Purpose Automated segmentation of anatomical structures in medical image analysis is a prerequisite for autonomous diagnosis as well as various computer and robot aided interventions. Recent methods based on deep convolutional neural networks (CNN) have outperformed former heuristic methods. However, those methods were primarily evaluated on rigid, real-world environments. In this study, existing segmentation methods were evaluated for their use on a new dataset of transoral endoscopic exploration. Methods Four machine learning based methods SegNet, UNet, ENet and ErfNet were trained with supervision on a novel 7-class dataset of the human larynx. The dataset contains 536 manually segmented images from two patients during laser incisions. The Intersection-over-Union (IoU) evaluation metric was used to measure the accuracy of each method. Data augmentation and network ensembling were employed to increase segmentation accuracy. Stochastic inference was used to show uncertainties of the individual models. Patient-to-patient transfer was investigated using patient-specific fine-tuning. Results In this study, a weighted average ensemble network of UNet and ErfNet was best suited for the segmentation of laryngeal soft tissue with a mean IoU of 84.7 %. The highest efficiency was achieved by ENet with a mean inference time of 9.22 ms per image. It is shown that 10 additional images from a new patient are sufficient for patient-specific fine-tuning. Conclusion CNN-based methods for semantic segmentation are applicable to endoscopic images of laryngeal soft tissue. The segmentation can be used for active constraints or to monitor morphological changes and autonomously detect pathologies. Further improvements could be achieved by using a larger dataset or training the models in a self-supervised manner on additional unlabeled data.

No abstract

No abstract

Associate Editor Ka-Wai Kwok oversaw the review of this article.

Purpose Laser ablation of hard tissue is not completely understood until now and not modeled for computer-assisted microsurgery. A precise planning and simulation is an essential step toward the usage of microsurgical laser bone ablation in the operating room. Methods Planning the volume for laser bone ablation is based on geometrical definitions. Shape and volume of the removed bone by single laser pulses were measured with a confocal microscope for modeling the microsurgical ablation. To remove the planned volume and to achieve smooth surfaces, a simulation of the laser pulse distribution is developed.A talk and a proceedings contribution with the German title Planung und Simulation von mikrochirurgischer Laserknochenablation [1] was presented at curac.08 in Leipzig, Germany. ResultsThe confocal measurements show a clear dependency from laser energy and resulting depth. Twodimensional Gaussian functions are fitting in these craters. Exemplarily three ablation layers were planned, simulated, executed and verified. Conclusions To model laser bone ablation in microsurgery the volume and shape of each laser pulse should be known and considered in the process of ablation planning and simulation.

An automatic laser focus adjustment on tissue surfaces based on stereoscopic scene information is feasible and has the potential to become an effective methodology for optimal ablation. Laser-to-camera registration facilitates advanced surgical planning for prospective user interfaces and augmented reality extensions.

The presented algorithm successfully extends piecewise affine deformation tracking to stereo vision taking the epipolar constraint into account. Improved surgical performance as demonstrated for laser incision planning highlights the potential of presented method regarding further applications in computer-assisted surgery.

No abstract