Organ Proximity Analysis: A Novel Approach to Spleen Localization for Accurate Injury Grading in Abdominal CT Scans
Bibliographic record
Abstract
Accurate grading of splenic injuries in abdominal CT scans is paramount for diagnosing and treating abdominal trauma. However, automating the segmentation of an injured spleen is a formidable task, given the numerous anomalies like shape, location, texture, and size variations. Deep neural networks often require extensive and expensive annotated datasets to achieve precise spleen segmentation. This paper presents a novel approach that integrates segmentation and localization techniques for spleen analysis. Initially, we segment the spleen using a segmentation model trained on limited normal spleen data. We then employ a localization decision-making process to determine whether the segmented spleen exhibits an out-of-distribution shape and location. If not, we utilize the segmentation map for cropping. In cases where the spleen displays atypical features, we leverage information from nearby organs to accurately locate the spleen. The cropped spleen is then processed through a 3D DenseNet, a deep convolutional network, for spleen classification, categorizing the injuries into normal, low (grades I to III) and high (grades IV & V) grade injuries following the American association for the surgery of trauma injury scoring scale. This innovative approach not only achieves accuracy levels comparable to segmentation-based methods but also reduces dependence on extensive annotated datasets, making it a noteworthy contribution to abdominal trauma diagnosis and treatment. Code https://github.com/hamghalam/Proximity-Analysis.
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 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 | 0.002 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".