Based on the developing situation of Computer Aided Diagnosis/Detection (CAD) software, considering the domestic and international regulation of CAD software, according to current Medical Device Classification Catalog and related laws of China Food and Drug Administration (CFDA), this paper investigated and analyzed the classification of CAD software, and provided technical suggestion on classifying principle of CAD software applying Artificial Intelligence (AI) or other advanced technology from medical device regulation scope, for the reference of regulatory and technical departments.
Artificial Intelligence ; China ; Diagnosis, Computer-Assisted ; Radiographic Image Interpretation, Computer-Assisted ; Software

This paper covers a brain tumor assisted diagnosis system based on medical image analysis. The system supplements the PACS functions such as display of medical images and database inquiry, segments slice in real-time using the algorithm of fuzzy region competition, extracts shape feature factors such as contour label, compactness, moment, Fourier Descriptor, chord length, radius and other medical data on the brain tumor image with irregular contour feature after segmentation and then feeds to Bayesian network in order to sort the brain tumor for the implementation of automatic assisted diagnosis.
Algorithms ; Automatic Data Processing ; Bayes Theorem ; Brain Neoplasms ; diagnostic imaging ; pathology ; Diagnosis, Computer-Assisted ; Humans ; Image Processing, Computer-Assisted ; methods ; Radiographic Image Enhancement ; methods ; Radiographic Image Interpretation, Computer-Assisted ; Software Design

It is of paramount importance for the diagnosis and therapy of lung cancer, even for the increasing of 5-year survival rate in that the early dignosis of malignant pulmonary nodules are made by intelligent identification successfully. As it stands, in intelligent identification of pulmonary nodules, computer-aided detection/diagnosis (CAD) plays the most important role. The key points of intelligent identification of pulmonary nodules are (1) Detecting pulmonary nodules based on the characterization of nodule appearance; (2) Measuring accurately the nodule size; (3) Computing accurately the growth rate. This article presents a review on the basic technologies and methods of CAD for identifying malignant pulmonary nodules in the course of making early diagnosis, including lung segmentation, registration of volume data, identification of benign/malignant pulmonary nodule, and so on.
Artificial Intelligence ; Diagnosis, Computer-Assisted ; methods ; Diagnosis, Differential ; Humans ; Lung Neoplasms ; diagnosis ; Radiographic Image Interpretation, Computer-Assisted ; Solitary Pulmonary Nodule ; diagnostic imaging ; Tomography, X-Ray Computed ; methods

The shape characteristics of breast mass in digital mammograms are important clues in discriminating malignant and benign tumors. To provide more valuable information from the breast mass for radiologist, an enhanced mass segment method is presented. A new region growing with some parameters can be used to segment the mass region effectively. Moreover, the feature of the mass edge is well kept.
Algorithms ; Breast Neoplasms ; diagnostic imaging ; Diagnosis, Computer-Assisted ; Female ; Humans ; Image Interpretation, Computer-Assisted ; methods ; Image Processing, Computer-Assisted ; Mammography ; methods ; Pattern Recognition, Automated ; methods ; Radiographic Image Enhancement ; methods

OBJECTIVETo improve the accuracy and efficiency of pulmonary nodule segmentation of thoracic CT image for computer-aided diagnostic (CAD) system, especially for those nodules adhering to the pleural or blood vessels.

METHODSWe proposed the automatic process of pulmonary nodule segmentation, and using region growing method based on the contrast and gradient, the pulmonary nodule images were acquired. A self-adapted morphologic segmentation algorithm was presented for the unsuccessful nodule segmentation using region growing.

RESULTS AND CONCLUSIONSExperiments on clinical 2D pulmonary images showed that the solitary pulmonary nodules and those adhering to the pleural or blood vessels could all be segmented. This pulmonary nodule segmentation algorithm is feasible for automated segmentation of the thoracic CT images.

Algorithms ; Diagnosis, Computer-Assisted ; Diagnosis, Differential ; Humans ; Radiographic Image Interpretation, Computer-Assisted ; methods ; Solitary Pulmonary Nodule ; diagnostic imaging ; Tomography, X-Ray Computed

Microcalcification is an early sign of breast cancer appearing as isolated bright spots in mammogram images. However, there is a difficulty in detecting the spots because they are small-sized and have noisy and big image background. Morphological bandpass filter (MBF) is a fast method for detecting microcalcifications, but the accuracy there-by is not satisfied. Though Laplacion-of-a-Gaussian (LoGF) method can achieve high accuracy in location, it is time consuming. For these reasons, a new detection method for combining the two above-mentioned methods is proposed in this paper. We conducted the experiments on the breast cancer database of Nanjing Zhongda Hospital. The experimental results confirm that the detecting speed for microcalcifications is comparable to that with the use of morphological filter method, and the detection precision is comparable to that with the use of LoGF method.
Algorithms ; Breast Neoplasms ; diagnostic imaging ; pathology ; Calcinosis ; diagnostic imaging ; Diagnosis, Computer-Assisted ; Female ; Humans ; Mammography ; methods ; Radiographic Image Interpretation, Computer-Assisted ; methods

Lung cancer is the most common tumor and one of the malignant tumors with the lowest livability after diagnosis, as is known so far. Large-scale image database is the foundation of developing computer-aided diagnosis methods, education and training in lung cancer diagnosis to improve medical diagnostic efficiency and to reduce the doctors' burden. In this study, aiming at improving the low data storage efficiency and solving the lacking of tool for data visualization and data retrieval existing in the use of traditional Lung Image Database Consortium (LIDC) from the lung cancer database, we developed a new lung cancer image database platform including an improved data model, a data integration tool, an image and annotation visualization tool and a data retrieving component. Firstly, the data format in LIDC was analyzed and an improved information model was provided to manage and manipulate large amount data stored in it. Next, some tools such as data integration component, DICOM, image and annotation visualization tool, and data query were designed and implemented. The study demonstrated that the lung cancer image database platform had the capacity of data collection, visualization, and query, and could promote diagnose lung cancer research.
Algorithms ; Databases, Factual ; Diagnosis, Computer-Assisted ; Humans ; Information Storage and Retrieval ; methods ; Lung Neoplasms ; diagnostic imaging ; pathology ; Radiographic Image Interpretation, Computer-Assisted ; methods ; Tomography, X-Ray Computed ; methods ; standards

How to accurately identify mini-nodules in a large amount of high resolution computed tomography (HRCT) images is always a significant and difficult issue in lung nodule computer-aided detection (CAD). This paper describes a new mini-nodules detection method which is based on a multi-feature tracking algorithm. Our detection method began after running the Da-Jing algorithm and morphological operation to extract the lung region of every HRCT image in a sequence. Once the lung had been extracted, a hybrid algorithm, combining gray threshold and improved template matching, was used to obtain the regions of interest (ROD). Next, several characteristics of each ROI were calculated to identify the final results by using multi-feature tracking throughout the whole HRCT image sequence. The results showed that the proposed method would be of high accuracy with a low occurrence of false positives.
Algorithms ; Diagnosis, Computer-Assisted ; methods ; Humans ; Lung Neoplasms ; diagnostic imaging ; Pattern Recognition, Automated ; methods ; Radiographic Image Interpretation, Computer-Assisted ; Solitary Pulmonary Nodule ; diagnostic imaging ; Tomography, X-Ray Computed

Calcifications in mammograms are important signs of early breast cancer. Its accurate detection can provide an important basis for diagnosis and treatment of the breast cancer. As the rapid development of medical imaging technology, computer aided diagnosis (CAD) of calcifications by means of computers and artificial intelligence has improved the efficiency and accuracy of diagnosis. However, the secretive nature of calcifications reduce the credibility of diagnosis. Therefore, CAD techniques need to be improved. In this paper, the CAD of calcification and the national and international status of algorithms are described, and the problems in automatic detection and classification of calcifications are also summarized.
Breast Neoplasms ; diagnostic imaging ; pathology ; Calcinosis ; diagnostic imaging ; Diagnosis, Computer-Assisted ; methods ; Female ; Humans ; Mammography ; methods ; Radiographic Image Interpretation, Computer-Assisted ; methods

OBJECTIVETo evaluate the values of full-field digital mammography (FFDM) and breast imaging reporting and data system (BI-RADS) on breast diseases.

METHODSEight hundreds and thirty-one patients with 871 focuses were analyzed who underwent imaging examinations with FFDM before operation during January 1, 2004 to December 31, 2005. All patients received operation and had identified pathological diagnosis including breast cancer, breast fibroma, intraductal papilloma and breast disease. The radiological diagnosis followed BI-RADS suggested by American College of Radiology.

RESULTSThe imaging diagnostic sensitivity of overall focuses was 80.9%, the specificity was 90.0%, the positive predictive value was 88.4%, the negative predictive value was 83.3% and the diagnose accuracy was 85.5%. Two hundreds and sixty cases (97.7%) were pathological diagnosed breast cancer in BI-RADS category V, 67.8% (82/121) in BI-RADS category IV and 16.7% (81/484) in BI-RADS category I-III.

CONCLUSIONSWhen the radiological diagnosis is BI-RADS category V, surgery biopsy is the option. To category IV focuses, surgery biopsy or stereotactic vacuum-assisted biopsy should be suggested. As to category I-III focuses, the management should be prudent, and other factors should be considered including the social and economic factors.

Breast Diseases ; diagnosis ; Breast Neoplasms ; diagnosis ; Female ; Humans ; Mammography ; methods ; Radiographic Image Interpretation, Computer-Assisted ; Reproducibility of Results ; Sensitivity and Specificity