Explore chapters and articles related to this topic
An Introduction to Medical Image Analysis in 3D
Published in Rohit Raja, Sandeep Kumar, Shilpa Rani, K. Ramya Laxmi, Artificial Intelligence and Machine Learning in 2D/3D Medical Image Processing, 2020
Upasana Sinha, Kamal Mehta, Prakash C. Sharma
“Tomosynthesis has been proven to enhance the care for breast most cancers detection and is extra sensitive, especially in sufferers at excessive danger or with dense breasts,” Harris explains. “It helps to differentiate matters that may be misinterpreted that are probably different artifacts.
Breast imaging
Published in A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha, Clark’s Procedures in Diagnostic Imaging: A System-Based Approach, 2020
A Stewart Whitley, Jan Dodgeon, Angela Meadows, Jane Cullingworth, Ken Holmes, Marcus Jackson, Graham Hoadley, Randeep Kumar Kulshrestha
Digital mammography has allowed development of a technique called tomosynthesis, in which a 3D image is acquired to allow multiplanar viewing that can clarify or reveal lesions not seen as well on conventional mammograms (Fig. 12.1a).
Breast cancer
Published in Ruijiang Li, Lei Xing, Sandy Napel, Daniel L. Rubin, Radiomics and Radiogenomics, 2019
Digital breast tomosynthesis (DBT) is similar to FFDM in patient set up (breast compression although with slightly less applied pressure and immobilization), however, the X-ray tube is not fixed, but rather moves along a trajectory (an arc), and exposes and images the breast at various time intervals and projection angle (15). The series of single-projection images is then subjected to a reconstruction algorithm to yield images of breast sections parallel to the detector. Images of these breast sections allow for the viewing of abnormalities with minimal overlapping tissue, basically, providing pseudo 3D images (or 2.5 D). Use of breast tomosynthesis in breast cancer screening is rapidly increasing (16).
The role of artificial intelligence in breast cancer screening: how can it improve detection?
Published in Expert Review of Molecular Diagnostics, 2020
The European commission initiative on breast cancer issued a recommendation for screening (strong recommendation for screening versus non-screening in 50–69 years, conditional recommendation for screening in age group 45–49 and 70–74 years.) Also recommendations are issued that identify the 2 year interval as the most appropriate screening interval, double reading of mammograms is recommended over single reading of mammograms. Also a neutral recommendation was formulated about the use of tomosynthesis (3D)-mammography as a primary means of screening versus the commonly used 2D Full Field Digital Mammography. The reason for a neutral recommendation was that there is still a lack of studies and a controversial discussion about the effect of the proven additional detection rates 3D-mammography provides in contrast to the lack of decrease of interval cancers shown in studies and the possible amount of overdiagnosis (meaning detection of cancers that would not have threatened the womens life, even if not had been detected) [4]. This also applies to the additional use of AI algorithms in screening programs. The aim is to find the clinical relevant cancers in a stage where treatment can be more effective and less harmful and to reduce the rate of overdiagnosis and overtreatment.
Neoadjuvant breast cancer treatment response; tumor size evaluation through different conventional imaging modalities in the NeoDense study
Published in Acta Oncologica, 2020
Ida Skarping, Daniel Förnvik, Uffe Heide-Jørgensen, Lisa Rydén, Sophia Zackrisson, Signe Borgquist
Ideally, oncological and surgical BC treatment should be performed according to a patient’s individual tumor response to NACT through repeated response evaluations; assessed clinically by inspection/palpation of the breast and lymph nodes, by imaging, and ultimately, pathological assessment. Mammography, ultrasound, and/or magnetic resonance imaging (MRI) are the imaging modalities most frequently used, and several studies have investigated the ability of these modalities in measuring tumor response during NACT for predicting residual pathological tumor size post-NACT [9–16]. However, the accuracy of the novel 3D-mammography tomosynthesis relative to other imaging modalities, has been less studied [14]. During the last decade, studies have shown the superiority of MRI in detecting pathological complete response (pCR) [17–19]; however, while the modality is clinically advantageous, shortcomings in terms of costs and availability remain [20]. Also, a recent review questioned the high performance of MRI as presented by individual studies [20].
What is the value of electromagnetic navigation in lung cancer and to what extent does it require improvement?
Published in Expert Review of Respiratory Medicine, 2020
Brian D. Shaller, Thomas R. Gildea
Tomosynthesis is a form of fluoroscopy in which a sequence of X-ray images are acquired over a limited angle of rotation (usually between 20 and 70 degrees) around a target and then processed to generate a three-dimensional reconstruction. Tomosynthesis using a C-arm fluoroscope permits visualization of smaller lesions and their immediate surrounding structures at a much lower radiation dose than CBCT (although with reduced image-fidelity). In a study conducted in a ventilated ex vivo porcine lung model, EMN was used to access and place fiducial markers as close as possible to 7-mm peripheral targets that were not visible on two-dimensional fluoroscopy. Targets were imaged with tomosynthesis before and after fiducial-placement, and the distance from the fiducial to the target as determined by tomosynthesis and as estimated by EMN were compared to measurements on CBCT. All 40 targets were visualized by tomosynthesis prior to navigation, and distances from the fiducial to the target on tomosynthesis were highly concordant with CBCT measurements, whereas distances as determined by the EMN system were not (correlation coefficient of 0.926 versus 0.048) [73].