Microscope-integrated optical coherence tomography for in vivo human brain tumor detection with artificial intelligence.

OBJECTIVE: It has been shown that optical coherence tomography (OCT) can identify brain tumor tissue and potentially be used for intraoperative margin diagnostics. However, there is limited evidence on its use in human in vivo settings, particularly in terms of its applicability and accuracy of residual brain tumor detection (RTD). For this reason, a microscope-integrated OCT system was examined to determine in vivo feasibility of RTD after resection with automated scan analysis. METHODS: Healthy and diseased brain was 3D scanned at the resection edge in 18 brain tumor patients and investigated for its informative value in regard to intraoperative tissue classification. Biopsies were taken at these locations and labeled by a neuropathologist for further analysis as ground truth. Optical OCT properties were obtained, compared, and used for separation with machine learning. In addition, two artificial intelligence-assisted methods were utilized for scan classification, and all approaches were examined for RTD accuracy and compared to standard techniques. RESULTS: In vivo OCT tissue scanning was feasible and easily integrable into the surgical workflow. Measured backscattered light signal intensity, signal attenuation, and signal homogeneity were significantly distinctive in the comparison of scanned white matter to increasing levels of scanned tumor infiltration (p < 0.001) and achieved high values of accuracy (85%) for the detection of diseased brain in the tumor margin with support vector machine separation. A neuronal network approach achieved 82% accuracy and an autoencoder approach 85% accuracy in the detection of diseased brain in the tumor margin. Differentiating cortical gray matter from tumor tissue was not technically feasible in vivo. CONCLUSIONS: In vivo OCT scanning of the human brain has been shown to contain significant value for intraoperative RTD, supporting what has previously been discussed for ex vivo OCT brain tumor scanning, with the perspective of complementing current intraoperative methods for this purpose, especially when deciding to withdraw from further resection toward the end of the surgery.

Margin assessment during breast conserving surgery using diffuse reflectance spectroscopy.

Significance: During breast-conserving surgeries, it is essential to evaluate the resection margins (edges of breast specimen) to determine whether the tumor has been removed completely. In current surgical practice, there are no methods available to aid in accurate real-time margin evaluation. Aim: In this study, we investigated the diagnostic accuracy of diffuse reflectance spectroscopy (DRS) combined with tissue classification models in discriminating tumorous tissue from healthy tissue up to 2 mm in depth on the actual resection margin of in vivo breast tissue. Approach: We collected an extensive dataset of DRS measurements on ex vivo breast tissue and in vivo breast tissue, which we used to develop different classification models for tissue classification. Next, these models were used in vivo to evaluate the performance of DRS for tissue discrimination during breast conserving surgery. We investigated which training strategy yielded optimum results for the classification model with the highest performance. Results: We achieved a Matthews correlation coefficient of 0.76, a sensitivity of 96.7% (95% CI 95.6% to 98.2%), a specificity of 90.6% (95% CI 86.3% to 97.9%) and an area under the curve of 0.98 by training the optimum model on a combination of ex vivo and in vivo DRS data. Conclusions: DRS allows real-time margin assessment with a high sensitivity and specificity during breast-conserving surgeries.

Application of deep learning to pressure injury staging.

OBJECTIVE: Accurate assessment of pressure injuries (PIs) is necessary for a good outcome. Junior and non-specialist nurses have less experience with PIs and lack clinical practice, and so have difficulty staging them accurately. In this work, a deep learning-based system for PI staging and tissue classification is proposed to help improve its accuracy and efficiency in clinical practice, and save healthcare costs. METHOD: A total of 1610 cases of PI and their corresponding photographs were collected from clinical practice, and each sample was accurately staged and the tissues labelled by experts for training a Mask Region-based Convolutional Neural Network (Mask R-CNN, Facebook Artificial Intelligence Research, Meta, US) object detection and instance segmentation network. A recognition system was set up to automatically stage and classify the tissues of the remotely uploaded PI photographs. RESULTS: On a test set of 100 samples, the average precision of this model for stage recognition reached 0.603, which exceeded that of the medical personnel involved in the comparative evaluation, including an enterostomal therapist. CONCLUSION: In this study, the deep learning-based PI staging system achieved the evaluation performance of a nurse with professional training in wound care. This low-cost system could help overcome the difficulty of identifying PIs by junior and non-specialist nurses, and provide valuable auxiliary clinical information.

Test-time augmentation with synthetic data addresses distribution shifts in spectral imaging.

PURPOSE: Surgical scene segmentation is crucial for providing context-aware surgical assistance. Recent studies highlight the significant advantages of hyperspectral imaging (HSI) over traditional RGB data in enhancing segmentation performance. Nevertheless, the current hyperspectral imaging (HSI) datasets remain limited and do not capture the full range of tissue variations encountered clinically. METHODS: Based on a total of 615 hyperspectral images from a total of 16 pigs, featuring porcine organs in different perfusion states, we carry out an exploration of distribution shifts in spectral imaging caused by perfusion alterations. We further introduce a novel strategy to mitigate such distribution shifts, utilizing synthetic data for test-time augmentation. RESULTS: The effect of perfusion changes on state-of-the-art (SOA) segmentation networks depended on the organ and the specific perfusion alteration induced. In the case of the kidney, we observed a performance decline of up to 93% when applying a state-of-the-art (SOA) network under ischemic conditions. Our method improved on the state-of-the-art (SOA) by up to 4.6 times. CONCLUSION: Given its potential wide-ranging relevance to diverse pathologies, our approach may serve as a pivotal tool to enhance neural network generalization within the realm of spectral imaging.

Toward the use of diffuse reflection spectroscopy for intra-operative tissue discrimination during sarcoma surgery.

Significance: Accurately distinguishing tumor tissue from normal tissue is crucial to achieve complete resections during soft tissue sarcoma (STS) surgery while preserving critical structures. Incomplete tumor resections are associated with an increased risk of local recurrence and worse patient prognosis. Aim: We evaluate the performance of diffuse reflectance spectroscopy (DRS) to distinguish tumor tissue from healthy tissue in STSs. Approach: DRS spectra were acquired from different tissue types on multiple locations in 20 freshly excised sarcoma specimens. A k-nearest neighbors classification model was trained to predict the tissue types of the measured locations, using binary and multiclass approaches. Results: Tumor tissue could be distinguished from healthy tissue with a classification accuracy of 0.90, sensitivity of 0.88, and specificity of 0.93 when well-differentiated liposarcomas were included. Excluding this subtype, the classification performance increased to an accuracy of 0.93, sensitivity of 0.94, and specificity of 0.93. The developed model showed a consistent performance over different histological subtypes and tumor locations. Conclusions: Automatic tissue discrimination using DRS enables real-time intra-operative guidance, contributing to more accurate STS resections.

Review of machine learning for optical imaging of burn wound severity assessment.

Significance: Over the past decade, machine learning (ML) algorithms have rapidly become much more widespread for numerous biomedical applications, including the diagnosis and categorization of disease and injury. Aim: Here, we seek to characterize the recent growth of ML techniques that use imaging data to classify burn wound severity and report on the accuracies of different approaches. Approach: To this end, we present a comprehensive literature review of preclinical and clinical studies using ML techniques to classify the severity of burn wounds. Results: The majority of these reports used digital color photographs as input data to the classification algorithms, but recently there has been an increasing prevalence of the use of ML approaches using input data from more advanced optical imaging modalities (e.g., multispectral and hyperspectral imaging, optical coherence tomography), in addition to multimodal techniques. The classification accuracy of the different methods is reported; it typically ranges from ∼70% to 90% relative to the current gold standard of clinical judgment. Conclusions: The field would benefit from systematic analysis of the effects of different input data modalities, training/testing sets, and ML classifiers on the reported accuracy. Despite this current limitation, ML-based algorithms show significant promise for assisting in objectively classifying burn wound severity.

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.

Shedding Light on Colorectal Cancer: An In Vivo Raman Spectroscopy Approach Combined with Deep Learning Analysis.

Raman spectroscopy has emerged as a powerful tool in medical, biochemical, and biological research with high specificity, sensitivity, and spatial and temporal resolution. Recent advanced Raman systems, such as portable Raman systems and fiber-optic probes, provide the potential for accurate in vivo discrimination between healthy and cancerous tissues. In our study, a portable Raman probe spectrometer was tested in immunosuppressed mice for the in vivo localization of colorectal cancer malignancies from normal tissue margins. The acquired Raman spectra were preprocessed, and principal component analysis (PCA) was performed to facilitate discrimination between malignant and normal tissues and to highlight their biochemical differences using loading plots. A transfer learning model based on a one-dimensional convolutional neural network (1D-CNN) was employed for the Raman spectra data to assess the classification accuracy of Raman spectra in live animals. The 1D-CNN model yielded an 89.9% accuracy and 91.4% precision in tissue classification. Our results contribute to the field of Raman spectroscopy in cancer diagnosis, highlighting its promising role within clinical applications.

Mask region-based CNNs for cervical cancer progression diagnosis on pap smear examinations.

This research presents a novel approach for cervical cancer detection and segmentation using tissue images with multiple cells. The study employs a novel deep learning architecture based on Mask Region-Based Convolutional Neural Network (RCNN) and statistical analysis. This new architecture enables us to achieve a high percentage of detection and pix-to-pix area segmentation. A mean Average Precision (mAP) higher than 60% for 3-class and 5-class was achieved. In addition, higher F1-scores of 70% for 3-class and 5-class were obtained. This investigation is a collaborative work, where a medical consultant collected the samples from the Papanicolaou (Pap) Smear examination and labeled the cells presented to the liquid-based cytology (LBC). Furthermore, the online available benchmark data set, SIPaKMeD, was also utilized. Additionally, sample images from the Mendeley data set were also labeled by the trained medical consultant for comparison. The proposed scheme automatically generates a full report for a medical consultant to identify the location of the malicious cells in the given images and expedite the diagnosis and treatment process.

Hyperspectral placenta dataset: Hyperspectral image acquisition, annotations, and processing of biological tissues in microsurgical training.

The dataset consists of 101 hyperspectral images of four human placentas and six hyperspectral images of contrast dyes (i.e., indocyanine green and red and blue food colorant) that were captured in the range 515-900 nm, step = 5 nm. The hyperspectral images were manually annotated, delineating the key anatomical structures: arteries, veins, stroma, and the umbilical cord. Standard reference materials were used for flat-field correction. The dataset is instrumental for advancing machine-learning algorithms and automated classification of anatomical structures, particularly the classification of superficial and deep vessels and transparent tissue layers.

A deep-learning approach for myocardial fibrosis detection in early contrast-enhanced cardiac CT images.

Aims: Diagnosis of myocardial fibrosis is commonly performed with late gadolinium contrast-enhanced (CE) cardiac magnetic resonance (CMR), which might be contraindicated or unavailable. Coronary computed tomography (CCT) is emerging as an alternative to CMR. We sought to evaluate whether a deep learning (DL) model could allow identification of myocardial fibrosis from routine early CE-CCT images. Methods and results: Fifty consecutive patients with known left ventricular (LV) dysfunction (LVD) underwent both CE-CMR and (early and late) CE-CCT. According to the CE-CMR patterns, patients were classified as ischemic (n = 15, 30%) or non-ischemic (n = 35, 70%) LVD. Delayed enhancement regions were manually traced on late CE-CCT using CE-CMR as reference. On early CE-CCT images, the myocardial sectors were extracted according to AHA 16-segment model and labeled as with scar or not, based on the late CE-CCT manual tracing. A DL model was developed to classify each segment. A total of 44,187 LV segments were analyzed, resulting in accuracy of 71% and area under the ROC curve of 76% (95% CI: 72%-81%), while, with the bull's eye segmental comparison of CE-CMR and respective early CE-CCT findings, an 89% agreement was achieved. Conclusions: DL on early CE-CCT acquisition may allow detection of LV sectors affected with myocardial fibrosis, thus without additional contrast-agent administration or radiational dose. Such tool might reduce the user interaction and visual inspection with benefit in both efforts and time.

Fiber optic probe-based ATR-FTIR spectroscopy for rapid breast cancer detection: A pilot study.

Breast cancer diagnosis is crucial for timely treatment and improved outcomes. This paper proposes a novel approach for rapid breast cancer diagnosis using optical fiber probe-based attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy from 750 to 4000 cm-1 . The technique enables direct analysis of tissue samples, eliminating the need for microtome sectioning and staining, thus saving time and resources. By capturing molecular fingerprint information, various machine-learning models were used to analyze the spectroscopic data to classify cancerous and non-cancerous tissues accurately. Comparing deparaffinized and paraffinized samples reveals the impact of sample preparation and experimental methods. The study demonstrates a strong correlation between the cancerous nature of a sample and its ATR-FTIR spectrum, suggesting its potential for breast cancer diagnosis (sensitivity of 74.2% and specificity of 78.3%). The proposed approach holds promise for integration into clinical operations, providing a rapid method for preliminary breast cancer diagnosis.

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.

Atherosclerosis plaque tissue classification using self-attention-based conditional variational auto-encoder generative adversarial network using OCT plaque image.

Adults with coronary artery disease often have atherosclerosis, this is defined as the accumulation of plaque in the tissues of the arterial wall. Cardiologists utilize optical coherence tomography (OCT), a light-based imaging method, to examine the layers of intracoronary tissue along pathological formations, such as plaque accumulation. Intracoronary cross-sectional images produced by state-of-the-art catheter-based imaging scheme have 10-15 µm high resolution. Nevertheless, interpretation of the obtained images depends on the operator, which takes a lot of time and is exceedingly error-prone from one observer to another. OCT image post-processing that automatically and accurately tags coronary plaques can help the technique become more widely used and lower the diagnostic error rate. To overcome these problems, Atherosclerosis plaque tissue classification using Self-Attention-Based Conditional Variational Auto-Encoder Generative Adversarial Network (APC-OCTPI-SACVAGAN) is proposed which classifies the Atherosclerosis plaque images as Fibro calcific plaque, Fibro atheroma, Thrombus, Fibrous plaque and Micro-vessel. The proposed APC-OCTPI-SACVAGAN technique is executed in MATLAB. The efficiency of proposed APC-OCTPI-SACVAGAN method attains 16.19 %, 17.93 %, 19.81 % and 1.57 % higher accuracy; 16.92 %, 11.54 %, 5.29 % and 1.946 % higher Area under curve; and 28.06 %, 25.32 %, 32.19 % and 39.185 % lower computational time comparing to the existing methods respectively.

Tissue Classification of Breast Cancer by Hyperspectral Unmixing.

(1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew's correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.

Maxillary labial peri-implant hard and soft tissue alteration observed on cross-sectional dimension: a 2-year prospective observational study.

OBJECTIVES: To evaluate how peri-implant hard and soft tissue height (BH, MH) alter after final prostheses placement related to labial hard and soft tissue thickness (BW, MW). MATERIALS AND METHODS: Forty-five platform-switched implants were classified into four groups according to BW and MW: type 1 (thick BW and thick MW), type 2 (thick BW and thin MW), type 3 (thin BW and thick MW), type 4 (thin BW and thin MW). Tissue resorption was evaluated on cone-beam CT images taken at final prostheses placement, at 1-year follow-up, and at 2-year follow-up. Kruskal-Wallis test and post hoc Mann-Whitney test were applied; significance was set to 0.05. RESULTS: BH resorption was 0.13 ± 0.12 mm in type 1, 0.26 ± 0.17 mm in type 2, 0.09 ± 0.09 mm in type 3, 0.94 ± 0.19 mm in type 4. Differences between type 1 and 4, type 2 and 4, and type 3 and 4 were statistically significant (p < 0.001, p = 0.005, p < 0.001, respectively). MH resorption was 0.10 ± 0.09 mm in type 1, 0.36 ± 0.16 mm in type 2, 0.12 ± 0.12 mm in Type 3, 0.79 ± 0.23 mm in type 4. Differences between type 1 and 2, type 1 and 4, type 2 and 3, type 2 and 4 and type 3 and 4 were statistically significant (p < 0.001). CONCLUSIONS: Significantly less BH/MH resorption occurs around implants with thick BW/MW than those with thin BW/MW in 2 years. Implants with thick peri-implant soft tissue resulted in significantly less tissue resorption in second year after final prostheses placement.

Needle-Based Electrical Impedance Imaging Technology for Needle Navigation.

Needle insertion is a common procedure in modern healthcare practices, such as blood sampling, tissue biopsy, and cancer treatment. Various guidance systems have been developed to reduce the risk of incorrect needle positioning. While ultrasound imaging is considered the gold standard, it has limitations such as a lack of spatial resolution and subjective interpretation of 2D images. As an alternative to conventional imaging techniques, we have developed a needle-based electrical impedance imaging system. The system involves the classification of different tissue types using impedance measurements taken with a modified needle and the visualization in a MATLAB Graphical User Interface (GUI) based on the spatial sensitivity distribution of the needle. The needle was equipped with 12 stainless steel wire electrodes, and the sensitive volumes were determined using Finite Element Method (FEM) simulation. A k-Nearest Neighbors (k-NN) algorithm was used to classify different types of tissue phantoms with an average success rate of 70.56% for individual tissue phantoms. The results showed that the classification of the fat tissue phantom was the most successful (60 out of 60 attempts correct), while the success rate decreased for layered tissue structures. The measurement can be controlled in the GUI, and the identified tissues around the needle are displayed in 3D. The average latency between measurement and visualization was 112.1 ms. This work demonstrates the feasibility of using needle-based electrical impedance imaging as an alternative to conventional imaging techniques. Further improvements to the hardware and the algorithm as well as usability testing are required to evaluate the effectiveness of the needle navigation system.

The neurosurgical benefit of contactless in vivo optical coherence tomography regarding residual tumor detection: A clinical study.

Purpose: In brain tumor surgery, it is crucial to achieve complete tumor resection while conserving adjacent noncancerous brain tissue. Several groups have demonstrated that optical coherence tomography (OCT) has the potential of identifying tumorous brain tissue. However, there is little evidence on human in vivo application of this technology, especially regarding applicability and accuracy of residual tumor detection (RTD). In this study, we execute a systematic analysis of a microscope integrated OCT-system for this purpose. Experimental design: Multiple 3-dimensional in vivo OCT-scans were taken at protocol-defined sites at the resection edge in 21 brain tumor patients. The system was evaluated for its intraoperative applicability. Tissue biopsies were obtained at these locations, labeled by a neuropathologist and used as ground truth for further analysis. OCT-scans were visually assessed with a qualitative classifier, optical OCT-properties were obtained and two artificial intelligence (AI)-assisted methods were used for automated scan classification. All approaches were investigated for accuracy of RTD and compared to common techniques. Results: Visual OCT-scan classification correlated well with histopathological findings. Classification with measured OCT image-properties achieved a balanced accuracy of 85%. A neuronal network approach for scan feature recognition achieved 82% and an auto-encoder approach 85% balanced accuracy. Overall applicability showed need for improvement. Conclusion: Contactless in vivo OCT scanning has shown to achieve high values of accuracy for RTD, supporting what has well been described for ex vivo OCT brain tumor scanning, complementing current intraoperative techniques and even exceeding them in accuracy, while not yet in applicability.

Hyperspectral Imaging in Brain Tumor Surgery-Evidence of Machine Learning-Based Performance.

BACKGROUND: Hyperspectral imaging (HSI) has the potential to enhance surgical tissue detection and diagnostics. Definite utilization of intraoperative HSI guidance demands validated machine learning and public datasets that currently do not exist. Moreover, current imaging conventions are dispersed, and evidence-based paradigms for neurosurgical HSI have not been declared. METHODS: We presented the rationale and a detailed clinical paradigm for establishing microneurosurgical HSI guidance. In addition, a systematic literature review was conducted to summarize the current indications and performance of neurosurgical HSI systems, with an emphasis on machine learning-based methods. RESULTS: The published data comprised a few case series or case reports aiming to classify tissues during glioma operations. For a multitissue classification problem, the highest overall accuracy of 80% was obtained using deep learning. Our HSI system was capable of intraoperative data acquisition and visualization with minimal disturbance to glioma surgery. CONCLUSIONS: In a limited number of publications, neurosurgical HSI has demonstrated unique capabilities in contrast to the established imaging techniques. Multidisciplinary work is required to establish communicable HSI standards and clinical impact. Our HSI paradigm endorses systematic intraoperative HSI data collection, which aims to facilitate the related standards, medical device regulations, and value-based medical imaging systems.

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.