Evaluating Deep Learning Algorithms in Pulmonary Nodule Detection
Bibliographic record
Abstract
Lung cancer is considered the deadliest cancer worldwide. In order to detect it, radiologists need to inspect multiple Computed Tomography (CT) scans. This task is tedious and time consuming. In recent years, promising methods based on deep learning object detection algorithms were proposed for the automatic nodule detection and classification. With those techniques, Computed Aided Detection (CAD) software can be developed to alleviate radiologist's burden and help speed-up the screening process. However, among available object detection frameworks, there are just a limited number that have been used for this purpose. Moreover, it can be challenging to know which one to choose as a baseline for the development of a new application for this task. Hence, in this work we propose a benchmark of recent state-of-the-art deep learning detectors such as Faster-RCNN, YOLO, SSD, RetinaNet and EfficientDet in the challenging task of pulmonary nodule detection. Evaluation is done using automatically segmented 2D images extracted from volumetric chest CT scans.
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 | 0.004 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".