Limitations of the SSIM quality metric in the context of diagnostic imaging
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
Lossy image compression is increasingly used in medical applications, but great care must be taken to ensure that no diagnostically relevant features are altered. Guidelines based on compression ratios are often use to mitigate this issue, but are criticized due to the considerable compressibility variations between images. Objective image quality assessment metrics should be used instead, but the most common, mean squared error, is known to be poorly correlated with our perception of quality. Structural similarity (SSIM) is probably currently the most popular alternative, but it is also increasingly criticized. Using computed tomography simulations, this paper shows some of the limitations of SSIM when used with medical images: uniform pooling, distortion underestimation near hard edges, instabilities in regions of low variance and insensitivity in regions high intensities. Furthermore, this paper demonstrates the effect of these limitations when SSIM is used to bound compression in a block coder such as JPEG 2000.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 it