The impact of image processing on cancer detection is still a concern to radiologists and physicists. This work aims to evaluate the effect of two types of image processing on cancer detection in mammography. An observer study was performed in which six radiologists inspected 349 cases (a mixture of normal cases, benign lesions and cancers) processed with two types of image processing. The observers marked areas they were suspicious were cancers. JAFROC analysis was performed to determine if there was a significant difference in cancer detection between the two types of image processing. Cancer detection was significantly better with the standard setting image processing (flavor A) compared with one that provides enhanced image contrast (flavor B), <i>p </i>= 0.036. The image processing was applied to images of the CDMAM test object, which were then analysed using CDCOM. The threshold gold thickness measured with the CDMAM test object was thinner using flavor A than flavor B image processing. Since Flavor A was found to be superior in both the observer study and the measurements using the CDMAM phantom, this may indicate that measurements using the CDMAM correlate with change in cancer detection with different types of image processing.
The aim of this study was to compare the detection of microcalcification clusters by human observers in breast images using 2D-mammography and narrow (15°/15 projections) and wide (50°/25 projections) angle digital breast tomosynthesis (DBT). Simulated microcalcification clusters with a range of microcalcification diameters (125 μm-275 μm) were inserted into 6 cm thick simulated compressed breasts. Breast images were produced with and without inserted microcalcification clusters using a set of image modelling tools, which were developed to represent clinical imaging by mammography and tomosynthesis. Commercially available software was used for image processing and image reconstruction. The images were then used in a series of 4-alternative forced choice (4AFC) human observer experiments conducted for signal detection with the microcalcification clusters as targets. The minimum detectable calcification diameter was found for each imaging modality: (i) 2D-mammography: 164±5 μm (ii) narrow angle DBT: 210±5 μm, (iii) wide angle DBT: 255±4 μm. A statistically significant difference was found between the minimum detectable calcification diameters that can be detected by the three imaging modalities. Furthermore, it was found that there was not a statistically significant difference between the results of the five observers that participated in this study. In conclusion, this study presents a method that quantifies the threshold diameter required for microcalcification detection, using high resolution, realistic images with observers, for the comparison of DBT geometries with 2D-mammography. 2Dmammography can visualise smaller detail diameter than both DBT imaging modalities and narrow-angle DBT can visualise a smaller detail diameter than wide-angle DBT.
Radiological imaging is fundamental within the healthcare industry and has become routinely adopted for diagnosis, disease monitoring and treatment planning. With the advent of digital imaging modalities and the rapid growth in both diagnostic and therapeutic imaging, the ability to be able to harness this large influx of data is of paramount importance. The Oncology Medical Image Database (OMI-DB) was created to provide a centralized, fully annotated dataset for research. The database contains both processed and unprocessed images, associated data, and annotations and where applicable expert determined ground truths describing features of interest. Medical imaging provides the ability to detect and localize many changes that are important to determine whether a disease is present or a therapy is effective by depicting alterations in anatomic, physiologic, biochemical or molecular processes. Quantitative imaging features are sensitive, specific, accurate and reproducible imaging measures of these changes.<p> </p> Here, we describe an extension to the OMI-DB whereby a range of imaging features and descriptors are pre-calculated using a high throughput approach. The ability to calculate multiple imaging features and data from the acquired images would be valuable and facilitate further research applications investigating detection, prognosis, and classification. The resultant data store contains more than 10 million quantitative features as well as features derived from CAD predictions. Theses data can be used to build predictive models to aid image classification, treatment response assessment as well as to identify prognostic imaging biomarkers.
Radiological imaging is fundamental within the healthcare industry and has become routinely adopted
for diagnosis, disease monitoring and treatment planning. Over the past two decades both diagnostic
and therapeutic imaging have undergone a rapid growth, the ability to be able to harness this large
influx of medical images can provide an essential resource for research and training. Traditionally, the
systematic collection of medical images for research from heterogeneous sites has not been
commonplace within the NHS and is fraught with challenges including; data acquisition, storage,
secure transfer and correct anonymisation.
Here, we describe a semi-automated system, which comprehensively oversees the collection of both
unprocessed and processed medical images from acquisition to a centralised database. The provision of
unprocessed images within our repository enables a multitude of potential research possibilities that
utilise the images. Furthermore, we have developed systems and software to integrate these data with
their associated clinical data and annotations providing a centralised dataset for research. Currently we
regularly collect digital mammography images from two sites and partially collect from a further three,
with efforts to expand into other modalities and sites currently ongoing. At present we have collected
34,014 2D images from 2623 individuals. In this paper we describe our medical image collection
system for research and discuss the wide spectrum of challenges faced during the design and
implementation of such systems.
Proc. SPIE. 9039, Medical Imaging 2014: PACS and Imaging Informatics: Next Generation and Innovations
KEYWORDS: Oncology, Computer aided diagnosis and therapy, Cancer, Databases, Image processing, Medical research, Medical imaging, Mammography, Digital mammography, Picture Archiving and Communication System
Many projects to evaluate or conduct research in medical imaging require the large-scale collection of images (both
unprocessed and processed) and associated data. This demand has led us to design and implement a flexible oncology
image repository, which prospectively collects images and data from multiple sites throughout the UK. This Oncology
Medical Image Database (OMI-DB) has been created to support research involving medical imaging and contains
unprocessed and processed medical images, associated annotations and data, and where applicable expert-determined
ground truths describing features of interest. The process of collection, annotation and storage is almost fully automated
and is extremely adaptable, allowing for quick and easy expansion to disparate imaging sites and situations. Initially the
database was developed as part of a large research project in digital mammography (OPTIMAM). Hence the initial focus
has been digital mammography; as a result, much of the work described will focus on this field. However, the OMI -DB
has been designed to support multiple modalities and is extensible and expandable to store any associated data with full
anonymisation. Currently, the majority of associated data is made up of radiological, clinical and pathological annotations
extracted from the UK’s National Breast Screening System (NBSS). In addition to the data, software and systems have
been created to allow expert radiologists to annotate the images with interesting clinical features and provide descriptors
of these features. The data from OMI-DB has been used in several observer studies and more are planned. To date we have
collected 34,104 2D mammography images from 2,623 individuals.
MedXViewer (Medical eXtensible Viewer) is an application designed to allow workstation-independent, PACS-less viewing and interaction with anonymised medical images (e.g. observer studies). The application was initially implemented for use in digital mammography and tomosynthesis but the flexible software design allows it to be easily extended to other imaging modalities. Regions of interest can be identified by a user and any associated information about a mark, an image or a study can be added. The questions and settings can be easily configured depending on the need of the research allowing both ROC and FROC studies to be performed. The extensible nature of the design allows for other functionality and hanging protocols to be available for each study. Panning, windowing, zooming and moving through slices are all available while modality-specific features can be easily enabled e.g. quadrant zooming in mammographic studies. MedXViewer can integrate with a web-based image database allowing results and images to be stored centrally. The software and images can be downloaded remotely from this centralised data-store. Alternatively, the software can run without a network connection where the images and results can be encrypted and stored locally on a machine or external drive. Due to the advanced workstation-style functionality, the simple deployment on heterogeneous systems over the internet without a requirement for administrative access and the ability to utilise a centralised database, MedXViewer has been used for running remote paper-less observer studies and is capable of providing a training infrastructure and co-ordinating remote collaborative viewing sessions (e.g. cancer reviews, interesting cases).
Introduction: The effect that the image quality associated with different image receptors has on cancer detection in mammography was measured using a novel method for changing the appearance of images. Method: A set of 270 mammography cases (one view, both breasts) was acquired using five Hologic Selenia and two Hologic Dimensions X-ray sets: 160 normal cases, 80 cases with subtle real non-calcification malignant lesions and 30 cases with biopsy proven benign lesions. Simulated calcification clusters were inserted into half of the normal cases. The 270 cases (Arm 1) were converted to appear as if they had been acquired on three other imaging systems: caesium iodide detector (Arm 2), needle image plate computed radiography (CR) (Arm 3) and powder phosphor CR (Arm 4). Five experienced mammography readers marked the location of suspected cancers in the images and classified the degree of visibility of the lesions. Statistical analysis was performed using JAFROC. Results: The differences in the visibility of calcification clusters between all pairs of arms were statistically significant (p<0.05), except between Arms 1 and 2. The difference in the visibility of non-calcification lesions was smaller than for calcification clusters, but the differences were still significant except between Arms 1 and 2 and between Arms 3 and 4. Conclusion: Detector type had a significant impact on the visibility of all types of subtle cancers, with the largest impact being on the visibility of calcification clusters.