed and uncompressed images was -0.039, 0.033 for the microcalcification finding; -0.055, 0.034 for the mass finding; and -0.039, 0.030 for both findings. Because each of these confidence intervals includes zero, no significant difference in detection accuracy between uncompressed and object-based SPIHT 80:1 compression was observed at a P value of 5%. The F test of the null hypothesis that all of the modes (uncompressed and four compressed modes) were equivalent yielded the following results: F = 0.255, P = .903 for the microcalcification finding; F = 0.340, P = .848 for the mass finding; and F = 0.122, P = .975 for both findings. CONCLUSION: To within the accuracy of these measurements, lossy compression of digital mammographic data at 80:1 with JPEG2000 or the object-based SPIHT algorithm can be performed without decreasing the rate of detection of clusters of microcalcifications and masses.     

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.     

Improved interpretation of digitized mammography with wavelet processing: a localization response operating characteristic study

OBJECTIVE: Our objective was the implementation and evaluation of a novel enhancement technique for improved interpretation of high-resolution digitized mammograms from computer monitors. MATERIALS AND METHODS: A wavelet algorithm was designed to attenuate the image spectral characteristics responsible for the long-range image correlation that often interferes with digital display. The algorithm was evaluated with a localization response operating characteristic (LROC) experiment with 500 negative, benign, and cancer cases with masses and calcification clusters. Three observers reviewed the original and wavelet-enhanced images on a 5-Mpixel monitor using a custom-made workstation user interface. RESULTS: Performance indexes were estimated for four different case combinations, each observer, and each interpretation mode. Wavelet enhancement improved the performance of all observers in all case combinations. Detection accuracy ranged from 0.678 to 0.827 for the unprocessed original data and 0.709-0.871 for the enhanced cases. Localization accuracy ranged from 0.547 to 0.785 for the original images and 0.568-0.847 for the enhanced cases, yielding increases of 5-15%. The difference between enhanced and original performances was statistically significant at the 0.10 level and in a few combinations at the 0.05 level. CONCLUSION: Soft-copy digitized mammography could replace standard film mammography under appropriate display parameters and conditions. The optimization of the soft-copy quality is expected to require more advanced processing techniques than standard gray-scale adjustments. Wavelet-based algorithms, such as the one proposed here, offer better soft-copy quality than the originals and a better starting point for additional manual gray-scale adjustments or automated postprocessing.     

Computer-aided detection of microcalcifications in mammograms. Methodology and preliminary clinical study

The authors investigated the feasibility of using computer methods for automated detection of clustered microcalcifications on clinical mammograms. A new difference-image approach using a matched filter/box-rim filter combination effectively removed the structured background from the image. A locally adaptive gray-level thresholding technique was then used for extraction of the signals from the resulting difference image. Signal-extraction criteria based on the size, contrast, number, and clustering properties of microcalcifications were next imposed on the detected signals to distinguish true signals from noise or artifacts. The detection accuracy of the computer scheme was evaluated by means of a free response receiver operating characteristic (FROC) analysis. It was found that, for simulated subtle microcalcifications superimposed on normal mammograms, the difference-image approach with a matched filter/box-rim filter combination could yield a true-positive cluster detection rate of 80% at a false-positive detection rate of one cluster per image. In a study of 20 clinical images containing moderately subtle microcalcifications, the automated computer scheme obtained an 82% true-positive cluster detection rate at a false-positive detection rate of one cluster per image. These results indicate that the automated method has the potential to aid radiologists in screening mammograms for clustered microcalcifications.     

Radiologist detection of microcalcifications with and without computer-aided detection: a comparative study

AIM: To compare the sensitivity and specificity of microcalcification detection by radiologists alone and assisted by a computer-aided detection (CAD) system. MATERIALS AND METHODS: Films of 106 patients were masked, randomized, digitized and analysed by the CAD-system. Five readers interpreted the original mammograms and were blinded to demographics, medical history and earlier films. Forty-two mammograms with malignant microcalcifications, 40 with benign microcalcifications and 24 normal mammograms were included. Results were recorded on a standardized image interpretation form. The mammograms with suspicious areas flagged by the CAD-system were displayed on mini-monitors and immediately re-reviewed. The interpretation was again recorded on a new copy of the standard form and classified according to six groups. RESULTS: Forty-one out of 42 (98%) malignant microcalcifications and 32 of 40 (80%) benign microcalcifications were flagged by the CAD-system. There was an average of 1.2 markers per image. The sensitivity for malignant microcalcifications detection by mammographers without and with the CAD-system ranged from 81% to 98% and from 88% to 98%, respectively. The mean difference without and with CAD-system was 2.2% (range 0-7%). CONCLUSION: No statistically significant changes in sensitivity were found when experienced mammographers were assisted by the CAD-system, with no significant compromise in specificity.     

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.     

Image processing of early gastric cancer cases]

Computer image processing was used to enhance gastric lesions in order to improve the detection of stomach cancer. Digitization was performed in 25 cases of early gastric cancer that had been confirmed surgically and pathologically. The image processing consisted of grey scale transformation, edge enhancement (Sobel operator), and high-pass filtering (unsharp masking). Gery scale transformation improved image quality for the detection of gastric lesions. The Sobel operator enhanced linear and curved margins, and consequently, suppressed the rest. High-pass filtering with unsharp masking was superior to visualization of the texture pattern on the mucosa. Eight of 10 small lesions (less than 2.0 cm) were successfully demonstrated. However, the detection of two lesions in the antrum, was difficult even with the aid of image enhancement. In the other 15 lesions (more than 2.0 cm), the tumor surface pattern and margin between the tumor and non-pathological mucosa were clearly visualized. Image processing was considered to contribute to the detection of small early gastric cancer lesions by enhancing the pathological lesions.