Clustering Methods for Vibro-Acoustic Sensing Features as a Potential Approach to Tissue Characterisation in Robot-Assisted Interventions

This article provides a comprehensive analysis of the feature extraction methods applied to vibro-acoustic signals (VA signals) in the context of robot-assisted interventions. The primary objective is to extract valuable information from these signals to understand tissue behaviour better and build upon prior research. This study is divided into three key stages: feature extraction using the Cepstrum Transform (CT), Mel-Frequency Cepstral Coefficients (MFCCs), and Fast Chirplet Transform (FCT); dimensionality reduction employing techniques such as Principal Component Analysis (PCA), t-Distributed Stochastic Neighbour Embedding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP); and, finally, classification using a nearest neighbours classifier. The results demonstrate that using feature extraction techniques, especially the combination of CT and MFCC with dimensionality reduction algorithms, yields highly efficient outcomes. The classification metrics (Accuracy, Recall, and F1-score) approach 99%, and the clustering metric is 0.61. The performance of the CT-UMAP combination stands out in the evaluation metrics.

Contact Endoscopy - Narrow Band Imaging (CE-NBI) data set for laryngeal lesion assessment

The endoscopic examination of subepithelial vascular patterns within the vocal fold is crucial for clinicians seeking to distinguish between benign lesions and laryngeal cancer. Among innovative techniques, Contact Endoscopy combined with Narrow Band Imaging (CE-NBI) offers real-time visualization of these vascular structures. Despite the advent of CE-NBI, concerns have arisen regarding the subjective interpretation of its images. As a result, several computer-based solutions have been developed to address this issue. This study introduces the CE-NBI data set, the first publicly accessible data set that features enhanced and magnified visualizations of subepithelial blood vessels within the vocal fold. This data set encompasses 11144 images from 210 adult patients with pathological vocal fold conditions, where CE-NBI images are annotated using three distinct label categories. The data set has proven invaluable for numerous clinical assessments geared toward diagnosing laryngeal cancer using Optical Biopsy. Furthermore, given its versatility for various image analysis tasks, we have devised and implemented diverse image classification scenarios using Machine Learning (ML) approaches to address critical clinical challenges in assessing laryngeal lesions.

Thyroid Nodule Detection and Region Estimation in Ultrasound Images: A Comparison between Physicians and an Automated Decision Support System Approach

BACKGROUND

Thyroid nodules are very common. In most cases, they are benign, but they can be malignant in a low percentage of cases. The accurate assessment of these nodules is critical to choosing the next diagnostic steps and potential treatment. Ultrasound (US) imaging, the primary modality for assessing these nodules, can lack objectivity due to varying expertise among physicians. This leads to observer variability, potentially affecting patient outcomes.

PURPOSE

This study aims to assess the potential of a Decision Support System (DSS) in reducing these variabilities for thyroid nodule detection and region estimation using US images, particularly in lesser experienced physicians.

METHODS

Three physicians with varying levels of experience evaluated thyroid nodules on US images, focusing on nodule detection and estimating cystic and solid regions. The outcomes were compared to those obtained from a DSS for comparison. Metrics such as classification match percentage and variance percentage were used to quantify differences.

RESULTS

Notable disparities exist between physician evaluations and the DSS assessments: the overall classification match percentage was just 19.2%. Individually, Physicians 1, 2, and 3 had match percentages of 57.6%, 42.3%, and 46.1% with the DSS, respectively. Variances in assessments highlight the subjectivity and observer variability based on physician experience levels.

CONCLUSIONS

The evident variability among physician evaluations underscores the need for supplementary decision-making tools. Given its consistency, the CAD offers potential as a reliable "second opinion" tool, minimizing human-induced variabilities in the critical diagnostic process of thyroid nodules using US images. Future integration of such systems could bolster diagnostic precision and improve patient outcomes.

Vibro-acoustic sensing of tissue-instrument-interactions allows a differentiation of biological tissue in computerised palpation

BACKGROUND

The shift towards minimally invasive surgery is associated with a significant reduction of tactile information available to the surgeon, with compensation strategies ranging from vision-based techniques to the integration of sensing concepts into surgical instruments. Tactile information is vital for palpation tasks such as the differentiation of tissues or the characterisation of surfaces. This work investigates a new sensing approach to derive palpation-related information from vibration signals originating from instrument-tissue-interactions.

METHODS

We conducted a feasibility study to differentiate three non-animal and three animal tissue specimens based on palpation of the surface. A sensor configuration was mounted at the proximal end of a standard instrument opposite the tissue-interaction point. Vibro-acoustic signals of 1680 palpation events were acquired, and the time-varying spectrum was computed using Continuous-Wavelet-Transformation. For validation, nine spectral energy-related features were calculated for a subsequent classification using linear Support Vector Machine and k-Nearest-Neighbor.

RESULTS

Indicators derived from the vibration signal are highly stable in a set of palpations belonging to the same tissue specimen, regardless of the palpating subject. Differences in the surface texture of the tissue specimens reflect in those indicators and can serve as a basis for differentiation. The classification following a supervised learning approach shows an accuracy of >93.8% for the three-tissue classification tasks and decreases to 78.8% for a combination of all six tissues.

CONCLUSIONS

Simple features derived from the vibro-acoustic signals facilitate the differentiation between biological tissues, showing the potential of the presented approach to provide information related to the interacting tissue. The results encourage further investigation of a yet little-exploited source of information in minimally invasive surgery.

Vibro-Acoustic Sensing of Instrument Interactions as a Potential Source of Texture-Related Information in Robotic Palpation

The direct tactile assessment of surface textures during palpation is an essential component of open surgery that is impeded in minimally invasive and robot-assisted surgery. When indirectly palpating with a surgical instrument, the structural vibrations from this interaction contain tactile information that can be extracted and analysed. This study investigates the influence of the parameters contact angle α and velocity v→ on the vibro-acoustic signals from this indirect palpation. A 7-DOF robotic arm, a standard surgical instrument, and a vibration measurement system were used to palpate three different materials with varying α and v→. The signals were processed based on continuous wavelet transformation. They showed material-specific signatures in the time-frequency domain that retained their general characteristic for varying α and v→. Energy-related and statistical features were extracted, and supervised classification was performed, where the testing data comprised only signals acquired with different palpation parameters than for training data. The classifiers support vector machine and k-nearest neighbours provided 99.67% and 96.00% accuracy for the differentiation of the materials. The results indicate the robustness of the features against variations in the palpation parameters. This is a prerequisite for an application in minimally invasive surgery but needs to be confirmed in realistic experiments with biological tissues.

A concept to combine a gamma probe with ultrasound imaging for improved localization of sentinel lymph nodes: a feasibility study of the concept

This paper presents the proof-of-concept study of an adaptor allowing the combination of a gamma probe with ultrasound (US) imaging, intending to improve the detectability of sentinel lymph nodes (SLNs). The performance of the adaptor in US imaging, in terms of depth of penetration and distance accuracy, and gamma scanning, in terms of sensitivity and spatial resolution, was investigated. We observed that the quality of the US imaging through the adaptor was promising and close to that of normal US imaging. However, the performance of the gamma probe through the adaptor was fairly poor, necessitating the improvement in the design of the adaptor for better gamma scanning. This study shall provide a basis for the development of a handheld gamma-US scanner for interventional procedures and small field-of-view (FOV) imaging in the future.

Thyroid Nodule Region Estimation using Auto-Regressive Modelling and Machine Learning

Ultrasound (US) imaging is used for the diagnosis and also evaluation of thyroid nodules. A Thyroid Imaging Reporting and Data System (TIRADS) is used for the risk stratification of thyroid nodules through US images. The composition of thyroid nodules plays an important role in the risk-stratification process. The percentages of cystic and solid components in a thyroid nodule are one of the features that are can be indicative of the risk of malignancy. In this work, we attempt to classify and estimate solid and cystic regions within nodules. 20x20 texture patches were extracted from solid and cystic regions and converted into signals. These signals are decomposed into low, mid, and high-frequency bands using Continuous Wavelet Transform (CWT). A total of 36 features were extracted from the decomposed signals using Auto- Regressive Modeling. The features were fed into three different Machine Learning (ML) algorithms (Artificial Neural Networks, K-Nearest Neighbors, and Random Forest Classifier) to provide us with a classification of solid versus cystic regions in thyroid nodule US images. The Random Forest Classifier obtained an Accuracy, Sensitivity, and Specificity of 90.41%, 99% and 91% respectively which was the highest among the three chosen ML algorithms. Additionally, the output from the classification phase was also be used to determine the percentage of cystic and solid regions with a given thyroid nodule US image.

Towards Identification of Biometric Properties in Blood Flow Sounds Using Neural Networks and Saliency Maps

In previous work, we demonstrated the potential of blood flow sounds for biometric authentication acquired by a custom-built auscultation device. For this purpose, we calculated the frequency spectrum for each cardiac cycle represented within the measurements based on continuous wavelet transform. The resulting spectral images were used to train a convolutional neural network based on measurements from seven users. In this work, we investigate which areas of those images are relevant for the network to correctly identify a user. Since they describe the frequencies’ energy within a cardiac cycle, this information can be used to gain knowledge on biometric properties within the signal. Therefore, we calculate the saliency maps for each input image and investigate their mean for each user, opening perspectives for further investigation of the spectral information that was found to be potentially relevant.

Surgeons' requirements for a surgical support system to improve laparoscopic access

Creating surgical access is a critical step in laparoscopic surgery. Surgeons have to insert a sharp instrument such as the Veress needle or a trocar into the patient’s abdomen until the peritoneal cavity is reached. They solely rely on their experience and distorted tactile feedback in that process, leading to a complication rate as high as 14% of all cases. Recent studies have shown the feasibility of surgical support systems that provide intraoperative feedback regarding the insertion process to improve laparoscopic access outcomes. However, to date, the surgeons’ requirements for such support systems remain unclear. This research article presents the results of an explorative study that aimed to acquire data about the information that helps surgeons improve laparoscopic access outcomes. The results indicate that feedback regarding the reaching of the peritoneal cavity is of significant importance and should be presented visually or acoustically. Finally, a solution should be straightforward and intuitive to use, should support or even improve the clinical workflow, but also cheap enough to facilitate its usage rate. While this study was tailored to laparoscopic access, its results also apply to other minimally invasive procedures.

Surface and Event Characterization - Proximal Audio Sensing to improve Manual and Robotic Device Interventions

Minimal-invasive procedures come with significant advantages for the patient. They also come with problems as the navigation/guidance of the devices to a target location is either based on pre-operatively acquired images and then performed free-hand or is accompanied by intraoperative imaging such as MRI or CT that is expensive, complicated and produces artifacts. Using robotic systems for moving and guiding these interventional and therapeutic devices adds additional issues like lack of palpation sensation and missing tissue feedback. While it is possible to add sensors to the distal tip, this creates other obstacles concerning reduced functionality, cables, sterility issues and added complexity and cost. We propose to use a proximally attached audio sensor to record the tissue tool interaction and provide real-time feedback to the clinician. This paper reports on initial attempts to use this technology with robotic arms for surface characterization and interventional vascular procedures that gain increased attention in combination with robotic devices. In summary, Proximal Audio Sensing could be a versatile, cost-effective and powerful tool to guide minimally invasive needle interventions and enable (semi-) autonomous robot-assisted surgery.

The Advances in Computer Vision That Are Enabling More Autonomous Actions in Surgery: A Systematic Review of the Literature

This is a review focused on advances and current limitations of computer vision (CV) and how CV can help us obtain to more autonomous actions in surgery. It is a follow-up article to one that we previously published in Sensors entitled, “Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?” As opposed to that article that also discussed issues of machine learning, deep learning and natural language processing, this review will delve deeper into the field of CV. Additionally, non-visual forms of data that can aid computerized robots in the performance of more autonomous actions, such as instrument priors and audio haptics, will also be highlighted. Furthermore, the current existential crisis for surgeons, endoscopists and interventional radiologists regarding more autonomy during procedures will be discussed. In summary, this paper will discuss how to harness the power of CV to keep doctors who do interventions in the loop.

Deep Convolution Neural Network for Laryngeal Cancer Classification on Contact Endoscopy-Narrow Band Imaging

(1) Background: Contact Endoscopy (CE) and Narrow Band Imaging (NBI) are optical imaging modalities that can provide enhanced and magnified visualization of the superficial vascular networks in the laryngeal mucosa. The similarity of vascular structures between benign and malignant lesions causes a challenge in the visual assessment of CE-NBI images. The main objective of this study is to use Deep Convolutional Neural Networks (DCNN) for the automatic classification of CE-NBI images into benign and malignant groups with minimal human intervention. (2) Methods: A pretrained Res-Net50 model combined with the cut-off-layer technique was selected as the DCNN architecture. A dataset of 8181 CE-NBI images was used during the fine-tuning process in three experiments where several models were generated and validated. The accuracy, sensitivity, and specificity were calculated as the performance metrics in each validation and testing scenario. (3) Results: Out of a total of 72 trained and tested models in all experiments, Model 5 showed high performance. This model is considerably smaller than the full ResNet50 architecture and achieved the testing accuracy of 0.835 on the unseen data during the last experiment. (4) Conclusion: The proposed fine-tuned ResNet50 model showed a high performance to classify CE-NBI images into the benign and malignant groups and has the potential to be part of an assisted system for automatic laryngeal cancer detection.

BODYTUNE: Multi Auscultation Device – Personal Health Parameter Monitoring at Home

Auscultation methods allow the non-invasive diagnosis of pathological conditions (e.g., of the lung, heart or blood vessels) based on sounds that the body produces (e.g., breathing, heartbeat, swallowing or the blood flow). Through regular homebased examinations and Big Data combined with Machine learning techniques like Deep Learning, these could help detect diseases in an early stage, thus preventing serious health conditions and subsequently ensuring optimal therapy through continuous monitoring. This paper presents BODYTUNE, a novel inexpensive multi-auscultation system that aims at providing a tool for establishing a baseline of audio signal derived classification parameters that could be used for the self-monitoring of personal health for everybody through the analysis of deviations from that baseline. In the future, Big Data analysis could additionally lead to prediction and early detection of disease events.

Vascular Auscultation of Carotid Artery: Towards Biometric Identification and Verification of Individuals

BACKGROUND

Biometric sensing is a security method for protecting information and property. State-of-the-art biometric traits are behavioral and physiological in nature. However, they are vulnerable to tampering and forgery.

METHODS

The proposed approach uses blood flow sounds in the carotid artery as a source of biometric information. A handheld sensing device and an associated desktop application were built. Between 80 and 160 carotid recordings of 11 s in length were acquired from seven individuals each. Wavelet-based signal analysis was performed to assess the potential for biometric applications.

RESULTS

The acquired signals per individual proved to be consistent within one carotid sound recording and between multiple recordings spaced by several weeks. The averaged continuous wavelet transform spectra for all cardiac cycles of one recording showed specific spectral characteristics in the time-frequency domain, allowing for the discrimination of individuals, which could potentially serve as an individual fingerprint of the carotid sound. This is also supported by the quantitative analysis consisting of a small convolutional neural network, which was able to differentiate between different users with over 95% accuracy.

CONCLUSION

The proposed approach and processing pipeline appeared promising for the discrimination of individuals. The biometrical recognition could clinically be used to obtain and highlight differences from a previously established personalized audio profile and subsequently could provide information on the source of the deviation as well as on its effects on the individual's health. The limited number of individuals and recordings require a study in a larger population along with an investigation of the long-term spectral stability of carotid sounds to assess its potential as a biometric marker. Nevertheless, the approach opens the perspective for automatic feature extraction and classification.

Carotid Sound Signal Artifact Detection based on Discrete Wavelet Transform Decomposition

Auscultation methods allow a non-invasive diagnosis of cardiovascular diseases like atherosclerosis based on blood flow sounds of the carotid arteries. Since this process is highly dependent on the clinician’s experience, it is of great interest to develop automated data processing techniques for objective assessment. We have recently proposed a computerassisted auscultation system that we use to acquire carotid blood flow sounds. In this work, we present an approach for detecting artifacts within the blood flow sound caused by swallowing or coughing events. For this purpose, we first decompose the signal using a discrete wavelet transform (DTW). Then, we compute an energy ratio between the DWT scales associated with the signal information with and without artifacts using a sliding window of 1 s length. Evaluation based on Kruskal-Wallis and Wilcoxon rank-sum tests shows a statistically significant difference (p-value<.0001) between the signal with and without artifact. Therefore, the proposed method allows the identification of the studied signal artifacts.

Artificial Intelligence Surgery: How Do We Get to Autonomous Actions in Surgery?

Most surgeons are skeptical as to the feasibility of autonomous actions in surgery. Interestingly, many examples of autonomous actions already exist and have been around for years. Since the beginning of this millennium, the field of artificial intelligence (AI) has grown exponentially with the development of machine learning (ML), deep learning (DL), computer vision (CV) and natural language processing (NLP). All of these facets of AI will be fundamental to the development of more autonomous actions in surgery, unfortunately, only a limited number of surgeons have or seek expertise in this rapidly evolving field. As opposed to AI in medicine, AI surgery (AIS) involves autonomous movements. Fortuitously, as the field of robotics in surgery has improved, more surgeons are becoming interested in technology and the potential of autonomous actions in procedures such as interventional radiology, endoscopy and surgery. The lack of haptics, or the sensation of touch, has hindered the wider adoption of robotics by many surgeons; however, now that the true potential of robotics can be comprehended, the embracing of AI by the surgical community is more important than ever before. Although current complete surgical systems are mainly only examples of tele-manipulation, for surgeons to get to more autonomously functioning robots, haptics is perhaps not the most important aspect. If the goal is for robots to ultimately become more and more independent, perhaps research should not focus on the concept of haptics as it is perceived by humans, and the focus should be on haptics as it is perceived by robots/computers. This article will discuss aspects of ML, DL, CV and NLP as they pertain to the modern practice of surgery, with a focus on current AI issues and advances that will enable us to get to more autonomous actions in surgery. Ultimately, there may be a paradigm shift that needs to occur in the surgical community as more surgeons with expertise in AI may be needed to fully unlock the potential of AIS in a safe, efficacious and timely manner.

Cyclist Effort Features: A Novel Technique for Image Texture Characterization Applied to Larynx Cancer Classification in Contact Endoscopy-Narrow Band Imaging

BACKGROUND

Feature extraction is an essential part of a Computer-Aided Diagnosis (CAD) system. It is usually preceded by a pre-processing step and followed by image classification. Usually, a large number of features is needed to end up with the desired classification results. In this work, we propose a novel approach for texture feature extraction. This method was tested on larynx Contact Endoscopy (CE)-Narrow Band Imaging (NBI) image classification to provide more objective information for otolaryngologists regarding the stage of the laryngeal cancer.

METHODS

The main idea of the proposed methods is to represent an image as a hilly surface, where different paths can be identified between a starting and an ending point. Each of these paths can be thought of as a Tour de France stage profile where a cyclist needs to perform a specific effort to arrive at the finish line. Several paths can be generated in an image where different cyclists produce an average cyclist effort representing important textural characteristics of the image. Energy and power as two Cyclist Effort Features (CyEfF) were extracted using this concept. The performance of the proposed features was evaluated for the classification of 2701 CE-NBI images into benign and malignant lesions using four supervised classifiers and subsequently compared with the performance of 24 Geometrical Features (GF) and 13 Entropy Features (EF).

RESULTS

The CyEfF features showed maximum classification accuracy of 0.882 and improved the GF classification accuracy by 3 to 12 percent. Moreover, CyEfF features were ranked as the top 10 features along with some features from GF set in two feature ranking methods.

CONCLUSION

The results prove that CyEfF with only two features can describe the textural characterization of CE-NBI images and can be part of the CAD system in combination with GF for laryngeal cancer diagnosis.

Auscultation System for Acquisition of Vascular Sounds - Towards Sound-Based Monitoring of the Carotid Artery

Introduction

Atherosclerotic diseases of the carotid are a primary cause of cerebrovascular events such as stroke. For the diagnosis and monitoring angiography, ultrasound- or magnetic resonance-based imaging is used which requires costly hardware. In contrast, the auscultation of carotid sounds and screening for bruits - audible patterns related to turbulent blood flow - is a simple examination with comparably little technical demands. It can indicate atherosclerotic diseases and justify further diagnostics but is currently subjective and examiner dependent.

Methods

We propose an easy-to-use computer-assisted auscultation system for a stable and reproducible acquisition of vascular sounds of the carotid. A dedicated skin-transducer-interface was incorporated into a handheld device. The interface comprises two bell-shaped structures, one with additional acoustic membrane, to ensure defined skin contact and a stable propagation path of the sound. The device is connected wirelessly to a desktop application allowing real-time visualization, assessment of signal quality and input of supplementary information along with storage of recordings in a database. An experimental study with 5 healthy subjects was conducted to evaluate usability and stability of the device. Five recordings per carotid served as data basis for a wavelet-based analysis of the stability of spectral characteristics of the recordings.

Results

The energy distribution of the wavelet-based stationary spectra proved stable for measurements of a particular carotid with the majority of the energy located between 3 and 40 Hz. Different spectral properties of the carotids of one individual indicate the presence of sound characteristics linked to the particular vessel. User-dependent parameters such as variations of the applied contact pressure appeared to have minor influence on the general stability.

Conclusion

The system provides a platform for reproducible carotid auscultation and the creation of a database of pathological vascular sounds, which is a prerequisite to investigate sound-based vascular monitoring.

Thyroid Nodule Classification for Physician Decision Support Using Machine Learning-Evaluated Geometric and Morphological Features

The classification of thyroid nodules using ultrasound (US) imaging is done using the Thyroid Imaging Reporting and Data System (TIRADS) guidelines that classify nodules based on visual and textural characteristics. These are composition, shape, size, echogenicity, calcifications, margins, and vascularity. This work aims to reduce subjectivity in the current diagnostic process by using geometric and morphological (G-M) features that represent the visual characteristics of thyroid nodules to provide physicians with decision support. A total of 27 G-M features were extracted from images obtained from an open-access US thyroid nodule image database. 11 significant features in accordance with TIRADS were selected from this global feature set. Each feature was labeled (0 = benign and 1 = malignant) and the performance of the selected features was evaluated using machine learning (ML). G-M features together with ML resulted in the classification of thyroid nodules with a high accuracy, sensitivity and specificity. The results obtained here were compared against state-of the-art methods and perform significantly well in comparison. Furthermore, this method can act as a computer aided diagnostic (CAD) system for physicians by providing them with a validation of the TIRADS visual characteristics used for the classification of thyroid nodules in US images.

Surgical audio information as base for haptic feedback in robotic-assisted procedures

This work aims to demonstrate the feasibility that haptic information can be acquired from a da Vinci robotic tool using audio sensing according to sensor placement requirements in a real clinical scenario. For that, two potential audio sensor locations were studied using an experimental setup for performing, in a repeatable way, interactions of a da Vinci forceps with three different tissues. The obtained audio signals were assessed in terms of their resulting signal-to-noise-ratio (SNR) and their capability to distinguish between different tissues. A spectral energy distribution analysis using Discrete Wavelet Transformation was performed to extract signal signatures from the tested tissues. Results show that a high SNR was obtained in most of the audio recordings acquired from both studied positions. Additionally, evident spectral energy-related patterns could be extracted from the audio signals allowing us to distinguish between different palpated tissues.

Endoscopic filter fluorometer for detection of accumulation of Protoporphyrin IX to improve photodynamic diagnostic (PDD)

Photodynamic diagnostic (PDD) is an optical enhancement option for the endoscope to support the detection of cancer, for example in the bladder. In real application PDD efficiency suffers due to the complex accumulation of the photosensitizing drug inside the tumor and the associated processes of heme syntheses to create the fluorescent components needed. To optimize the diagnostic outcome of PDD it would be helpful to predict the optimal time for diagnosis based on measurable precursors. In a previous cell study, we proposed a new filter fluorometer to image the accumulation of the precursors Coproporphyrin III (CP-III) and Uroporphyrin III (UP-III) that metabolize to Protoporphyrin IX (PP-IX) later. This accumulation process can be used to predict the optimal time slot for diagnostic imaging. Therefore, a new filter system was designed to distinguish between CP-III and PP-IX. In this work we tested this filter system in combination with a standard PDD endoscopic imaging system. Goal of this study was to prove the technical feasibility in a non-patient setup to prepare a later clinical study.

Frequency and average gray-level information for thermal ablation status in ultrasound B-Mode sequences

During thermal ablation in a target tissue the information about temperature is crucial for decision making of successful therapy. An observable temporal and spatial temperature propagation would give a visual feedback of irreversible cell damage of the target tissue. Potential temperature features in ultrasound (US) B-Mode image sequences during radiofrequency (RF) ablation in ex-vivo porcine liver were found and analysed. These features could help to detect the transition between reversible and irreversible damage of the ablated target tissue. Experimental RF ablations of ex-vivo porcine liver were imaged with US B-Mode imaging and image sequences were recorded. Temperature was simultaneously measured within the liver tissue around a bipolar RF needle electrode. In the B-Mode images, regions of interest (ROIs) around the centre of the measurement spots were analysed in post-processing using average gray-level (AVGL) compared against temperature. The pole of maximum energy level in the time-frequency domain of the AVGL changes was investigated in relation to the measured temperatures. Frequency shifts of the pole were observed which could be related to transitions between the states of tissue damage.

Acoustic sensing of tissue-tool interactions – potential applications in arthroscopic surgery

Arthroscopic surgery is a technically challenging but common minimally invasive procedure with a long learning curve and a high incidence of iatrogenic damage. These damages can occur due to the lack of feedback and supplementary information regarding tissue-instrumentcontact during surgery. Deliberately performed interactions can be used however to obtain clinically relevant information, e.g. when a surgeon uses the tactile feedback to assess the condition of articular cartilage. Yet, the perception of such events is highly subjective. We propose a novel proximally attached sensing concept applied to arthroscopic surgery to allow an objective characterization and utilization of interactions. It is based on acoustic emissions which originate from tissue-instrument-contact, that propagate naturally via the instrument shaft and that can be obtained by a transducer setup outside of the body. The setup was tested on its ability to differentiate various conditions of articular cartilage. A femoral head with varying grades of osteoarthritic cartilage was tapped multiple times ex-vivo with a conventional Veress needle with a sound transducer attached at the outpatient end. A wavelet-based processing of the obtained signals and subsequent analysis of distribution of spectral energy showed the potential of tool-tissue-interactions to characterize different cartilage conditions. The proposed concept needs further evaluation with a dedicated design of the palpation tool and should be tested in realistic arthroscopic scenarios.

Surgical Audio Guidance: Feasibility Check for Robotic Surgery Procedures

In robot-assisted procedures, the surgeon controls the surgical instruments from a remote console, while visually monitoring the procedure through the endoscope. There is no haptic feedback available to the surgeon, which impedes the assessment of diseased tissue and the detection of hidden structures beneath the tissue, such as vessels. Only visual clues are available to the surgeon to control the force applied to the tissue by the instruments, which poses a risk for iatrogenic injuries. Additional information on haptic interactions of the employed instruments and the treated tissue that is provided to the surgeon during robotic surgery could compensate for this deficit. Acoustic emissions (AE) from the instrument/tissue interactions, transmitted by the instrument are a potential source of this information. AE can be recorded by audio sensors that do not have to be integrated into the instruments, but that can be modularly attached to the outside of the instruments shaft or enclosure. The location of the sensor on a robotic system is essential for the applicability of the concept in real situations. While the signal strength of the acoustic emissions decreases with distance from the point of interaction, an installation close to the patient would require sterilization measures. The aim of this work is to investigate whether it is feasible to install the audio sensor in non-sterile areas far away from the patient and still be able to receive useful AE signals. To determine whether signals can be recorded at different potential mounting locations, instrument/tissue interactions with different textures were simulated in an experimental setup. The results showed that meaningful and valuable AE can be recorded in the non-sterile area of a robotic surgical system despite the expected signal losses.

Manual versus Automatic Classification of Laryngeal Lesions based on Vascular Patterns in CE+NBI Images

Longitudinal and perpendicular changes in the blood vessels of the vocal fold have been related to the advancement from benign to malignant laryngeal cancer stages. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) provides intraoperative realtime visualization of vascular pattern in Larynx. The evaluation of these vascular patterns in CE+NBI images is a subjective process leading to differentiation difficulty and subjectivity between benign and malignant lesions. The main objective of this work is to compare multi-observer classification versus automatic classification of laryngeal lesions. Six clinicians visually classified CE+NBI images into benign and malignant lesions. For the automatic classification of CE+NBI images, we used an algorithm based on characterizing the level of the vessel’s disorder. The results of the manual classification showed that there is no objective interpretation, leading to difficulties to visually distinguish between benign and malignant lesions. The results of the automatic classification of CE+NBI images on the other hand showed the capability of the algorithm to solve these issues. Based on the observed results we believe that, the automatic approach could be a valuable tool to assist clinicians to classifying laryngeal lesions.

Patch Based Texture Classification of Thyroid Ultrasound Images using Convolutional Neural Network

Ultrasound (US) is an affordable and important imaging modality in medical imaging without potential hazards for patients and medical practitioners as compared to computed tomography which uses X-rays, magnetic resonance imaging which uses magnetic field and radio waves that could heat up the patient's body during long examinations, nuclear imaging, etc. Texture classification of anatomical structures in US images is an essential step for disease diagnosis and monitoring. In this work, we employed a convolutional neural network to segment thyroid gland in US images. This is particularly important for thyroid diseases diagnosis as they involve changes in the shape and size of the thyroid over time. The training of the Convolutional Neural Network (CNN) was not done directly on the acquired US images but on texture database that is created by dividing the thyroid US images of size 760 × 500 pixels into smaller texture patches of size 20 × 20 pixels. We obtained a Dice coefficient (DC) of 0.876 and Hausdorff Distance (HD) of 7.3 using the trained CNN that classifies the thyroid tissues as thyroid or non-thyroid. This approach was compared to the classic image processing approaches like active contours with edges (ACWE), graph cut (GC) and pixel-based classifier (PBC) which obtained a DC of 0.805, 0.745 and 0.666 respectively and Volumetric and Mass-Spring Models which obtained a HD of 11.1 and 9.8 respectively.

Cardiotocograph Data Classification Improvement by Using Empirical Mode Decomposition

This work proposes to study the fetal heart rate (FHR) signal based on information about its dynamics as a signal resulting from the modulation by the autonomic nervous system. The analysis is performed using the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique. The main idea is to extract a set of signal features based on that technique and also conventional time-domain features proposed in the literature in order to study their performance by using a support vector machine (SVM) as a classifier. As a hypothesis, we postulate that by including CEEMDAN based features, the classification performance should improve compared with the performance achieved by conventional features. The proposed method has been evaluated using real FHR data extracted from the open access CTU-UHB database. Results show that the classification performance improved from 67, 6% using only conventional features, to 71, 7% by incorporating CEEMDAN based features.

A Preliminary Study on Automatic Characterization and Classification of Vascular Patterns of Contact Endoscopy Images

The structure and organization of blood vessels in the vocal fold go through changes during the advancement from healthy to benign and further on to malignant stages. Contact Endoscopy (CE) is an optical technique providing real-time information related to the vascular structure of laryngeal mucosa. However, this technique comes with subjectivity in the interpretation of vascular patterns. In this study, a novel automated approach is proposed for vessel pattern charac-terization and classification of larynx CE + Narrow Band Imaging (NBI) images. This method is mainly based on the computation of indicators related to the level of disorder of vessels. 12 features were extracted from the indicators and were fed into two supervised classifiers. Linear Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) showed an accuracy of 95.76% and 93.92% for vascular patterns and 86.04% and 82.23% for larynx histopathologies classification, respectively. These promising results show that the proposed method can potentially solve the subjectivity issues of CE.

Evaluation of Vascular Patterns Using Contact Endoscopy and Narrow-Band Imaging (CE-NBI) for the Diagnosis of Vocal Fold Malignancy

The endoscopic detection of perpendicular vascular changes (PVC) of the vocal folds has been associated with vocal fold cancer, dysplastic lesions, and papillomatosis, according to a classification proposed by the European Laryngological Society (ELS). The combination of contact endoscopy with narrow-band imaging (NBI-CE) allows intraoperatively a highly contrasted, real-time visualization of vascular changes of the vocal folds. Aim of the present study was to determine the association of PVC to specific histological diagnoses, the level of interobserver agreement in the detection of PVC, and their diagnostic effectiveness in diagnosing laryngeal malignancy. The evaluation of our data confirmed the association of PVC to vocal fold cancer, dysplastic lesions, and papillomatosis. The level of agreement between the observers in the identification of PVC was moderate for the less-experienced observers and almost perfect for the experienced observers. The identification of PVC during NBI-CE proved to be a valuable indicator for diagnosing malignant and premalignant lesions.

Design of an Auscultation System for Phonoangiography and Monitoring of Carotid Artery Diseases

Cerebrovascular diseases such as stenosis of the carotid artery are accountable for about 1 million death per year across Europe. Diagnostic tools like US, angiography or MRI require specific hardware and highly depend on the experience of the examining clinician. In contrast auscultation with a stethoscope can be used to screen for bruits - audible vascular sounds associated with turbulent blood flow. Dynamical changes in the flow due to pathological narrowing of the vessel can indicate the need for additional diagnostic investigations. A reliable auscultation setup is prerequisite to ensure high signal quality, adequate processing and the objective evaluation of a still subjectively assessed audible signal. We propose a computer assisted auscultation device for the characterisation of carotid bruits to facilitate the assessment of long-term changes in the vessel condition. Main goal of this work are design considerations regarding the mechanical interface of the proposed system to the skin. An experimental setup was used to compare the signal quality and morphology of different setups to a digital stethoscope. A combined system with two different interface configurations is proposed, current limitations of the system and potential improvements are discussed.

Novel Ultrasound Texture Based Similarity Metric Using Autoregressive Modelling

Designing an ultrasound (US) specific similarity metric is essential in integrating advanced techniques like image segmentation and registration to US based interventional procedures. Applying conventional similarity metrics to ultrasound images is hampered by intrinsic noise patterns in an US image. In this work, we propose a texture based similarity metric (TexSimAR) using Autoregressive (AR) modelling. The key idea is to treat an US image as data resulting from a dynamical process which can be parametrically modelled. Using this approach it is possible to compute a parametric spectrum of individual US images and subsequently use it to estimate a similarity value between them. For evaluation, we used thyroid US images and similarity values were calculated between thyroid and non-thyroid regions. A cost function was designed to compare TexSimAR with other conventional similarity metrics. TexSimAR clearly distinguished between thyroid and non-thyroid regions outperfoming the conventional similarity metrics.

Higher Order Statistical Analysis for Thyroid Texture Classification and Segmentation in 2D ultrasound Images

Ultrasound (US) imaging is one of the most cost-effective imaging modality that utilizes sound waves for generating medical images of anatomical structure. However, the presence of speckle noise and low contrast in the US images makes it difficult to use for proper classification of anatomical structures in clinical scenarios. Hence, it is important to devise a method that is robust and accurate even in the presence of speckle noise and is not affected by the low image contrast. In this work, a novel approach for thyroid texture characterization based on extracting features utilizing higher order spectral analysis (HOSA) was used. A Support Vector Machine (SVM) was applied on the extracted features to classify the thyroid texture. Since HOSA is a well suited technique for processing non-Gaussian data involving non-linear dynamics, good classification of thyroid texture can be obtained in US images as they also contain non-Gaussian Speckle noise and nonlinear characteristics. A final accuracy of 93.27%, sensitivity of 0.92 and specificity of 0.62 were obtained using the proposed approach.

Novel Similarity Metric for Image-Based Out-Of-Plane Motion Estimation in 3D Ultrasound

Over the past decade, Freehand 3D Ultrasound(US) reconstruction using only image information has become a widely researched topic because it eliminates the need for an external tracking system and provides real-time volumetric information. But most of the state-of-art methods are inhibited by their inability to find a simple and robust similarity metric that could learn and estimate the spatial transformation between two US slices in a US sweep. In this work, we propose a novel similarity metric (TexSimAR), which computes the similarity value between two consecutive US images by correlating the parametric representation of the image-texture instead of the image itself. The purpose of this approach is to capture and compare the dynamics in the texture characteristics of two US images. We modelled these dynamics using a parametrical auto-regressive (AR) model. Experiments were performed on forearm datasets of three subjects. For every pair of consecutive US slices, we computed our TexSimAR similarity value and out-of-plane transformation from the ground truth to train a Support Vector Machine (SVM) based regression model, which was then used to predict the out-of-plane transformation with the similarity value as input. The proposed method shows promising results with predictions better than state-of-the-art methods even with 1/8^th of training data compared to other methods in the literature.

Improved Acquisition of Vibroarthrographic Signals of the Knee Joint

This paper presents an improved solution for vibroarthrographic measurements. Four different setups for sensor attachment to the knee were assessed with a focus on the stability and reproducibility of the measured signals. By means of power spectral density estimates, the main signal components were compared and afterwards evaluated by conducting a cross-correlation analysis.

Assessment of Sound Features for Needle Perforation Event Detection

This paper studies the use of non-invasive acoustic emission recordings for clinical device tracking. In particular, audio signals recorded at the proximal end of a needle are used to detect perforation events that occur when the needle tip crosses internal tissue layers.A comparative study is performed to assess the capacity of different features and envelopes in detecting perforation events. The results obtained from the considered experimental setup show a statistically significant correlation between the extracted envelopes and the perforation events, thus leading the way for future development of perforation detection algorithms.

Computer Assisted Auscultation System for Phonoangiography of the Carotid Artery

Cerebrovascular diseases such as stenosis, atherosclerosis or distention of the carotid artery are accountable for about 1 million death per year across Europe. Diagnostic tools like ultrasound imaging, angiography or magnetic resonance-based imaging require specific hardware and highly depend on the experience of the examining clinician. In contrast auscultation with a stethoscope can be used to screen for carotid bruits - audible vascular sounds associated with turbulent blood flow - a method called phonoangiography. A reliable auscultation setup is prerequisite to ensure high signal quality, adequate processing and the objective evaluation of this audible signal. We propose a computer assisted auscultation system for the acquisition of vascular sounds of the carotid. The system comprises of an auscultation device, a smartphone-based control application and cloud-based signal analysis and storage. It is designed to facilitate the objective assessment, screening and monitoring of long-term changes in the vessel condition based on auscultation of the carotid artery.

Audio waves and its loss of energy in puncture needles

The location of a puncture needle’s tip and the resistance of tissue against puncture are crucial information for clinicians during a percutaneous procedure. The tip location and needle alignment can be observed by image guidance. Tactile information caused by tissue resistance to rupture, allow clinicians the perception of structural changes during puncture. Nevertheless, this sense is individual and subjective. To improve percutaneous procedures, the implementation of transducers to enhance or complement the senses offer objective feedback to the user. Known approaches are e.g. based on integrated force sensors. However, this is connected to higher device costs, sterilization and certification issues. A recent publication shows the implementation of an audio transducer clipped at the proximal end of the needle. This sensor is capable of acquiring emitted sounds of the distal tiptissue interaction that are transmitted over the needle structure. The interpretation of the measured audio signals is highly depended on the transmission over the needle, the tissue and, the penetration depth. To evaluate the influence of these parameters, this work implements a simplified experimental setup in a controlled environment with a minimum of noise and without micro tremors induced by clinician’s hands. A steel rod simulating a needle is inserted into pork meat of different thickness. A controlled impact covering the needle’s tip mimics tissue contact. The resulting signals are recorded and analyzed for better understanding of the system.

Foetal heart rate assessment by empirical mode decomposition and spectral analysis

This paper focuses on studying the time-variant dynamics involved in the foetal heart rate (FHR) response resulting from the autonomic nervous system modulation. It provides a comprehensive analysis of such dynamics by relating the spectral information involved in the FHR signal with foetal physiological characteristics. This approach is based on two signal processing methods: the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and time-varying autoregressive (TV-AR) modelling. First, the CEEMDAN allows to decompose the signal into intrinsic mode functions (IMFs). Then, the TV-AR modelling allows to analyse their spectral dynamics. Results reveal that the IMFs can involve significant spectral information (p -value < 0.05) that can help to assess the foetal condition.

Texture differentiation using audio signal analysis with robotic interventional instruments

Robotic minimally invasive surgery (RMIS) has played an important role in the last decades. In traditional surgery, surgeons rely on palpation using their hands. However, during RMIS, surgeons use the visual-haptics technique to compensate the missing sense of touch. Various sensors have been widely used to retrieve this natural sense, but there are still issues like integration, costs, sterilization and the small sensing area that prevent such approaches from being applied. A new method based on acoustic emission has been recently proposed for acquiring audio information from tool-tissue interaction during minimally invasive procedures that provide user guidance feedback. In this work the concept was adapted for acquiring audio information from a RMIS grasper and a first proof of concept is presented. Interactions of the grasper with various artificial and biological texture samples were recorded and analyzed using advanced signal processing and a clear correlation between audio spectral components and the tested texture were identified.

Novel automated vessel pattern characterization of larynx contact endoscopic video images

Purpose

Contact endoscopy (CE) is a minimally invasive procedure providing real-time information about the cellular and vascular structure of the superficial layer of laryngeal mucosa. This method can be combined with optical enhancement methods such as narrow band imaging (NBI). However, these techniques have some problems like subjective interpretation of vascular patterns and difficulty in differentiation between benign and malignant lesions. We propose a novel automated approach for vessel pattern characterization of larynx CE + NBI images in order to solve these problems.

Methods

In this approach, five indicators were computed to characterize the level of vessel’s disorder based on evaluation of consistency of gradient and two-dimensional curvature analysis and then 24 features were extracted from these indicators. The method evaluated the ability of the extracted features to classify CE + NBI images based on the vascular pattern and based on the laryngeal lesions. Four datasets were generated from 32 patients involving 1485 images. The classification scenarios were implemented using four supervised classifiers.

Results

For classification of CE + NBI images based on the vascular pattern, polykernel support vector machine (SVM), SVM with radial basis function (RBF), k-nearest neighbor (kNN), and random forest (RF) show an accuracy of 97%, 96%, 96%, and 96%, respectively. For the classification based on the histopathology, Polykernel SVM showed an accuracy of 84%, 86% and 84%, RBF SVM showed an accuracy of 81%, 87% and 83%, kNN showed an accuracy of 89%, 87%, 91%, RF showed an accuracy of 90%, 88% and 91% for classification between benign histopathologies, between malignant histopathologies and between benign and malignant lesions, respectively.

Conclusion

These promising results show that the proposed method could solve the problem of subjectivity in interpretation of vascular patterns and also support the clinicians in the early detection of benign, pre-malignant and malignant lesions.

Parametrical modelling for texture characterization-A novel approach applied to ultrasound thyroid segmentation

Texture analysis is an important topic in Ultrasound (US) image analysis for structure segmentation and tissue classification. In this work a novel approach for US image texture feature extraction is presented. It is mainly based on parametrical modelling of a signal version of the US image in order to process it as data resulting from a dynamical process. Because of the predictive characteristics of such a model representation, good estimations of texture features can be obtained with less data than generally used methods require, allowing higher robustness to low Signal-to-Noise ratio and a more localized US image analysis. The usability of the proposed approach was demonstrated by extracting texture features for segmenting the thyroid in US images. The obtained results showed that features corresponding to energy ratios between different modelled texture frequency bands allowed to clearly distinguish between thyroid and non-thyroid texture. A simple k-means clustering algorithm has been used for separating US image patches as belonging to thyroid or not. Segmentation of thyroid was performed in two different datasets obtaining Dice coefficients over 85%.

Proximally placed signal acquisition sensoric for robotic tissue tool interactions

Robotic surgeries are still limited with respect to the surgeon’s natural senses. The tactile sense is exceptional important in conventional clinical procedures. To identify critical structures inside the tissue, palpation is a commonly used technique in conventional open surgeries. The underlying organ or pathological structures conditions (healthy, abnormally hard or soft) can for example be localized and assessed through this process. Palpation needs a tactile sense; however, that is commonly not available or limited in robotic surgeries. The palpation need was already addressed by several research groups that integrated complex sensor-feedback-systems into prototype surgical instruments for robotic systems. We propose a new technique to acquire data of the tissue tool interaction of the surgical instruments. The structure borne transmission path is used to measure acoustic emission (AE) at the outpatient (proximal) end of the instruments with the help of different sensors attached to the surface of the surgical tool. Initial tests were performed using a microphone in combination with a stethoscope. This setup showed promising results and a more integrated prototype was subsequently designed. A piezoelectric charge accelerometer was used as vibration sensor and compared to a MEMS microphone. A signal acquisition system was developed to acquire signals from both sensors in parallel. The sensors were then attached onto the shaft of a daVinci Prograsp Forceps instrument. According to the surgery observation, a series of simulated experiments was conducted. The tip of the grasper was swiped manually over a human subject’s dorsal and palmar hand side, lateral side of neck and over the carotid artery. Additionally, contact with soft tissue and other instruments were evaluated since these are events of interest during surgery. Advanced signal processing techniques allowed the identification and characterization of significant events such as palpation dynamics, contact and pulsation. Signals acquired by the MEMS microphone showed the most promising results. This approach will now be used to build a prototype for further evaluation in a clinical setup. The paper presents the first results that show that this novel technique can provide valuable information about the tool-tissue interaction in robotic surgery that typically can only be obtained through advanced distal sensor systems or actual human touch.

Vascular pattern detection and recognition in endoscopic imaging of the vocal folds

At present transoral laryngeal interventions are mainly observed and controlled by an external two dimensional direct microscopic view. This modality provides an overall view on the surgery situs in a straight line of sight. For treatment planning and appropriate documentation, an endoscopic inspection is mandatory prior to surgery. Nowadays a detailed endoscopic work-up of laryngeal lesions can be performed by contact endoscopy in combination with structure enhancement like Narrow Band Imaging. High resolution and magnification of up to 150 times provide detailed visualization of vascular structures and pathological changes of the tissue surface. In these procedures it is difficult however to localize the evaluated areas on large scale scenes like the microscopic view used for surgery. To provide a fast and easy image matching an automated vessel pattern recognition and allocation is presented. Endoscopic images depicting representative vessel structures of the vocal folds are selected out of contact endoscopy video scenes. These images are pre-processed for background homogenization. A Frangi Vessel Segmentation filter and morphological operations are used to extract the vessel structure and match it to the microscopic image. Using this method 4 detailed contact endoscopy images could be allocated in different scenes of the microscope video. This method can be used to simplify treatment planning and to prepare image data for documentation.

Foetal heart rate signal spectral analysis by using time-varying autoregressive modelling

During labour, foetal monitoring enables clinicians to prevent potential adverse outcomes, whose surveillance procedure is commonly based on analysis of cardiotocographic (CTG) signals. Unfortunately, this procedure is difficult because it involves human interpretation of highly complex signals. In order to improve the CTG assessment, different approaches based on signal processing techniques have been proposed. However, most of them do not consider the progression of the foetal response over time. In this work, we propose to study such progression along the foetal heart rate (FHR) signal by using spectral analysis based on time-varying autoregressive modelling. The main idea is to investigate if a particular FHR signal episode in the time-domain reflects dynamical changes in the frequency-domain that can help to assess the foetal condition. Results show that each FHR deceleration leaves a particular time-varying frequency signature described by the spectral energy components which could help to distinguish between a normal and a pathological foetus.

Anatomical Structure Segmentation in Ultrasound Volumes Using Cross Frame Belief Propagating Iterative Random Walks

Ultrasound (US) is widely used as a low-cost alternative to computed tomography or magnetic resonance and primarily for preliminary imaging. Since speckle intensity in US images is inherently stochastic, readers are often challenged in their ability to identify the pathological regions in a volume of a large number of images. This paper introduces a generalized approach for volumetric segmentation of structures in US images and volumes. We employ an iterative random walks (IRW) solver, a random forest learning model, and a gradient vector flow (GVF) based interframe belief propagation technique for achieving cross-frame volumetric segmentation. At the start, a weak estimate of the tissue structure is obtained using estimates of parameters of a statistical mechanics model of US tissue interaction. Ensemble learning of these parameters further using a random forest is used to initialize the segmentation pipeline. IRW is used for correcting the contour in various steps of the algorithm. Subsequently, a GVF-based interframe belief propagation is applied to adjacent frames based on the initialization of contour using information in the current frame to segment the complete volume by frame-wise processing. We have experimentally evaluated our approach using two different datasets. Intravascular ultrasound (IVUS) segmentation was evaluated using 10 pullbacks acquired at 20 MHz and thyroid US segmentation is evaluated on 16 volumes acquired at [Formula: see text] MHz. Our approach obtains a Jaccard score of [Formula: see text] for IVUS segmentation and [Formula: see text] for thyroid segmentation while processing each frame in [Formula: see text] for the IVUS and in [Formula: see text] for thyroid segmentation without the need of any computing accelerators such as GPUs.

Novel clinical device tracking and tissue event characterization using proximally placed audio signal acquisition and processing

We propose a new and complementary approach to image guidance for monitoring medical interventional devices (MID) with human tissue interaction and surgery augmentation by acquiring acoustic emission data from the proximal end of the MID outside the patient to extract dynamical characteristics of the interaction between the distal tip and the tissue touched or penetrated by the MID. We conducted phantom based experiments (n = 955) to show dynamic tool/tissue interaction during tissue needle passage (a) and vessel perforation caused by guide wire artery perforation (b). We use time-varying auto-regressive (TV-AR) modelling to characterize the dynamic changes and time-varying maximal energy pole (TV-MEP) to compute subsequent analysis of MID/tissue interaction characterization patterns. Qualitative and quantitative analysis showed that the TV-AR spectrum and the TV-MEP indicated the time instants of the needle path through different phantom objects (a) and clearly showed a perforation versus other generated artefacts (b). We demonstrated that audio signals acquired from the proximal part of an MID could provide valuable additional information to surgeons during minimally invasive procedures.

In-room ultrasound fusion combined with fully compatible 3D-printed holding arm - rethinking interventional MRI

There is no real need to discuss the potential advantages - mainly the excellent soft tissue contrast, nonionizing radiation, flow, and molecular information - of magnetic resonance imaging (MRI) as an intraoperative diagnosis and therapy system particularly for neurological applications and oncological therapies. Difficult patient access in conventional horizontal-field superconductive magnets, very high investment and operational expenses, and the need for special nonferromagnetic therapy tools have however prevented the widespread use of MRI as imaging and guidance tool for therapy purposes. The interventional use of MRI systems follows for the last 20+ years the strategy to use standard diagnostic systems and add more or less complicated and expensive components (eg, MRI-compatible robotic systems, specially shielded in-room monitors, dedicated tools and devices made from low-susceptibility materials, etc) to overcome the difficulties in the therapy process. We are proposing to rethink that approach using an in-room portable ultrasound (US) system that can be safely operated till 1 m away from the opening of a 3T imaging system. The live US images can be tracked using an optical inside-out approach adding a camera to the US probe in combination with optical reference markers to allow direct fusion with the MRI images inside the MRI suite. This leads to a comfortable US-guided intervention and excellent patient access directly on the MRI patient bed. This was combined with an entirely mechanical MRI-compatible 7 degrees of freedom holding arm concept, which shows that this test environment is a different way to create a cost-efficient and effective setup that combines the advantages of MRI and US by largely avoiding the drawbacks of current interventional MRI concepts.

Analysis of the foetal heart rate in cardiotocographic recordings through a progressive characterization of decelerations

The main purpose of this work is to propose a new method for characterization and visualization of FHR deceleration episodes in terms of their depth, length and location. This is performed through the estimation of a progressive baseline computed using a median filter allowing to identify and track the evolution of decelerations in cardiotocographic CTG recordings. The proposed method has been analysed using three representative cases of normal and pathological CTG recordings extracted from the CTU-UHB database freely available on the PhysioNet Website. Results show that both the progressive baseline and the parameterized deceleration episodes can describe different time-variant behaviour, whose characteristics and progression can help the observer to discriminate between normal and pathological FHR signal patterns. This opens perspectives for classification of non-reassuring CTG recordings as a sign of foetal acidemia.

Miniature CNT-based X-ray tube: assessment for use in intraoperative radiation therapy

Carbon nanotube (CNT) is a new technology used to generate gamma photons in X-ray tubes. CNTs, in comparison to other small X-ray sources, produce high X-ray intensities and as they are not based on a thermionic principle they considered cold electron sources with a very high conversion of electrical to photon energy. Their small size and other interesting properties could make them feasible for use in intraoperative radiation therapy applications. In this study, physical characteristics of the photon beam generated by the CNT-based X-ray source were assessed. A soft X-ray ionization chamber and a flat panel detector was used to measure dose and photon counts, respectively. The repetitively produced pulses had almost the same photon intensities with differences of less than 1% between them. For a typical selected pulse, the variation in the pulse amplitude was also insignificant, which shows a stable radiation exposure of the tube during the ON-mode. When moving from the center of the beam profile to the lateral distance of 25 mm, both intensity profile and dose profile showed a falling trend by a factor of almost 3 in the measured values.

We also tested the miniature tube with our novel radiation beam shaping collimator designed for a possible application to treat larynx tumor, which showed the possibility of interventional radiation therapy using this miniature source. An endoscopic camera attached to the system can also make it possible to optically visualize the radiation exposed area.

In conclusion, CNT-based X-ray source with suitable attached collimator to shape the beam of the source, seems to provide an opportunity to deliver radiation to a desired tumor area in minimally invasive image guided medical procedures mainly in the normal cavities of the body.