Search

Background and objective: A positive surgical margin (PSM) occurs in up to 32% of patients undergoing robot-assisted radical prostatectomy (RARP). Diffuse reflectance spectroscopy (DRS), which measures tissue composition according to its optical properties, can potentially be used for real-time PSM detection during RARP. Our objective was to assess the feasibility of DRS in distinguishing prostate cancer from benign tissue in RARP specimens. Methods: In a single-center prospective study, DRS measurements were taken ex vivo for RARP specimens from 59 patients with biopsy-proven prostate carcinoma. Discriminating features from the DRS spectra were used to create a machine learning–based classification algorithm. The data were split patient-wise into training (70%) and testing (30%) sets, with ten iterations to ensure algorithm robustness. The average sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) from ten classification iterations were calculated. Key findings and limitations: We collected 542 DRS measurements, of which 53% were tumor and 47% were healthy-tissue measurements. Twenty discriminating features from the DRS spectra were used as the input for a support vector machine model. This model achieved average sensitivity of 89%, specificity of 82%, accuracy of 85%, and AUC of 0.91 for the test set. Limitations include the binary label input for classification. Conclusions and clinical implications: DRS can potentially discriminate prostate cancer from benign tissue. Before implementing the technique in clinical practice, further research is needed to assess its performance on heterogeneous tissue volumes and measurements from the prostate surface. Patient summary: We looked at the ability of a technique called diffuse reflectance spectroscopy to guide surgeons in discriminating prostate cancer tissue from benign prostate tissue in real time during prostate cancer surgery. Our study showed promising results in an experimental setting. Future research will focus on bringing this technique to clinical practice.

Study Design: Preclinical experimental study. Objective: To develop an intraoperative ultrasound-assisted imaging device, which could be placed at the surgical site through an endoscopic working channel and which could help surgeons recognition of different tissue types during endoscopic spinal surgery (ESS). Summary of Background Data: ESS remains a challenging task for spinal surgeons. Great prof iciency and experience are needed to perform procedures such as intervertebral discectomy and neural decompression within a narrow channel. The limited surgical view poses a risk of damaging important structures, such as nerve roots. Methods: We constructed a spinal endoscopic ultrasound system, using a 4-mm custom ultrasound probe, which can be easily inserted through the ESS working channel, allowing up to 10 mm depth detection. This system was applied to ovine lumbar spine samples to obtain ultrasound images. Subsequently, we proposed a 2-stage classification algorithm, based on a pretrained DenseNet architecture for automated tissue recognition. The recognition algorithm was evaluated for accuracy and consistency. Results: The probe can be easily used in the ESS working channel and produces clear and characteristic ultrasound images. We collected 367 images for training and testing of the recognition algorithm, including images of the spinal cord, nucleus pulposus, adipose tissue, bone, annulus fibrosis, and nerve roots. The algorithm achieved over 90% accuracy in recognizing all types of tissues with a Kappa value of 0.875. The recognition times were under 0.1 s using the current configuration. Conclusion: Our system was able to be used in existing ESS working channels and identify at-risk spinal structures in vitro. The trained algorithms could identify 6 intraspinal tissue types accurately and quickly. The concept and innovative application of intraoperative ultrasound in ESS may shorten the learning curve of ESS and improve surgical efficiency and safety. [ABSTRACT FROM AUTHOR]

In recent years, spatial transcriptomics (ST) research has become a popular field of study and has shown great potential in medicine. However, there are few bibliometric analyses in this field. Thus, in this study, we aimed to find and analyze the frontiers and trends of this medical research field based on the available literature. A computerized search was applied to the WoSCC (Web of Science Core Collection) Database for literature published from 2006 to 2023. Complete records of all literature and cited references were extracted and screened. The bibliometric analysis and visualization were performed using CiteSpace, VOSviewer, Bibliometrix R Package software, and Scimago Graphica. A total of 1467 papers and reviews were included. The analysis revealed that the ST publication and citation results have shown a rapid upward trend over the last 3 years. Nature Communications and Nature were the most productive and most co-cited journals, respectively. In the comprehensive global collaborative network, the United States is the country with the most organizations and publications, followed closely by China and the United Kingdom. The author Joakim Lundeberg published the most cited paper, while Patrik L. Ståhl ranked first among co-cited authors. The hot topics in ST are tissue recognition, cancer, heterogeneity, immunotherapy, differentiation, and models. ST technologies have greatly contributed to in-depth research in medical fields such as oncology and neuroscience, opening up new possibilities for the diagnosis and treatment of diseases. Moreover, artificial intelligence and big data drive additional development in ST fields. Spatial transcriptomics (ST) technologies and application prospects. (1) Imaging-based approaches, including in situ sequencing (ISS)—where transcripts are amplified and sequenced in tissue—and ISH-based approaches—where imaging probes are sequentially hybridized in tissue. (2) NGS-based techniques, in which positional information is encoded onto transcripts prior to NGS sequencing. [ABSTRACT FROM AUTHOR]

Laser-induced breakdown spectroscopy (LIBS) was recently introduced as a rapid bone analysis technique in bone-infiltrating head and neck cancers. Research efforts on laser surgery systems with controlled tissue feedback are currently limited to animal specimens and the use of nontumorous tissues. Accordingly, this study aimed to characterize the electrolyte composition of tissues in human mandibular bone-infiltrating head and neck cancer. Mandible cross-sections from 12 patients with bone-invasive head and neck cancers were natively investigated with LIBS. Representative LIBS spectra (n = 3049) of the inferior alveolar nerve, fibrosis, tumor stroma, and cell-rich tumor areas were acquired and histologically validated. Tissue-specific differences in the LIBS spectra were determined by receiver operating characteristics analysis and visualized by principal component analysis. The electrolyte emission values of calcium (Ca) and potassium (K) significantly (p < 0.0001) differed in fibrosis, nerve tissue, tumor stroma, and cell-rich tumor areas. Based on the intracellular detection of Ca and K, LIBS ensures the discrimination between the inferior alveolar nerve and cell-rich tumor tissue with a sensitivity of ≥95.2% and a specificity of ≥87.2%. The heterogeneity of electrolyte emission values within tumorous and nontumorous tissue areas enables LIBS-based tissue recognition in mandibular bone-infiltrating head and neck cancer. [ABSTRACT FROM AUTHOR]

Objective One of the major difficulties in spinal surgery is the injury of important tissues caused by tissue misclassification, which is the source of surgical complications. Accurate recognization of the tissues is the key to increase safety and effect as well as to reduce the complications of spinal surgery. The study aimed at tissue recognition in the spinal operation area based on electrical impedance and the boundaries of electrical impedance between cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus. Methods Two female white swines with body weight of 40 kg were used to expose cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus under general anesthesia and aseptic conditions. The electrical impedance of these tissues at 12 frequencies (in the range of 10–100 kHz) was measured by electrochemical analyzer with a specially designed probe, at 22.0–25.0°C and 50%–60% humidity. Two types of tissue recognition models ‐ one combines principal component analysis (PCA) and support vector machine (SVM) and the other combines combines SVM and ensemble learning ‐ were constructed, and the boundaries of electrical impedance of the five tissues at 12 frequencies of current were figured out. Linear correlation, two‐way ANOVA, and paired T‐test were conducted to analyze the relationship between the electrical impedance of different tissues at different frequencies. Results The results suggest that the differences of electrical impedance mainly came from tissue type (p

Neural networks are known to be vulnerable against adversarial attacks – images with carefully crafted adversarial perturbations that are imperceptible to the human eye. In medical imaging tasks this can be a major threat for making predictions based on deep neural network solutions. In this paper we propose a pipeline for augmenting a histological image dataset using weak adversarial attacks and demonstrate an increase in accuracy on the clean test set of a neural classifier trained on the augmented dataset. When trained on the clean train set, the neural network achieves an accuracy of 90.65 on the clean test set, and an accuracy of 93.56 on the same test set when trained using the proposed augmentation method. [ABSTRACT FROM AUTHOR]

Objective: Rapid evaporative ionization mass spectrometry (REIMS) is a metabolomic technique analyzing tissue metabolites, which can be applied intraoperatively in real-time. The objective of this study was to profile the lipid composition of colorectal tissues using REIMS, assessing its accuracy for real-time tissue recognition and risk-stratification. Summary Background Data: Metabolic dysregulation is a hallmark feature of carcinogenesis; however, it remains unknown if this can be leveraged for real-time clinical applications in colorectal disease. Methods: Patients undergoing colorectal resection were included, with carcinoma, adenoma and paired-normal mucosa sampled. Ex vivo analysis with REIMS was conducted using monopolar diathermy, with the aerosol aspirated into a Xevo G2S QToF mass spectrometer. Negatively charged ions over 600 to 1000 m/z were used for univariate and multivariate functions including linear discriminant analysis. Results: A total of 161 patients were included, generating 1013 spectra. Unique lipidomic profiles exist for each tissue type, with REIMS differentiating samples of carcinoma, adenoma, and normal mucosa with 93.1% accuracy and 96.1% negative predictive value for carcinoma. Neoplasia (carcinoma or adenoma) could be predicted with 96.0% accuracy and 91.8% negative predictive value. Adenomas can be risk-stratified by grade of dysplasia with 93.5% accuracy, but not histological subtype. The structure of 61 lipid metabolites was identified, revealing that during colorectal carcinogenesis there is progressive increase in relative abundance of phosphatidylglycerols, sphingomyelins, and mono-unsaturated fatty acid-containing phospholipids. Conclusions: The colorectal lipidome can be sampled by REIMS and leveraged for accurate real-time tissue recognition, in addition to riskstratification of colorectal adenomas. Unique lipidomic features associated with carcinogenesis are described. [ABSTRACT FROM AUTHOR]

Objective: One of the major difficulties in spinal surgery is the injury of important tissues caused by tissue misclassification, which is the source of surgical complications. Accurate recognization of the tissues is the key to increase safety and effect as well as to reduce the complications of spinal surgery. The study aimed at tissue recognition in the spinal operation area based on electrical impedance and the boundaries of electrical impedance between cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus. Methods: Two female white swines with body weight of 40 kg were used to expose cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus under general anesthesia and aseptic conditions. The electrical impedance of these tissues at 12 frequencies (in the range of 10–100 kHz) was measured by electrochemical analyzer with a specially designed probe, at 22.0–25.0°C and 50%–60% humidity. Two types of tissue recognition models ‐ one combines principal component analysis (PCA) and support vector machine (SVM) and the other combines combines SVM and ensemble learning ‐ were constructed, and the boundaries of electrical impedance of the five tissues at 12 frequencies of current were figured out. Linear correlation, two‐way ANOVA, and paired T‐test were conducted to analyze the relationship between the electrical impedance of different tissues at different frequencies. Results: The results suggest that the differences of electrical impedance mainly came from tissue type (p < 0.0001), the electrical impedance of five kinds of tissue was statistically different from each other (p < 0.0001). The tissue recognition accuracy of the algorithm based on principal component analysis and support vector machine ranged from 83%–100%, and the overall accuracy was 95.83%. The classification accuracy of the algorithm based on support vector machine and ensemble learning was 100%, and the boundaries of electrical impedance of five tissues at various frequencies were calculated. Conclusion: The electrical impedance of cortical bone, cancellous bone, spinal cord, muscle, and nucleus pulposus had significant differences in 10–100 kHz frequency. The application of support vector machine realized the accurate tissue recognition in the spinal operation area based on electrical impedance, which is expected to be translated and applied to tissue recognition during spinal surgery. [ABSTRACT FROM AUTHOR]

Traditional brightness-mode ultrasound imaging is primarily constrained by the low specificity among tissues and the inconsistency among sonographers. The major cause is the imaging method that represents the amplitude of echoes as brightness and ignores other detailed information, leaving sonographers to interpret based on organ contours that depend highly on specific imaging planes. Other ultrasound imaging modalities, color Doppler imaging or shear wave elastography, overlay motion or stiffness information to brightness-mode images. However, tissue-specific scattering properties and spectral patterns remain unknown in ultrasound imaging. Here we demonstrate that the distribution (size and average distance) of scattering particles leads to characteristic wavelet spectral patterns, which enables tissue recognition and high-contrast ultrasound imaging. Ultrasonic wavelet spectra from similar particle distributions tend to cluster in the eigenspace according to principal component analysis, whereas those with different distributions tend to be distinguishable from one another. For each distribution, a few wavelet spectra are unique and act as a fingerprint to recognize the corresponding tissue. Illumination of specific tissues and organs with designated colors according to the recognition results yields high-contrast ultrasound imaging. The fully-colorized tissue-specific ultrasound imaging potentially simplifies the interpretation and promotes consistency among sonographers, or even enables the applicability for non-professionals. • Verified the effect of scatterer distribution on the wavelet spectrum. • A few wavelet spectra are unique and act as a fingerprint to recognize tissue. • Illumination of tissues with recognition result yields high-contrast ultrasound image. • The fully colorized tissue-specific ultrasound imaging simplifies the interpretation. [ABSTRACT FROM AUTHOR]

Nerves are critical structures that may be difficult to recognize during surgery. Inadvertent nerve injuries can have catastrophic consequences for the patient and lead to life-long pain and a reduced quality of life. Hyperspectral imaging (HSI) is a non-invasive technique combining photography with spectroscopy, allowing non-invasive intraoperative biological tissue property quantification. We show, for the first time, that HSI combined with deep learning allows nerves and other tissue types to be automatically recognized in in vivo hyperspectral images. An animal model was used, and eight anesthetized pigs underwent neck midline incisions, exposing several structures (nerve, artery, vein, muscle, fat, skin). State-of-the-art machine learning models were trained to recognize these tissue types in HSI data. The best model was a convolutional neural network (CNN), achieving an overall average sensitivity of 0.91 and a specificity of 1.0, validated with leave-one-patient-out cross-validation. For the nerve, the CNN achieved an average sensitivity of 0.76 and a specificity of 0.99. In conclusion, HSI combined with a CNN model is suitable for in vivo nerve recognition.

This ex-vivo study evaluates the feasibility of diffuse reflectance spectroscopy (DRS) for discriminating tumor from healthy tissue, with the aim to develop a technology that can assess resection margins for the presence of tumor cells during oral cavity cancer surgery. Diffuse reflectance spectra were acquired on fresh surgical specimens from 28 patients with oral cavity squamous cell carcinoma. The spectra (400 to 1600 nm) were detected after illuminating tissue with a source fiber at 0.3-, 0.7-, 1.0-, and 2.0-mm distances from a detection fiber, obtaining spectral information from different sampling depths. The spectra were correlated with histopathology. A total of 76 spectra were obtained from tumor tissue and 110 spectra from healthy muscle tissue. The first- and second-order derivatives of the spectra were calculated and a classification algorithm was developed using fivefold cross validation with a linear support vector machine. The best results were obtained by the reflectance measured with a 1-mm source-detector distance (sensitivity, specificity, and accuracy are 89%, 82%, and 86%, respectively). DRS can accurately discriminate tumor from healthy tissue in an ex-vivo setting using a 1-mm source-detector distance. Accurate validation methods are warranted for larger sampling depths to allow for guidance during oral cavity cancer excision. [ABSTRACT FROM AUTHOR]

A pressure ulcer is a clinical pathology of localized damage to the skin and underlying tissue caused by pressure, shear, or friction. Diagnosis, treatment, and care of pressure ulcers are costly for health services. Accurate wound evaluation is a critical task for optimizing the efficacy of treatment and care. Clinicians usually evaluate each pressure ulcer by visual inspection of the damaged tissues, which is an imprecise manner of assessing the wound state. Current computer vision approaches do not offer a global solution to this particular problem. In this paper, a hybrid approach based on neural networks and Bayesian classifiers is used in the design of a computational system for automatic tissue identification in wound images. A mean shift procedure and a region-growing strategy are implemented for effective region segmentation. Color and texture features are extracted from these segmented regions. A set of k multilayer perceptrons is trained with inputs consisting of color and texture patterns, and outputs consisting of categorical tissue classes which are determined by clinical experts. This training procedure is driven by a -fold cross-validation method. Finally, a Bayesian committee machine is formed by training a Bayesian classifier to combine the classifications of the k neural networks. Specific heuristics based on the wound topology are designed to significantly improve the results of the classification. We obtain high efficiency rates from a binary cascade approach for tissue identification. Results are compared with other similar machine-learning approaches, including multiclass Bayesian committee machine classifiers and support vector machines. The different techniques analyzed in this paper show high global classification accuracy rates. Our binary cascade approach gives high global performance rates (average sensitivity = 78.7%, specificity = 94.7%, and accuracy (= 91.5%) and shows the highest average sensitivity score ( = 86.3%) when detecting necrotic tissue in the wound. [ABSTRACT FROM AUTHOR]

Abstract: The recognition response of Penaeus (Litopenaeus) vannamei against thoracic nerve cord–ganglia transplants from three species of Penaeidae: P. vannamei, P. (Litopenaeus) stylirostris, and Trachypenaeus byrdi, and one species of Palaemonidae: Macrobrachium tenellum, was evaluated. Implanted tissues were removed from recipients at the end of different incubation periods, catalogued based on three gross categories (missing, unmelanized, and melanized), and analyzed by histology. Some intraspecific implants of thoracic ganglia from P. vannamei were missing after a few weeks, without activating a haemocytic response leading to encapsulation. The same condition was observed for thoracic ganglia from P. stylirostris and T. byrdi. Unmelanized tissue sections from P. vannamei, P. stylirostris, and T. byrdi, were commonly recovered; however, most implants had a smaller size than their original length (5–6 mm). Intraspecific transplantation in P. stylirostris also generated a time-related reduction in graft size. Based on our observations, missing implants, small grafts and compacted structure of tissues indicate an absorption mechanism from the host without encapsulation. Histological analysis of unmelanized tissues from Penaeidae reveals that the structure of nerve cords is similar to controls, showing living nerve cord cells surrounded by the neurilemma, and no haemocytic encapsulation at the periphery. Neurosecretory cells were also observed alive, but the structure of ganglia was different from control ganglia. On the other hand, tissues from M. tenellum were all encapsulated, showing distinctive black depositions and the distinctive layers of haemocytes. These findings suggest that neither interspecific nor intraspecific thoracic ganglia transplants within Penaeidae keep their tissue integrity inside P. vannamei. The endocrine implications for inducing ovarian maturation have to be investigated. [Copyright &y& Elsevier]

Nerves are critical structures that may be difficult to recognize during surgery. Inadvertent nerve injuries can have catastrophic consequences for the patient and lead to life-long pain and a reduced quality of life. Hyperspectral imaging (HSI) is a non-invasive technique combining photography with spectroscopy, allowing non-invasive intraoperative biological tissue property quantification. We show, for the first time, that HSI combined with deep learning allows nerves and other tissue types to be automatically recognized in in vivo hyperspectral images. An animal model was used, and eight anesthetized pigs underwent neck midline incisions, exposing several structures (nerve, artery, vein, muscle, fat, skin). State-of-the-art machine learning models were trained to recognize these tissue types in HSI data. The best model was a convolutional neural network (CNN), achieving an overall average sensitivity of 0.91 and a specificity of 1.0, validated with leave-one-patient-out cross-validation. For the nerve, the CNN achieved an average sensitivity of 0.76 and a specificity of 0.99. In conclusion, HSI combined with a CNN model is suitable for in vivo nerve recognition. [ABSTRACT FROM AUTHOR]

Background and Objectives: There is a clinical need to assess the resection margins of tongue cancer specimens, intraoperatively. In the current ex vivo study, we evaluated the feasibility of hyperspectral diffuse reflectance imaging (HSI) for distinguishing tumor from the healthy tongue tissue., Study Design/materials and Methods: Fresh surgical specimens (n = 14) of squamous cell carcinoma of the tongue were scanned with two hyperspectral cameras that cover the visible and near-infrared spectrum (400-1,700 nm). Each pixel of the hyperspectral image represents a measure of the diffuse optical reflectance. A neural network was used for tissue-type prediction of the hyperspectral images of the visual and near-infrared data sets separately as well as both data sets combined., Results: HSI was able to distinguish tumor from muscle with a good accuracy. The diagnostic performance of both wavelength ranges (sensitivity/specificity of visual and near-infrared were 84%/80% and 77%/77%, respectively) appears to be comparable and there is no additional benefit of combining the two wavelength ranges (sensitivity and specificity were 83%/76%)., Conclusions: HSI has a strong potential for intra-operative assessment of tumor resection margins of squamous cell carcinoma of the tongue. This may optimize surgery, as the entire resection surface can be scanned in a single run and the results can be readily available. Lasers Surg. Med. © 2019 Wiley Periodicals, Inc., (© 2019 Wiley Periodicals, Inc.)

• A new proposal based on superpixels and deep-learning models for wound segmentation is proposed. • Distinct parameterizations for the approach are discussed and evaluated experimentally. • The proposed method provides tissue segmentation and wounded area quantification more accurately than compared approaches. The image-based identification of distinct tissues within dermatological wounds enhances patients' care since it requires no intrusive evaluations. This manuscript presents an approach, we named QTDU , that combines deep learning models with superpixel-driven segmentation methods for assessing the quality of tissues from dermatological ulcers. QTDU consists of a three-stage pipeline for the obtaining of ulcer segmentation, tissues' labeling, and wounded area quantification. We set up our approach by using a real and annotated set of dermatological ulcers for training several deep learning models to the identification of ulcered superpixels. Empirical evaluations on 179,572 superpixels divided into four classes showed QTDU accurately spot wounded tissues (AUC = 0.986, sensitivity = 0.97, and specificity = 0.974) and outperformed machine-learning approaches in up to 8.2% regarding F1-Score through fine-tuning of a ResNet-based model. Last, but not least, experimental evaluations also showed QTDU correctly quantified wounded tissue areas within a 0.089 Mean Absolute Error ratio. Results indicate QTDU effectiveness for both tissue segmentation and wounded area quantification tasks. When compared to existing machine-learning approaches, the combination of superpixels and deep learning models outperformed the competitors within strong significant levels. [ABSTRACT FROM AUTHOR]