# PET Image Denoising on Whole-Body PET FDG scans low-BMI patient

Source: [PET Image Denoising on Whole-Body PET FDG scans low-BMI patient](<https://www.sota2.com/research/sota/pet-image-denoising-on-whole-body-pet-fdg-scans-low-bmi-patient>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:48:35.332Z

Evaluation of PET image denoising performance using whole-body FDG scans from low-BMI patients, assessed via metrics like Lesion Bias and Liver CoV.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | PET Image Denoising |
| Dataset (including any stated split) | Whole-Body PET FDG scans low-BMI patient |
| Metric | Lesion Bias |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Lesion Bias](<https://www.sota2.com/research/sota/pet-image-denoising-on-whole-body-pet-fdg-scans-low-bmi-patient.md?metric=Lesion%20Bias>): Lower is better; unit: PERCENT.

- [Liver CoV](<https://www.sota2.com/research/sota/pet-image-denoising-on-whole-body-pet-fdg-scans-low-bmi-patient.md?metric=Liver%20CoV>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Lesion Bias | Result date | Report paper |
| --- | --- | --- | --- |
| v1-net | -6.3 | Not recorded | 68fa6af11e209131cea2b3b9 |
| FT-net | -4.71 | Not recorded | 68fa6af11e209131cea2b3b9 |
| v2-net | -4.07 | Not recorded | 68fa6af11e209131cea2b3b9 |
| TGD-net | -3.77 | Not recorded | 68fa6af11e209131cea2b3b9 |

### v1-net

Lesion Bias: -6.3. Result ID: 698e443affc3901de09c27d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b3b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63631e209131ce9fe4fc.md>)

[Implementation](<https://github.com/cszn/DnCNN>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FT-net

Lesion Bias: -4.71. Result ID: 698e443affc3901de09c27d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b3b9.md>)

Recorded evaluation configuration: {"training\_regime":"fine-tuning"}. This record does not assert independent reproduction.

### v2-net

Lesion Bias: -4.07. Result ID: 698e443affc3901de09c27d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b3b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63631e209131ce9fe4fc.md>)

[Implementation](<https://github.com/cszn/DnCNN>)

Recorded evaluation configuration: {"training\_regime":"training-from-scratch"}. This record does not assert independent reproduction.

### TGD-net

Lesion Bias: -3.77. Result ID: 698e443affc3901de09c27da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b3b9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af11e209131cea2b3b9.md>)

Recorded evaluation configuration: {"phi":"0.3"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.