Next Article in Journal
Light Yield Response of Neutron Scintillation Screens to Sudden Flux Changes
Next Article in Special Issue
Evaluating Performance of Microwave Image Reconstruction Algorithms: Extracting Tissue Types with Segmentation Using Machine Learning
Previous Article in Journal
Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning
Previous Article in Special Issue
Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection
Article

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

1
STMicroelectronics—ADG Central R&D Division, 95125 Catania, Italy
2
Medical Oncology Department, United Lincolnshire NHS Hospital Trust, Lincoln LN2, Lincolnshire, UK
3
DIEEI, University of Catania, 95125 Catania, Italy
4
IPLAB, University of Catania, 95125 Catania, Italy
5
Department of Chemical, Biological, Pharmaceutical and Environmental Sciences, University of Messina, 98100 Messina, Italy
*
Author to whom correspondence should be addressed.
J. Imaging 2020, 6(12), 133; https://doi.org/10.3390/jimaging6120133
Received: 27 October 2020 / Revised: 28 November 2020 / Accepted: 1 December 2020 / Published: 3 December 2020
(This article belongs to the Special Issue Advanced Computational Methods for Oncological Image Analysis)
Immunotherapy is regarded as one of the most significant breakthroughs in cancer treatment. Unfortunately, only a small percentage of patients respond properly to the treatment. Moreover, to date, there are no efficient bio-markers able to early discriminate the patients eligible for this treatment. In order to help overcome these limitations, an innovative non-invasive deep pipeline, integrating Computed Tomography (CT) imaging, is investigated for the prediction of a response to immunotherapy treatment. We report preliminary results collected as part of a case study in which we validated the implemented method on a clinical dataset of patients affected by Metastatic Urothelial Carcinoma. The proposed pipeline aims to discriminate patients with high chances of response from those with disease progression. Specifically, the authors propose ad-hoc 3D Deep Networks integrating Self-Attention mechanisms in order to estimate the immunotherapy treatment response from CT-scan images and such hemato-chemical data of the patients. The performance evaluation (average accuracy close to 92%) confirms the effectiveness of the proposed approach as an immunotherapy treatment response biomarker. View Full-Text
Keywords: 3D-CNN; immunotherapy; radiomics; self-attention 3D-CNN; immunotherapy; radiomics; self-attention
Show Figures

Graphical abstract

MDPI and ACS Style

Rundo, F.; Banna, G.L.; Prezzavento, L.; Trenta, F.; Conoci, S.; Battiato, S. 3D Non-Local Neural Network: A Non-Invasive Biomarker for Immunotherapy Treatment Outcome Prediction. Case-Study: Metastatic Urothelial Carcinoma. J. Imaging 2020, 6, 133. https://doi.org/10.3390/jimaging6120133

AMA Style

Rundo F, Banna GL, Prezzavento L, Trenta F, Conoci S, Battiato S. 3D Non-Local Neural Network: A Non-Invasive Biomarker for Immunotherapy Treatment Outcome Prediction. Case-Study: Metastatic Urothelial Carcinoma. Journal of Imaging. 2020; 6(12):133. https://doi.org/10.3390/jimaging6120133

Chicago/Turabian Style

Rundo, Francesco, Giuseppe L. Banna, Luca Prezzavento, Francesca Trenta, Sabrina Conoci, and Sebastiano Battiato. 2020. "3D Non-Local Neural Network: A Non-Invasive Biomarker for Immunotherapy Treatment Outcome Prediction. Case-Study: Metastatic Urothelial Carcinoma" Journal of Imaging 6, no. 12: 133. https://doi.org/10.3390/jimaging6120133

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop