# Prostate Cancer Detection on Prostate MRI dataset

Source: [Prostate Cancer Detection on Prostate MRI dataset](<https://www.sota2.com/research/sota/prostate-cancer-detection-on-prostate-mri-dataset>)

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

Data updated: 2026-03-20T08:59:45.480Z

Evaluation of models on detecting prostate cancer using the Prostate MRI dataset, typically measured using AUC.

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 | Prostate Cancer Detection |
| Dataset (including any stated split) | Prostate MRI dataset |
| Metric | AUC |
| Unit | PERCENT |
| Direction | Higher 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

- [AUC](<https://www.sota2.com/research/sota/prostate-cancer-detection-on-prostate-mri-dataset.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUC | Result date | Report paper |
| --- | --- | --- | --- |
| Ours (HOG+SVM) | 91.7 | Not recorded | 69bcd4710636e5bf4afc2908 |
| Ours (ResNet18) | 90.5 | Not recorded | 69bcd4710636e5bf4afc2908 |
| Hamm et al. \[9\] | 89 | Not recorded | 69bcd4710636e5bf4afc2908 |
| Li et al. \[13\] | 89 | Not recorded | 69bcd4710636e5bf4afc2908 |

### Ours (HOG+SVM)

AUC: 91.7. Result ID: 69bd0c7047f34ce924a73cec.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

Recorded evaluation configuration: {"Year":"2026","Dataset Size":"162 images","Input Type":"T2-only","Model Type":"Classical ML","Evaluation Level":"Image-level","csPCa Prevalence":"64% (102/162)","Parameters":"Minimal"}. This record does not assert independent reproduction.

### Ours (ResNet18)

AUC: 90.5. Result ID: 69bd0c7047f34ce924a73ceb.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

Recorded evaluation configuration: {"Year":"2026","Dataset Size":"162 images","Input Type":"T2-only","Model Type":"Transfer CNN","Evaluation Level":"Image-level","csPCa Prevalence":"64% (102/162)","Parameters":"11M"}. This record does not assert independent reproduction.

### Hamm et al. \[9\]

AUC: 89. Result ID: 69bd0c7047f34ce924a73ce8.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

Recorded evaluation configuration: {"Year":"2023","Dataset Size":"1,224","Input Type":"bp-MRI (T2+DWI)","Model Type":"Explainable DL (XAI)","Evaluation Level":"Lesion-level","csPCa Prevalence":"~49%"}. This record does not assert independent reproduction.

### Li et al. \[13\]

AUC: 89. Result ID: 69bd0c7047f34ce924a73cea.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4710636e5bf4afc2908.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72931e209131cea57392.md>)

Recorded evaluation configuration: {"Year":"2025","Dataset Size":"1,476","Input Type":"bp-MRI (T2+DWI)","Model Type":"CSwin Transformer","Evaluation Level":"Patient-level","csPCa Prevalence":"~38% (PI-CAI)","Parameters":"80M+"}. This record does not assert independent reproduction.

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