Development of an image pre-processor for operational hyperspectral laryngeal cancer detection

Hyperspectral imaging and evaluation of surgical margins: where do we stand?

PURPOSE OF REVIEW

To highlight the recent literature on the use of hyperspectral imaging (HSI) for cancer margin evaluation ex vivo, for head and neck cancer pathology and in vivo during head and neck cancer surgery.

RECENT FINDINGS

HSI can be used ex vivo on unstained and stained tissue sections to analyze head and neck tissue and tumor cells in combination with machine learning approaches to analyze head and neck cancer cell characteristics and to discriminate the tumor border from normal tissue. Data on in vivo applications during head and neck cancer surgery are preliminary and limited. Even now an accuracy of 80% for tumor versus nonneoplastic tissue classification can be achieved for certain tasks, within the current in vivo settings.

SUMMARY

Significant progress has been made to introduce HSI for ex vivo head and neck cancer pathology evaluation and for an intraoperative use to define the tumor margins. To optimize the accuracy for in vivo use, larger HSI databases with annotations for head and neck cancer are needed.

Systematic meta-analysis of computer-aided detection to detect early esophageal cancer using hyperspectral imaging

One of the leading causes of cancer deaths is esophageal cancer (EC) because identifying it in early stage is challenging. Computer-aided diagnosis (CAD) could detect the early stages of EC have been developed in recent years. Therefore, in this study, complete meta-analysis of selected studies that only uses hyperspectral imaging to detect EC is evaluated in terms of their diagnostic test accuracy (DTA). Eight studies are chosen based on the Quadas-2 tool results for systematic DTA analysis, and each of the methods developed in these studies is classified based on the nationality of the data, artificial intelligence, the type of image, the type of cancer detected, and the year of publishing. Deeks' funnel plot, forest plot, and accuracy charts were made. The methods studied in these articles show the automatic diagnosis of EC has a high accuracy, but external validation, which is a prerequisite for real-time clinical applications, is lacking.

In vivo evaluation of a hyperspectral imaging system for minimally invasive surgery (HSI-MIS)

BACKGROUND

Hyperspectral Imaging (HSI) is a reliable and safe imaging method for taking intraoperative perfusion measurements. This is the first study translating intraoperative HSI to an in vivo laparoscopic setting using a CE-certified HSI-system for minimally invasive surgery (HSI-MIS). We aim to compare it to an established HSI-system for open surgery (HSI-Open).

METHODS

Intraoperative HSI was done using the HSI-MIS and HSI-Open at the Region of Interest (ROI). 19 patients undergoing gastrointestinal resections were analyzed in this study. The HSI-MIS-acquired images were aligned with those from the HSI-Open, and spectra and parameter images were compared pixel-wise. We calculated the Mean Absolute Error (MAE) for Tissue Oxygen Saturation (StO₂), Near-Infrared Perfusion Index (NIR-PI), Tissue Water Index (TWI), and Organ Hemoglobin Index (OHI), as well as the Root Mean Squared Error (RMSE) over the whole spectrum. Our analysis of parameters was optimized using partial least squares (PLS) regression. Two experienced surgeons carried out an additional color-change analysis, comparing the ROI images and deciding whether they provided the same (acceptable) or different visual information (rejected).

RESULTS

HSI and subsequent image registration was possible in 19 patients. MAE results for the original calculation were StO_{2 orig.} 17.2% (± 7.7%)_, NIR-PI_orig. 16.0 (± 9.5), TWI_orig. 18.1 (± 7.9), OHI_orig. 14.4 (± 4.5). For the PLS calculation, they were StO_{2 PLS} 12.6% (± 5.2%), NIR-PI_PLS 10.3 (± 6.0), TWI_PLS 10.6 (± 5.1), and OHI_PLS 11.6 (± 3.0). The RMSE between both systems was 0.14 (± 0.06). In the color-change analysis; both surgeons accepted more images generated using the PLS method.

CONCLUSION

Intraoperative HSI-MIS is a new technology and holds great potential for future applications in surgery. Parameter deviations are attributable to technical differences and can be reduced by applying improved calculation methods. This study is an important step toward the clinical implementation of HSI for minimally invasive surgery.

Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification

Specular Reflections often exist in the endoscopic image, which not only hurts many computer vision algorithms but also seriously interferes with the observation and judgment of the surgeon. The information behind the recovery specular reflection areas is a necessary pre-processing step in medical image analysis and application. The existing highlight detection method is usually only suitable for medium-brightness images. The existing highlight removal method is only applicable to images without large specular regions, when dealing with high-resolution medical images with complex texture information, not only does it have a poor recovery effect, but the algorithm operation efficiency is also low. To overcome these limitations, this paper proposes a specular reflection detection and removal method for endoscopic images based on brightness classification. It can effectively detect the specular regions in endoscopic images of different brightness and can improve the operating efficiency of the algorithm while restoring the texture structure information of the high-resolution image. In addition to achieving image brightness classification and enhancing the brightness component of low-brightness images, this method also includes two new steps: In the highlight detection phase, the adaptive threshold function that changes with the brightness of the image is used to detect absolute highlights. During the highlight recovery phase, the priority function of the exemplar-based image inpainting algorithm was modified to ensure reasonable and correct repairs. At the same time, local priority computing and adaptive local search strategies were used to improve algorithm efficiency and reduce error matching. The experimental results show that compared with the other state-of-the-art, our method shows better performance in terms of qualitative and quantitative evaluations, and the algorithm efficiency is greatly improved when processing high-resolution endoscopy images.

An Improvised Deep-Learning-Based Mask R-CNN Model for Laryngeal Cancer Detection Using CT Images

Recently, laryngeal cancer cases have increased drastically across the globe. Accurate treatment for laryngeal cancer is intricate, especially in the later stages. This type of cancer is an intricate malignancy inside the head and neck area of patients. In recent years, diverse diagnosis approaches and tools have been developed by researchers for helping clinical experts to identify laryngeal cancer effectively. However, these existing tools and approaches have diverse issues related to performance constraints such as lower accuracy in the identification of laryngeal cancer in the initial stage, more computational complexity, and large time consumption in patient screening. In this paper, the authors present a novel and enhanced deep-learning-based Mask R-CNN model for the identification of laryngeal cancer and its related symptoms by utilizing diverse image datasets and CT images in real time. Furthermore, our suggested model is capable of capturing and detecting minor malignancies of the larynx portion in a significant and faster manner in the real-time screening of patients, and it saves time for the clinicians, allowing for more patient screening every day. The outcome of the suggested model is enhanced and pragmatic and obtained an accuracy of 98.99%, precision of 98.99%, F1 score of 97.99%, and recall of 96.79% on the ImageNet dataset. Several studies have been performed in recent years on laryngeal cancer detection by using diverse approaches from researchers. For the future, there are vigorous opportunities for further research to investigate new approaches for laryngeal cancer detection by utilizing diverse and large dataset images.

In vivo multi spectral colonoscopy in mice

Multi- and hyperspectral endoscopy are possibilities to improve the endoscopic detection of neoplastic lesions in the colon and rectum during colonoscopy. However, most studies in this context are performed on histological samples/biopsies or ex vivo. This leads to the question if previous results can be transferred to an in vivo setting. Therefore, the current study evaluated the usefulness of multispectral endoscopy in identifying neoplastic lesions in the colon. The data set consists of 25 mice with colonic neoplastic lesions and the data analysis is performed by machine learning. Another question addressed was whether adding additional spatial features based on Gauss-Laguerre polynomials leads to an improved detection rate. As a result, detection of neoplastic lesions was achieved with an MCC of 0.47. Therefore, the classification accuracy of multispectral colonoscopy is comparable with hyperspectral colonoscopy in the same spectral range when additional spatial features are used. Moreover, this paper strongly supports the current path towards the application of multi/hyperspectral endoscopy in clinical settings and shows that the challenges from transferring results from ex vivo to in vivo endoscopy can be solved.

Video: Clinical evaluation of a laparoscopic hyperspectral imaging system

Background

Hyperspectral imaging (HSI) during surgical procedures is a new method for perfusion quantification and tissue discrimination. Its use has been limited to open surgery due to large camera sizes, missing color video, or long acquisition times. A hand-held, laparoscopic hyperspectral camera has been developed now to overcome those disadvantages and evaluated clinically for the first time.

Methods

In a clinical evaluation study, gastrointestinal resectates of ten cancer patients were investigated using the laparoscopic hyperspectral camera. Reference data from corresponding anatomical regions were acquired with a clinically approved HSI system. An image registration process was executed that allowed for pixel-wise comparisons of spectral data and parameter images (StO₂: oxygen saturation of tissue, NIR PI: near-infrared perfusion index, OHI: organ hemoglobin index, TWI: tissue water index) provided by both camera systems. The mean absolute error (MAE) and root mean square error (RMSE) served for the quantitative evaluations. Spearman’s rank correlation between factors related to the study design like the time of spectral white balancing and MAE, respectively RMSE, was calculated.

Results

The obtained mean MAEs between the TIVITA® Tissue and the laparoscopic hyperspectral system resulted in StO₂: 11% ± 7%, NIR PI: 14±3, OHI: 14± 5, and TWI: 10 ± 2. The mean RMSE between both systems was 0.1±0.03 from 500 to 750 nm and 0.15 ±0.06 from 750 to 1000 nm. Spearman’s rank correlation coefficients showed no significant correlation between MAE or RMSE and influencing factors related to the study design.

Conclusion

Qualitatively, parameter images of the laparoscopic system corresponded to those of the system for open surgery. Quantitative deviations were attributed to technical differences rather than the study design. Limitations of the presented study are addressed in current large-scale in vivo trials.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00464-022-09282-y.

In vivo detection of head and neck tumors by hyperspectral imaging combined with deep learning methods

Currently, there are no fast and accurate screening methods available for head and neck cancer, the eighth most common tumor entity. For this study, we used hyperspectral imaging, an imaging technique for quantitative and objective surface analysis, combined with deep learning methods for automated tissue classification. As part of a prospective clinical observational study, hyperspectral datasets of laryngeal, hypopharyngeal and oropharyngeal mucosa were recorded in 98 patients before surgery in vivo. We established an automated data interpretation pathway that can classify the tissue into healthy and tumorous using convolutional neural networks with 2D spatial or 3D spatio-spectral convolutions combined with a state-of-the-art Densenet architecture. Using 24 patients for testing, our 3D spatio-spectral Densenet classification method achieves an average accuracy of 81%, a sensitivity of 83% and a specificity of 79%.

Biomedical Applications of Translational Optical Imaging: From Molecules to Humans

Light is a powerful investigational tool in biomedicine, at all levels of structural organization. Its multitude of features (intensity, wavelength, polarization, interference, coherence, timing, non-linear absorption, and even interactions with itself) able to create contrast, and thus images that detail the makeup and functioning of the living state can and should be combined for maximum effect, especially if one seeks simultaneously high spatiotemporal resolution and discrimination ability within a living organism. The resulting high relevance should be directed towards a better understanding, detection of abnormalities, and ultimately cogent, precise, and effective intervention. The new optical methods and their combinations needed to address modern surgery in the operating room of the future, and major diseases such as cancer and neurodegeneration are reviewed here, with emphasis on our own work and highlighting selected applications focusing on quantitation, early detection, treatment assessment, and clinical relevance, and more generally matching the quality of the optical detection approach to the complexity of the disease. This should provide guidance for future advanced theranostics, emphasizing a tighter coupling-spatially and temporally-between detection, diagnosis, and treatment, in the hope that technologic sophistication such as that of a Mars rover can be translationally deployed in the clinic, for saving and improving lives.

Automatic Recognition of Colon and Esophagogastric Cancer with Machine Learning and Hyperspectral Imaging

There are approximately 1.8 million diagnoses of colorectal cancer, 1 million diagnoses of stomach cancer, and 0.6 million diagnoses of esophageal cancer each year globally. An automatic computer-assisted diagnostic (CAD) tool to rapidly detect colorectal and esophagogastric cancer tissue in optical images would be hugely valuable to a surgeon during an intervention. Based on a colon dataset with 12 patients and an esophagogastric dataset of 10 patients, several state-of-the-art machine learning methods have been trained to detect cancer tissue using hyperspectral imaging (HSI), including Support Vector Machines (SVM) with radial basis function kernels, Multi-Layer Perceptrons (MLP) and 3D Convolutional Neural Networks (3DCNN). A leave-one-patient-out cross-validation (LOPOCV) with and without combining these sets was performed. The ROC-AUC score of the 3DCNN was slightly higher than the MLP and SVM with a difference of 0.04 AUC. The best performance was achieved with the 3DCNN for colon cancer and esophagogastric cancer detection with a high ROC-AUC of 0.93. The 3DCNN also achieved the best DICE scores of 0.49 and 0.41 on the colon and esophagogastric datasets, respectively. These scores were significantly improved using a patient-specific decision threshold to 0.58 and 0.51, respectively. This indicates that, in practical use, an HSI-based CAD system using an interactive decision threshold is likely to be valuable. Experiments were also performed to measure the benefits of combining the colorectal and esophagogastric datasets (22 patients), and this yielded significantly better results with the MLP and SVM models.

Visualization of quantitative lipid distribution in mouse liver through near-infrared hyperspectral imaging

Lipid distribution in the liver provides crucial information for diagnosing the severity of fatty liver and fatty liver-associated liver cancer. Therefore, a noninvasive, label-free, and quantitative modality is eagerly anticipated. We report near-infrared hyperspectral imaging for the quantitative visualization of lipid content in mouse liver based on partial least square regression (PLSR) and support vector regression (SVR). Analysis results indicate that SVR with standard normal variate pretreatment outperforms PLSR by achieving better root mean square error (15.3 mg/g) and higher determination coefficient (0.97). The quantitative mapping of lipid content in the mouse liver is realized using SVR.

Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning

The aim of this study is to incorporate polarized hyperspectral imaging (PHSI) with machine learning for automatic detection of head and neck squamous cell carcinoma (SCC) on hematoxylin and eosin (H&E) stained tissue slides. A polarized hyperspectral imaging microscope had been developed in our group. In this paper, we imaged 20 H&E stained tissue slides from 10 patients with SCC of the larynx by the PHSI microscope. Several machine learning algorithms, including support vector machine (SVM), random forest, Gaussian naive Bayes, and logistic regression, were applied to the collected image data for the automatic detection of SCC on the H&E stained tissue slides. The performance of these methods was compared among the collected PHSI data, the pseudo-RGB images generated from the PHSI data, and the PHSI data after applying the principal component analysis (PCA) transformation. The results suggest that SVM is a superior classifier for the classification task based on the PHSI data cubes compared to the other three classifiers. The incorporate of four Stokes vector parameters improved the classification accuracy. Finally, the PCA transformed image data did not improve the accuracy as it might lose some important information from the original PHSI data. The preliminary results show that polarized hyperspectral imaging can have many potential applications in digital pathology.

Hyperspectral characterization of re-epithelialization in an in vitro wound model

In vitro wound models are useful for research on wound re-epithelialization. Hyperspectral imaging represents a non-destructive alternative to histology analysis for detection of re-epithelialization. This study aims to characterize the main optical behavior of a wound model in order to enable development of detection algorithms. K-Means clustering and agglomerative analysis were used to group spatial regions based on the spectral behavior, and an inverse photon transport model was used to explain differences in optical properties. Six samples of the wound model were prepared from human tissue and followed over 22 days. Re-epithelialization occurred at a mean rate of 0.24 mm² /day after day 8 to 10. Suppression of wound spectral features was the main feature characterizing re-epithelialized and intact tissue. Modeling the photon transport through a diffuse layer placed on top of wound tissue properties reproduced the spectral behavior. The missing top layer represented by wounds is thus optically detectable using hyperspectral imaging.

Exploiting scale-invariance: a top layer targeted inverse model for hyperspectral images of wounds

Detection of re-epithelialization in wound healing is important, but challenging. Hyperspectral imaging can be used for non-destructive characterization, but efficient techniques are needed to extract and interpret the information. An inverse photon transport model suitable for characterization of re-epithelialization is validated and explored in this study. It exploits scale-invariance to enable fitting of the epidermal skin layer only. Monte Carlo simulations indicate that the fitted layer transmittance and reflectance spectra are unique, and that there exists an infinite number of coupled parameter solutions. The method is used to explain the optical behavior of and detect re-epithelialization in an in vitro wound model.

Surgical spectral imaging

Recent technological developments have resulted in the availability of miniaturised spectral imaging sensors capable of operating in the multi- (MSI) and hyperspectral imaging (HSI) regimes. Simultaneous advances in image-processing techniques and artificial intelligence (AI), especially in machine learning and deep learning, have made these data-rich modalities highly attractive as a means of extracting biological information non-destructively. Surgery in particular is poised to benefit from this, as spectrally-resolved tissue optical properties can offer enhanced contrast as well as diagnostic and guidance information during interventions. This is particularly relevant for procedures where inherent contrast is low under standard white light visualisation. This review summarises recent work in surgical spectral imaging (SSI) techniques, taken from Pubmed, Google Scholar and arXiv searches spanning the period 2013-2019. New hardware, optimised for use in both open and minimally-invasive surgery (MIS), is described, and recent commercial activity is summarised. Computational approaches to extract spectral information from conventional colour images are reviewed, as tip-mounted cameras become more commonplace in MIS. Model-based and machine learning methods of data analysis are discussed in addition to simulation, phantom and clinical validation experiments. A wide variety of surgical pilot studies are reported but it is apparent that further work is needed to quantify the clinical value of MSI/HSI. The current trend toward data-driven analysis emphasises the importance of widely-available, standardised spectral imaging datasets, which will aid understanding of variability across organs and patients, and drive clinical translation.

Adaptive deep learning for head and neck cancer detection using hyperspectral imaging

It can be challenging to detect tumor margins during surgery for complete resection. The purpose of this work is to develop a novel learning method that learns the difference between the tumor and benign tissue adaptively for cancer detection on hyperspectral images in an animal model. Specifically, an auto-encoder network is trained based on the wavelength bands on hyperspectral images to extract the deep information to create a pixel-wise prediction of cancerous and benign pixel. According to the output hypothesis of each pixel, the misclassified pixels would be reclassified in the right prediction direction based on their adaptive weights. The auto-encoder network is again trained based on these updated pixels. The learner can adaptively improve the ability to identify the cancer and benign tissue by focusing on the misclassified pixels, and thus can improve the detection performance. The adaptive deep learning method highlighting the tumor region proved to be accurate in detecting the tumor boundary on hyperspectral images and achieved a sensitivity of 92.32% and a specificity of 91.31% in our animal experiments. This adaptive learning method on hyperspectral imaging has the potential to provide a noninvasive tool for tumor detection, especially, for the tumor whose margin is indistinct and irregular.

In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer

In contrast to conventional optical imaging modalities, hyperspectral imaging (HSI) is able to capture much more information from a certain scene, both within and beyond the visual spectral range (from 400 to 700 nm). This imaging modality is based on the principle that each material provides different responses to light reflection, absorption, and scattering across the electromagnetic spectrum. Due to these properties, it is possible to differentiate and identify the different materials/substances presented in a certain scene by their spectral signature. Over the last two decades, HSI has demonstrated potential to become a powerful tool to study and identify several diseases in the medical field, being a non-contact, non-ionizing, and a label-free imaging modality. In this review, the use of HSI as an imaging tool for the analysis and detection of cancer is presented. The basic concepts related to this technology are detailed. The most relevant, state-of-the-art studies that can be found in the literature using HSI for cancer analysis are presented and summarized, both in-vivo and ex-vivo. Lastly, we discuss the current limitations of this technology in the field of cancer detection, together with some insights into possible future steps in the improvement of this technology.

Spectral Spatial Variation

Automatic carcinoma detection from hyper/multi spectral images is of essential importance due to the fact that these images cannot be presented directly to the clinician. However, standard approaches for carcinoma detection use hundreds or even thousands of features. This would cost a high amount of RAM (random access memory) for a pixel wise analysis and would slow down the classification or make it even impossible on standard PCs. To overcome this, strong features are required. We propose that the spectral-spatial-variation (SSV) is one of these strong features. SSV is the residuum of the three dimensional hyper spectral data cube minus its approximation with a fitting in a small volume of the 3D image. By using it, the classification results of carcinoma detection in the stomach with multi spectral imaging will be increase significantly compared to not using the SSV. In some cases, the AUC can be even as high as by the usage of 72 spatial features.

A clinically translatable hyperspectral endoscopy (HySE) system for imaging the gastrointestinal tract

Hyperspectral imaging (HSI) enables visualisation of morphological and biochemical information, which could improve disease diagnostic accuracy. Unfortunately, the wide range of image distortions that arise during flexible endoscopy in the clinic have made integration of HSI challenging. To address this challenge, we demonstrate a hyperspectral endoscope (HySE) that simultaneously records intrinsically co-registered hyperspectral and standard-of-care white light images, which allows image distortions to be compensated computationally and an accurate hyperspectral data cube to be reconstructed as the endoscope moves in the lumen. Evaluation of HySE performance shows excellent spatial, spectral and temporal resolution and high colour fidelity. Application of HySE enables: quantification of blood oxygenation levels in tissue mimicking phantoms; differentiation of spectral profiles from normal and pathological ex vivo human tissues; and recording of hyperspectral data under freehand motion within an intact ex vivo pig oesophagus model. HySE therefore shows potential for enabling HSI in clinical endoscopy.

Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method

Diagnosing nasopharyngeal carcinoma (NPC) is a significant challenge because of the highly complex process. We proposed an approach to diagnose NPC serum using a combination of hyperspectral imaging and weight-based principal component analysis. Samples were prepared by pressing boric acid into pellets for use as the sera substrate. The sera, collected from 100 healthy volunteers and 60 NPC patients, was dripped onto the surface of the substrate for hyperspectral imaging. The characteristic spectral bands were selected based on the variable weight obtained from a support vector machine (SVM) model, using principal component analysis (PCA) to reduce the dimension in the extracted bands. Obtained results show that the accuracy rate, sensitivity, and specificity between the NPC sera and the sera of the healthy controls reached extremely high levels of 99.15%, 98.79%, and 99.36%, respectively. For the model's consistency evaluation, we found that the Kappa and area under the curve (AUC) of the receiver operating characteristic (ROC) curve were 0.99 and 0.98, respectively. These results suggest that the developed approach could serve as a noninvasive diagnostic and screening tool for highly accurate and consistent detection of NPC. Hence, a combination of hyperspectral imaging (HSI) and a weighted principal component analysis (WPCA)-SVM model represents a powerful and promising tool for NPC diagnosis.

Spatio-spectral classification of hyperspectral images for brain cancer detection during surgical operations

Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal brain by these tumors makes their accurate identification by the naked eye difficult. Since surgery is the common treatment for brain cancer, an accurate radical resection of the tumor leads to improved survival rates for patients. However, the identification of the tumor boundaries during surgery is challenging. Hyperspectral imaging is a non-contact, non-ionizing and non-invasive technique suitable for medical diagnosis. This study presents the development of a novel classification method taking into account the spatial and spectral characteristics of the hyperspectral images to help neurosurgeons to accurately determine the tumor boundaries in surgical-time during the resection, avoiding excessive excision of normal tissue or unintentionally leaving residual tumor. The algorithm proposed in this study to approach an efficient solution consists of a hybrid framework that combines both supervised and unsupervised machine learning methods. Firstly, a supervised pixel-wise classification using a Support Vector Machine classifier is performed. The generated classification map is spatially homogenized using a one-band representation of the HS cube, employing the Fixed Reference t-Stochastic Neighbors Embedding dimensional reduction algorithm, and performing a K-Nearest Neighbors filtering. The information generated by the supervised stage is combined with a segmentation map obtained via unsupervised clustering employing a Hierarchical K-Means algorithm. The fusion is performed using a majority voting approach that associates each cluster with a certain class. To evaluate the proposed approach, five hyperspectral images of surface of the brain affected by glioblastoma tumor in vivo from five different patients have been used. The final classification maps obtained have been analyzed and validated by specialists. These preliminary results are promising, obtaining an accurate delineation of the tumor area.

MatCol: a tool to measure fluorescence signal colocalisation in biological systems

Protein colocalisation is often studied using pixel intensity-based coefficients such as Pearson, Manders, Li or Costes. However, these methods cannot be used to study object-based colocalisations in biological systems. Therefore, a novel method is required to automatically identify regions of fluorescent signal in two channels, identify the co-located parts of these regions, and calculate the statistical significance of the colocalisation. We have developed MatCol to address these needs. MatCol can be used to visualise protein and/or DNA colocalisations and fine tune user-defined parameters for the colocalisation analysis, including the application of median or Wiener filtering to improve the signal to noise ratio. Command-line execution allows batch processing of multiple images. Users can also calculate the statistical significance of the observed object colocalisations compared to overlap by random chance using Student's t-test. We validated MatCol in a biological setting. The colocalisations of telomeric DNA and TRF2 protein or TRF2 and PML proteins in >350 nuclei derived from three different cell lines revealed a highly significant correlation between manual and MatCol identification of colocalisations (linear regression R2 = 0.81, P < 0.0001). MatCol has the ability to replace manual colocalisation counting, and the potential to be applied to a wide range of biological areas.

[Early recognition of cancerous lesions in the mouth and oropharynx: Automated evaluation of hyperspectral image stacks]

BACKGROUND

Early detection of cancerous lesions is still crucial for a patient's prognosis. Although diagnostic access to the oral cavity and oropharynx is comparably easy, the incidence of resulting disease remains high. This is due to the fact that in many cases, malignity is recognized too late on a purely visual basis. Previously, we discussed the application of hyperspectral imaging for early detection of precancerous and cancerous lesions of the larynx. This time, we evaluate the method in the oral cavity and oropharynx.

MATERIALS AND METHODS

In 85 patients scheduled for endoscopy, hyperspectral imaging was performed. We used a rigid 0-degree endoscope, a light-adjustable monochromator, and a hyperspectral camera. For evaluation of the method, 3 patients were chosen exemplarily. Training sites from physiological and cancerous tissues were marked. Hyperspectral data from 1 patient were used to train a classifier, which was then used for automatic detection of precancerous and cancerous lesions in another 2 patients.

RESULTS

Intraoperative hyperspectral imaging was performed without any problems. Classification showed sensitivities of 61 and 43%, and a specificity of 100%.

CONCLUSION

This proof-of-concept study underscores the high potential of hyperspectral imaging for early recognition of cancer in the mouth and oropharynx. Besides a better prognosis for cancer patients, this approach could lead to higher cost efficiency in the health system.

Hyperspectral Imaging Using Flexible Endoscopy for Laryngeal Cancer Detection

Hyperspectral imaging (HSI) is increasingly gaining acceptance in the medical field. Up until now, HSI has been used in conjunction with rigid endoscopy to detect cancer in vivo. The logical next step is to pair HSI with flexible endoscopy, since it improves access to hard-to-reach areas. While the flexible endoscope's fiber optic cables provide the advantage of flexibility, they also introduce an interfering honeycomb-like pattern onto images. Due to the substantial impact this pattern has on locating cancerous tissue, it must be removed before the HS data can be further processed. Thereby, the loss of information is to minimize avoiding the suppression of small-area variations of pixel values. We have developed a system that uses flexible endoscopy to record HS cubes of the larynx and designed a special filtering technique to remove the honeycomb-like pattern with minimal loss of information. We have confirmed its feasibility by comparing it to conventional filtering techniques using an objective metric and by applying unsupervised and supervised classifications to raw and pre-processed HS cubes. Compared to conventional techniques, our method successfully removes the honeycomb-like pattern and considerably improves classification performance, while preserving image details.