Improved Dense Recurrent Residual U-Net for Skin Lesion Segmentation
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Accurate segmentation of skin lesion areas is of great significance for computer-aided diagnosis. However, due to the irregular shape, boundary blurring, and noise interference of skin lesion images, accurate segmentation is difficult and has low precision. Therefore, it proposes an improved dense recurrent residual U-Net model. Firstly, This improved network use of dense recurrent residual connections in the Squeeze-and-Excitation convolution block design to alleviate gradient vanishing and provide accurate location information for segmentation; Secondly, the integration of feature adaptive modules between the encoder and decoder to enhance feature fusion between adjacent layers. Finally, a combined Dice and cross-entropy loss function is adopted to mitigate the class imbalance issue in skin lesion image segmentation. The model is evaluated on the public dataset ISIC 2017, achieving Jaccard, Dice, and accuracy scores of 78.86%, 86.92%, and 94.61% respectively. The experimental results demonstrate that the proposed model outperforms other networks in terms of segmentation performance and provides more accurate segmentation results.
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.
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 | 0.001 | 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 | 0.001 |
| 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 it