Morphologic Accuracy in Differentiating Primary Lung Adenocarcinoma From Squamous Cell Carcinoma in Cytology Specimens
Bibliographic record
Abstract
CONTEXT: -The National Cancer Care Network and the combined College of American Pathologists/International Association for the Study of Lung Cancer/Association for Molecular Pathology guidelines indicate that all lung adenocarcinomas (ADCs) should be tested for epidermal growth factor receptor (EGFR) mutations and anaplastic lymphoma kinase (ALK) rearrangements. As the majority of patients present at a later stage, the subclassification and molecular analysis must be done on cytologic material. OBJECTIVE: -To evaluate the accuracy and interobserver variability among cytopathologists in subtyping non-small cell lung carcinoma using cytologic preparations. DESIGN: -Nine cytopathologists from different institutions submitted cases of non-small cell lung carcinoma with surgical follow-up. Cases were independently, blindly reviewed by each cytopathologist. A diagnosis of ADC or squamous cell carcinoma was rendered based on the Diff-Quik, Papanicolaou, and hematoxylin-eosin stains. The specimen types included fine-needle aspiration from lung, lymph node, and bone; touch preparations from lung core biopsies; bronchial washings; and bronchial brushes. A major disagreement was defined as a case being misclassified 3 or more times. RESULTS: -Ninety-three cases (69 ADC, 24 squamous cell carcinoma) were examined. Of 818 chances (93 cases × 9 cytopathologists) to correctly identify all the cases, 753 correct diagnoses were made (92% overall accuracy). Twenty-five of 69 cases of ADC (36%) and 7 of 24 cases of squamous cell carcinoma (29%) had disagreement (P = .16). Touch preparations were more frequently misdiagnosed compared with other specimens. Diagnostic accuracy of each cytopathologist varied from 78.4% to 98.7% (mean, 91.7%). CONCLUSION: -Lung ADC can accurately be distinguished from squamous cell carcinoma by morphology in cytologic specimens with excellent interobserver concordance across multiple institutions and levels of cytology experience.
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 | 0.009 | 0.038 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".