Biochemical Prostate Cancer Recurrence Prediction: Thinking Fast & Slow
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910588664283136 |
|---|---|
| author | You, Suhang Adap, Sanyukta Thakur, Siddhesh Baheti, Bhakti Bakas, Spyridon |
| author_facet | You, Suhang Adap, Sanyukta Thakur, Siddhesh Baheti, Bhakti Bakas, Spyridon |
| contents | Time to biochemical recurrence in prostate cancer is essential for prognostic monitoring of the progression of patients after prostatectomy, which assesses the efficacy of the surgery. In this work, we proposed to leverage multiple instance learning through a two-stage ``thinking fast \& slow'' strategy for the time to recurrence (TTR) prediction. The first (``thinking fast'') stage finds the most relevant WSI area for biochemical recurrence and the second (``thinking slow'') stage leverages higher resolution patches to predict TTR. Our approach reveals a mean C-index ($Ci$) of 0.733 ($θ=0.059$) on our internal validation and $Ci=0.603$ on the LEOPARD challenge validation set. Post hoc attention visualization shows that the most attentive area contributes to the TTR prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Biochemical Prostate Cancer Recurrence Prediction: Thinking Fast & Slow You, Suhang Adap, Sanyukta Thakur, Siddhesh Baheti, Bhakti Bakas, Spyridon Computer Vision and Pattern Recognition Artificial Intelligence 68T10 I.5.4 Time to biochemical recurrence in prostate cancer is essential for prognostic monitoring of the progression of patients after prostatectomy, which assesses the efficacy of the surgery. In this work, we proposed to leverage multiple instance learning through a two-stage ``thinking fast \& slow'' strategy for the time to recurrence (TTR) prediction. The first (``thinking fast'') stage finds the most relevant WSI area for biochemical recurrence and the second (``thinking slow'') stage leverages higher resolution patches to predict TTR. Our approach reveals a mean C-index ($Ci$) of 0.733 ($θ=0.059$) on our internal validation and $Ci=0.603$ on the LEOPARD challenge validation set. Post hoc attention visualization shows that the most attentive area contributes to the TTR prediction. |
| title | Biochemical Prostate Cancer Recurrence Prediction: Thinking Fast & Slow |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence 68T10 I.5.4 |
| url | https://arxiv.org/abs/2409.02284 |