The CAD system in the field of the brain nuclear medicine has been developed for diagnosis of dementia. The technique using voxel-based statistical analysis system has been developed and is used in the clinical study for brain glucose metabolic PET images and perfusion SPECT images. There may be few artifacts on the analysis process and it is always necessary to compare the findings with visual inspections. These methods have not yet established the evidence of good diagnostic performances. These techniques are expected to have high diagnostic accuracy and to be applied to other brain images: amino acid metabolic images, brain receptor images and amyloid images.
This article shows several medical images with a consideration of the application to computer assisted diagnosis (CAD). The expected CAD functions based on the clinical significance of imaging diagnosis were discussed. From the image reading perspective, the development of CAD in recognition of the lesion extension and anatomical structure were requested. From the image generation perspective, it is expected that a combination of CAD and imaging techniques for material separation will increase the diagnostic accuracy, and can disseminate the recent image techniques.
In this article, the author describes potential performances of CAD as computer aided diagnosis for breast imaging. For cancer diagnosis, primary diagnostic modality differs depending on the primary organ. In comparison with other cancers, many modalities have been applied to breast imaging for diagnosis. CAD as computer aided detection for screening mammography utilizing analog image has been developed first among breast imaging. Accordingly, CAD for hand-held US, automated breast scanners for ultrasound, MRI and DBT have been developed and been reported regarding these detection performances. CAD as computer aided detection for breast imaging has much more necessity in compared with other cancers' imaging. As current settings, computer-aided detection for breast imaging works for only one modality. Integrated CAD for multimodality imaging would have necessity in future to reduce reading overload with radiologists. To proceed and develop the new CAD, multimodality imaging reading workstation should be organized for breast imaging. In addition, the author reports a new computer aided application of volumetric analysis of breast density as the future potential performances of CAD as computer-aided diagnostic support for breast imaging.
Advanced computed tomography (CT) and magnetic resonance imaging (MRI) techniques enable us to evaluate various anatomic, physiologic, and pathologic status of abdominal organs. However, it is sometimes difficult to elicit thoroughly useful information in managing patients. In this paper, status about CT and MRI techniques in the upper abdomen is described. Then, engineering approaches, including computer-aided diagnosis (CAD) techniques, which are potentially useful in solving the problems are discussed.
Socioeconomical environment for medical imaging is dramatically changing in these decades. Uncontrollable explosion of medical imaging, i.e. number of examinations, volume of images or data, quality and quantity improvement, has been afflicting radiologists, technicians, and management team of the hospital. Although uroradiology is a relatively limited subspecialty in clinical medicine, the prostate cancer is one of the most frequently diagnosed malignancies in men. In addition, as the prostate cancer is mainly found in elder population, it would be an ideal example to discuss future in medicine. Thus, the current status and facing problems in the selection of optimal treatment strategies for the prostate cancer will be firstly demonstrated as a socioeconomical background. Then, current and potential future role of imaging and computer-assisted diagnosis will be illustrated in a sequences of clinical decision work flow of the treatment strategies of the prostate cancer: screening, diagnosis, differential diagnosis, staging, selecting optimal treatment, and follow-up. I sincerely hope future developments of computer-assisted diagnosis or artificial intelligence will improve our labor environments. Thus, we, radiologists, must prepare to change our roles in imaging studies.
Positron emission tomography (PET) and X-ray computed tomography (CT) are used for the localization and analysis of breast cancer and axillary metastasis. In this study, we develop a method for the automated detection of breast tumors and axillary metastasis in PET/CT images. Our scheme extracts the breast region, which includes axilla, from CT images and then detects high-uptake regions inside the breast region from PET images. First, a bounding box is calculated for the breast and the axilla using bone and lung information obtained from CT images. Second, high-uptake regions are detected in PET images using massive structure enhancement and thresholding. The areas outside the breast regions are excluded from initial candidate regions. False positives (FPs) are eliminated using the location and the shape of initial candidate regions before obtaining final candidate regions. In our experiments, we evaluated tumor detection ability of the proposed method. Breast regions were identified and extracted correctly in all cases. Sensitivity of tumor detection was 0.76 with a number of FPs/case of 3.9. These results indicate that the proposed method may be useful for breast tumor and axillary metastasis detection using PET/CT images.
As to the relationship between radiation dose and image quality in X-ray CT examinations, one can say, “the more radiation exposure we give, the better image quality we get”, as in the other X-ray examinations. Therefore, this relationship is a so-called trade-off relation, and it is a fundamental rule that radiation dose should be as low as possible under constraints to maintain diagnostic performance. Because the effects of image quality improvement by reducing radiation dose are expected to show “saturation” behavior as many natural phenomena, this improvement problem can be solved to a certain extent as an optimization problem. In this paper, I give an outline of some important research results that have been done for the relationship between radiation dose and image quality in X-ray CT examinations.