The use of conventional clinical trials to optimise technology and techniques in breast cancer screening carries with it issues of dose, high cost and delay. This has motivated the development of Virtual Clinical Trials (VCTs) as an alternative <i>in-silico</i> assessment paradigm. However, such an approach requires a set of modelling tools that can realistically represent the key biological and technical components within the imaging chain. The OPTIMAM image simulation toolbox provides a complete validated end-to-end solution for VCTs, wherein commonly-found regular and irregular lesions can be successfully and realistically simulated. As spiculated lesions are the second most common form of solid mass we report on our latest developments to produce realistic spiculated lesion models, with particular application in Alternative Forced Choice trials. We make use of sets of spicules drawn using manually annotated landmarks and interpolated by a fitted 3D spline for each spicule. Once combined with a solid core, these are inserted into 2D and tomosynthesis image segments and blended using a combination of elongation, rotational alignment with background, spicule twisting and core radial contraction effects. A mixture of real and simulated images (86 2D and 86 DBT images) with spiculated lesions were presented to an experienced radiologist in an observer study. The latest observer study results demonstrated that 88.4% of simulated images of lesions in 2D and 67.4% of simulated lesions in DBT were rated as definitely or probably real on a six-point scale. This presents a significant improvement on our previous work which did not employ any background blending algorithms to simulate spiculated lesions in clinical images.
Virtual clinical trials (VCTs) represent an alternative assessment paradigm that overcomes issues of dose, high cost and delay encountered in conventional clinical trials for breast cancer screening. However, to fully utilize the potential benefits of VCTs requires a machine-based observer that can rapidly and realistically process large numbers of experimental conditions. To address this, a Deep Learning Model Observer (DLMO) was developed and trained to identify lesion targets from normal tissue in small (200 x 200 pixel) image segments, as used in Alternative Forced Choice (AFC) studies. The proposed network consists of 5 convolutional layers with 2x2 kernels and ReLU (Rectified Linear Unit) activations, followed by max pooling with size equal to the size of the final feature maps and three dense layers. The class outputs weights from the final fully connected dense layer are used to consider sets of n images in an n-AFC paradigm to determine the image most likely to contain a target. To examine the DLMO performance on clinical data, a training set of 2814 normal and 2814 biopsy-confirmed malignant mass targets were used. This produced a sensitivity of 0.90 and a specificity of 0.92 when presented with a test data set of 800 previously unseen clinical images. To examine the DLMOs minimum detectable contrast, a second dataset of 630 simulated backgrounds and 630 images with simulated lesion and spherical targets (4mm and 6mm diameter), produced contrast thresholds equivalent to/better than human observer performance for spherical targets, and comparable (12 % difference) for lesion targets.
Patient respiratory motion is a major problem during external beam radiotherapy of the thoracic and abdominal regions due to the associated organ and target motion. In addition, such motion introduces uncertainty in both radiotherapy planning and delivery and may potentially vary between the planning and delivery sessions. The aim of this work is to examine subject-specific external respiratory motion and its associated drift from an assumed average cycle which is the basis for many respiratory motion compensated applications including radiotherapy treatment planning and delivery. External respiratory motion data were acquired from a group of
20 volunteers using a marker-less 3D depth camera, Kinect for Windows. The anterior surface encompassing
thoracic and abdominal regions were subject to principal component analysis (PCA) to investigate dominant variations. The first principal component typically describes more than 70% of the motion data variance in the thoracic and abdominal surfaces. Across all of the subjects used in this study, 58% of subjects demonstrate largely abdominal breathing and 33% exhibited largely thoracic dominated breathing. In most cases there is observable drift in respiratory motion during the 300s capture period, which is visually demonstrated using Kernel Density Estimation. This study demonstrates that for this cohort of apparently healthy volunteers, there is significant respiratory motion drift in most cases, in terms of amplitude and relative displacement between the thoracic and abdominal respiratory components. This has implications for the development of effective motion compensation methodology.
This paper describes a quantitative assessment of the Microsoft Kinect for X-box360<sup>TM</sup> for potential application
in tracking respiratory and body motion in diagnostic imaging and external beam radiotherapy. However, the
results can also be used in many other biomedical applications. We consider the performance of the Kinect in
controlled conditions and find mm precision at depths of 0.8-1.5m. We also demonstrate the use of the Kinect for
monitoring respiratory motion of the anterior surface. To improve the performance of respiratory monitoring,
we fit a spline model of the chest surface through the depth data as a method of a marker-less monitoring of
a respiratory motion. In addition, a comparison between the Kinect camera with and without zoom lens and
a marker-based system was used to evaluate the accuracy of using the Kinect camera as a respiratory tracking
This paper describes a method of using a tracking system to track the upper part of the anterior surface during
scanning for developing patient-specific models of respiration. In the experimental analysis, the natural variation
in the anterior surface during breathing will be modeled to reveal the dominant pattern in the breathing cycle.
The main target is to produce a patient-specific set of parameters that describes the configuration of the anterior
surface for all respiration phases. These data then will be linked to internal organ motion to identify the effect
of the morphology of each on motion using particle filter to account for previously unseen patterns of motion. In
this initial study, a set of volunteers were imaged using the Codamotion infrared marker-based system. In the
marker-based system, the temporal variation of the respiratory motion was studied. This showed that for the
12 volunteer cohort, the mean displacement of the thorax surface TS (abdomen surface AS) region is 10.7±5.6
mm (16.0±9.5mm). Finally, PCA was shown to capture the redundancy in the data set with the first principal
component (PC) accounting for more than 96% of the overall variance in both AS and TS datasets. A fitting
to the dominant modes of variation using a simple piecewise sinusoid has suggested a maximum error of about
1.1mm across the complete cohort dataset.