Search

In the above article [1], we found major issues with the data we used. Specifically, we received data from [2] for five distinct tissues, with ten specimens per tissue. However, upon closer examination, we realized that the data for these specimens were not unique; rather, they were scaled variations derived from a single specimen. As a result, our training, testing, and validation datasets were not independent, leading to an artificially high accuracy rate of 100%.

Using a laser for cutting bones instead of the traditional saws improves a patient’s healing process. Additionally, the laser has the potential to reduce the collateral damage to the surrounding tissue if appropriately applied. This can be achieved by building additional sensing elements besides the laser itself into an endoscope. To this end, we use a microsecond pulsed Erbium-doped Yttrium Aluminium Garnet (Er:YAG) laser to cut bones. During ablation, each pulse emits an acoustic shock wave that is captured by an air-coupled transducer. In our research, we use the data from these acoustic waves to predict the depth of the cut during the ablation process. We use a Neural Network (NN) to estimate the depth, where we use one or multiple consecutive measurements of acoustic waves. The NN outperforms the base-line method that assumes a constant ablation rate with each pulse to predict the depth. The results are evaluated and compared against the ground-truth depth measurements from Optical Coherence Tomography (OCT) images that measure the depth in real-time during the ablation process.

Today’s mechanical tools for bone cutting (osteotomy) lead to mechanical trauma that prolong the healing process. Medical device manufacturers continuously strive to improve their tools to minimize such trauma. One example of such a new tool and procedure is minimally invasive surgery with laser as the cutting element. This setup allows for tissue ablation using laser light instead of mechanical tools, which reduces the post-surgery healing time. During surgery, a reliable feedback system is crucial to avoid collateral damage to the surrounding tissues. Therefore, we propose a tissue classification method that analyzes the acoustic waves produced during laser ablation and show its applicability in an ex-vivo experiment. The ablation process with a microsecond pulsed Erbium-doped Yttrium Aluminium Garnet (Er:YAG) laser produces acoustic waves that we captured with an air-coupled transducer. Consequently, we used these captured waves to classify five porcine tissue types: hard bone, soft bone, muscle, fat, and skin tissue. For automated tissue classification of the measured acoustic waves, we propose three Neural Network (NN) approaches: A Fully-connected Neural Network (FcNN), a one-dimensional Convolutional Neural Network (CNN), and a Recurrent Neural Network (RNN). The time- and the frequency-dependent parts of the measured waves’ pressure variation were used as separate inputs to train and validate the designed NNs. In a final step, we used Grad-CAM to find the frequencies’ activation map and conclude that the low frequencies are the most important ones for this classification task. In our experiments, we achieved an accuracy of 100% for the five tissue types for all the proposed NNs. We tested the different classifiers for their robustness and concluded that using frequency-dependent data together with a FcNN is the most robust approach.

Countless low-surface brightness objects - including spiral galaxies, dwarf galaxies, and noise patterns - have been detected in recent large surveys. Classically, astronomers visually inspect those detections to distinguish between real low-surface brightness galaxies and artefacts. Employing the Dark Energy Survey (DES) and machine learning techniques, Tanoglidis et al. (2020) have shown how this task can be automatically performed by computers. Here, we build upon their pioneering work and further separate the detected low-surface brightness galaxies into spirals, dwarf ellipticals, and dwarf irregular galaxies. For this purpose, we have manually classified 5567 detections from multi-band images from DES and searched for a neural network architecture capable of this task. Employing a hyperparameter search, we find a family of convolutional neural networks achieving similar results as with the manual classification, with an accuracy of 85% for spiral galaxies, 94% for dwarf ellipticals, and 52% for dwarf irregulars. For dwarf irregulars - due to their diversity in morphology - the task is difficult for humans and machines alike. Our simple architecture shows that machine learning can reduce the workload of astronomers studying large data sets by orders of magnitudes, as will be available in the near future with missions such as Euclid.