Addressing Boundary Ambiguity in Renal Tumor Segmentation: A Softmax-Refined Deep Learning Approach
Bibliographic record
Abstract
Kidney tumor segmentation from CT images remains a challenging task due to the presence of noise, indistinct boundaries, diminished contrast, and varying morphological characteristics between the kidney and tumor.Most existing methods rely on the Softmax function to generate pixel-wise class probabilities and segmentation outcomes, but this approach has limitations in accurately delineating pixels with ill-defined edges.To overcome this problem, we propose a novel Edge-Refine Network (ERNet) that refines the Softmax-based pixel attributions to achieve precise segmentation of kidney tumors.ERNet leverages the Segmentation via Gradient-weighted Class Activation Mapping (Seg-Grad-CAM), a novel technique that produces interpretable heatmaps that highlight the pixels that are difficult to segment.By using backpropagation, ERNet retrains the model with the heatmap weights and the target probabilities from the Softmax function, thereby enhancing the segmentation accuracy.We evaluate our method on publicly available kidney tumor datasets and show that ERNet outperforms the state-of-the-art methods in kidney tumor segmentation, achieving a 2.9% improvement in the Dice score and a 4.17% reduction in the ASD.Moreover, ERNet exhibits superior precision in segmenting intricate details, especially in regions with ambiguous boundaries.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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".