Using Machine Learning and Optical Microscopy Image Analysis of Immunosensors Made on Plasmonic Substrates: Application to Detect the SARS-CoV-2 Virus
Bibliographic record
Abstract
In this article, we introduce a diagnostic platform comprising an optical microscopy image analysis system coupled with machine learning. Its efficacy is demonstrated in detecting SARS-CoV-2 virus particles at concentrations as low as 1 PFU (plaque-forming unit) per milliliter by processing images from an immunosensor on a plasmonic substrate. This high performance was achieved by classifying images with the support vector machine (SVM) algorithm and the MobileNetV3_small convolutional neural network (CNN) model, which attained an accuracy of 91.6% and a specificity denoted by an F1 score of 96.9% for the negative class. Notably, this approach enabled the detection of SARS-CoV-2 concentrations 1000 times lower than the limit of detection achieved with localized surface plasmon resonance (LSPR) sensing using the same immunosensors. It is also significant that a binary classification between control and positive classes using the MobileNetV3_small model and the random forest algorithm achieved an accuracy of 96.5% for SARS-CoV-2 concentrations down to 1 PFU/mL. At such low concentrations, straightforward screening of newly infected patients may be feasible. In supporting experiments, we verified that texture was the main contributor to the distinguishability of images taken at different SARS-CoV-2 concentrations, indicating that the combination of ML and image analysis may be applied to any biosensor whose detection mechanism is based on adsorption.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".