Abstract 1170P
Background
Predictive and prognostic biomarkers represent the cornerstone of clinical oncology. Improving the prognostication of melanoma is needed to select patients for effective adjuvant therapies. Taking into account that tumor tissue contains a large amount of clinically relevant hidden information that is not fully exploited, we propose a weakly-supervised deep-learning approach on H&E-stained whole-slide image (WSI) to directly predict survival outcomes in melanoma patients.
Methods
We designed a deep neural (DL) network that extracts features from no-padding patches of WSI (tiles of size 512x512 pixels) using a self-supervised learning framework, which are then fed along with survival information into the DL network assigning a survival risk score to each WSI/patient. The model was trained and validated on 195 cases of primary melanoma diagnosed between 2015 and 2017 originating from the IHP Group and the French RicMel network. Performance was evaluated using cross-validations as well as an external set of 238 cases from the TCGA database. Concordance index (c-index) was used as a metric to assess the performance of the proposed approach.
Results
For the prediction of survival outcomes, the proposed pipeline yielded a c-index of 0.75 and 0.66 for the IHP Group cohort and TCGA dataset respectively. Furthermore, we were able to significantly discriminate the 2 groups of patients, with a good and a poor prognosis in terms of survival with p<0.001 for IHP and p=0.01 for the TCGA based on Kaplan-Meier survival analysis. Our prediction model outperforms the reported scores for the other types of tumours based on deep learning frameworks.
Conclusions
This innovative weakly-supervised deep-learning approach to HE image analysis allows the deep-network to choose its own morphological features, and thus highlights new morphological prognostic biomarkers. Based on this prognostic risk score, we aim to accelerate and improve the clinical decision-making process in the field of melanoma. Due to this exiting result, the performance of our algorithm is challenge on a third independent dataset.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
1100P - Open-label non-randomized phase IB study to characterize the safety, tolerability and recommended dose of tinostamustin in combination with nivolumab in patients with advanced melanoma (ENIGMA)
Presenter: Markus Joerger
Session: Poster session 13
1101P - The effect of LNS8801 in combination with pembrolizumab in patients with treatment-refractory cutaneous melanoma
Presenter: Jordi Rodon
Session: Poster session 13
1102P - Evaluation of surrogate endpoints for overall survival within the RELATIVITY-047 trial
Presenter: Peter Mohr
Session: Poster session 13
1103P - Nivolumab (NIVO) plus relatlimab (RELA) vs NIVO in previously untreated metastatic or unresectable melanoma: 2-year subgroup analyses from RELATIVITY-047
Presenter: Georgina Long
Session: Poster session 13
1104P - Efficacy of immune checkpoint inhibition in metastatic or non-resectable melanoma after failure of adjuvant anti-PD1 treatment: A EUMelareg real-world evidence study
Presenter: Michael Weichenthal
Session: Poster session 13
1105P - First-line nivolumab plus ipilimumab in advanced melanoma patients previously treated with adjuvant systemic therapy
Presenter: Katarzyna Kozak
Session: Poster session 13
1106P - Anti-PD-1 (PD1) monotherapy or in combination with anti-CTLA-4 for metastatic melanoma (MM) patients (pts) with liver metastases (mets)
Presenter: Ines Pires da Silva
Session: Poster session 13
1107P - BRAF mutation status does not impact outcomes with tebentafusp in advanced cutaneous melanoma
Presenter: Alexander Shoushtari
Session: Poster session 13
1108P - Outcomes of patients with unresectable or metastatic melanoma after cessation of immunotherapy following complete response or toxicities
Presenter: Nur Sakinah Zulkifli
Session: Poster session 13