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

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.

Real-time classification of tumour and non-tumour tissue in colorectal cancer using diffuse reflectance spectroscopy and neural networks to aid margin assessment

BACKGROUND

Colorectal cancer is the third most commonly diagnosed malignancy and the second leading cause of mortality worldwide. A positive resection margin following surgery for colorectal cancer is linked with higher rates of local recurrence and poorer survival. We investigated diffuse reflectance spectroscopy (DRS) to distinguish tumour and non-tumour tissue in ex vivo colorectal specimens, to aid margin assessment and provide augmented visual maps to the surgeon in real-time.

METHODS

Patients undergoing elective colorectal cancer resection surgery at a London-based hospital were prospectively recruited. A hand-held DRS probe was used on the surface of freshly resected ex vivo colorectal tissue. Spectral data was acquired for tumour and non-tumour tissue. Binary classification was achieved using conventional machine learning classifiers and a convolutional neural network (CNN), which were evaluated in terms of sensitivity, specificity, accuracy and the area under the curve.

RESULTS

A total of 7692 mean spectra were obtained for tumour and non-tumour colorectal tissue. The CNN-based classifier was the best performing machine learning algorithm, when compared to contrastive approaches, for differentiating tumour and non-tumour colorectal tissue, with an overall diagnostic accuracy of 90.8% and area under the curve of 96.8%. Live on-screen classification of tissue type was achieved using a graduated colourmap.

CONCLUSION

A high diagnostic accuracy for a DRS probe and tracking system to differentiate ex vivo tumour and non-tumour colorectal tissue in real-time with on-screen visual feedback was highlighted by this study. Further in vivo studies are needed to ensure integration into a surgical workflow.

Diffuse reflectance spectroscopy for colorectal cancer surgical guidance: towards real-time tissue characterization and new biomarkers

Colorectal cancer (CRC) is the third most common and second most deadly type of cancer worldwide, representing 11.3% of the diagnosed cancer cases and resulting in 10.2% (0.88 million) of the cancer related deaths in 2020. CRCs are typically detected at the late stage, which leads to high mortality and morbidity. Mortality and poor prognosis are partially caused by cancer recurrence and postoperative complications. Patient survival could be increased by improving precision in surgical resection using accurate surgical guidance tools based on diffuse reflectance spectroscopy (DRS). DRS enables real-time tissue identification for potential cancer margin delineation through determination of the circumferential resection margin (CRM), while also supporting non-invasive and label-free approaches for laparoscopic surgery to avoid short-term complications of open surgery as suitable. In this study, we have estimated the scattering properties and chromophore concentrations based on 2949 DRS measurements of freshly excised ex vivo specimens of 47 patients, and used this estimation to classify normal colorectal wall (CW), fat and tumor tissues. DRS measurements were performed with fiber-optic probes of 630 μm source-detector distance (SDD; probe 1) and 2500 μm SDD (probe 2) to measure tissue layers ∼0.5-1 mm and ∼0.5-2 mm deep, respectively. By using the 5-fold cross-validation of machine learning models generated with the classification and regression tree (CART) algorithm, we achieved 95.9 ± 0.7% sensitivity, 98.9 ± 0.3% specificity, 90.2 ± 0.4% accuracy, and 95.5 ± 0.3% AUC for probe 1. Similarly, we achieved 96.9 ± 0.8% sensitivity, 98.9 ± 0.2% specificity, 94.0 ± 0.4% accuracy, and 96.7 ± 0.4% AUC for probe 2.

Frameworks of wavelength selection in diffuse reflectance spectroscopy for tissue differentiation in orthopedic surgery

Significance

Wavelength selection from a large diffuse reflectance spectroscopy (DRS) dataset enables removal of spectral multicollinearity and thus leads to improved understanding of the feature domain. Feature selection (FS) frameworks are essential to discover the optimal wavelengths for tissue differentiation in DRS-based measurements, which can facilitate the development of compact multispectral optical systems with suitable illumination wavelengths for clinical translation.

Aim

The aim was to develop an FS methodology to determine wavelengths with optimal discriminative power for orthopedic applications, while providing the frameworks for adaptation to other clinical scenarios.

Approach

An ensemble framework for FS was developed, validated, and compared with frameworks incorporating conventional algorithms, including principal component analysis (PCA), linear discriminant analysis (LDA), and backward interval partial least squares (biPLS).

Results

Via the one-versus-rest binary classification approach, a feature subset of 10 wavelengths was selected from each framework yielding comparable balanced accuracy scores (PCA: 94.8 ± 3.47 % , LDA: 98.2 ± 2.02 % , biPLS: 95.8 ± 3.04 % , and ensemble: 95.8 ± 3.16 % ) to those of using all features (100%) for cortical bone versus the rest class labels. One hundred percent balanced accuracy scores were generated for bone cement versus the rest. Different feature subsets achieving similar outcomes could be identified due to spectral multicollinearity.

Conclusions

Wavelength selection frameworks provide a means to explore domain knowledge and discover important contributors to classification in spectroscopy. The ensemble framework generated a model with improved interpretability and preserved physical interpretation, which serves as the basis to determine illumination wavelengths in optical instrumentation design.

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.

Insights into Biochemical Sources and Diffuse Reflectance Spectral Features for Colorectal Cancer Detection and Localization

Colorectal cancer (CRC) is the third most common and second most deadly type of cancer worldwide. Early detection not only reduces mortality but also improves patient prognosis by allowing the use of minimally invasive techniques to remove cancer while avoiding major surgery. Expanding the use of microsurgical techniques requires accurate diagnosis and delineation of the tumor margins in order to allow complete excision of cancer. We have used diffuse reflectance spectroscopy (DRS) to identify the main optical CRC biomarkers and to optimize parameters for the integration of such technologies into medical devices. A total number of 2889 diffuse reflectance spectra were collected in ex vivo specimens from 47 patients. Short source-detector distance (SDD) and long-SDD fiber-optic probes were employed to measure tissue layers from 0.5 to 1 mm and from 0.5 to 1.9 mm deep, respectively. The most important biomolecules contributing to differentiating DRS between tissue types were oxy- and deoxy-hemoglobin (Hb and HbO₂), followed by water and lipid. Accurate tissue classification and potential DRS device miniaturization using Hb, HbO₂, lipid and water data were achieved particularly well within the wavelength ranges 350-590 nm and 600-1230 nm for the short-SDD probe, and 380-400 nm, 420-610 nm, and 650-950 nm for the long-SDD probe.

Comparison of preprocessing techniques to reduce nontissue-related variations in hyperspectral reflectance imaging

SIGNIFICANCE

Hyperspectral reflectance imaging can be used in medicine to identify tissue types, such as tumor tissue. Tissue classification algorithms are developed based on, e.g., machine learning or principle component analysis. For the development of these algorithms, data are generally preprocessed to remove variability in data not related to the tissue itself since this will improve the performance of the classification algorithm. In hyperspectral imaging, the measured spectra are also influenced by reflections from the surface (glare) and height variations within and between tissue samples.

AIM

To compare the ability of different preprocessing algorithms to decrease variations in spectra induced by glare and height differences while maintaining contrast based on differences in optical properties between tissue types.

APPROACH

We compare eight preprocessing algorithms commonly used in medical hyperspectral imaging: standard normal variate, multiplicative scatter correction, min-max normalization, mean centering, area under the curve normalization, single wavelength normalization, first derivative, and second derivative. We investigate conservation of contrast stemming from differences in: blood volume fraction, presence of different absorbers, scatter amplitude, and scatter slope-while correcting for glare and height variations. We use a similarity metric, the overlap coefficient, to quantify contrast between spectra. We also investigate the algorithms for clinical datasets from the colon and breast.

CONCLUSIONS

Preprocessing reduces the overlap due to glare and distance variations. In general, the algorithms standard normal variate, min-max, area under the curve, and single wavelength normalization are the most suitable to preprocess data used to develop a classification algorithm for tissue classification. The type of contrast between tissue types determines which of these four algorithms is most suitable.

Picosecond-resolved fluorescence resonance energy transfer (FRET) in diffuse reflectance spectroscopy explores biologically relevant hidden molecular contacts in a non-invasive way

The potentiality of Förster resonance energy transfer (FRET) for studying molecular interactions inside biological tissues with improved spatial (Angström) and temporal (picosecond) resolution is well established. On the other hand, the efficacy of diffuse reflectance spectroscopy (DRS) that uses optical radiation in order to determine physiological parameters including haemoglobin, and oxygen saturation is well known. Here we have made an attempt to combine diffuse reflectance spectroscopy (DRS) with picosecond-resolved FRET in order to show improvement in the exploration of molecular contacts in biological tissue models. We define the technique as ultrafast time-resolved diffuse reflectance spectroscopy (UTRDRS). The illuminated photon of the fluorophore from the surface of the tissue-mimicking layers carries the hidden information of the molecular contact. In order to investigate the validation of the Kubelka-Munk (KM) formulism for the developed UTRDRS technique in tissue phantoms, we have studied the propagation of incandescent and picosecond-laser light through several layers of cellulose membranes. While picosecond-resolved FRET in the diffuse reflected light confirms the hidden nano-contact (4.6 nm) of two different dye layers (8-anilino-1-naphthalenesulfonic acid and Nile blue), high-resolution optical microscopy on the cross-section of the layers reveals the proximity and contacts of the layers with limited spatial resolution (∼300 nm). We have also investigated two biologically relevant molecules, namely carboxyfluorescein and haemoglobin, in tissue phantom layers in order to show the efficacy of the UTRDRS technique. Overall, our studies based on UTRDRS in tissue mimicking layers may have potential applications in non-invasive biomedical diagnosis for patients suffering from skin diseases.

Real-time tracking of a diffuse reflectance spectroscopy probe used to aid histological validation of margin assessment in upper gastrointestinal cancer resection surgery

SIGNIFICANCE

Diffuse reflectance spectroscopy (DRS) allows discrimination of tissue type. Its application is limited by the inability to mark the scanned tissue and the lack of real-time measurements.

AIM

This study aimed to develop a real-time tracking system to enable localization of a DRS probe to aid the classification of tumor and non-tumor tissue.

APPROACH

A green-colored marker attached to the DRS probe was detected using hue-saturation-value (HSV) segmentation. A live, augmented view of tracked optical biopsy sites was recorded in real time. Supervised classifiers were evaluated in terms of sensitivity, specificity, and overall accuracy. A developed software was used for data collection, processing, and statistical analysis.

RESULTS

The measured root mean square error (RMSE) of DRS probe tip tracking was 1.18  ±  0.58  mm and 1.05  ±  0.28  mm for the x and y dimensions, respectively. The diagnostic accuracy of the system to classify tumor and non-tumor tissue in real time was 94% for stomach and 96% for the esophagus.

CONCLUSIONS

We have successfully developed a real-time tracking and classification system for a DRS probe. When used on stomach and esophageal tissue for tumor detection, the accuracy derived demonstrates the strength and clinical value of the technique to aid margin assessment in cancer resection surgery.

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.

Diffuse Reflectance Parameters of Treated Leishmaniasis Cutaneous Ulcers and Association with Histopathologies in an Animal Model: A Proof of Concept

Cutaneous leishmaniasis (CL) is a parasitic disease that produces chronic skin ulcers. Although it has a worldwide presence, it is a neglected disease that still requires novel tools for its management. In order to study the use of optical tools in CL, this article presents a preliminary study of the correlation between CL histopathological and optical parameters. Optical parameters correspond to absorption and scattering coefficients obtained from diffuse reflectance spectra of treated CL in golden hamsters. Independently, histopathological data were collected from the same hamsters. As a result, after Spearman correlation and the Kruskal-Wallis test, inverse correlation was found between absorption/scattering optical parameters and inflammatory histopathological values, such as the scattering parameter related to the diameter of fibroblasts with the histopathological parameters of fibrosis, polymorphonuclear neutrophils, lymphocytes, plasmocytes, hyperplasia, and Leishmania, and the absorption parameter oxygen saturation showed a relation with the granulation tissue histopathological parameter. These correlations agree with the expected behavior of tissue composition during the healing process in CL. The results correspond to a proof of concept that shows that optical diffuse reflectance-based tools and methods could be considered as an alternative to assist in CL diagnosis and treatment follow-up.

Over 1000 nm Near-Infrared Multispectral Imaging System for Laparoscopic In Vivo Imaging

In this study, a laparoscopic imaging device and a light source able to select wavelengths by bandpass filters were developed to perform multispectral imaging (MSI) using over 1000 nm near-infrared (OTN-NIR) on regions under a laparoscope. Subsequently, MSI (wavelengths: 1000–1400 nm) was performed using the built device on nine live mice before and after tumor implantation. The normal and tumor pixels captured within the mice were used as teaching data sets, and the tumor-implanted mice data were classified using a neural network applied following a leave-one-out cross-validation procedure. The system provided a specificity of 89.5%, a sensitivity of 53.5%, and an accuracy of 87.8% for subcutaneous tumor discrimination. Aggregated true-positive (TP) pixels were confirmed in all tumor-implanted mice, which indicated that the laparoscopic OTN-NIR MSI could potentially be applied in vivo for classifying target lesions such as cancer in deep tissues.

Evaluation of wavelength ranges and tissue depth probed by diffuse reflectance spectroscopy for colorectal cancer detection

Colorectal cancer (CRC) is the third most common type of cancer worldwide and the second most deadly. Recent research efforts have focused on developing non-invasive techniques for CRC detection. In this study, we evaluated the diagnostic capabilities of diffuse reflectance spectroscopy (DRS) for CRC detection by building 6 classification models based on support vector machines (SVMs). Our dataset consists of 2889 diffuse reflectance spectra collected from freshly excised ex vivo tissues of 47 patients over wavelengths ranging from 350 and 1919 nm with source-detector distances of 630-µm and 2500-µm to probe different depths. Quadratic SVMs were used and performance was evaluated using twofold cross-validation on 10 iterations of randomized training and test sets. We achieved (93.5 ± 2.4)% sensitivity, (94.0 ± 1.7)% specificity AUC by probing the superficial colorectal tissue and (96.1 ± 1.8)% sensitivity, (95.7 ± 0.6)% specificity AUC by sampling deeper tissue layers. To the best of our knowledge, this is the first DRS study to investigate the potential of probing deeper tissue layers using larger SDD probes for CRC detection in the luminal wall. The data analysis showed that using a broader spectrum and longer near-infrared wavelengths can improve the diagnostic accuracy of CRC as well as probing deeper tissue layers.

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.