BackgroundDigital mammography is the most reliable imaging modality for breast carcinoma diagnosis and breast micro-calcifications is regarded as one of the most important signs on imaging diagnosis. In this paper, a computer-aided diagnosis (CAD) system is presented for breast micro-calcifications based on dual-tree complex wavelet transform (DT-CWT) to facilitate radiologists like double reading.MethodsFirstly, 25 abnormal ROIs were extracted according to the center and diameter of the lesions manually and 25 normal ROIs were selected randomly. Then micro-calcifications were segmented by combining space and frequency domain techniques. We extracted three texture features based on wavelet (Haar, DB4, DT-CWT) transform. Totally 14 descriptors were introduced to define the characteristics of the suspicious micro-calcifications. Principal Component Analysis (PCA) was used to transform these descriptors to a compact and efficient vector expression. Support Vector Machine (SVM) classifier was used to classify potential micro-calcifications. Finally, we used the receiver operating characteristic (ROC) curve and free-response operating characteristic (FROC) curve to evaluate the performance of the CAD system.ResultsThe results of SVM classifications based on different wavelets shows DT-CWT has a better performance. Compared with other results, DT-CWT method achieved an accuracy of 96% and 100% for the classification of normal and abnormal ROIs, and the classification of benign and malignant micro-calcifications respectively. In FROC analysis, our CAD system for clinical dataset detection achieved a sensitivity of 83.5% at a false positive per image of 1.85.ConclusionsCompared with general wavelets, DT-CWT could describe the features more effectively, and our CAD system had a competitive performance.

PurposeTo analyse the diagnostic signs present in slices of human breast tumour specimens using synchrotron radiation phase-contrast imaging computed tomography (PCI-CT) for the first time and assess the feasibility of this technique for clinical applications.Materials and MethodsThe ethics committee of our university and relevant clinical hospital approved this prospective study, and written informed consent was obtained from all patients. PCI-CT of human breast tumour specimens with synchrotron radiation was performed at the Shanghai Synchrotron Radiation Facility (SSRF). A total of 14 specimens of early-stage carcinomas and 8 specimens of adenomas were enrolled. Based on raw data reconstruction, the diagnostic signs present in the slices were analysed and correlated with histopathology. We proposed a criterion for clinical diagnosis according to the evaluated signs and the Breast Imaging Reporting and Data System (BI-RADS) for reference. The criterion was then assessed by clinicians in a double-blind method. Finally, descriptive statistics were evaluated, depending on the assessment results.ResultsThe 14 carcinoma specimens and 8 adenoma specimens were diagnosed as malignant and benign tumours, respectively. The total coincidence rate was 100%.ConclusionOur study results demonstrate that the X-ray diagnostic signs observed in the specimen slices and the criterion used for clinical diagnosis were accurate and reliable. The criterion based on signs analysis can be used to differentiate early-stage benign or malignant tumours. As a promising imaging method, PCI-CT can serve as a possible and feasible supplement to BI-RADS in the future.

BackgroundChronic obstructive pulmonary disease (COPD) is one of the leading causes of morbidity and mortality worldwide, and emphysema is a common component of COPD. Currently, it is very difficult to detect early stage emphysema using conventional radiographic imaging without contrast agents, because the change in X-ray attenuation is not detectable with absorption-based radiography. Compared with the absorption-based CT, phase contrast imaging has more advantages in soft tissue imaging, because of its high spatial resolution and contrast.MethodsIn this article, we used diffraction enhanced imaging (DEI) method to get the images of early stage emphysematous and healthy samples, then extract X-ray absorption, refraction, and ultra-small-angle X-ray scattering (USAXS) information from DEI images using multiple image radiography (MIR). We combined the absorption image with the USAXS image by a scatter plot. The critical threshold in the scatter plot was calibrated using the linear discriminant function in the pattern recognition.ResultsUSAXS image was sensitive to the change of tissue micro-structure, it could show the lesions which were invisible in the absorption image. Combined with the absorption-based image, the USAXS information enabled better discrimination between healthy and emphysematous lung tissue in a mouse model. The false-color images demonstrated that our method was capable of classifying healthy and emphysematous tissues.ConclusionHere we present USAXS images of early stage emphysematous and healthy samples, where the dependence of the USAXS signal on micro-structures of biomedical samples leads to improved diagnosis of emphysema in lung radiographs.