An algorithm developed by deep learning from digitalised haematoxylin and eosin-stained whole tumour slide images outperformed classical AFIP/Miettinen relapse risk prediction in patients with gastrointestinal stromal tumours (GIST). A second algorithm predicted mutations with high accuracy.
GIST, the most frequent mesenchymal tumour of the GI tract, shows a variable clinical behaviour ranging from benign to malignant. Risk assessment according to the AFIP/Miettinen classification (high, intermediate, or low risk of relapse) and mutational profiling are major tools for patient management. The AFIP/Miettinen classification includes parameters such as the size of the tumour, localisation, and mitotic count . However, the AFIP/Miettinen classification comes with subjectivity (mitotic count), costly mutational profiling and is time-consuming, and not yet available in all countries (or centres). Therefore, Dr Raul Perret (Institute Bergonié, France) and colleagues evaluated the efficacy of 2 deep learning models: 1 to predict relapse-free survival in GIST patients and 1 to predict mutational profiles .
Both models were based on histology, i.e. digitised haematoxylin and eosin-stained whole tumour slide images. The relapse-predicting model was trained using whole tumour slide images from 305 patients (Institut Bergonié) and validated using slide images from 286 patients (Léon Bérard Centre). Both cohorts had a similar distribution of GIST types (localisation, TKI treatment). The mutation profile-predicting model was trained using images from 1,233 patients (Institut Bergonié) and validated on images from 238 patients (Léon Bérard Centre).
The algorithm for relapse prediction outperformed prediction based on AFIP/Miettinen classification (C-index 0.81 vs 0.76). Combining deep learning with tumour location and tumour size (Deep Miettinen), further improved C-index to 0.83. Deep Miettinen was able to stratify patients into subgroups at high or low risk for relapse-free survival. Also, the algorithm was able to split patients, characterised as ‘high risk for relapse’ according to classical AFIP/Miettinen, into 2 additional groups: high versus low risk. Likewise, the algorithm was able to split classical AFIP/Miettinen ‘intermediate risk’ patients into high-risk and low-risk groups.
The algorithm for the prediction of the presence of mutations reached an area under the receiver operating characteristic curve (AUC) for predicting KIT mutations of 0.80 in the training cohort and 0.85 in the validation cohort. AUC for predicting PDGFRA mutations was 0.92 in both cohorts. More specific, AUC for predicting PDGFRA exon 18D824V mutation was 0.87 in both cohorts and predicting KIT exon 11del 557–558 mutation was 0.69 in the training cohort and 0.76 in the validation cohort.
“Our results strongly suggest that implementing deep learning with digitised whole slide images may represent a reproducible way to improve tailoring therapy and precision medicine for patients with GIST. However, further validation of the models is needed,” concluded Dr Perret.
- Miettinen M, Lasota J. Semin Diagn Pathol. 2006;23(2):70–83.
- Italiano A, et al. Deep learning predicts patients’ outcome and mutations from H&E slides in gastrointestinal stromal tumor (GIST). Abstract 1484O, ESMO Congress 2022, 09–13 September, Paris, France.
Copyright ©2022 Medicom Medical Publishers
« Addition of pembrolizumab to lenvatinib does not improve OS in advanced HCC Next Article
OS benefit of sacituzumab govitecan in pre-treated HR-positive/HER2-negative metastatic breast cancer »
Table of Contents: ESMO 2022
Letter from the Editor
High pathological responses to neoadjuvant immune checkpoint inhibition in locally advanced dMMR colon cancer
Fruquintinib: a potential new treatment for patients with refractory mCRC
Second-line avelumab is effective in patients with MSI-H/dMMR mCRC
Upper Gastrointestinal Cancer
Deep learning models predict the risk of relapse and the mutational profile in GIST
Addition of pembrolizumab to lenvatinib does not improve OS in advanced HCC
New, highly selective inhibitor of FGFR2 driver alterations and resistance mutations
Chemo-immunotherapy in gastric cancer is more effective when administered in parallel
Tumour infiltrating lymphocytes identify patients with immunogenic triple-negative breast cancer
OS benefit of abemaciclib in HR-positive/HER2-negative advanced breast cancer not (yet) statistically significant
OS benefit of sacituzumab govitecan in pre-treated HR-positive/HER2-negative metastatic breast cancer
A pathway from air pollution to lung cancer in non-smokers identified
Selective KRASG12C inhibitor sotorasib demonstrates superior PFS and ORR compared to docetaxel in previously treated patients with NSCLC
Promising clinical activity of tepotinib plus osimertinib in NSCLC with MET amplification after progression on first-line osimertinib
High pathological responses in borderline resectable NSCLC patients after induction with dual immunotherapy and concurrent chemoradiotherapy
Treatment with tumour-infiltrating lymphocytes for advanced melanoma outperforms ipilimumab
Neoadjuvant pembrolizumab outperforms adjuvant pembrolizumab in resectable stage III–IV melanomas
Survival-benefit of neoadjuvant T-VEC maintained over 5 years of follow-up
Baseline ctDNA predicts survival in resected stage III–IV melanoma
Genitourinary Cancer – Prostate Cancer
Overall survival benefit of abiraterone in mHSPC is maintained for 7 years
Limited benefit of adding long-term ADT to post-operative radiotherapy in prostate cancer
Intensified ADT benefits biochemical progression-free survival in biochemically relapsed prostate cancer
Genitourinary Cancer – Non-Prostate Cancer
Adjuvant nivolumab plus ipilimumab does not improve survival in patients with localised RCC at high risk of relapse after nephrectomy
Triple therapy improves progression-free survival in patients with advanced RCC versus dual therapy
Adjuvant atezolizumab does not improve outcomes for patients with RCC and increased risk of recurrence
OS benefit for advanced ovarian cancer patients treated with maintenance olaparib
Maintenance tegafur-uracil does not improve survival in locally advanced cervical cancer
Head and Neck Cancer
Adding first-line pembrolizumab to CRT in locally advanced HNSCC does not significantly prolong survival or event-free survival
5-FU-free chemotherapy combination as an alternative for first-line treatment of recurrent or metastatic HNSCC
Epstein Barr virus-specific autologous cytotoxic T lymphocytes do not improve survival in nasopharyngeal carcinoma