Search

This work addresses the automatic segmentation of the joint capsule in ultrasound images of the metacarpophalangeal joint using an adapted version of the well known UNet model. These images are used in the diagnosis of rheumatic diseases, one of the main causes of impairment and pain in developed countries. The identification of the joint capsule gives important clues about the presence or Rheumatoid Arthritis. This structure can be used to extract metrics to help quantify the disease stage and progression. The solution proposed here has the potential to reduce the burden on the radiologists as well as the subjectivity of the diagnosis by providing quantitative measurements, such as the synovitis area. The proposed approach was compared with two other works present in the literature. Results show that our solution outperforms the two reference methods with 90% of the joint capsules identified with a DICE higher than 0.67.

Rheumatic heart disease remains a major burden in the developing countries. The World Heart Federation proposed guidelines for the echocardiographic detection of the disease, in which the mitral leaflets’ morphology assessment is a key indicator. The drawback is that these guidelines are dependent on the clinician experience. To overcome this limitation, we propose an automatic segmentation of the mitral leaflets using a new method based on convolutional neural network, specifically the UNet architecture. The results indicate a median DICE coefficient of 0.74 in PLAX and 0.79 in A4C for the anterior mitral leaflet segmentation, while median DICE of 0.60 in PLAX and 0.69 A4C are met for the posterior leaflet. A visual evaluation of this segmentation approach by two cardiologists is in line with the numerical results. The false detection due to overestimation and artifacts remains an issue to be addressed in the future.

Rheumatic heart disease is the serious consequence of repeated episodes of acute rheumatic fever. It is the major cause of heart valve damage resulting in morbidity and mortality. Its early detection is considered vital to control the disease's progression. The key manifestations that are visible in the early stages of this disease are changes in the thickness, shape and mobility of the mitral valve leaflets. Echocardiography based screening is sensitive enough to identify these changes in early stages of the disease. In this work, an automatic approach is proposed to measure, quantify and analyze the thickness of the anterior mitral leaflet, in an echocardiographic video. The shape of the anterior mitral leaflet is simplified via morphological skeletonization and spline modelling to get the central line of the leaflet. To analyze the overall thickness from the tip to its base, the anterior mitral leaflet is divided into four quartiles. In ach quartile the thickness is measured as the length of the line segment resulting from the intersection of the contour with the normal direction of the central point of each quartile. Finally, the thickness is analyzed by measuring the variance per quartile, divided by leaflet position (open, straight and closed). The comparison between the normal and pathological leaflets are also presented, exhibiting statistical significant differences in all quartiles, especially near the tip of the leaflet.

Haptically enabled hands-on or tele-operated surgical robotic systems provide a unique opportunity to integrate pre- and intra-operative information into physical actions through active constraints (also known as virtual fixtures). In many surgical procedures, including cardiac interventions, where physiological motion complicates tissue manipulation, dynamic active constraints can improve the performance of the intervention in terms of safety and accuracy. The non-energy-storing class of dynamic guidance constraints attempt to assist the clinician in following a reference path, while guaranteeing that the control system will not generate undesired motion due to stored potential energy. An important aspect that has not received much attention from the researchers is that while these methods help increase the performance, they should by no means distract the user systematically. In this paper, a viscosity-based dynamic guidance constraint is introduced that continuously redirects the tool's motion towards the reference path. The proportionality and continuity of generated forces make the method less distracting and subjectively appealing. The performance is validated and compared with two existing non-energy-storing methods through extensive experimentation.