Patient-specific placental vessel segmentation with limited data.

A major obstacle in applying machine learning for medical fields is the disparity between the data distribution of the training images and the data encountered in clinics. This phenomenon can be explained by inconsistent acquisition techniques and large variations across the patient spectrum. The result is poor translation of the trained models to the clinic, which limits their implementation in medical practice. Patient-specific trained networks could provide a potential solution. Although patient-specific approaches are usually infeasible because of the expenses associated with on-the-fly labeling, the use of generative adversarial networks enables this approach. This study proposes a patient-specific approach based on generative adversarial networks. In the presented training pipeline, the user trains a patient-specific segmentation network with extremely limited data which is supplemented with artificial samples generated by generative adversarial models. This approach is demonstrated in endoscopic video data captured during fetoscopic laser coagulation, a procedure used for treating twin-to-twin transfusion syndrome by ablating the placental blood vessels. Compared to a standard deep learning segmentation approach, the pipeline was able to achieve an intersection over union score of 0.60 using only 20 annotated images compared to 100 images using a standard approach. Furthermore, training with 20 annotated images without the use of the pipeline achieves an intersection over union score of 0.30, which, therefore, corresponds to a 100% increase in performance when incorporating the pipeline. A pipeline using GANs was used to generate artificial data which supplements the real data, this allows patient-specific training of a segmentation network. We show that artificial images generated using GANs significantly improve performance in vessel segmentation and that training patient-specific models can be a viable solution to bring automated vessel segmentation to the clinic.

Autonomous Magnetic Navigation in Endoscopic Image Mosaics.

Endoscopes navigate within the human body to observe anatomical structures with minimal invasiveness. A major shortcoming of their use is their narrow field-of-view during navigation in large, hollow anatomical regions. Mosaics of endoscopic images can provide surgeons with a map of the tool's environment. This would facilitate procedures, improve their efficiency, and potentially generate better patient outcomes. The emergence of magnetically steered endoscopes opens the way to safer procedures and creates an opportunity to provide robotic assistance both in the generation of the mosaic map and in navigation within this map. This paper proposes methods to autonomously navigate magnetic endoscopes to 1) generate endoscopic image mosaics and 2) use these mosaics as user interfaces to navigate throughout the explored area. These are the first strategies, which allow autonomous magnetic navigation in large, hollow organs during minimally invasive surgeries. The feasibility of these methods is demonstrated experimentally both in vitro and ex vivo in the context of the treatment of twin-to-twin transfusion syndrome. This minimally invasive procedure is performed in utero and necessitates coagulating shared vessels of twin fetuses on the placenta. A mosaic of the vasculature in combination with autonomous navigation has the potential to significantly facilitate this challenging surgery.

Chapter 7: Technological Aids and Coronal Caries.

In recent decades, dentistry has developed significantly in all areas. While in the past, caries was mainly treated operatively, the today's management has shifted toward noninvasive, minimal invasive, and, only if needed, invasive treatment options. Aiming at enabling the most noninvasive or conservative treatment option requires early caries detection, which, however, remains challenging. The progression of early or noncavitated caries lesions can nowadays be successfully controlled, as well as lesions arrested by oral hygiene procedures combined with the use of fluorides, sealants, or resin infiltration. Methods such as near-infrared light transillumination, fibre-optic transillumination, digital fibre-optic transillumination, laser fluorescence, or quantitative light fluorescence measurements were introduced in the dental market to provide X-ray-free caries detection, assessment, and monitoring. For approximal surfaces that are not directly visible, bitewing radiography is still the standard in detecting caries lesions. The use of artificial intelligence has become the most recent technological aid for the detection of caries lesions on bitewing radiographs and clinical images and has to be understood as an emerging technology, which requires extensive research in the future. The aim of this chapter is to give an overview of different possibilities to detect coronal caries lesions and suggestions of how to improve this process.

Thermoset Shape Memory Polymer Variable Stiffness 4D Robotic Catheters.

Variable stiffness catheters are typically composed of an encapsulated core. The core is usually composed of a low melting point alloy (LMPA) or a thermoplastic polymer (TP). In both cases, there is a need to encapsulate the core with an elastic material. This imposes a limit to the volume of variable stiffness (VS) material and limits miniaturization. This paper proposes a new approach that relies on the use of thermosetting materials. The variable stiffness catheter (VSC) proposed in this work eliminates the necessity for an encapsulation layer and is made of a unique biocompatible thermoset polymer with an embedded heating system. This significantly reduces the final diameter, improves manufacturability, and increases safety in the event of complications. The device can be scaled to sub-millimeter dimensions, while maintaining a high stiffness change. In addition, integration into a magnetic actuation system allows for precise actuation of one or multiple tools.

A Submillimeter Continuous Variable Stiffness Catheter for Compliance Control.

Minimally invasive robotic surgery often requires functional tools that can change their compliance to adapt to the environment and surgical needs. This paper proposes a submillimeter continuous variable stiffness catheter equipped with a phase-change alloy that has a high stiffness variation in its different states, allowing for rapid compliance control. Variable stiffness is achieved through a variable phase boundary in the alloy due to a controlled radial temperature gradient. This catheter can be safely navigated in its soft state and rigidified to the required stiffness during operation to apply a desired force at the tip. The maximal contact force that the catheter applies to tissue can be continuously modified by a factor of 400 (≈20 mN-8 N). The catheter is equipped with a magnet and a micro-gripper to perform a fully robotic ophthalmic minimally invasive surgery on an eye phantom by means of an electromagnetic navigation system.

Perforation forces of the intact porcine anterior lens capsule.

During the first step of cataract surgery, the lens capsule is perforated and a circular hole is created with a sharp instrument, a procedure called capsulorhexis. To develop automated systems that can assist ophthalmologists during capsulorhexis, the forces required must be quantified. This study investigates perforation forces of the central anterior lens capsule in porcine eyes, which are used as a conservative model for the human eye. A micro-mechanical characterisation method is presented that measures capsular bag perforation forces with a high precision positioning and high-resolution force sensing system. The force during perforation of the anterior lens capsule was measured with various sized needles and indentation speeds and is found to be 15-35mN. A bio-mechanical model is identified that describes an exponential correlation between indentation force and depth, indicating strain hardening behaviour of the porcine anterior lens capsule.

Toothbrushing after an erosive attack: will waiting avoid tooth wear?

The purpose of this study was to determine if storage for up to 4 h in human saliva results in a decrease of erosive tooth wear (ETW) and in an increase of surface microhardness (SMH) of enamel samples after an erosive attack with subsequent abrasion. Furthermore, we determined the impact of individual salivary parameters on ETW and SMH. Enamel samples were distributed into five groups: group 1 had neither erosion nor saliva treatment; groups 2-5 were treated with erosion, then group 2 was placed in a humid chamber and groups 3-5 were incubated in saliva for 30 min, 2 h, and 4 h, respectively. After erosion and saliva treatments, all groups were treated with abrasion. Surface microhardness and ETW were measured before and after erosion, incubation in saliva, and abrasion. Surface microhardness and ETW showed significant changes throughout the experiment: SMH decreased and ETW increased in groups 2-5, regardless of the length of incubation in saliva. The results of groups 3-5 (exposed to saliva) were not significantly different from those of group 2 (not exposed to saliva). Exposure of eroded enamel to saliva for up to 4 h was not able to increase SMH or reduce ETW. However, additional experiments with artificial saliva without proteins showed protection from erosive tooth wear. The recommendation to postpone toothbrushing of enamel after an erosive attack should be reconsidered.