Deep Learning and Radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer

Abstract

Treatment of locally advanced rectal cancer involves chemoradiation, followed by total mesorectum excision. Complete response after chemoradiation is an accurate surrogate for long-term local control. Predicting complete response from pre-treatment features could represent a major step towards conservative treatment. Patients with a T2-4 N0-1 rectal adenocarcinoma treated between June 2010 and October 2016 with neo-adjuvant chemoradiation from three academic institutions were included. All clinical and treatment data was integrated in our clinical data warehouse, from which we extracted the features. Radiomics features were extracted from the tumor volume from the treatment planning CT Scan. A Deep Neural Network (DNN) was created to predict complete response, as a methodological proof-of-principle. The results were compared to a baseline Linear Regression model using only the TNM stage as a predictor and a second model created with Support Vector Machine on the same features used in the DNN. Ninety-five patients were included in the final analysis. There were 49 males (52%) and 46 females (48%). Median tumour size was 48 mm (15–130). Twenty-two patients (23%) had pathologic complete response after chemoradiation. One thousand six hundred eighty-three radiomics features were extracted. The DNN predicted complete response with an 80% accuracy, which was better than the Linear Regression model (69.5%) and the SVM model (71.58%). Our model correctly predicted complete response after neo-adjuvant rectal chemoradiotherapy in 80% of the patients of this multicenter cohort. Our results may help to identify patients who would benefit from a conservative treatment, rather than a radical resection.

Application of Artificial Intelligence to Gastroenterology and Hepatology

“…This technology might be used to identify patients most likely to benefit from conservative treatment vs radical resection. 71 A DL-based model was developed to predict survival times at 5 years for 1190 patients with gastric cancer based on clinical and pathology data and treatment regimens. This system achieved an area under the receiver operating characteristic curve (AUROC) of 0.92 and identified associations between molecular features of tumor and optimal adjuvant treatment.…”

Perceptions of artificial intelligence in healthcare: findings from a qualitative survey study among actors in France

“…It could be argued that this may just be the result of a mere passing fad. However, it appears that the will to develop its application within the healthcare system is still very strong [4,[7][8][9]. For example, the journal Nature published an article in 2017 in which machine learning (an AI technique) was able to diagnose skin cancer as efficiently as dermatologists [10].…”

Hypoxia-related radiomics predict immunotherapy response: A multi-cohort study of NSCLC

“…The mechanism of serum albumin with respect to immunotherapy response is yet to be established however, it was used in The Gustave Roussy Immune Score as a prognostic marker in immunotherapy phase I trials 40 . Emerging evidence demonstrates the utility of radiomics as a non-invasive approach to quantify and predict lung cancer treatment response of tyrosine kinase inhibitors 41,42 , platinum-based chemotherapy 43 , neo-adjuvant chemo-radiation 44,45 , stereotactic body radiation therapy 46,47 , and immunotherapy 8,48,49 . With respect to immunotherapy treatment response, our group previously demonstrated that pre-treatment clinical covariates and radiomic features predicted rapid disease progression phenotypes, including hyperprogression (AUROCs ranging 0.804-0.865) among 228 NSCLC patients treated with single agent or double agent immunotherapy 8 .…”