This will count as one of your downloads.
You will have access to both the presentation and article (if available).
On the relevance of modulation transfer function measurements in digital mammography quality control
Methods: 4 phantoms were investigated: CDMAM, L1, CIRS BR3D and Modular DBT Phantom (two different inserts). The phantoms were imaged on recent DBT models: Fujifilm Amulet Innovality (ST mode), GE HC Senographe Pristina, Hologic 3Dimensions, IMS Giotto Class and Siemens Mammomat Revelation. Images were acquired at automatic exposure control (AEC) level, half AEC and twice AEC. SM was calculated. The CDMAM and L1 phantom were read by human readers via a 4-Alternative Forced Choice method and thresholds were established. CIRS BR3D and Modular DBT Phantom were analysed by counting visible lesions.
Results: The scores obtained from the phantoms had the same tendencies among systems. The phantoms highlight many specific characteristics of the SM algorithms such as tuning contrast enhancement to a range of sizes. The phantoms confirm, as in 2D and DBT, an impact of dose on detectability of microcalcification-like inserts but not on masses. None of the phantoms evaluate the SM for different glandular tissue or thickness distributions.
Conclusion: For all phantoms, SM found a number of lesion-like targets and an impact of dose as expected. Whether these phantom readings are representative for quality in SM in real practice is not yet proven. More elaborated sensitivity studies should be done prior to the use of the phantoms in routine QC. Ultimately, accurate assessment of SM may have to be done via virtual trials.
Feed-forward convolutional neural networks (CNN) have been successfully applied in the medical imaging domain. A 12 layer CNN model was constructed to extract features for image classification. A structured phantom was scanned on a Siemens DBT system at three dose levels: dose set by the automatic exposure control (AEC) system, half this dose and double. After training the CNN on 36 DBT acquisitions (51840 image segments), newly acquired test images were categorized by the algorithm into the dose categories with an accuracy of 99.7%. Parallel to that the standard methods as NNPS and pixel value (PV) mean and variance calculated for the projection and reconstructed planes also show ability to detect the dose level change with some limitations for the reconstructed planes. This result indicates the potential for further use of deep learning algorithms for DQC when using only the reconstructed DBT planes.
A novel platform to simplify human observer performance experiments in clinical reading environments
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Development of new breast X-ray imaging technologies or improvements to hardware or software of current systems usually require the accurate assessment of image quality. Image quality assessment methods are also required for quality control (QC) of clinical systems, for example as required by the U.S. Mammography Quality Standards Act (MQSA) program. The gold standard for assessment of image quality is human reader studies assessing diagnostic performance over a cohort of representative clinical images. These clinical trials are often difficult and expensive to perform, and therefore researchers have been studying alternative approaches that can assess diagnostic task performance without imaging patients.
This short course will discuss methods for objectively assessing task performance of breast imaging systems without conducting a clinical trial. One approach that will be discussed is the in silico modeling of a clinical trial. This approach involves complete computer modeling of each step in the imaging chain including: 1) modeling of breast and relevant breast lesions, 2) modeling of the imaging system, and 3) modeling of the observer. Another more experimental approach that will also be discussed involves: 1) development of anthropomorphic physical phantoms with diagnostic features, 2) imaging of these phantoms on breast imaging commercial or prototype systems, and 3) assessment of task performance with either model or human observers.
For maximum efficiency, the proposed in silico and experimental approaches require the development of computer or model observers that can emulate either ideal or human observer task performance. This short course will discuss the use of new machine learning algorithms that can be used to model observer performance in the assessment of breast imaging technology.
This course will describe and make attendees aware of useful open-source software tools that can be downloaded.
View contact details
No SPIE Account? Create one
