Advanced Deep Learning Embedded Motion Radiomics Pipeline for Predicting Anti-PD-1/PD-L1 Immunotherapy Response in the Treatment of Bladder Cancer: Preliminary Results

Abstract

A key objective of modern medicine is precision medicine, whose purpose is to personalize the treatment based on the specific characteristics of the patients and their illness. To guide treatment decisions, it is generally necessary to have a sample of the neoplastic tissue, which is obtained only with biopsies or similar invasive surgical procedures. As tumors are heterogeneous in their volume and change over time, a dynamic analysis of diagnostic medical images can provide a better understanding of the entire tumor, both in the screening and follow-up phase. In this work, the authors proposed the use of a radiomics pipeline which is able to characterize the possible response of the oncological patients to the anti- programmed death-ligand protein 1 (PD-L1) immunotherapeutic treatment. The immunotherapeutic treatment consists of a modern therapeutic approach in which the physicians try to reactivate the patient's immune system so that it recognizes and destroys cancer cells. The oncological biomarkers capable of characterizing patients who can benefit from immunotherapy from those who would not, are being studied. One of them is related to the expression of the PD-L1 inhibitor in the surface of neoplastic cells which are analyzed in this paper, considering that the analyzed immunotherapeutic treatment is of the anti-PD-L1 type. In this context, the authors propose a pipeline for an immunotherapy response prediction based on the analysis of only CT-scan images of patients with metastatic bladder cancer. Using a framework based on the use of deep Autoeconder network, CT-scan images were analyzed to extract the features capable of discriminating the patient's response to anti-PD-L1 immunotherapy treatment from those who are not. The preliminary results obtained (accuracy of approximately 86% with a sensitivity of approximately 80% against a specificity of approximately 89%) on the analyzed patient dataset, allows the confirmation of the feasibility of the proposed method. Although validated in a dataset containing patients with only one tumor histology (bladder cancer), the proposed method shows how modern radiomics techniques can contribute significantly in the implementation of non-invasive predictive systems that support the physician in the therapeutic choice. The idea of the authors is to create a form of oncological point of care on an embedded platform that allows physicians to always have a support tool in choosing the best therapy to suggest to the patient.

3D Non-Local Neural Network: A Non-Invasive Biomarker for Immunotherapy Treatment Outcome Prediction. Case-Study: Metastatic Urothelial Carcinoma

“…The first stage deals with automated CT scan lesion segmentation (Auto-Initialized Cascaded Level Sets system) and the other one handles treatment response prediction (with an AUC of 0.73) using the previously segmented lesions. As for immunotherapy, some of the authors of this paper in Reference [ 34 ] proposed a deep network based on auto-encoders for cancer treatment outcome prediction in patients treated with Pembrolizumab (anti PD-1/PD-L1 ICIs checkpoint). To our knowledge, Reference [ 34 ] is one of the first works employing artificial intelligence for the prediction of immunotherapy outcomes.…”

“…As for immunotherapy, some of the authors of this paper in Reference [ 34 ] proposed a deep network based on auto-encoders for cancer treatment outcome prediction in patients treated with Pembrolizumab (anti PD-1/PD-L1 ICIs checkpoint). To our knowledge, Reference [ 34 ] is one of the first works employing artificial intelligence for the prediction of immunotherapy outcomes. The work herein described extends the pipeline proposed in Reference [ 34 ] by introducing a 3D deep model enriched with a self-attention mechanism, which improve the learning phase of the joint visual and clinical data features.…”

“…To our knowledge, Reference [ 34 ] is one of the first works employing artificial intelligence for the prediction of immunotherapy outcomes. The work herein described extends the pipeline proposed in Reference [ 34 ] by introducing a 3D deep model enriched with a self-attention mechanism, which improve the learning phase of the joint visual and clinical data features. While it is important to have accurate automated computer methods for cancer treatment efficacy prediction, the interpretability and the explanation for why these methods reach specific decisions are of equal importance for the involved physicians.…”

Radiomics in immuno-oncology

“…70 Subsequent studies have shown similar associations between specific radiomic features and post-immune checkpoint inhibitor response. [71][72][73][74][75][76] Tunali et al demonstrated that combining radiomic features with clinical data enhanced the predictive power of the radiomic algorithm (AUC ¼ 0.80-0.87 with radiomic features and AUC ¼ 0.77-0.78 without radiomic features). 77 A combination of RNA sequence data and CT-derived radiomic features was also able to identify immune infiltration in solid tumours.…”

Deep learning classification of lung cancer histology using CT images

“…There is a growing body of evidence pointing to the prognostic value of such features 5,16,17 as well as their utility in stratifying patients 18 . While radiomics has primarily relied on the explicit extraction of hand-crafted imaging features 17,19 , more recent studies have shifted towards deep learning-convolutional neural networks (CNNs) specifically-where representative features are learned automatically from data [20][21][22][23][24][25][26] . This has fostered the construction of advanced multi-parametric algorithms for cognitive decision-making in many clinical settings 14 .…”