Ultrasound (US) imaging is a complex imaging modality, where the tissues are typically characterised by an inhomogeneous image intensity and by a variable image definition at the boundaries that depends on the direction of the incident sound wave. For this reason, conventional image segmentation approaches where the regions of interest are represented by exact masks are inherently inefficient for US images. To solve this issue, we present the first application of a Bayesian convolutional neural network (CNN) based on Monte Carlo dropout on US imaging. This approach is particularly relevant for quantitative applications since differently from traditional CNNs, it enables to infer for each image pixel not only the probability of being part of the target but also the algorithm confidence (i.e. uncertainty) in assigning that probability. In this work, this technique has been applied on US images of the femoral cartilage in the framework of a new application, where high-refresh-rate volumetric US is used for guidance in minimally invasive robotic surgery for the knee. Two options were explored, where the Bayesian CNN was trained with the femoral cartilage contoured either on US, or on magnetic resonance imaging (MRI) and then projected onto the corresponding US volume. To evaluate the segmentation performance, we propose a novel approach where a probabilistic ground-truth annotation was generated combining the femoral cartilage contours from registered US and MRI volumes. Both cases produced a significantly better segmentation performance when compared against traditional CNNs, achieving a dice score coefficient increase of about 6% and 8%, respectively.

MRI is a non-ionising imaging modality that could be used as an alternative to Xray-based imaging methods to accurately assess the 3D morphology of the vertebral anatomy of scoliosis patients. However, a major caveat in utilising MRI is the significant amount of time required to manually segment the anatomy of interest. To overcome this limitation, we implemented a fully automatic method for the 3D segmentation of thoracic vertebrae, including vertebral body and posterior elements, of healthy adolescents and patients with Adolescent Idiopathic Scoliosis (AIS) using MRI data. 62 MRI scans were obtained from 3 healthy volunteers and 25 patients with AIS. A state-of-the-art deep-learning network for segmentation was trained using image patches of the apical vertebra (T7, T8, T9 or T10) extracted from 20 AIS patient MRIs. Ad-hoc data augmentation was adopted to represent the unlabeled vertebral levels in the dataset (T5-T6, T11-T12). The vertebral levels T5-T12 were then segmented for the remaining MRI datasets by feeding to the network the MRI patches generated by translating a window of fixed size and stride onto the MRI volume. The mean dice score coefficient for the AIS patient vertebral levels T5-T12 was of 87% ± 4.3%, which was comparable to the performance achieved by two experts. On average, 93% and 97% of the MRI segmented slices were considered clinically acceptable morphological reconstructions of AIS and healthy volunteer vertebrae, respectively. The proposed method can be considered as the first step towards more routine MRI-based imaging of AIS osseous deformities, reducing the cumulative exposure of young patients to ionising radiation.

Knee arthroscopy is a complex minimally invasive surgery that can cause unintended injuries to femoral cartilage and/or post-operative complications. Autonomous robotic systems using real time volumetric ultrasound (US) imaging guidance hold potential for reducing significantly these issues and for improving patient outcomes. To enable the robotic system to navigate autonomously in the knee joint, the imaging system should provide the robot with a real-time comprehensive map of the surgical site. To this end, the first step is automatic image quality assessment, to ensure that the boundaries of the relevant knee structures are defined well enough to be detected, outlined and then tracked. In this paper, a recently developed one-class classifier deep learning algorithm was used to discriminate among US images acquired in a simulated surgical scenario on which the femoral cartilage either could or could not be outlined. 38,656 2D US images were extracted from 151 3D US volumes, collected from 6 volunteers, and were labelled as ‘1’ or as ‘0’ when an expert was or was not able to outline the cartilage on the image, respectively. The algorithm was evaluated using the expert labels as ground-truth with a 5-fold cross validation, where each fold was trained and tested on average with 15,640 and 6,246 labelled images, respectively. The algorithm reached a mean accuracy of 78.4 % ± 5.0, mean specificity of 72.5 % ± 9.4, mean sensitivity of 82.8 % ± 5.8 and mean area under the curve of 85 % ± 4.4. In addition, inter and intra observer tests involving two experts were performed on an image subset of 1536 2D US images. Percent agreement values of 0.89 and 0.93 were achieved between two experts (i.e., inter-observer) and by each expert (i.e., intra-observer), respectively. These results show the feasibility of the first essential step in the development of automatic US image acquisition and interpretation systems for autonomous robotic knee arthroscopy.

In prostate cancer treatment with external beam radiation therapy (EBRT), prostate motion and internal changes in tissue distribution can lead to a decrease in plan quality. In most currently used planning methods, the uncertainties due to prostate motion are compensated by irradiating a larger treatment volume. However, this could cause underdosage of the treatment volume and overdosage of the organs at risk (OARs). To reduce this problem, in this proof of principle study we developed and evaluated a novel adaptive planning method. The strategy proposed corrects the dose delivered by each beam according to the actual position of the target in order to produce a final dose distribution dosimetrically as similar as possible to the prescribed one. Our adaptive planning method was tested on a phantom case and on a clinical case. For the first, a pilot study was performed on an in-silico pelvic phantom. A “library” of intensity modulated RT (IMRT) plans corresponding to possible positions of the prostate during a treatment fraction was generated at planning stage. Then a 3D random walk model was used to simulate possible displacements of the prostate during the treatment fraction. At treatment stage, at the end of each beam, based on the current position of the target, the beam from the library of plans, which could reproduce the best approximation of the prescribed dose distribution, was selected and delivered. In the clinical case, the same approach was used on two prostate cancer patients: for the first a tissue deformation was simulated in-silico and for the second a cone beam CT (CBCT) taken during the treatment was used to simulate an intra-fraction change. Then, dosimetric comparisons with the standard treatment plan and, for the second patient, also with an isocenter shift correction, were performed. For the phantom case, the plan generated using the adaptive planning method was able to meet all the dosimetric requirements and to correct for a misdosage of 13% of the dose prescription on the prostate. For the first clinical case, the standard planning method caused underdosage of the seminal vesicles, respectively by 5% and 4% of the prescribed dose, when the position changes for the target were correctly taken into account. The proposed adaptive planning method corrected any possible missed target coverage, reducing at the same time the dose on the OARs. For the second clinical case, both with the standard planning strategy and with the isocenter shift correction target coverage was significantly worsened (in particular uniformity) and some organs exceeded some toxicity objectives. While with our approach, the most uniform coverage for the target was produced and systematically the lowest toxicity values for the organs at risk were achieved. In our proof of principle study, the adaptive planning method performed better than the standard planning and the isocenter shift methods for prostate EBRT. It improved the coverage of the treatment volumes and lowered the dose to the OARs. This planning method is particularly promising for hypofractionated IMRT treatments in which a higher precision and control on dose deposition are needed. Further studies will be performed to test more extensively the proposed adaptive planning method and to evaluate it at a full clinical level.