A learning-based automatic spinal MRI segmentation
Bibliographic record
Abstract
Image segmentation plays an important role in medical image analysis and visualization since it greatly enhances the clinical diagnosis. Although many algorithms have been proposed, it is still challenging to achieve an automatic clinical segmentation which requires speed and robustness. Automatically segmenting the vertebral column in Magnetic Resonance Imaging (MRI) image is extremely challenging as variations in soft tissue contrast and radio-frequency (RF) in-homogeneities cause image intensity variations. Moveover, little work has been done in this area. We proposed a generic slice-independent, learning-based method to automatically segment the vertebrae in spinal MRI images. A main feature of our contributions is that the proposed method is able to segment multiple images of different slices simultaneously. Our proposed method also has the potential to be imaging modality independent as it is not specific to a particular imaging modality. The proposed method consists of two stages: candidate generation and verification. The candidate generation stage is aimed at obtaining the segmentation through the energy minimization. In this stage, images are first partitioned into a number of image regions. Then, Support Vector Machines (SVM) is applied on those pre-partitioned image regions to obtain the class conditional distributions, which are then fed into an energy function and optimized with the graph-cut algorithm. The verification stage applies domain knowledge to verify the segmented candidates and reject unsuitable ones. Experimental results show that the proposed method is very efficient and robust with respect to image slices.
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 | 0.001 |
| 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 | 0.000 | 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".