An investigational deep learning model requiring one histopathologic slide accurately predicted the risk of distant recurrence in patients with endometrial cancer, according to findings presented at the AACR Annual Meeting 2023.
Endometrial cancer is the most common type of uterine cancer. While patients with early-stage uterine cancer have an approximately 95% five-year survival rate, those who develop a distant recurrence have a very poor survival outcome.
The risk of distant recurrence may be reduced by adjuvant systemic therapy; therefore, correctly identifying patients at high risk and low risk of distant recurrence is crucial for personalised adjuvant treatment recommendations and for reducing unnecessary morbidity from toxic treatments.
Current methods of risk stratification are either inaccurate or costly. The increasing number of prognostic variables has made it difficult to combine the relevant factors into a single risk score.
To overcome these challenges, Fremond and colleagues examined the potential of deep learning to predict patients’ risk of distant recurrence using digitised histopathological slides.
“Deep learning is a powerful computer-aided predictive technology that has entered the field of pathology because it can be trained to read complex visual information from tumour slides after digitisation,” Sarah Fremond, a PhD candidate in computational pathology and deep learning for endometrial cancer at Leiden University Medical Center in the Netherlands.
Prediction consistent with patient outcomes
To develop the model, Fremond and colleagues utilised long-term follow-up data from patients enrolled in the PORTEC-1/-2/-3 randomised clinical trials and patients in three separate clinical cohorts, amounting to 1,761 patients with endometrial cancer who had not received prior adjuvant chemotherapy.
One representative histopathological slide image of the tumour was used from each of 1,408 patients to train and optimise the model. “This means that the model was exposed many times to the histopathological image and to the information regarding the time to distant recurrence in each patient until the model started to recognise visual features that were predictive of distant recurrence,” Fremond explained.
To assess its performance and generalisability, the resulting model was then tested on the previously unseen dataset of 353 patients whose data were not used to train the model. The model identified 89 of these patients as having a low risk of distant recurrence, 175 an intermediate risk, and 89 a high risk.
These predictions were consistent with the patients’ outcomes: 3.37% of patients categorised as low-risk experienced a distant recurrence, as compared with 15.43% and 36% of those categorised as intermediate-risk and high-risk, respectively.
Fremond noted that the results outperformed pathologist-identified features, such as tumour type, grade, and molecular class, typically used to assign risk groups.
“Although additional external validation is needed, the performance of this model serves as an important proof of concept that deep learning models have the potential to optimize clinical care for patients with endometrial cancer,” she said.