Journal of Biophotonics最新文献

{"title":"Correction to “Label-Free Typing of Colorectal Cancer by Optical Time-Stretch Imaging Flow Cytometry With Multi-Instance Learning”","authors":"","doi":"10.1002/jbio.70265","DOIUrl":"10.1002/jbio.70265","url":null,"abstract":"<p>S. Pi, L. Mei, L. Tao, S. Mei, and Z. Ye, “Label-Free Typing of Colorectal Cancer by Optical Time-Stretch Imaging Flow Cytometry With Multi-Instance Learning,” <i>Journal of Biophotonics</i> 18, no. 8 (2025): e70026, https://doi.org/10.1002/jbio.70026.</p><p>The first affiliation listed in the paper is corrected due to a recent institutional reform and official renaming.</p><p>Original Affiliation: School of Medicine, Wuhan City College, Wuhan, China.</p><p>Updated Affiliation: Medical Department, City University of Wuhan, Wuhan, China.</p><p>We apologize for this error.</p>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jbio.70265","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147629620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stochastic Time-Resolved Opto-Electrochemical Analysis of Free Nanourchin-Conjugated Antibody Interactions With Breast Cancer Biomarkers in Serum","authors":"Mohammad E. Khosroshahi,&nbsp;Roxana Chabok,&nbsp;Victor Oyebolu","doi":"10.1002/jbio.70263","DOIUrl":"10.1002/jbio.70263","url":null,"abstract":"<div>\u0000 \u0000 <p>The combined opto-electrochemical (Opto-EC) platform enables non-invasive, real-time monitoring of biochemical kinetics, electron-transfer processes, and surface-binding events. Here, we detect the CA15-3 breast-cancer biomarker using free and randomly gold-nanourchin (GNU)–conjugated antibodies (mAb) within a serum droplet, integrated into a time-resolved Opto-EC immunoassay on an indium-tin-oxide (ITO) film. Biolayer formation on the ITO surface alters charge-transfer dynamics and reduces surface-potential differences. Time-resolved FT-NIR spectroscopy reveals peaks at 4083, 4555, and 5560–6000 cm⁻¹, associated with overtone and combination bands of O<span></span>H, N<span></span>H, and mixed N<span></span>H/C<span></span>H vibrations. Stochastic FT-NIR and SERS fluctuations reflect time-dependent conformational changes, binding-site accessibility, and vibrational-mode variations. Correlation-coefficient dynamics indicate shifts in the analyte's molecular environment, influencing PCA clustering. A time-mapped Raman heatmap further tracks evolving peak positions and intensities, offering complementary insight into biomarker–sensor interactions. The free and randomly conjugated antigen–antibody system exhibits nonlinear stochastic behavior.</p>\u0000 </div>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147629652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spectroscopic Quantification of Plasma Free Hemoglobin Based on Paired Domain Adaptation and Orthogonality Constraints","authors":"Haiyue Lv,&nbsp;Mengqiu Zhang","doi":"10.1002/jbio.70266","DOIUrl":"10.1002/jbio.70266","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objective</h3>\u0000 \u0000 <p>We propose a paired domain-adaptation deep regression method for multi-pathlength spectroscopy to quantify plasma free hemoglobin (FHB) robustly across measurement conditions.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>UV–Vis–NIR spectra (300–1160 nm; 945 wavelengths) were acquired using an Avantes spectrometer, with five optical pathlengths per sample. Spectra were preprocessed by standard normal variate (SNV), and labels were log-transformed (log (1 + <i>y</i>)) to mitigate long-tailed instability. The network integrates domain–path affine calibration, a 1D-CNN encoder, and attention-based multi-path fusion, followed by shared–private feature disentanglement. A paired consistency loss aligns only the shared representation across paired domains, and an orthogonality constraint encourages domain-specific separation. Performance was evaluated via regression-stratified five-fold cross-validation using RMSE and <i>R</i>² on the raw scale.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>For <i>N</i> = 251 samples, <i>λ</i>_pair = 1.0 achieved RMSE = 260.53 ± 62.01 and <i>R</i>² = 0.748 ± 0.088.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>The method improves cross-domain robustness and interpretability for plasma FHB prediction.</p>\u0000 </section>\u0000 </div>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147597211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cell-MICS: Detecting Immune Cells With Label-Free Two-Photon Autofluorescence and Deep Learning","authors":"Lucas Kreiss,&nbsp;Amey Chaware,&nbsp;Maryam Roohian,&nbsp;Sarah Lemire,&nbsp;Oana-Maria Thoma,&nbsp;Birgitta Carlé,&nbsp;Maximilian Waldner,&nbsp;Sebastian Schürmann,&nbsp;Oliver Friedrich,&nbsp;Roarke Horstmeyer","doi":"10.1002/jbio.70260","DOIUrl":"10.1002/jbio.70260","url":null,"abstract":"<p>Multiphoton imaging has been widely used for deep-tissue imaging. Although its label-free, metabolic contrast is ideal for investigating inflammation, the label-free two-photon induced autofluorescence is often regarded as less specific compared to conventional antibody markers. In this work, we investigate the potential for multiphoton imaging with computational specificity (MICS) by training a convolutional neural network on images of different immune cells. A low-complexity squeezeNet architecture was able to achieve reliable immune cell classification results (0.89 ROC-AUC, 0.95 PR-AUC for binary classification between T cells and neutrophils; 0.689 F1 score, 0.697 precision, 0.748 recall for multi-class classification between six isolated cell types). Perturbation tests confirmed that the model was not confused by the extracellular environment and that 2P-AF from NADH and FAD is equally important for the classification. In the future, deep learning could provide computational specificity for specific immune cells in unstained tissues, with great potential for label-free in vivo endomicroscopy.</p>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13044570/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147597242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Skin Tone in Hyperspectral Imaging and Its Implications for Fairness in AI","authors":"Laurie S. van de Weerd,&nbsp;Nick J. van de Berg,&nbsp;L. Lucia Rijstenberg,&nbsp;Ralf L. O. van de Laar,&nbsp;Helena C. van Doorn,&nbsp;Heleen J. van Beekhuizen","doi":"10.1002/jbio.70254","DOIUrl":"10.1002/jbio.70254","url":null,"abstract":"<p>Artificial intelligence (AI) is increasingly applied in healthcare, but concerns remain about bias affecting under-represented groups. We investigated whether skin tone is systematically encoded in hyperspectral imaging data and how this affects classifications. Images were collected from 45 healthy women of the upper leg skin and vulvar mucosal tissue. Skin tones were grouped using the individual typology angle scale. Physiological parameters (oxygen saturation, haemoglobin, water and near-infrared indices) were compared across groups. Unsupervised and supervised classification models were evaluated. Skin tone values ranged from −0.7 to 75.8 (20 very light, 9 light, 9 intermediate, 7 tan and 2 brown). All physiological parameters differed significantly across groups (<i>p</i> &lt; 0.001). Unsupervised learning achieved 38.5% balanced accuracy, whereas supervised learning reached 71.4%, with high accuracies for tan (94.6%) and brown (95.0%) groups. Skin tone influences HSI data; it may act as a confounder in AI models, underscoring the need for diverse datasets to ensure equitable performance.</p>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13036822/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147583409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tissue Mimicking Phantoms for Biomedical Optics: A Systematic Review of Inverse Adding–Doubling Characterization and Clinical Relevance","authors":"Elvis A. García-Cortés,&nbsp;Luís M. Oliveira,&nbsp;Julio C. Pérez-Sansalvador,&nbsp;Teresita Spezzia-Mazzocco","doi":"10.1002/jbio.70261","DOIUrl":"10.1002/jbio.70261","url":null,"abstract":"<div>\u0000 \u0000 <p>Tissue mimicking phantoms are essential for calibration and clinical translation of biophotonic techniques. Although the inverse adding–doubling (IAD) method is widely regarded as a reference standard for determining absorption and reduced scattering coefficients, significant inter-laboratory variability persists due to differences in integrating-sphere configurations, loss-compensation strategies, and model assumptions. This PRISMA-guided review (2015–2025) analyzes 10 experimental studies and proposes a unified comparison framework based on scattering power-law parameters <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mfenced>\u0000 <mrow>\u0000 <mi>a</mi>\u0000 <mo>,</mo>\u0000 <mi>b</mi>\u0000 </mrow>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ left(a,bright) $$</annotation>\u0000 </semantics></math> to relate phantom fabrication to clinically relevant optical targets. Nonlinear regression of continuous <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msubsup>\u0000 <mi>μ</mi>\u0000 <mi>s</mi>\u0000 <mo>′</mo>\u0000 </msubsup>\u0000 <mfenced>\u0000 <mi>λ</mi>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ {mu}_s^{prime}left(lambda right) $$</annotation>\u0000 </semantics></math> spectra shows that selected PVC plastisol formulations reproduce dermal-like scattering slopes and that the power-law model provides consistent spectral descriptions (<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mover>\u0000 <mi>R</mi>\u0000 <mo>¯</mo>\u0000 </mover>\u0000 <mn>2</mn>\u0000 </msup>\u0000 <mo>=</mo>\u0000 <mn>0.98</mn>\u0000 </mrow>\u0000 <annotation>$$ {overline{R}}^2=0.98 $$</annotation>\u0000 </semantics></math>). By linking measurement methodology, spectral fitting, and mapping in <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mfenced>\u0000 <mrow>\u0000 <mi>a</mi>\u0000 <mo>,</mo>\u0000 <mi>b</mi>\u0000 </mrow>\u0000 </mfenced>\u0000 </mrow>\u0000 <annotation>$$ left(a,bright) $$</annotation>\u0000 </semantics></math> space, this work provides a practical framework to interpret variability and guide development of tissue-equivalent phantoms for reliable calibration of biophotonic devices.</p>\u0000 </div>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 4","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147597233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Convolutional Neural Network-Self-Attention Mechanism Enhanced Near-Infrared: Non-Invasive Breakthrough for Alzheimer's Disease Versus Vascular Dementia","authors":"Meiyuan Chen,&nbsp;Mengjiao Xue,&nbsp;Yuanpeng Li,&nbsp;Wenchang Huang,&nbsp;Lingli Liu,&nbsp;Yuna Chen,&nbsp;Yan Chen,&nbsp;Furong Huang,&nbsp;Shan Tu,&nbsp;Jian Tang,&nbsp;Jun Liu,&nbsp;Junhui Hu","doi":"10.1002/jbio.202500383","DOIUrl":"10.1002/jbio.202500383","url":null,"abstract":"<div>\u0000 \u0000 <p>Alzheimer's disease (AD) and vascular dementia (VaD) are two common forms of dementia. Differentiating between them is challenging due to the lack of clear clinical and auxiliary test differences. In this study, we developed a novel diagnostic method combining near-infrared spectroscopy with a convolutional neural network and self-attention mechanism (CNN-SAM). The CNN-SAM model, which integrates the self-attention mechanism to highlight important spectral features, outperformed other models with 99.3% accuracy. Data pre-processing, feature extraction, and parameter optimization further enhanced the model's performance. Visualization using the self-attention mechanism revealed key spectral bands at 1364 and 1484 nm as crucial for distinguishing AD and VaD. This approach offers a rapid, non-invasive, and accurate method for the diagnosis of AD and VaD, potentially advancing clinical practice.</p>\u0000 </div>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 3","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145460929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved Sensitivity in Large Field of View Multispectral Laser-Scanning Photoacoustic Microscopy for Measuring Oxygen Saturation In Vivo","authors":"Mohsin Zafar,&nbsp;Amir Khansari,&nbsp;Rayyan Manwar,&nbsp;Kamran Avanaki","doi":"10.1002/jbio.202500378","DOIUrl":"10.1002/jbio.202500378","url":null,"abstract":"<p>Multispectral photoacoustic microscopy (PAM) using stimulated Raman scattering (SRS) has been employed to measure oxygen saturation (sO₂) in biological tissue. However, laser-scanning photoacoustic microscopy (LS-PAM) inherently suffers from low detection sensitivity due to the use of a flat transducer and non-coaxial alignment of the transducer with the optical scan. Although wide-field-of-view LS-PAM has been implemented, it typically results in coarser lateral resolution and hence lower sensitivity than existing LS-PAM systems. Here, we present a wide-field multispectral LS-PAM system for measuring sO₂ in biological tissue. Instead of relying on two discrete wavelengths, our method employs two wavelength groups—a isosbestic group (532 nm and 545 nm) and a deoxyhemoglobin-dominant group (545 nm and 558 nm). We demonstrate that using these groups improves the signal-to-noise ratio (SNR) of the detected signals, leading to more accurate sO₂ measurements. The performance of this system is validated through both phantom and in vivo studies.</p>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 3","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12980567/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145491178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visible Light-Near Infrared Hyperspectral Imaging and Deep Learning Enable Rapid, Non-Staining Assessment of Lung Adenocarcinoma","authors":"Yanhai Zhang,&nbsp;Chongxuan Tian,&nbsp;Xiaoguang Wang,&nbsp;Zhiwei Xue,&nbsp;Zhengshuai Jiang,&nbsp;Qize Lv,&nbsp;Xiaming Gu,&nbsp;Jinlin Deng,&nbsp;Donghai Wang,&nbsp;Wei Li","doi":"10.1002/jbio.202500362","DOIUrl":"10.1002/jbio.202500362","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate identification of driver mutations such as ALK, EGFR, and KRAS in lung adenocarcinoma is essential for guiding personalized therapies, yet standard genomic assays are invasive and may alter tissue integrity. In this study, we introduce a non-destructive genotyping approach that combines visible-to-near–infrared hyperspectral imaging (400–1000 nm) of unstained pathological sections with a dual-branch deep-learning fusion framework and gradient-boosting classification. The imaging system captures rich spectral–spatial signatures, which are processed by a fusion network that synergistically extracts global contextual features and local textural details. These fused representations are then classified by an optimized XGBoost model. Evaluation on 90 clinical specimens yielded class-specific accuracies between 83.5% and 90.2%, and area under the ROC curve values from 0.83 to 0.91. Our results demonstrate that hyperspectral imaging coupled with deep-learning fusion enables rapid, tumor genotyping, offering a promising tool for real-time clinical diagnostics in the field of biomedical photonics.</p>\u0000 </div>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 3","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145498059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast Mid-Infrared Spectral Probe Decisions Match H&E Stain Results for Keratinocytic Carcinoma","authors":"Rebecca C. Bradley,&nbsp;Maria G. Vazquez de Vasquez,&nbsp;Charles L. Hitchcock,&nbsp;Angela S. Casey,&nbsp;James V. Coe,&nbsp;Ronald Siegle","doi":"10.1002/jbio.202500311","DOIUrl":"10.1002/jbio.202500311","url":null,"abstract":"<p>We designed a handheld and fast mid-infrared fiber-optic spectral probe using a quantum cascade laser (QCL) and a reduced range of wavelengths, to see if keratinocytic carcinoma (KC) could be distinguished from adjacent nonmalignant tissue using discarded skin tissues from Mohs surgery. This study employed two adjacent frozen sections of discarded tissue: one was stained with H&amp;E (the gold standard for skin cancer diagnosis) to identify the location of cancer by a pathologist, while the other was left unstained for mid-infrared spectral probing on and off cancer as guided by the adjacent H&amp;E stain. A total of 346 spectra from 18 consenting patients were collected during Mohs surgery. After adding a dehumidifier, an accuracy of 95% was obtained on a case sample basis. It will be worthwhile to assess the probe's utility at the surface of live human skin (study approved by the Advarra Institutional Review Board [PRO00044823]).</p>","PeriodicalId":184,"journal":{"name":"Journal of Biophotonics","volume":"19 3","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12980700/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145440326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}