Publications

Acute respiratory distress syndrome often necessitates prolonged periods of mechanical ventilation for patient management. Therefore, it is crucial to make appropriate decisions regarding extubation to prevent potential harm to patients and avoid the associated risks of reintubation and extubation cycles. One atypical form of acute respiratory distress syndrome is associated with COVID-19, impacting patients admitted to the intensive care unit. This study presents the design of two classifiers: the first employs machine learning techniques, while the second utilizes a convolutional neural network. Their purpose is to assess whether a patient can safely be disconnected from a mechanical ventilator following a spontaneous breathing test. The machine learning algorithm uses descriptors derived from the variability of time-frequency representations computed with the non-uniform fast Fourier transform. These representations are applied to time series data, which consist of markers extracted from the electrocardiographic and respiratory flow signals sourced from the Weandb database. The input image for the convolutional neural network is formed by combining the spectrum of the RR signal and the spectrum of two parameters recorded from the respiratory flow signal, calculated using non-uniform fast Fourier transform. Three pre-trained network architectures are analyzed: Googlenet, Alexnet and Resnet-18. The best model is obtained with a CNN with the Resnet-18 architecture, presenting an accuracy of 90.1 +/- 4.3%.

JTD Keywords: Convolutional neural networ, Extubation, Instantaneous frequency, Mechanical ventilation, Mechanically ventilated patients, Non-uniform fast fourier transform, Variabilit, Weaning

Providing force feedback as relevant information in current Robot-Assisted Minimally Invasive Surgery systems constitutes a technological challenge due to the constraints imposed by the surgical environment. In this context, force estimation techniques represent a potential solution, enabling to sense the interaction forces between the surgical instruments and soft-tissues. Specifically, if visual feedback is available for observing soft-tissues’ deformation, this feedback can be used to estimate the forces applied to these tissues. To this end, a force estimation model, based on Convolutional Neural Networks and Long-Short Term Memory networks, is proposed in this work. This model is designed to process both, the spatiotemporal information present in video sequences and the temporal structure of tool data (the surgical tool-tip trajectory and its grasping status). A series of analyses are carried out to reveal the advantages of the proposal and the challenges that remain for real applications. This research work focuses on two surgical task scenarios, referred to as pushing and pulling tissue. For these two scenarios, different input data modalities and their effect on the force estimation quality are investigated. These input data modalities are tool data, video sequences and a combination of both. The results suggest that the force estimation quality is better when both, the tool data and video sequences, are processed by the neural network model. Moreover, this study reveals the need for a loss function, designed to promote the modeling of smooth and sharp details found in force signals. Finally, the results show that the modeling of forces due to pulling tasks is more challenging than for the simplest pushing actions.

JTD Keywords: Convolutional neural networks, Force estimation, LSTM networks, Robotic surgery