This study evaluates the performance of deep learning models in the prediction of the end time of procedures performed in the cardiac catheterization laboratory (cath lab). We employed only the clinical phases derived from video analysis as input to the algorithms. Our results show that InceptionTime and LSTM-FCN yielded the most accurate predictions. InceptionTime achieves Mean Absolute Error (MAE) values below 5 min and Symmetric Mean Absolute Percentage Error (SMAPE) under 6% at 60-s sampling intervals. In contrast, LSTM with attention mechanism and standard LSTM models have higher error rates, indicating challenges in handling both long-term and short-term dependencies. CNN-based models, especially InceptionTime, excel at feature extraction across different scales, making them effective for time-series predictions. We also analyzed training and testing times. CNN models, despite higher computational costs, significantly reduce prediction errors. The Transformer model has the fastest inference time, making it ideal for real-time applications. An ensemble model derived by averaging the two best performing algorithms reported low MAE and SMAPE, although needing longer training. Future research should validate these findings across different procedural contexts and explore ways to optimize training times without losing accuracy. Integrating these models into clinical scheduling systems could improve efficiency in cath labs. Our research demonstrates that the models we implemented can form the basis of an automated tool, which predicts the optimal time to call the next patient with an average error of approximately 30 s. These findings show the effectiveness of deep learning models, especially CNN-based architectures, in accurately predicting procedure end times.

Surgical workflow analysis optimizes efficiency, resource use, and patient safety in catheterization labs. Traditional manual methods are labour-intensive and inconsistent, driving the need for automated solutions that utilize machine learning and computer vision. This thesis introduces an explainable two-stage model for workflow analysis using ceiling-mounted cameras. The approach combines a YOLOv8 object detection model with a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM). The first stage detects key objects for input into the second stage, where the GMM-HMM infers workflow phases by modelling spatial and temporal dynamics for real-time classification. Validation on two hospital datasets achieves 95.2% accuracy for the RdGG dataset and 95.4% for HH Tampere, demonstrating generalizability across environments. Experimental results show high accuracy in detecting workflow phases, highlighting explainability and robustness. The combined efficiencies of YOLOv8 and GMM-HMM allow for precise phase transition identification. The model's real-time application and adaptability across hospitals suggest its clinical implementation potential. This research furthers automated workflow analysis by enhancing interpretability and adaptability. Future work aims to improve robustness against occlusions, integrate audio data, and explore applications in other surgical settings.

Objective: Detecting the cancerous growth margin and achieving a negative margin is one of the challenges that surgeons face during cancer procedures. A smart electrosurgical knife with integrated optical fibers has been designed previously to enable real-time use of diffuse reflectance spectroscopy for intraoperative margin assessment. In this paper, the thermal effect of the electrosurgical knife on tissue sensing is investigated. Methods: Porcine tissues and phantoms were used to investigate the performance of the smart electrosurgical knife after electrosurgery. The fat-to-water content ratio (F/W-ratio) served as the discriminative parameter for distinguishing tissues and tissue mimicking phantoms with varying fat content. The F/W-ratio of tissues and phantoms was measured with the smart electrosurgical knife before and after 14 minutes of electrosurgery. Additionally, a layered porcine tissue and phantom were sliced and measured from top to bottom with the smart electrosurgical knife. Results: Mapping the thermal activity of the electrosurgical knife's electrode during animal tissue electrosurgery revealed temperatures exceeding 400 °C. Electrosurgery for 14 minutes had no impact on the device's accurate detection of the F/W-ratio. The smart electrosurgical knife enables real-time tissue detection and predicts the fat content of the next layer from 4 mm ahead. Conclusion: The design of the smart electrosurgical knife outlined in this paper demonstrates its potential utility for tissue detection during electrosurgery. Significance: In the future, the smart electrosurgical knife could be a valuable intraoperative margin assessment tool, aiding surgeons in detecting tumor borders and achieving negative margins.

Our research highlights the potential of Diffuse Reflectance Spectroscopy (DRS) in detecting cortical breaches during pedicle screw placement. We propose a sideways-looking fiber-optic probe, integrating diffuse light emission with both forward and sideways light collection. Experiments on an optical tissue phantom validate the probe’s potential to distinguish bone tissues and provide real-time guidance for spine surgery. Our findings prove that DRS with diffuse emission can detect perpendicular breaches, and demonstrate how the integration of a 45^◦ slanted fiber coated with gold enables parallel breach detection, advancing spine surgery by allowing for accurate pedicle screw placement.

Deep learning-based object detectors, while offering exceptional performance, are data-dependent and can suffer from generalization issues. In this work, we investigated deep neural networks for detecting people and medical instruments for the vision-based workflow analysis system inside Catheterization Laboratories (Cath Labs). The central problem explored in this paper is the fact that the performance of the detector can degrade drastically if it is trained and tested on data from different Cath Labs. Our research aimed to investigate the underlying causes of this specific performance degradation and find solutions to mitigate this issue. We employed the YOLOv8 object detector and created datasets from clinical procedures recorded at Reinier de Graaf Hospital (RdGG) and Philips Best Campus, supplemented with publicly accessible images. Through a series of experiments complemented by data visualization, we discovered that the performance degradation primarily stems from data distribution shifts in the feature space. Notably, the object detector trained on non-sensitive online images can generalize to unseen Cath Labs, outperforming the model trained on a procedure recording from a different Cath Lab. The detector trained on the online images achieved an mAP@0.5 of 0.517 on the RdGG dataset. Furthermore, by switching to the most suitable camera for each object in the Cath Lab, the multi-camera system can further improve the detection performance significantly. An aggregated L-camera mAP@0.5 of 0.679 is achieved for single-object classes on the RdGG dataset.

Introduction: Anastomotic leakage after gastrointestinal surgery has a high impact on patient's quality of life and its origin is associated with inadequate perfusion. Imaging photoplethysmography (iPPG) is a noninvasive imaging technique that measures blood-volume changes in the microvascular tissue bed and detects changes in tissue perfusion. Materials and methods: Intraoperative iPPG imaging was performed in 29 patients undergoing an open segment resection of the small intestine or colon. During each surgery, imaging was performed on fully perfused (true positives) and ischemic intestines (true negatives) and the anastomosis (unknowns). Imaging consisted of a 30-s video from which perfusion maps were extracted, providing detailed information about blood flow within the intestine microvasculature. To detect the predictive capabilities of iPPG, true positive and true negative perfusion conditions were used to develop two different perfusion classification methods. Results: iPPG-derived perfusion parameters were highly correlated with perfusion—perfused or ischemic—in intestinal tissues. A perfusion confidence map distinguished perfused and ischemic intestinal tissues with 96% sensitivity and 86% specificity. Anastomosis images were scored as adequately perfused in 86% of cases and 14% inconclusive. The cubic-Support Vector Machine achieved 90.9% accuracy and an area under the curve of 96%. No anastomosis-related postoperative complications were encountered in this study. Conclusions: This study shows that noninvasive intraoperative iPPG is suitable for the objective assessment of small intestine and colon anastomotic perfusion. In addition, two perfusion classification methods were developed, providing the first step in an intestinal perfusion prediction model.

Accuracy in spinal fusion varies greatly depending on the experience of the physician. Real-time tissue feedback with diffuse reflectance spectroscopy has been shown to provide cortical breach detection using a conventional probe with two parallel fibers. In this study, Monte Carlo simulations and optical phantom experiments were conducted to investigate how angulation of the emitting fiber affects the probed volume to allow for the detection of acute breaches. Difference in intensity magnitude between cancellous and cortical spectra increased with the fiber angle, suggesting that outward angulated fibers are beneficial in acute breach scenarios. Proximity to the cortical bone could be detected best with fibers angulated at θf = 45° for impending breaches between θp = 0° and θp = 45°. An orthopedic surgical device comprising a third fiber perpendicular to the device axis could thus cover the full impending breach range from θp = 0° to θp = 90°.

Introduction: Steering light is relevant to many medical applications that require tissue illumination, sensing, or modification. To control the propagation direction of light beams, a great variety of innovative fiber-optic medical devices have been designed. Areas covered: This review provides a comprehensive overview of the patent literature on light beam control in fiber-optic medical devices. The Web of Science Derwent Innovation Index database was scanned, and 81 patents on fiber-optic devices published in the last 20 years (2001–2021) were retrieved and categorized based on the working principle to steer light (refraction/reflection, scattering, diffraction) and the design strategy that was employed (within fiber, at fiber end, outside fiber). Expert opinion: Patents describing medical devices were found for all categories, except for generating diffraction at the fiber end surface. The insight in the different designs reveals that there are still several opportunities to design innovative devices that can collect light at an angle off-axis, reduce the angular distribution of light, or split light into multiple beams.

During oncological surgery, it can be challenging to identify the tumor and establish adequate resection margins. This study proposes a new two-layer approach in which diffuse reflectance spectroscopy (DRS) is used to predict the top layer thickness and classify the layers in two-layered phantom and animal tissue. Using wavelet-based and peak-based DRS spectral features, the proposed method could predict the top layer thickness with an accuracy of up to 0.35 mm. In addition, the tissue types of the first and second layers were classified with an accuracy of 0.95 and 0.99. Distinguishing multiple tissue layers during spectral analyses results in a better understanding of more complex tissue structures encountered in surgical practice.

Emerging intraoperative tumor margin assessment techniques require the development of more complex and reliable organ phantoms to assess the performance of the technique before its translation into the clinic. In this work, electrically conductive tissue-mimicking materials (TMMs) based on fat, water and agar/gelatin were produced with tunable optical properties. The composition of the phantoms allowed for the assessment of tumor margins using diffuse reflectance spectroscopy, as the fat/water ratio served as a discriminating factor between the healthy and malignant tissue. Moreover, the possibility of using polyvinyl alcohol (PVA) or transglutaminase in combination with fat, water and gelatin for developing TMMs was studied. The diffuse spectral response of the developed phantom materials had a good match with the spectral response of porcine muscle and adipose tissue, as well as in vitro human breast tissue. Using the developed recipe, anatomically relevant heterogeneous breast phantoms representing the optical properties of different layers of the human breast were fabricated using 3D-printed molds. These TMMs can be used for further development of phantoms applicable for simulating the realistic breast conserving surgery workflow in order to evaluate the intraoperative optical-based tumor margin assessment techniques during electrosurgery.