Hybrid CNN model employing patch-based exemplar for accessory spleen detection in abdominal CT images
Bibliographic record
Abstract
The accessory spleen, a condition affecting a subset of the population, often presents diagnostic challenges due to its potential for being mistaken for a tumor or cyst.This underscores the importance of accurate identification of the accessory spleen.In this study, the development of a patch-based hybrid Convolutional Neural Network (CNN) model designed for the automatic detection of the accessory spleen is presented.The proposed model applies a five-step process in the detection of the accessory spleen, encompassing the extraction of the potential accessory spleen region, extraction of features from this region, selection of consistent and significant features, integration of these features, and their subsequent classification.Specialist physicians were responsible for the extraction of the region of interest.For feature extraction, four distinct CNN architectures were employed (AlexNet, Vgg16, MobileNet, Resnet50), and the feature vectors derived from these architectures were integrated.The Neighborhood Components Analysis (NCA) and ReliefF algorithms were utilized for the selection of the most representative features, which were subsequently classified using Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN).The study revealed that the highest performance was achieved through the combination of SVM and ReliefF, yielding an accuracy of 93.87% (evaluated via 10-fold crossvalidation).The findings suggest that the proposed model could offer valuable decision support for physicians in the preliminary identification of the accessory spleen during clinical evaluations of tumors and similar structures resembling the accessory spleen.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".