AI Science Tracker
EN

University of Florence

2 discoveries from 2020

Discoveries

Raman spectra and neural learning distinguish three melanoma cell lines

Source check: Source checked. Not independent scientific confirmation.

Finding: A neural classifier distinguished Raman spectra from three melanoma cell lines carrying different BRAF or NRAS variants, including a rare BRAF variant. The study collected 50 spectra per line and reported 96.7% accuracy with five-fold spectral cross-validation. This is an in-vitro cell-line measurement, with feature-selection and spectrum-level evaluation caveats; it does not demonstrate independent patient diagnosis or establish that genotype caused the spectral differences.

Technology: Artificial neural network; principal-component features

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
A feed-forward neural network learns nonlinear boundaries from principal-component Raman features to discriminate the measured cell lines.
Test and result
New Raman measurements from three melanoma cell lines, with neural and linear-discriminant spectral classification.
Limitation / still unknown
Independent cultures, patient-level diagnosis and causal assignment of spectral differences to genotype remain unestablished.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://doi.org/10.1002/jbio.202000365

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 21 Nov 2026. Review scope: Primary relevant Methods/results/limitations and exact front/canonical identity; current primary PubMed linked correction/retraction metadata checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Recognition of Cutaneous Melanoma on Digitized Histopathological Slides via Artificial Intelligence Algorithm.

Source check: Source checked. Not independent scientific confirmation.

Finding: The article reports 96.5% training classification accuracy, sensitivity 95.7%, specificity 97.7% and κ 0.929; it notes larger datasets are needed. External replication and prospective utility were not established in the reviewed material.

Technology: An Inception-ResNet-v2 CNN classified melanoma and healthy tissue patches from digitized histopathology slides.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
An Inception-ResNet-v2 CNN classified melanoma and healthy tissue patches from digitized histopathology slides.
Test and result
The article reports 96.5% training classification accuracy, sensitivity 95.7%, specificity 97.7% and κ 0.929; it notes larger datasets are needed.
Limitation / still unknown
External replication, causal effects and prospective utility were not established in the reviewed material.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2020.01559/full

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.