Review: in vivo optical spectral tissue sensing-how to go from research to routine clinical application?

A Contrast-Enhanced CT-Based Deep Learning System for Preoperative Prediction of Colorectal Cancer Staging and RAS Mutation

PURPOSE

This study aimed to build a deep learning system using enhanced computed tomography (CT) portal-phase images for predicting colorectal cancer patients' preoperative staging and RAS gene mutation status.

METHODS

The contrast-enhanced CT image dataset comprises the CT portal-phase images from a retrospective cohort of 231 colorectal cancer patients. The deep learning system was developed via migration learning for colorectal cancer detection, staging, and RAS gene mutation status prediction. This study used pre-trained Yolov7, vision transformer (VIT), swin transformer (SWT), EfficientNetV2, and ConvNeXt. 4620, and contrast-enhanced CT images and annotated tumor bounding boxes were included in the tumor identification and staging dataset. A total of 19,700 contrast-enhanced CT images comprise the RAS gene mutation status prediction dataset.

RESULTS

In the validation cohort, the Yolov7-based detection model detected and staged tumors with a mean accuracy precision (IoU = 0.5) (mAP_0.5) of 0.98. The area under the receiver operating characteristic curve (AUC) in the test set and validation set for the VIT-based prediction model in predicting the mutation status of the RAS genes was 0.9591 and 0.9554, respectively. The detection network and prediction network of the deep learning system demonstrated great performance in explaining contrast-enhanced CT images.

CONCLUSION

In this study, a deep learning system was created based on the foundation of contrast-enhanced CT portal-phase imaging to preoperatively predict the stage and RAS mutation status of colorectal cancer patients. This system will help clinicians choose the best treatment option to increase colorectal cancer patients' chances of survival and quality of life.

Accurate preoperative staging and HER2 status prediction of gastric cancer by the deep learning system based on enhanced computed tomography

PURPOSE

To construct the deep learning system (DLS) based on enhanced computed tomography (CT) images for preoperative prediction of staging and human epidermal growth factor receptor 2 (HER2) status in gastric cancer patients.

METHODS

The raw enhanced CT image dataset consisted of CT images of 389 patients in the retrospective cohort, The Cancer Imaging Archive (TCIA) cohort, and the prospective cohort. DLS was developed by transfer learning for tumor detection, staging, and HER2 status prediction. The pre-trained Yolov5, EfficientNet, EfficientNetV2, Vision Transformer (VIT), and Swin Transformer (SWT) were studied. The tumor detection and staging dataset consisted of 4860 enhanced CT images and annotated tumor bounding boxes. The HER2 state prediction dataset consisted of 38900 enhanced CT images.

RESULTS

The DetectionNet based on Yolov5 realized tumor detection and staging and achieved a mean Average Precision (IoU=0.5) (mAP_0.5) of 0.909 in the external validation cohort. The VIT-based PredictionNet performed optimally in HER2 status prediction with the area under the receiver operating characteristics curve (AUC) of 0.9721 and 0.9995 in the TCIA cohort and prospective cohort, respectively. DLS included DetectionNet and PredictionNet had shown excellent performance in CT image interpretation.

CONCLUSION

This study developed the enhanced CT-based DLS to preoperatively predict the stage and HER2 status of gastric cancer patients, which will help in choosing the appropriate treatment to improve the survival of gastric cancer patients.

Tissue-mimicking phantom materials with tunable optical properties suitable for assessment of diffuse reflectance spectroscopy during electrosurgery

Emerging intraoperative tumor margin assessment techniques require the development of more complex and reliable organ phantoms to assess the performance of the technique before its translation into the clinic. In this work, electrically conductive tissue-mimicking materials (TMMs) based on fat, water and agar/gelatin were produced with tunable optical properties. The composition of the phantoms allowed for the assessment of tumor margins using diffuse reflectance spectroscopy, as the fat/water ratio served as a discriminating factor between the healthy and malignant tissue. Moreover, the possibility of using polyvinyl alcohol (PVA) or transglutaminase in combination with fat, water and gelatin for developing TMMs was studied. The diffuse spectral response of the developed phantom materials had a good match with the spectral response of porcine muscle and adipose tissue, as well as in vitro human breast tissue. Using the developed recipe, anatomically relevant heterogeneous breast phantoms representing the optical properties of different layers of the human breast were fabricated using 3D-printed molds. These TMMs can be used for further development of phantoms applicable for simulating the realistic breast conserving surgery workflow in order to evaluate the intraoperative optical-based tumor margin assessment techniques during electrosurgery.

Monitoring the Response of Skin Melanoma Cell Line (A375) to Treatment with Vemurafenib: A Pilot In Vitro Optical Spectroscopic Study

Objective: The aim of this study was to investigate the feasibility of optical spectroscopy as a nondestructive approach in monitoring the skin melanoma cancer cell response to treatment. Background: Owing to the growing trend of personalized medicine, monitoring the treatment response individually is particularly crucial for optimizing cancer therapy efficiency. In the past decade, optical sensing, using diffuse reflectance spectroscopy, has been used to improve the identification of cancerous lesions in various organs. Until now, surveys have mainly focused on the nondestructive application of optical sensing used to diagnose and discriminate normal and abnormal biomedical lesions or samples. Meanwhile, the response to the treatment might be monitored using these nondestructive technologies, thereby enabling further therapeutic modification. Methods: The human skin melanoma cell line (A375) donated from Switzerland (University Hospital Basel) was cultured. Vemurafenib (Zelboraf; Genentech/Roche, South San Francisco, CA) was used for cell treatments. The visible-near-infrared reflectance spectroscopy was conducted at different time intervals (before treatment, and at 1, 2, 7, and 14 days post-treatment for three drug doses 5, 25, and 75 μM) on cell plates using the portable CCD-based fiber optical spectrometer (USB2000; Ocean Optics). After data collection, the refractive index analysis for the fore-mentioned doses and days in one selected wavelength of 620 nm was examined using the previously developed computer program. Then, biological assays were selected as gold standard of cell death, apoptosis, and drug resistance gene expression. Results: There was a considerable decrease in the refractive index of cell samples in which biological assay confirmed cell death. Based on the flow cytometry data, a drug dose of 25 μM on day 7 seemed to induce necrosis. These findings show that spectroscopic findings strongly agree with concurrent biological studies and might lead to their use as an alternative method for monitoring treatment response to achieve more optimized cancer treatment. Conclusions: The findings show that reflectance spectroscopy, as a nondestructive real-time label-free way, is capable of providing quantitative information for treatment response determination that corresponds with biological assays.

Ultrawide-bandwidth on-chip spectrometer design using band-pass filters

Here, we present the design and simulation of an ultrawide-bandwidth on-chip spectrometer that can be used in various applications, e.g. spectral tissue sensing. It covers 1200 nm wavelength range (400 nm-1600 nm) with 2 nm spectral resolution. The overall design size is only 3 × 3 cm². The ultra-wide spectral range is made possible by using novel on-chip band-pass filters for the coarse wavelength division. The fine resolution is provided by the arrayed waveguide gratings. The band-pass filter is formed by using bend waveguides and adiabatic full-couplers. The additional loss caused by the band-pass filter is relatively small. The proposed spectrometer covers entire 400 nm-1600 nm range continuously with low crosstalk values. We envision that this design can be used in several different applications including food safety, agriculture, industrial inspection, optical imaging, and biomedical research.

Biochemical characterization of pathogenic bacterial species using Raman spectroscopy and discrimination model based on selected spectral features

This study aimed to evaluate the differences in the Raman spectra of nine clinical species of bacteria isolated from infections (three Gram-positive and six Gram-negative species), correlating the spectra with the chemical composition of each species and to develop a classification model through discriminant analysis to categorize each bacterial strain using the peaks with the most significant differences. Bacteria were cultured in Mueller Hinton agar and a sample of biomass was harvested and placed in an aluminum sample holder. A total of 475 spectra from 115 different strains were obtained through a dispersive Raman spectrometer (830 nm) with exposure time of 50 s. The intensities of the peaks were evaluated by one-way analysis of variance (ANOVA) and the peaks with significant differences were related to the differences in the biochemical composition of the strains. Discriminant analysis based on quadratic distance applied to the peaks with the most significant differences and partial least squares applied to the whole spectrum showed 89.5% and 90.1% of global accuracy, respectively, for classification of the spectra in all the groups. Raman spectroscopy could be a promising technique to identify spectral differences related to the biochemical content of pathogenic microorganisms and to provide a faster diagnosis of infectious diseases.

Developing Fully Automated Quality Control Methods for Preprocessing Raman Spectra of Biomedical and Biological Samples

Spectral preprocessing is frequently required to render Raman spectra useful for further processing and analyses. The various preprocessing steps, individually and sequentially, are increasingly being automated to cope with large volumes of data from, for example, hyperspectral imaging studies. Full automation of preprocessing is especially desirable when it produces consistent results and requires minimal user input. It is therefore essential to evaluate the "quality" of such preprocessed spectra. However, relatively few methods exist to evaluate preprocessing quality, and fully automated methods for doing so are virtually non-existent. Here we provide a brief overview of fully automated spectral preprocessing and fully automated quality assessment of preprocessed spectra. We follow this with the introduction of fully automated methods to establish figures-of-merit that encapsulate preprocessing quality. By way of illustration, these quantitative methods are applied to simulated and real Raman spectra. Quality factor and quality parameter figures-of-merit resulting from individual preprocessing step quality tests, as well as overall figures-of-merit, were found to be consistent with the quality of preprocessed spectra.

Rapid intra-operative diagnosis of kidney cancer by attenuated total reflection infrared spectroscopy of tissue smears

Herein, a technique to analyze air-dried kidney tissue impression smears by means of attenuated total reflection infrared (ATR-IR) spectroscopy is presented. Spectral tumor markers-absorption bands of glycogen-are identified in the ATR-IR spectra of the kidney tissue smear samples. Thin kidney tissue cryo-sections currently used for IR spectroscopic analysis lack such spectral markers as the sample preparation causes irreversible molecular changes in the tissue. In particular, freeze-thaw cycle results in degradation of the glycogen and reduction or complete dissolution of its content. Supervised spectral classification was applied to the recorded spectra of the smears and the test spectra were classified with a high accuracy of 92% for normal tissue and 94% for tumor tissue, respectively. For further development, we propose that combination of the method with optical fiber ATR probes could potentially be used for rapid real-time intra-operative tissue analysis without interfering with either the established protocols of pathological examination or the ordinary workflow of operating surgeon. Such approach could ensure easier transition of the method to clinical applications where it may complement the results of gold standard histopathology examination and aid in more precise resection of kidney tumors.