Prognostic value of 18F-FDG PET/CT-based radiomics combining dosiomics and dose volume histogram for head and neck cancer

Abstract

Objectives By comparing the prognostic performance of 18F-FDG PET/CT-based radiomics combining dose features [Includes Dosiomics feature and the dose volume histogram (DVH) features] with that of conventional radiomics in head and neck cancer (HNC), multidimensional prognostic models were constructed to investigate the overall survival (OS) in HNC. Materials and methods A total of 220 cases from four centres based on the Cancer Imaging Archive public dataset were used in this study, 2260 radiomics features and 1116 dosiomics features and 8 DVH features were extracted for each case, and classified into seven different models of PET, CT, Dose, PET+CT, PET+Dose, CT+Dose and PET+CT+Dose. Features were selected by univariate Cox and Spearman correlation coefficients, and the selected features were brought into the least absolute shrinkage and selection operator (LASSO)-Cox model. A nomogram was constructed to visually analyse the prognostic impact of the incorporated dose features. C-index and Kaplan–Meier curves (log-rank analysis) were used to evaluate and compare these models. Results The cases from the four centres were divided into three different training and validation sets according to the hospitals. The PET+CT+Dose model had C-indexes of 0.873 (95% CI 0.812–0.934), 0.759 (95% CI 0.663–0.855) and 0.835 (95% CI 0.745–0.925) in the validation set respectively, outperforming the rest models overall. The PET+CT+Dose model did well in classifying patients into high- and low-risk groups under all three different sets of experiments (p < 0.05). Conclusion Multidimensional model of radiomics features combining dosiomics features and DVH features showed high prognostic performance for predicting OS in patients with HNC.

A radiomic‐ and dosiomic‐based machine learning regression model for pretreatment planning in 177Lu‐DOTATATE therapy

“…While dosiomics has been extensively studied in EBRT, 23,24 its application in nuclear medicine (NM) has been relatively limited. However, there is a growing interest in combining radiomics and dosiomics approaches lately to achieve a more comprehensive and accurate assessment of treatment response and prognosis in cancer patients 25–28 …”

“…However, there is a growing interest in combining radiomics and dosiomics approaches lately to achieve a more comprehensive and accurate assessment of treatment response and prognosis in cancer patients. [25][26][27][28] As previously described, NETs typically respond to PRRT with disease stabilization, but the optimal sequence for PRRT is not yet determined due to challenges in targeting multiple tumors in the midgut area. Dosimetric evaluation is mainly focused on protecting vital organs, and developing tailored therapy regimens to minimize radiotoxic damage to these organs.…”

Prognostic Value of a Combined Nomogram Model Integrating 3-Dimensional Deep Learning and Radiomics for Head and Neck Cancer

“…), providing deeper diagnostic, predictive, and prognostic value over visual examinations. 9,10 Opposed to biopsy and surgical examinations, radiomics provided new ideas for noninvasive examinations. 11 The radiomics of HNC has been developing rapidly in recent years.…”

“…21 CNN was also valuable in diagnostics and image characterization, 22 which allowed to identify nonlinear relationships in complex data more accurately and to extract deeper and more complex features than radiomics. 10,23 Combining deep features with radiomics features had been found to complement radiomics features and improve model performance. Bourigault et al 24 and Peng et al 25 combined deep features and radiomics features to predict DFS in HNC and nasopharyngeal carcinoma patients, respectively.…”

“…Radiomics was an emerging and rapidly growing research field, which applied machine learning to analyze high-throughput features extracted from medical images (Magnetic Resonance Imaging, CT, PET, etc. ), providing deeper diagnostic, predictive, and prognostic value over visual examinations 9,10 . Opposed to biopsy and surgical examinations, radiomics provided new ideas for noninvasive examinations 11 .…”