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.

Spatial and Spectral Reconstruction of Breast Lumpectomy Hyperspectral Images.

(1) Background: Hyperspectral imaging has emerged as a promising margin assessment technique for breast-conserving surgery. However, to be implicated intraoperatively, it should be both fast and capable of yielding high-quality images to provide accurate guidance and decision-making throughout the surgery. As there exists a trade-off between image quality and data acquisition time, higher resolution images come at the cost of longer acquisition times and vice versa. (2) Methods: Therefore, in this study, we introduce a deep learning spatial-spectral reconstruction framework to obtain a high-resolution hyperspectral image from a low-resolution hyperspectral image combined with a high-resolution RGB image as input. (3) Results: Using the framework, we demonstrate the ability to perform a fast data acquisition during surgery while maintaining a high image quality, even in complex scenarios where challenges arise, such as blur due to motion artifacts, dead pixels on the camera sensor, noise from the sensor's reduced sensitivity at spectral extremities, and specular reflections caused by smooth surface areas of the tissue. (4) Conclusion: This gives the opportunity to facilitate an accurate margin assessment through intraoperative hyperspectral 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.

Diffuse reflectance spectroscopy for accurate margin assessment in breast-conserving surgeries: importance of an optimal number of fibers.

During breast-conserving surgeries, it remains challenging to accomplish adequate surgical margins. We investigated different numbers of fibers for fiber-optic diffuse reflectance spectroscopy to differentiate tumorous breast tissue from healthy tissue ex vivo up to 2 mm from the margin. Using a machine-learning classification model, the optimal performance was obtained using at least three emitting fibers (Matthew's correlation coefficient (MCC) of 0.73), which was significantly higher compared to the performance of using a single-emitting fiber (MCC of 0.48). The percentage of correctly classified tumor locations varied from 75% to 100% depending on the tumor percentage, the tumor-margin distance and the number of fibers.

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.

Microcamera Visualisation System to Overcome Specular Reflections for Tissue Imaging.

In vivo tissue imaging is an essential tool for medical diagnosis, surgical guidance, and treatment. However, specular reflections caused by glossy tissue surfaces can significantly degrade image quality and hinder the accuracy of imaging systems. In this work, we further the miniaturisation of specular reflection reduction techniques using micro cameras, which have the potential to act as intra-operative supportive tools for clinicians. In order to remove these specular reflections, two small form factor camera probes, handheld at 10 mm footprint and miniaturisable to 2.3 mm, are developed using different modalities, with line-of-sight to further miniaturisation. (1) The sample is illuminated via multi-flash technique from four different positions, causing a shift in reflections which are then filtered out in a post-processing image reconstruction step. (2) The cross-polarisation technique integrates orthogonal polarisers onto the tip of the illumination fibres and camera, respectively, to filter out the polarisation maintaining reflections. These form part of a portable imaging system that is capable of rapid image acquisition using different illumination wavelengths, and employs techniques that lend themselves well to further footprint reduction. We demonstrate the efficacy of the proposed system with validating experiments on tissue-mimicking phantoms with high surface reflection, as well as on excised human breast tissue. We show that both methods can provide clear and detailed images of tissue structures along with the effective removal of distortion or artefacts caused by specular reflections. Our results suggest that the proposed system can improve the image quality of miniature in vivo tissue imaging systems and reveal underlying feature information at depth, for both human and machine observers, leading to better diagnosis and treatment outcomes.

Diffuse reflection spectroscopy at the fingertip: design and performance of a compact side-firing probe for tissue discrimination during colorectal cancer surgery.

Optical technologies are widely used for tissue sensing purposes. However, maneuvering conventional probe designs with flat-tipped fibers in narrow spaces can be challenging, for instance during pelvic colorectal cancer surgery. In this study, a compact side-firing fiber probe was developed for tissue discrimination during colorectal cancer surgery using diffuse reflectance spectroscopy. The optical behavior was compared to flat-tipped fibers using both Monte Carlo simulations and experimental phantom measurements. The tissue classification performance was examined using freshly excised colorectal cancer specimens. Using the developed probe and classification algorithm, an accuracy of 0.92 was achieved for discriminating tumor tissue from healthy tissue.

Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging.

Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.

Layer thickness prediction and tissue classification in two-layered tissue structures using diffuse reflectance spectroscopy.

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

Optical tissue measurements of invasive carcinoma and ductal carcinoma in situ for surgical guidance.

BACKGROUND: Although the incidence of positive resection margins in breast-conserving surgery has decreased, both incomplete resection and unnecessary large resections still occur. This is especially the case in the surgical treatment of ductal carcinoma in situ (DCIS). Diffuse reflectance spectroscopy (DRS), an optical technology based on light tissue interactions, can potentially characterize tissue during surgery thereby guiding the surgeon intraoperatively. DRS has shown to be able to discriminate pure healthy breast tissue from pure invasive carcinoma (IC) but limited research has been done on (1) the actual optical characteristics of DCIS and (2) the ability of DRS to characterize measurements that are a mixture of tissue types. METHODS: In this study, DRS spectra were acquired from 107 breast specimens from 107 patients with proven IC and/or DCIS (1488 measurement locations). With a generalized estimating equation model, the differences between the DRS spectra of locations with DCIS and IC and only healthy tissue were compared to see if there were significant differences between these spectra. Subsequently, different classification models were developed to be able to predict if the DRS spectrum of a measurement location represented a measurement location with "healthy" or "malignant" tissue. In the development and testing of the models, different definitions for "healthy" and "malignant" were used. This allowed varying the level of homogeneity in the train and test data. RESULTS: It was found that the optical characteristics of IC and DCIS were similar. Regarding the classification of tissue with a mixture of tissue types, it was found that using mixed measurement locations in the development of the classification models did not tremendously improve the accuracy of the classification of other measurement locations with a mixture of tissue types. The evaluated classification models were able to classify measurement locations with > 5% malignant cells with a Matthews correlation coefficient of 0.41 or 0.40. Some models showed better sensitivity whereas others had better specificity. CONCLUSION: The results suggest that DRS has the potential to detect malignant tissue, including DCIS, in healthy breast tissue and could thus be helpful for surgical guidance.

Experimental validation of a recently developed model for single-fiber reflectance spectroscopy.

SIGNIFICANCE: We recently developed a model for the reflectance measured with (multi-diameter) single-fiber reflectance (SFR) spectroscopy as a function of the reduced scattering coefficient µs', the absorption coefficient µa, and the phase function parameter psb. We validated this model with simulations. AIM: We validate our model experimentally. To prevent overfitting, we investigate the wavelength-dependence of psb and propose a parametrization with only three parameters. We also investigate whether this parametrization enables measurements with a single fiber, as opposed to multiple fibers used in multi-diameter SFR (MDSFR). APPROACH: We validate our model on 16 phantoms with two concentrations of Intralipid-20% (µs'=13 and 21 cm - 1 at 500 nm) and eight concentrations of Evans Blue (µa = 1 to 20 cm - 1 at 605 nm). We parametrize psb as 10 - 5 · ( p1 ( λ / 650 ) + p2(λ/650)2 + p3(λ/650)3 ) . RESULTS: Average errors were 7% for µs', 11% for µa, and 16% with the parametrization of psb; and 7%, 17%, and 16%, respectively, without. The parametrization of psb improved the fit speed 25 times (94 s to <4 s). Average errors for only one fiber were 50%, 33%, and 186%, respectively. CONCLUSIONS: Our recently developed model provides accurate results for MDSFR measurements but not for a single fiber. The psb parametrization prevents overfitting and speeds up the fit.

Toward improved endoscopic surveillance with multidiameter single fiber reflectance spectroscopy in patients with Barrett's esophagus.

Patients with Barrett's esophagus are at an increased risk to develop esophageal cancer and, therefore, undergo regular endoscopic surveillance. Early detection of neoplasia enables endoscopic treatment, which improves outcomes. However, early Barrett's neoplasia is easily missed during endoscopic surveillance. This study investigates multidiameter single fiber reflectance spectroscopy (MDSFR) to improve Barrett's surveillance. Based on the concept of field cancerization, it may be possible to identify the presence of a neoplastic lesion from measurements elsewhere in the esophagus or even the oral cavity. In this study, MDSFR measurements are performed on non-dysplastic Barrett's mucosa, squamous mucosa, oral mucosa, and the neoplastic lesion (if present). Based on logistic regression analysis on the scattering parameters measured by MDSFR, a classifier is developed that can predict the presence of neoplasia elsewhere in the Barrett's segment from measurements on the non-dysplastic Barrett's mucosa (sensitivity 91%, specificity 71%, AUC = 0.77). Classifiers obtained from logistic regression analysis for the squamous and oral mucosa do not result in an AUC significantly different from 0.5.

Subdiffuse scattering and absorption model for single fiber reflectance spectroscopy.

Single fiber reflectance (SFR) spectroscopy is a technique that is sensitive to small-scale changes in tissue. An additional benefit is that SFR measurements can be performed through endoscopes or biopsy needles. In SFR spectroscopy, a single fiber emits and collects light. Tissue optical properties can be extracted from SFR spectra and related to the disease state of tissue. However, the model currently used to extract optical properties was derived for tissues with modified Henyey-Greenstein phase functions only and is inadequate for other tissue phase functions. Here, we will present a model for SFR spectroscopy that provides accurate results for a large range of tissue phase functions, reduced scattering coefficients, and absorption coefficients. Our model predicts the reflectance with a median error of 5.6% compared to 19.3% for the currently used model. For two simulated tissue spectra, our model fit provides accurate results.

Analytical model for diffuse reflectance in single fiber reflectance spectroscopy.

Cancer progression leads to changing scattering properties of affected tissues. Single fiber reflectance (SFR) spectroscopy detects these changes at small spatial scales, making it a promising tool for early in situ detection. Despite its simplicity and versatility, SFR signal modeling is hugely complicated so that, presently, only approximate models exist. We use a classic approach from geometrical probability to derive accurate analytical expressions for diffuse reflectance in SFR that shows a strong improvement over existing models. We consider the case of limited collection efficiency and the presence of absorption. A Monte Carlo light transport study demonstrates that we adequately describe the contribution of diffuse reflectance to the SFR signal. Additional steps are required to include semi-ballistic, non-diffuse reflectance also present in the SFR measurement.

Subdiffuse scattering model for single fiber reflectance spectroscopy.

To detect small-scale changes in tissue with optical techniques, small sampling volumes are required. Single fiber reflectance (SFR) spectroscopy has a sampling depth of a few hundred micrometers. SFR spectroscopy uses a single fiber to emit and collect light. The only available model to determine optical properties with SFR spectroscopy was derived for tissues with modified Henyey-Greenstein phase functions. Previously, we demonstrated that this model is inadequate for other tissue phase functions. We develop a model to relate SFR measurements to scattering properties for a range of phase functions, in the absence of absorption. Since the source and detector overlap, the reflectance cannot be accurately described by diffusion theory alone: SFR measurements are subdiffuse. Therefore, we describe the reflectance as a combination of a diffuse and a semiballistic component. We use the model of Farrell et al. for the diffuse component, solved for an overlapping source and detector fiber. For the semiballistic component, we derive a new parameter, psb, which incorporates the integrals of the phase function over 1 deg in the backward direction and 23 deg in the forward direction. Our model predicts the reflectance with a median error of 2.1%, compared to 9.0% for the currently available model.

Toward assessment of resection margins using hyperspectral diffuse reflection imaging (400-1,700 nm) during tongue cancer surgery.

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.

Using Diffuse Reflectance Spectroscopy to Distinguish Tumor Tissue From Fibrosis in Rectal Cancer Patients as a Guide to Surgery.

BACKGROUND AND OBJECTIVES: In patients with rectal cancer who received neoadjuvant (chemo)radiotherapy, fibrosis is induced in and around the tumor area. As tumors and fibrosis have similar visual and tactile feedback, they are hard to distinguish during surgery. To prevent positive resection margins during surgery and spare healthy tissue, it would be of great benefit to have a real-time tissue classification technology that can be used in vivo. STUDY DESIGN/MATERIALS AND METHODS: In this study diffuse reflectance spectroscopy (DRS) was evaluated for real-time tissue classification of tumor and fibrosis. DRS spectra of fibrosis and tumor were obtained on excised rectal specimens. After normalization using the area under the curve, a support vector machine was trained using a 10-fold cross-validation. RESULTS: Using spectra of pure tumor tissue and pure fibrosis tissue, we obtained a mean accuracy of 0.88. This decreased to a mean accuracy of 0.61 when tumor measurements were used in which a layer of healthy tissue, mainly fibrosis, was present between the tumor and the measurement surface. CONCLUSION: It is possible to distinguish pure fibrosis from pure tumor. However, when the measurements on tumor also involve fibrotic tissue, the classification accuracy decreases. Lasers Surg. Med. © 2019 Wiley Periodicals, Inc.

Multidiameter single-fiber reflectance spectroscopy of heavily pigmented skin: modeling the inhomogeneous distribution of melanin.

When analyzing multidiameter single-fiber reflectance (MDSFR) spectra, the inhomogeneous distribution of melanin pigments in skin tissue is usually not accounted for. Especially in heavily pigmented skins, this can result in bad fits and biased estimation of tissue optical properties. A model is introduced to account for the inhomogeneous distribution of melanin pigments in skin tissue. In vivo visible MDSFR measurements were performed on heavily pigmented skin of type IV to VI. Skin tissue optical properties and related physiological properties were extracted from the measured spectra using the introduced model. The absorption of melanin pigments described by the introduced model demonstrates a good correlation with the co-localized measurement of the well-known melanin index.

Optimizing algorithm development for tissue classification in colorectal cancer based on diffuse reflectance spectra.

Diffuse reflectance spectroscopy can be used in colorectal cancer surgery for tissue classification. The main challenge in the classification task is to separate healthy colorectal wall from tumor tissue. In this study, four normalization techniques, four feature extraction methods and five classifiers are applied to nine datasets, to obtain the optimal method to separate spectra measured on healthy colorectal wall from spectra measured on tumor tissue. All results are compared to the use of the entire non-normalized spectra. It is found that the most optimal classification approach is to apply a feature extraction method on non-normalized spectra combined with support vector machine or neural network classifier.

Broadband hyperspectral imaging for breast tumor detection using spectral and spatial information.

Complete tumor removal during breast-conserving surgery remains challenging due to the lack of optimal intraoperative margin assessment techniques. Here, we use hyperspectral imaging for tumor detection in fresh breast tissue. We evaluated different wavelength ranges and two classification algorithms; a pixel-wise classification algorithm and a convolutional neural network that combines spectral and spatial information. The highest classification performance was obtained using the full wavelength range (450-1650 nm). Adding spatial information mainly improved the differentiation of tissue classes within the malignant and healthy classes. High sensitivity and specificity were accomplished, which offers potential for hyperspectral imaging as a margin assessment technique to improve surgical outcome.