This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Investigating the potential of untrained convolutional layers and pruning in computational pathology
The aim of this work is to investigate whether breast cone-beam computed tomography (CBCT) can provide better lesion detectability compared to 2D mammography or digital breast tomosynthesis (DBT).
Lesions with a diameter of 4 mm, 5 mm and 6 mm have been inserted in a simulated breast phantom. In total 180 images are analysed, out of which 90 images contain lesions (equally divided between the 4 mm, 5mm and 6mm diameter lesions) and the rest represent normal breast tissues. The TIGRE (Tomographic Iterative GPU-based Reconstruction) has been used to simulate 360 projections and to reconstruct the images using the FeldKamp, Davis and Kress (FDK) algorithm. Scattered radiation and Poisson noise have also been added to the projections prior the image reconstruction.
In total 10 observers, some with, and some without experience of mammography images, have been used as observers for this preliminary 4AFC study. The analysis of the 4AFC study shows that the mean minimum detectable lesion size for the breast CBCT is 2.96±0.23 mm with a 95% confidence intervals of [2.73, 3.19].
We propose a marker-less single system solution for patient set-up and respiratory motion management based on low cost 3D depth camera technology (such as the Microsoft Kinect). In this new work we assess this approach in a study group of six volunteer subjects. Separate simulated treatment mimic treatment "fractions" or set-ups are compared for each subject, undertaken using conventional laser-based alignment and with intrinsic depth images produced by Kinect. Microsoft Kinect is also compared with the well-known RPM system for respiratory motion management in terms of monitoring free-breathing and DIBH. Preliminary results suggest that Kinect is able to produce mm-level surface alignment and a comparable DIBH respiratory motion management when compared to the popular RPM system. Such an approach may also yield significant benefits in terms of patient throughput as marker alignment and respiratory motion can be automated in a single system.
Recursive Bayesian estimation of respiratory motion using a modified autoregressive transition model
View contact details
No SPIE Account? Create one
