Journal of Biomedical Optics最新文献

{"title":"Hyperspectral imaging with deep learning for quantification of tissue hemoglobin, melanin, and scattering.","authors":"Thomas T Livecchi, Steven L Jacques, Hrebesh M Subhash, Mark C Pierce","doi":"10.1117/1.JBO.29.9.093507","DOIUrl":"10.1117/1.JBO.29.9.093507","url":null,"abstract":"<p><strong>Significance: </strong>Hyperspectral cameras capture spectral information at each pixel in an image. Acquired spectra can be analyzed to estimate quantities of absorbing and scattering components, but the use of traditional fitting algorithms over megapixel images can be computationally intensive. Deep learning algorithms can be trained to rapidly analyze spectral data and can potentially process hyperspectral camera data in real time.</p><p><strong>Aim: </strong>A hyperspectral camera was used to capture <math><mrow><mn>1216</mn> <mo>×</mo> <mn>1936</mn> <mtext>  pixel</mtext></mrow> </math> wide-field reflectance images of <i>in vivo</i> human tissue at 205 wavelength bands from 420 to 830 nm.</p><p><strong>Approach: </strong>The optical properties of oxyhemoglobin, deoxyhemoglobin, melanin, and scattering were used with multi-layer Monte Carlo models to generate simulated diffuse reflectance spectra for 24,000 random combinations of physiologically relevant tissue components. These spectra were then used to train an artificial neural network (ANN) to predict tissue component concentrations from an input reflectance spectrum.</p><p><strong>Results: </strong>The ANN achieved low root mean square errors in a test set of 6000 independent simulated diffuse reflectance spectra while calculating concentration values more than 4000× faster than a conventional iterative least squares approach.</p><p><strong>Conclusions: </strong><i>In vivo</i> finger occlusion and gingival abrasion studies demonstrate the ability of this approach to rapidly generate high-resolution images of tissue component concentrations from a hyperspectral dataset acquired from human subjects.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093507"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11378079/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142154206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection and margin assessment of thyroid carcinoma with microscopic hyperspectral imaging using transformer networks.","authors":"Minh Ha Tran, Ling Ma, Hasan Mubarak, Ofelia Gomez, James Yu, Michelle Bryarly, Baowei Fei","doi":"10.1117/1.JBO.29.9.093505","DOIUrl":"10.1117/1.JBO.29.9.093505","url":null,"abstract":"<p><strong>Significance: </strong>Hyperspectral imaging (HSI) is an emerging imaging modality for oncological applications and can improve cancer detection with digital pathology.</p><p><strong>Aim: </strong>The study aims to highlight the increased accuracy and sensitivity of detecting the margin of thyroid carcinoma in hematoxylin and eosin (H&E)-stained histological slides using HSI and data augmentation methods.</p><p><strong>Approach: </strong>Using an automated microscopic imaging system, we captured 2599 hyperspectral images from 65 H&E-stained human thyroid slides. Images were then preprocessed into 153,906 image patches of dimension <math><mrow><mn>250</mn> <mo>×</mo> <mn>250</mn> <mo>×</mo> <mn>84</mn> <mtext>  pixels</mtext></mrow> </math> . We modified the TimeSformer network architecture, which used alternating spectral attention and spatial attention layers. We implemented several data augmentation methods for HSI based on the RandAugment algorithm. We compared the performances of TimeSformer on HSI against the performances of pretrained ConvNext and pretrained vision transformers (ViT) networks on red, green, and blue (RGB) images. Finally, we applied attention unrolling techniques on the trained TimeSformer network to identify the biological features to which the network paid attention.</p><p><strong>Results: </strong>In the testing dataset, TimeSformer achieved an accuracy of 90.87%, a weighted <math> <mrow><msub><mi>F</mi> <mn>1</mn></msub> </mrow> </math> score of 89.79%, a sensitivity of 91.50%, and an area under the receiving operator characteristic curve (AU-ROC) score of 97.04%. Additionally, TimeSformer produced thyroid carcinoma tumor margins with an average Jaccard score of 0.76 mm. Without data augmentation, TimeSformer achieved an accuracy of 88.23%, a weighted <math> <mrow><msub><mi>F</mi> <mn>1</mn></msub> </mrow> </math> score of 86.46%, a sensitivity of 85.53%, and an AU-ROC score of 94.94%. In comparison, the ViT network achieved an 89.98% accuracy, an 88.14% weighted <math> <mrow><msub><mi>F</mi> <mn>1</mn></msub> </mrow> </math> score, an 84.77% sensitivity, and a 96.17% AU-ROC. Our visualization results showed that the network paid attention to biological features.</p><p><strong>Conclusions: </strong>The TimeSformer model trained with hyperspectral histological data consistently outperformed conventional RGB-based models, highlighting the superiority of HSI in this context. Our proposed augmentation methods improved the accuracy, the <math> <mrow><msub><mi>F</mi> <mn>1</mn></msub> </mrow> </math> score, and the sensitivity score.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093505"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11268383/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141758976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"All-reflective tethered capsule endoscope for multimodal optical coherence tomography in the esophagus.","authors":"Xavier Attendu, Paul R Bloemen, Niels H Kind, Dirk J Faber, Daniel M de Bruin, Caroline Boudoux, Ton G van Leeuwen","doi":"10.1117/1.JBO.29.9.096003","DOIUrl":"https://doi.org/10.1117/1.JBO.29.9.096003","url":null,"abstract":"<p><strong>Significance: </strong>Esophageal cancer is becoming increasingly prevalent in Western countries. Early detection is crucial for effective treatment. Multimodal imaging combining optical coherence tomography (OCT) with complementary optical imaging techniques may provide enhanced diagnostic capabilities by simultaneously assessing tissue morphology and biochemical content.</p><p><strong>Aim: </strong>We aim to develop a tethered capsule endoscope (TCE) that can accommodate a variety of point-scanning techniques in addition to OCT without requiring design iterations on the optical or mechanical design.</p><p><strong>Approach: </strong>We propose a TCE utilizing exclusively reflective optics to focus and steer light from and to a double-clad fiber. Specifically, we use an ellipsoidal mirror to achieve finite conjugation between the fiber tip and the imaging plane.</p><p><strong>Results: </strong>We demonstrate a functional all-reflective TCE. We first detail the design, fabrication, and assembly steps required to obtain such a device. We then characterize its performance and demonstrate combined OCT at 1300 nm and visible spectroscopic imaging in the 500- to 700-nm range. Finally, we discuss the advantages and limitations of the proposed design.</p><p><strong>Conclusions: </strong>An all-reflective TCE is feasible and allows for achromatic high-quality imaging. Such a device could be utilized as a platform for testing various combinations of modalities to identify the optimal candidates without requiring design iterations.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"096003"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11412323/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142288116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning–enabled fluorescence imaging for surgical guidance: in silico training for oral cancer depth quantification","authors":"Natalie J. Won, Mandolin Bartling, Josephine La Macchia, Stefanie Markevich, Scott Holtshousen, Arjun Jagota, Christina Negus, Esmat Najjar, Brian C. Wilson, Jonathan C. Irish, Michael J. Daly","doi":"10.1117/1.jbo.30.s1.s13706","DOIUrl":"https://doi.org/10.1117/1.jbo.30.s1.s13706","url":null,"abstract":"SignificanceOral cancer surgery requires accurate margin delineation to balance complete resection with post-operative functionality. Current in vivo fluorescence imaging systems provide two-dimensional margin assessment yet fail to quantify tumor depth prior to resection. Harnessing structured light in combination with deep learning (DL) may provide near real-time three-dimensional margin detection.AimA DL-enabled fluorescence spatial frequency domain imaging (SFDI) system trained with in silico tumor models was developed to quantify the depth of oral tumors.ApproachA convolutional neural network was designed to produce tumor depth and concentration maps from SFDI images. Three in silico representations of oral cancer lesions were developed to train the DL architecture: cylinders, spherical harmonics, and composite spherical harmonics (CSHs). Each model was validated with in silico SFDI images of patient-derived tongue tumors, and the CSH model was further validated with optical phantoms.ResultsThe performance of the CSH model was superior when presented with patient-derived tumors (P-value<0.05). The CSH model could predict depth and concentration within 0.4 mm and 0.4 μg/mL, respectively, for in silico tumors with depths less than 10 mm.ConclusionsA DL-enabled SFDI system trained with in silico CSH demonstrates promise in defining the deep margins of oral tumors.","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"44 1","pages":""},"PeriodicalIF":3.5,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142258366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning-assisted mid-infrared spectrochemical fibrillar collagen imaging in clinical tissues.","authors":"Wihan Adi, Bryan E Rubio Perez, Yuming Liu, Sydney Runkle, Kevin W Eliceiri, Filiz Yesilkoy","doi":"10.1117/1.JBO.29.9.093511","DOIUrl":"10.1117/1.JBO.29.9.093511","url":null,"abstract":"<p><strong>Significance: </strong>Label-free multimodal imaging methods that can provide complementary structural and chemical information from the same sample are critical for comprehensive tissue analyses. These methods are specifically needed to study the complex tumor-microenvironment where fibrillar collagen's architectural changes are associated with cancer progression. To address this need, we present a multimodal computational imaging method where mid-infrared spectral imaging (MIRSI) is employed with second harmonic generation (SHG) microscopy to identify fibrillar collagen in biological tissues.</p><p><strong>Aim: </strong>To demonstrate a multimodal approach where a morphology-specific contrast mechanism guides an MIRSI method to detect fibrillar collagen based on its chemical signatures.</p><p><strong>Approach: </strong>We trained a supervised machine learning (ML) model using SHG images as ground truth collagen labels to classify fibrillar collagen in biological tissues based on their mid-infrared hyperspectral images. Five human pancreatic tissue samples (sizes are in the order of millimeters) were imaged by both MIRSI and SHG microscopes. In total, 2.8 million MIRSI spectra were used to train a random forest (RF) model. The other 68 million spectra were used to validate the collagen images generated by the RF-MIRSI model in terms of collagen segmentation, orientation, and alignment.</p><p><strong>Results: </strong>Compared with the SHG ground truth, the generated RF-MIRSI collagen images achieved a high average boundary <math><mrow><mi>F</mi></mrow> </math> -score (0.8 at 4-pixel thresholds) in the collagen distribution, high correlation (Pearson's <math><mrow><mi>R</mi></mrow> </math> 0.82) in the collagen orientation, and similarly high correlation (Pearson's <math><mrow><mi>R</mi></mrow> </math> 0.66) in the collagen alignment.</p><p><strong>Conclusions: </strong>We showed the potential of ML-aided label-free mid-infrared hyperspectral imaging for collagen fiber and tumor microenvironment analysis in tumor pathology samples.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093511"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11448345/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142371949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of scattering phase function and polarization on the accuracy of diffuse and sub-diffuse spatial frequency domain imaging.","authors":"Alec B Walter, E Duco Jansen","doi":"10.1117/1.JBO.29.9.095001","DOIUrl":"10.1117/1.JBO.29.9.095001","url":null,"abstract":"<p><strong>Significance: </strong>Although spatial frequency domain imaging (SFDI) has been well characterized under diffuse optical conditions, tissue measurements made outside the diffuse regime can provide new diagnostic information. Before such measurements can become clinically relevant, however, the behavior of sub-diffuse SFDI and its effect on the accuracy of derived tissue parameters must be assessed.</p><p><strong>Aim: </strong>We aim to characterize the impact that both the assumed scattering phase function (SPF) and the polarization state of the illumination light source have on the accuracy of SFDI-derived optical properties when operating under diffuse or sub-diffuse conditions, respectively.</p><p><strong>Approach: </strong>Through the use of a set of well-characterized optical phantoms, SFDI accuracy was assessed at four wavelengths (395, 545, 625, and 850 nm) and two different spatial frequencies (0.3 and <math><mrow><mn>1.0</mn> <mtext>  </mtext> <msup><mrow><mi>mm</mi></mrow> <mrow><mo>-</mo> <mn>1</mn></mrow> </msup> </mrow> </math> ), which provided a broad range of diffuse and sub-diffuse conditions, using three different SPFs. To determine the effects of polarization, the SFDI accuracy was assessed using both unpolarized and cross-polarized illumination.</p><p><strong>Results: </strong>It was found that the assumed SPF has a direct and significant impact on the accuracy of the SFDI-derived optical properties, with the best choice of SPF being dictated by the polarization state. As unpolarized SFDI retains the sub-diffuse portion of the signal, optical properties were found to be more accurate when using the full SPF that includes forward and backscattering components. By contrast, cross-polarized SFDI yielded accurate optical properties when using a forward-scattering SPF, matching the behavior of cross-polarization to attenuate the immediate backscattering of sub-diffuse reflectance. Using the correct pairings of SPF and polarization enabled using a reflectance standard, instead of a more subjective phantom, as the reference measurement.</p><p><strong>Conclusions: </strong>These results provide the foundation for a more thorough understanding of SFDI and enable new applications of this technology in which sub-diffuse conditions dominate (e.g., <math> <mrow> <msub><mrow><mi>μ</mi></mrow> <mrow><mi>a</mi></mrow> </msub> <mo>≮</mo> <msubsup><mrow><mi>μ</mi></mrow> <mrow><mi>s</mi></mrow> <mrow><mo>'</mo></mrow> </msubsup> </mrow> </math> ) or high spatial frequencies are required.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"095001"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11379407/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142154207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Depth detection limit of a fluorescent object in tissue-like medium with background emission in continuous-wave measurements: a phantom study.","authors":"Goro Nishimura, Takahiro Suzuki, Yukio Yamada, Haruki Niwa, Takuji Koike","doi":"10.1117/1.JBO.29.9.097001","DOIUrl":"10.1117/1.JBO.29.9.097001","url":null,"abstract":"<p><strong>Significance: </strong>Although the depth detection limit of fluorescence objects in tissue has been studied, reports with a model including noise statistics for designing the optimum measurement configuration are missing. We demonstrate a variance analysis of the depth detection limit toward clinical applications such as noninvasively assessing the risk of aspiration.</p><p><strong>Aim: </strong>It is essential to analyze how the depth detection limit of the fluorescence object in a strong scattering medium depends on the measurement configuration to optimize the configuration. We aim to evaluate the depth detection limit from theoretical analysis and phantom experiments and discuss the source-detector distance that maximizes this limit.</p><p><strong>Approach: </strong>Experiments for detecting a fluorescent object in a biological tissue-mimicking phantom of ground beef with background emission were conducted using continuous wave fluorescence measurements with a point source-detector scheme. The results were analyzed using a model based on the photon diffusion equations. Then, variance analysis of the signal fluctuation was introduced.</p><p><strong>Results: </strong>The model explained the measured fluorescence intensities and their fluctuations well. The variance analysis showed that the depth detection limit in the presence of ambient light increased with the decrease in the source-detector distance, and the optimum distance was in the range of 10 to 15 mm. The depth detection limit was found to be <math><mrow><mo>∼</mo> <mn>30</mn> <mtext>  </mtext> <mi>mm</mi></mrow> </math> with this optimum distance for the phantom.</p><p><strong>Conclusions: </strong>The presented analysis provides a guide for the optimum design of the measurement configuration for detecting fluorescence objects in clinical applications.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"097001"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11368132/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142119932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and validation of a high-speed hyperspectral laparoscopic imaging system.","authors":"Kelden Pruitt, Ling Ma, Armand Rathgeb, Jeffrey C Gahan, Brett A Johnson, Douglas W Strand, Baowei Fei","doi":"10.1117/1.JBO.29.9.093506","DOIUrl":"10.1117/1.JBO.29.9.093506","url":null,"abstract":"<p><strong>Significance: </strong>Minimally invasive surgery (MIS) has shown vast improvement over open surgery by reducing post-operative stays, intraoperative blood loss, and infection rates. However, in spite of these improvements, there are still prevalent issues surrounding MIS that may be addressed through hyperspectral imaging (HSI). We present a laparoscopic HSI system to further advance the field of MIS.</p><p><strong>Aim: </strong>We present an imaging system that integrates high-speed HSI technology with a clinical laparoscopic setup and validate the system's accuracy and functionality. Different configurations that cover the visible (VIS) to near-infrared (NIR) range of electromagnetism are assessed by gauging the spectral fidelity and spatial resolution of each hyperspectral camera.</p><p><strong>Approach: </strong>Standard Spectralon reflectance tiles were used to provide ground truth spectral footprints to compare with those acquired by our system using the root mean squared error (RMSE). Demosaicing techniques were investigated and used to measure and improve spatial resolution, which was assessed with a USAF resolution test target. A perception-based image quality evaluator was used to assess the demosaicing techniques we developed. Two configurations of the system were developed for evaluation. The functionality of the system was investigated in a phantom study and by imaging <i>ex vivo</i> tissues.</p><p><strong>Results: </strong>Multiple configurations of our system were tested, each covering different spectral ranges, including VIS (460 to 600 nm), red/NIR (RNIR) (610 to 850 nm), and NIR (665 to 950 nm). Each configuration is capable of achieving real-time imaging speeds of up to 20 frames per second. RMSE values of <math><mrow><mn>3.51</mn> <mo>±</mo> <mn>2.03</mn> <mo>%</mo></mrow> </math> , <math><mrow><mn>3.43</mn> <mo>±</mo> <mn>0.84</mn> <mo>%</mo></mrow> </math> , and 3.47% were achieved for the VIS, RNIR, and NIR systems, respectively. We obtained sub-millimeter resolution using our demosaicing techniques.</p><p><strong>Conclusions: </strong>We developed and validated a high-speed hyperspectral laparoscopic imaging system. The HSI system can be used as an intraoperative imaging tool for tissue classification during laparoscopic surgery.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093506"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11321365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141975759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learnable real-time inference of molecular composition from diffuse spectroscopy of brain tissue.","authors":"Ivan Ezhov, Kevin Scibilia, Luca Giannoni, Florian Kofler, Ivan Iliash, Felix Hsieh, Suprosanna Shit, Charly Caredda, Frédéric Lange, Bruno Montcel, Ilias Tachtsidis, Daniel Rueckert","doi":"10.1117/1.JBO.29.9.093509","DOIUrl":"https://doi.org/10.1117/1.JBO.29.9.093509","url":null,"abstract":"<p><strong>Significance: </strong>Diffuse optical modalities such as broadband near-infrared spectroscopy (bNIRS) and hyperspectral imaging (HSI) represent a promising alternative for low-cost, non-invasive, and fast monitoring of living tissue. Particularly, the possibility of extracting the molecular composition of the tissue from the optical spectra deems the spectroscopy techniques as a unique diagnostic tool.</p><p><strong>Aim: </strong>No established method exists to streamline the inference of the biochemical composition from the optical spectrum for real-time applications such as surgical monitoring. We analyze a machine learning technique for inference of changes in the molecular composition of brain tissue.</p><p><strong>Approach: </strong>We propose modifications to the existing learnable methodology based on the Beer-Lambert law. We evaluate the method's applicability to linear and nonlinear formulations of this physical law. The approach is tested on data obtained from the bNIRS- and HSI-based monitoring of brain tissue.</p><p><strong>Results: </strong>The results demonstrate that the proposed method enables real-time molecular composition inference while maintaining the accuracy of traditional methods. Preliminary findings show that Beer-Lambert law-based spectral unmixing allows contrasting brain anatomy semantics such as the vessel tree and tumor area.</p><p><strong>Conclusion: </strong>We present a data-driven technique for inferring molecular composition change from diffuse spectroscopy of brain tissue, potentially enabling intra-operative monitoring.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093509"},"PeriodicalIF":3.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11421663/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142347390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of phantom microstructure on their optical properties.","authors":"Jošt Stergar, Rok Hren, Matija Milanič","doi":"10.1117/1.JBO.29.9.093502","DOIUrl":"10.1117/1.JBO.29.9.093502","url":null,"abstract":"<p><strong>Significance: </strong>Developing stable, robust, and affordable tissue-mimicking phantoms is a prerequisite for any new clinical application within biomedical optics. To this end, a thorough understanding of the phantom structure and optical properties is paramount.</p><p><strong>Aim: </strong>We characterized the structural and optical properties of PlatSil SiliGlass phantoms using experimental and numerical approaches to examine the effects of phantom microstructure on their overall optical properties.</p><p><strong>Approach: </strong>We employed scanning electron microscope (SEM), hyperspectral imaging (HSI), and spectroscopy in combination with Mie theory modeling and inverse Monte Carlo to investigate the relationship between phantom constituent and overall phantom optical properties.</p><p><strong>Results: </strong>SEM revealed that microspheres had a broad range of sizes with average <math><mrow><mo>(</mo><mn>13.47</mn><mo>±</mo><mn>5.98</mn><mo>)</mo><mtext>  </mtext><mi>μ</mi><mi>m</mi></mrow></math> and were also aggregated, which may affect overall optical properties and warrants careful preparation to minimize these effects. Spectroscopy was used to measure pigment and SiliGlass absorption coefficient in the VIS-NIR range. Size distribution was used to calculate scattering coefficients and observe the impact of phantom microstructure on scattering properties. The results were surmised in an inverse problem solution that enabled absolute determination of component volume fractions that agree with values obtained during preparation and explained experimentally observed spectral features. HSI microscopy revealed pronounced single-scattering effects that agree with single-scattering events.</p><p><strong>Conclusions: </strong>We show that knowledge of phantom microstructure enables absolute measurements of phantom constitution without prior calibration. Further, we show a connection across different length scales where knowledge of precise phantom component constitution can help understand macroscopically observable optical properties.</p>","PeriodicalId":15264,"journal":{"name":"Journal of Biomedical Optics","volume":"29 9","pages":"093502"},"PeriodicalIF":3.5,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11070965/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140876461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}