Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing
Abstract The development of optical sensors for label-free quantification of cell parameters has numerous uses in the biomedical arena. However, using current optical probes requires the laborious collection of sufficiently large datasets that can be used to calibrate optical probe signals to true m...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85930-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594679013572608 |
|---|---|
| author | Anjana Hevaganinge Eva Lowenstein Anna Filatova Mihir Modak Nandi Thales Mogo Bryana Rowley Jenny Yarmowsky Joshua Ehizibolo Ravidu Hevaganinge Amy Musser Abbey Kim Anthony Neri Jessica Conway Yiding Yuan Maurizio Cattaneo Sui Seng Tee Yang Tao |
| author_facet | Anjana Hevaganinge Eva Lowenstein Anna Filatova Mihir Modak Nandi Thales Mogo Bryana Rowley Jenny Yarmowsky Joshua Ehizibolo Ravidu Hevaganinge Amy Musser Abbey Kim Anthony Neri Jessica Conway Yiding Yuan Maurizio Cattaneo Sui Seng Tee Yang Tao |
| author_sort | Anjana Hevaganinge |
| collection | DOAJ |
| description | Abstract The development of optical sensors for label-free quantification of cell parameters has numerous uses in the biomedical arena. However, using current optical probes requires the laborious collection of sufficiently large datasets that can be used to calibrate optical probe signals to true metabolite concentrations. Further, most practitioners find it difficult to confidently adapt black box chemometric models that are difficult to troubleshoot in high-stakes applications such as biopharmaceutical manufacturing. Replacing optical probes with contactless short-wave infrared (SWIR) hyperspectral cameras allows efficient collection of thousands of absorption signals in a handful of images. This high repetition allows for effective denoising of each spectrum, so interpretable linear models can quantify metabolites. To illustrate, an interpretable linear model called L-SLR is trained using small datasets obtained with a SWIR HSI camera to quantify fructose, viable cell density (VCD), glucose, and lactate. The performance of this model is also compared to other existing linear models, namely Partial Least Squares (PLS) and Non-negative Matrix Factorization (NMF). Using only 50% of the dataset for training, reasonable test performance of mean absolute error (MAE) and correlations (r2) are achieved for glucose (r2 = 0.88, MAE = 37 mg/dL), lactate (r2 = 0.93, MAE = 15.08 mg/dL), and VCD (r2 = 0.81, MAE = 8.6 × 105 cells/mL). Further, these models are also able to handle quantification of a metabolite like fructose in the presence of high background concentration of similar metabolite with almost identical chemical interactions in water like glucose. The model achieves reasonable quantification performance for large fructose level (100–1000 mg/dL) quantification (r2 = 0.92, MAE = 25.1 mg/dL) and small fructose level (< 60 mg/dL) concentrations (r2 = 0.85, MAE = 4.97 mg/dL) in complex media like Fetal Bovine Serum (FBS). Finally, the model provides sparse interpretable weight matrices that hint at the underlying solution changes that correlate to each cell parameter prediction. |
| format | Article |
| id | doaj-art-31a261dc5bc04552ae31e6bb4abaf810 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-31a261dc5bc04552ae31e6bb4abaf8102025-01-19T12:23:51ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-025-85930-2Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensingAnjana Hevaganinge0Eva Lowenstein1Anna Filatova2Mihir Modak3Nandi Thales Mogo4Bryana Rowley5Jenny Yarmowsky6Joshua Ehizibolo7Ravidu Hevaganinge8Amy Musser9Abbey Kim10Anthony Neri11Jessica Conway12Yiding Yuan13Maurizio Cattaneo14Sui Seng Tee15Yang Tao16Fischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandFischell Department of Bioengineering, University of MarylandDepartment of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of MedicineFischell Department of Bioengineering, University of MarylandAbstract The development of optical sensors for label-free quantification of cell parameters has numerous uses in the biomedical arena. However, using current optical probes requires the laborious collection of sufficiently large datasets that can be used to calibrate optical probe signals to true metabolite concentrations. Further, most practitioners find it difficult to confidently adapt black box chemometric models that are difficult to troubleshoot in high-stakes applications such as biopharmaceutical manufacturing. Replacing optical probes with contactless short-wave infrared (SWIR) hyperspectral cameras allows efficient collection of thousands of absorption signals in a handful of images. This high repetition allows for effective denoising of each spectrum, so interpretable linear models can quantify metabolites. To illustrate, an interpretable linear model called L-SLR is trained using small datasets obtained with a SWIR HSI camera to quantify fructose, viable cell density (VCD), glucose, and lactate. The performance of this model is also compared to other existing linear models, namely Partial Least Squares (PLS) and Non-negative Matrix Factorization (NMF). Using only 50% of the dataset for training, reasonable test performance of mean absolute error (MAE) and correlations (r2) are achieved for glucose (r2 = 0.88, MAE = 37 mg/dL), lactate (r2 = 0.93, MAE = 15.08 mg/dL), and VCD (r2 = 0.81, MAE = 8.6 × 105 cells/mL). Further, these models are also able to handle quantification of a metabolite like fructose in the presence of high background concentration of similar metabolite with almost identical chemical interactions in water like glucose. The model achieves reasonable quantification performance for large fructose level (100–1000 mg/dL) quantification (r2 = 0.92, MAE = 25.1 mg/dL) and small fructose level (< 60 mg/dL) concentrations (r2 = 0.85, MAE = 4.97 mg/dL) in complex media like Fetal Bovine Serum (FBS). Finally, the model provides sparse interpretable weight matrices that hint at the underlying solution changes that correlate to each cell parameter prediction.https://doi.org/10.1038/s41598-025-85930-2Contactless bio-sensorShort wave infrared (SWIR)Near infrared (NIR)Machine learning |
| spellingShingle | Anjana Hevaganinge Eva Lowenstein Anna Filatova Mihir Modak Nandi Thales Mogo Bryana Rowley Jenny Yarmowsky Joshua Ehizibolo Ravidu Hevaganinge Amy Musser Abbey Kim Anthony Neri Jessica Conway Yiding Yuan Maurizio Cattaneo Sui Seng Tee Yang Tao Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing Scientific Reports Contactless bio-sensor Short wave infrared (SWIR) Near infrared (NIR) Machine learning |
| title | Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing |
| title_full | Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing |
| title_fullStr | Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing |
| title_full_unstemmed | Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing |
| title_short | Exploration of linear and interpretable models for quantification of cell parameters via contactless short-wave infrared hyperspectral sensing |
| title_sort | exploration of linear and interpretable models for quantification of cell parameters via contactless short wave infrared hyperspectral sensing |
| topic | Contactless bio-sensor Short wave infrared (SWIR) Near infrared (NIR) Machine learning |
| url | https://doi.org/10.1038/s41598-025-85930-2 |
| work_keys_str_mv | AT anjanahevaganinge explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT evalowenstein explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT annafilatova explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT mihirmodak explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT nandithalesmogo explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT bryanarowley explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT jennyyarmowsky explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT joshuaehizibolo explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT raviduhevaganinge explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT amymusser explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT abbeykim explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT anthonyneri explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT jessicaconway explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT yidingyuan explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT mauriziocattaneo explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT suisengtee explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing AT yangtao explorationoflinearandinterpretablemodelsforquantificationofcellparametersviacontactlessshortwaveinfraredhyperspectralsensing |