Computer-aided Nodule Detection in the Lung Apices in Head and Neck Computed Tomography Angiography
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
PURPOSE: Computed tomography angiography (CTA) of the head and neck includes the pulmonary apices, a common location for pulmonary nodules. Computer-aided detection (CAD) is an adjunctive tool for the detection of lung nodules and is widely used in standard chest CT scans. We evaluated whether the available software can be applied to CTA head and neck examinations, which include the lung apices, resulting in improved accuracy for lung nodule detection. MATERIALS AND METHODS: In this retrospective single-center study, 191 previously reported head and neck CTA scans were re-evaluated for apical pulmonary nodules by 2 radiologists. Subsequently, CAD software ( Syngo .via, Siemens Healthiness AG) was applied to the lung apices and the results were compared between CAD and research radiologists (first reading) or clinical radiologist (null reading). In addition, the CAD performance in limited lung fields was compared with the accepted CAD assessment applied to whole lungs. RESULTS: Of the 191 patients, 110 (57.6%) were men, with a mean age of 68 years. In the 24 CT scans, the research radiologists detected 40 nodules. In the 180 scans evaluated by CAD, the software detected 39 nodules in 22 examinations, with a sensitivity of 60.8% and a PPV of 63.6%. In the remaining 158 examinations in which CAD did not detect nodules, the radiologists concurred in 149 scans, with a specificity of 94.9%, NPV of 94.3%, and accuracy of 90.6%. CONCLUSION: The study results indicate that CAD is an unexpected quick supportive tool for nodule detection, particularly for excluding clinically significant nodules in lung apices on CTA head and neck, showing similar results for partial and full lung fields.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it