Voxel-based identification of local recurrence sub-regions from pre-treatment PET/CT for locally advanced head and neck cancers

A common [18F]-FDG PET radiomic signature to predict survival in patients with HPV-induced cancers

Locally advanced cervical cancer (LACC) and anal and oropharyngeal squamous cell carcinoma (ASCC and OPSCC) are mostly caused by oncogenic human papillomaviruses (HPV). In this paper, we developed machine learning (ML) models based on clinical, biological, and radiomic features extracted from pre-treatment fluorine-18-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET) images to predict the survival of patients with HPV-induced cancers. For this purpose, cohorts from five institutions were used: two cohorts of patients treated for LACC including 104 patients from Gustave Roussy Campus Cancer (Center 1) and 90 patients from Leeds Teaching Hospitals NHS Trust (Center 2), two datasets of patients treated for ASCC composed of 66 patients from Institut du Cancer de Montpellier (Center 3) and 67 patients from Oslo University Hospital (Center 4), and one dataset of 45 OPSCC patients from the University Hospital of Zurich (Center 5). Radiomic features were extracted from baseline [18F]-FDG PET images. The ComBat technique was applied to mitigate intra-scanner variability. A modified consensus nested cross-validation for feature selection and hyperparameter tuning was applied on four ML models to predict progression-free survival (PFS) and overall survival (OS) using harmonized imaging features and/or clinical and biological variables as inputs. Each model was trained and optimized on Center 1 and Center 3 cohorts and tested on Center 2, Center 4, and Center 5 cohorts. The radiomic-based CoxNet model achieved C-index values of 0.75 and 0.78 for PFS and 0.76, 0.74, and 0.75 for OS on the test sets. Radiomic feature-based models had superior performance compared to the bioclinical ones, and combining radiomic and bioclinical variables did not improve the performances. Metabolic tumor volume (MTV)-based models obtained lower C-index values for a majority of the tested configurations but quite equivalent performance in terms of time-dependent AUCs (td-AUC). The results demonstrate the possibility of identifying common PET-based image signatures for predicting the response of patients with induced HPV pathology, validated on multi-center multiconstructor data.

A subregion-based prediction model for local-regional recurrence risk in head and neck squamous cell carcinoma

BACKGROUND AND PURPOSE

Given that the intratumoral heterogeneity of head and neck squamous cell carcinoma may be related to the local control rate of radiotherapy, the aim of this study was to construct a subregion-based model that can predict the risk of local-regional recurrence, and to quantitatively assess the relative contribution of subregions.

MATERIALS AND METHODS

The CT images, PET images, dose images and GTVs of 228 patients with head and neck squamous cell carcinoma from four different institutions of the The Cancer Imaging Archive(TCIA) were included in the study. Using a supervoxel segmentation algorithm called maskSLIC to generate individual-level subregions. After extracting 1781 radiomics and 1767 dosiomics features from subregions, an attention-based multiple instance risk prediction model (MIR) was established. The GTV model was developed based on the whole tumour area and was used to compare the prediction performance with the MIR model. Furthermore, the MIR-Clinical model was constructed by integrating the MIR model with clinical factors. Subregional analysis was carried out through the Wilcoxon test to find the differential radiomic features between the highest and lowest weighted subregions.

RESULTS

Compared with the GTV model, the C-index of MIR model was significantly increased from 0.624 to 0.721(Wilcoxon test, p value< 0.0001). When MIR model was combined with clinical factors, the C-index was further increased to 0.766. Subregional analysis showed that for LR patients, the top three differential radiomic features between the highest and lowest weighted subregions were GLRLM_ShortRunHighGrayLevelEmphasis, GRLM_HghGrayLevelRunEmphasis and GLRLM_LongRunHighGrayLevelEmphasis.

CONCLUSION

This study developed a subregion-based model that can predict the risk of local-regional recurrence and quantitatively assess relevant subregions, which may provide technical support for the precision radiotherapy in head and neck squamous cell carcinoma.

Locoregional recurrence prediction in head and neck cancer based on multi-modality and multi-view feature expansion

Objective. Locoregional recurrence (LRR) is one of the leading causes of treatment failure in head and neck (H&N) cancer. Accurately predicting LRR after radiotherapy is essential to achieving better treatment outcomes for patients with H&N cancer through developing personalized treatment strategies. We aim to develop an end-to-end multi-modality and multi-view feature extension method (MMFE) to predict LRR in H&N cancer. Approach. Deep learning (DL) has been widely used for building prediction models and has achieved great success. Nevertheless, 2D-based DL models inherently fail to utilize the contextual information from adjacent slices, while complicated 3D models have a substantially larger number of parameters, which require more training samples, memory and computing resources. In the proposed MMFE scheme, through the multi-view feature expansion and projection dimension reduction operations, we are able to reduce the model complexity while preserving volumetric information. Additionally, we designed a multi-modality convolutional neural network that can be trained in an end-to-end manner and can jointly optimize the use of deep features of CT, PET and clinical data to improve the model’s prediction ability. Main results. The dataset included 206 eligible patients, of which, 49 had LRR while 157 did not. The proposed MMFE method obtained a higher AUC value than the other four methods. The best prediction result was achieved when using all three modalities, which yielded an AUC value of 0.81. Significance. Comparison experiments demonstrated the superior performance of the MMFE as compared to other 2D/3D-DL-based methods. By combining CT, PET and clinical features, the MMFE could potentially identify H&N cancer patients at high risk for LRR such that personalized treatment strategy can be developed accordingly.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

Targeting Treatment Resistance in Head and Neck Squamous Cell Carcinoma - Proof of Concept for CT Radiomics-Based Identification of Resistant Sub-Volumes

Purpose

Radiomics has already been proposed as a prognostic biomarker in head and neck cancer (HNSCC). However, its predictive power in radiotherapy has not yet been studied. Here, we investigated a local radiomics approach to distinguish between tumor sub-volumes with different levels of radiosensitivity as a possible target for radiation dose intensification.

Materials and Methods

Of 40 patients (n=28 training and n=12 validation) with biopsy confirmed locally recurrent HNSCC, pretreatment contrast-enhanced CT images were registered with follow-up PET/CT imaging allowing identification of controlled (GTVcontrol) vs non-controlled (GTVrec) tumor sub-volumes on pretreatment imaging. A bi-regional model was built using radiomic features extracted from pretreatment CT in the GTVrec and GTVcontrol to differentiate between those regions. Additionally, concept of local radiomics was implemented to perform detection task. The original tumor volume was divided into sub-volumes with no prior information on the location of recurrence. Radiomic features from those sub-volumes were then used to detect recurrent sub-volumes using multivariable logistic regression.

Results

Radiomic features extracted from non-controlled regions differed significantly from those in controlled regions (training AUC = 0.79 CI 95% 0.66 - 0.91 and validation AUC = 0.88 CI 95% 0.72 – 1.00). Local radiomics analysis allowed efficient detection of non-controlled sub-volumes both in the training AUC = 0.66 (CI 95% 0.56 – 0.75) and validation cohort 0.70 (CI 95% 0.53 – 0.86), however performance of this model was inferior to bi-regional model. Both models indicated that sub-volumes characterized by higher heterogeneity were linked to tumor recurrence.

Conclusion

Local radiomics is able to detect sub-volumes with decreased radiosensitivity, associated with location of tumor recurrence in HNSCC in the pre-treatment CT imaging. This proof of concept study, indicates that local CT radiomics can be used as predictive biomarker in radiotherapy and potential target for dose intensification.

A self-adaptive prescription dose optimization algorithm for radiotherapy

Purpose

The aim of this study is to investigate an implementation method and the results of a voxel-based self-adaptive prescription dose optimization algorithm for intensity-modulated radiotherapy.

Materials and methods

The self-adaptive prescription dose optimization algorithm used a quadratic objective function, and the optimization engine was implemented using the molecular dynamics. In the iterative optimization process, the optimization prescription dose changed with the relationship between the initial prescription dose and the calculated dose. If the calculated dose satisfied the initial prescription dose, the optimization prescription dose was equal to the calculated dose; otherwise, the optimization prescription dose was equal to the initial prescription dose. We assessed the performance of the self-adaptive prescription dose optimization algorithm with two cases: a mock head and neck case and a breast case. Isodose lines, dose–volume histogram, and dosimetric parameters were compared between the conventional molecular dynamics optimization algorithm and the self-adaptive prescription dose optimization algorithm.

Results

The self-adaptive prescription dose optimization algorithm produces the different optimization results compared with the conventional molecular dynamics optimization algorithm. For the mock head and neck case, the planning target volume (PTV) dose uniformity improves, and the dose to organs at risk is reduced, ranging from 1 to 4%. For the breast case, the use of self-adaptive prescription dose optimization algorithm also leads to improvements in the dose distribution, with the dose to organs at risk almost unchanged.

Conclusion

The self-adaptive prescription dose optimization algorithm can generate an ideal clinical plan more effectively, and it could be integrated into a treatment planning system after more cases are studied.

Positron emission tomography for radiotherapy planning in head and neck cancer: What impact?

PET-computed tomography (CT) plays a growing role to guide target volume delineation for head and neck cancer in radiation oncology. Pretherapeutic [18F]FDG PET-CT adds information to morphological imaging. First, as a whole-body imaging modality, it reveals regional or distant metastases that induce major therapeutic changes in more than 10% of the cases. Moreover, it allows better pathological lymph node selection which improves overall regional control and overall survival. Second, locally, it allows us to define the metabolic tumoral volume, which is a reliable prognostic feature for survival outcome. [18F]FDG PET-CT-based gross tumor volume (GTV) is on average significantly smaller than GTV based on CT. Nevertheless, the overlap is incomplete and more evaluation of composite GTV based on PET and GTV based on CT are needed. However, in clinical practice, the study showed that using GTV PET alone for treatment planning was similar to using GTVCT for local control and dose distribution was better as a dose to organs at risk significantly decreased. In addition to FDG, pretherapeutic PET could give access to different biological tumoral volumes - thanks to different tracers - guiding heterogeneous dose delivery (dose painting concept) to resistant subvolumes. During radiotherapy treatment, follow-up [18F]FDG PET-CT revealed an earlier and more important diminution of GTV than other imaging modality. It may be a valuable support for adaptative radiotherapy as a new treatment plan with a significant impact on dose distribution became possible. Finally, additional studies are required to prospectively validate long-term outcomes and lower toxicity resulting from the use of PET-CT in treatment planning.

Deep Learning in Head and Neck Tumor Multiomics Diagnosis and Analysis: Review of the Literature

Head and neck tumors are the sixth most common neoplasms. Multiomics integrates multiple dimensions of clinical, pathologic, radiological, and biological data and has the potential for tumor diagnosis and analysis. Deep learning (DL), a type of artificial intelligence (AI), is applied in medical image analysis. Among the DL techniques, the convolution neural network (CNN) is used for image segmentation, detection, and classification and in computer-aided diagnosis. Here, we reviewed multiomics image analysis of head and neck tumors using CNN and other DL neural networks. We also evaluated its application in early tumor detection, classification, prognosis/metastasis prediction, and the signing out of the reports. Finally, we highlighted the challenges and potential of these techniques.

Radiomics at a Glance: A Few Lessons Learned from Learning Approaches

Simple Summary

Radiomics has become a prominent component of medical imaging research and many studies show its specific value as a support tool for clinical decision-making processes. Radiomic data are typically analyzed with statistical and machine learning methods, which change depending on the disease context and the imaging modality. We found a certain bias in the literature towards the use of such methods and believe that this limitation may influence the capacity of producing accurate and reliable decisions. Therefore, in view of the relevance of various types of learning methods, we report their significance and discuss their unrevealed potential.

Abstract

Processing and modeling medical images have traditionally represented complex tasks requiring multidisciplinary collaboration. The advent of radiomics has assigned a central role to quantitative data analytics targeting medical image features algorithmically extracted from large volumes of images. Apart from the ultimate goal of supporting diagnostic, prognostic, and therapeutic decisions, radiomics is computationally attractive due to specific strengths: scalability, efficiency, and precision. Optimization is achieved by highly sophisticated statistical and machine learning algorithms, but it is especially deep learning that stands out as the leading inference approach. Various types of hybrid learning can be considered when building complex integrative approaches aimed to deliver gains in accuracy for both classification and prediction tasks. This perspective reviews some selected learning methods by focusing on both their significance for radiomics and their unveiled potential.

PET and MRI guided adaptive radiotherapy: Rational, feasibility and benefit

Adaptive radiotherapy (ART) corresponds to various replanning strategies aiming to correct for anatomical variations occurring during the course of radiotherapy. The goal of the article was to report the rational, feasibility and benefit of using PET and/or MRI to guide this ART strategy in various tumor localizations. The anatomical modifications defined by scanner taking into account tumour mobility and volume variation are not always sufficient to optimise treatment. The contribution of functional imaging by PET or the precision of soft tissue by MRI makes it possible to consider optimized ART. Today, the most important data for both PET and MRI are for lung, head and neck, cervical and prostate cancers. PET and MRI guided ART appears feasible and safe, however in a very limited clinical experience. Phase I/II studies should be therefore performed, before proposing cost-effectiveness comparisons in randomized trials and before using the approach in routine practice.

Radioresistant tumours: From identification to targeting

From surviving fraction to tumour curability, definitions of tumour radioresistance may vary depending on the view angle. Yet, mechanisms of radioresistance have been identified and involve tumour-specific oncogenic signalling pathways, tumour metabolism and proliferation, tumour microenvironment/hypoxia, genomics. Correlations between tumour biology (histology) and imaging allow theragnostic approaches that use non-invasive biological imaging using tracer functionalization of tumour pathway biomarkers, imaging of hypoxia, etc. Modelling dose prescription function based on their tumour radio-resistant factor enhancement ratio, related to metabolism, proliferation, hypoxia is an area of investigation. Yet, the delivery of dose painting by numbers/voxel-based radiotherapy with low lineal energy transfer particles may be limited by the degree of modulation complexity needed to achieve the doses needed to counteract radioresistance. Higher lineal energy transfer particles or combinations of different particles, or combinations with drugs and devices such as done with radioenhancing nanoparticles may be promising.

Reinventing radiation therapy with machine learning and imaging bio-markers (radiomics): State-of-the-art, challenges and perspectives

Radiation therapy is a pivotal cancer treatment that has significantly progressed over the last decade due to numerous technological breakthroughs. Imaging is now playing a critical role on deployment of the clinical workflow, both for treatment planning and treatment delivery. Machine-learning analysis of predefined features extracted from medical images, i.e. radiomics, has emerged as a promising clinical tool for a wide range of clinical problems addressing drug development, clinical diagnosis, treatment selection and implementation as well as prognosis. Radiomics denotes a paradigm shift redefining medical images as a quantitative asset for data-driven precision medicine. The adoption of machine-learning in a clinical setting and in particular of radiomics features requires the selection of robust, representative and clinically interpretable biomarkers that are properly evaluated on a representative clinical data set. To be clinically relevant, radiomics must not only improve patients' management with great accuracy but also be reproducible and generalizable. Hence, this review explores the existing literature and exposes its potential technical caveats, such as the lack of quality control, standardization, sufficient sample size, type of data collection, and external validation. Based upon the analysis of 165 original research studies based on PET, CT-scan, and MRI, this review provides an overview of new concepts, and hypotheses generating findings that should be validated. In particular, it describes evolving research trends to enhance several clinical tasks such as prognostication, treatment planning, response assessment, prediction of recurrence/relapse, and prediction of toxicity. Perspectives regarding the implementation of an AI-based radiotherapy workflow are presented.

Correlation Between FDG Hotspots on Pre-radiotherapy PET/CT and Areas of HNSCC Local Relapse: Impact of Treatment Position and Images Registration Method

Aim: Several series have already demonstrated that intratumoral subvolumes with high tracer avidity (hotspots) in 18F-flurodesoxyglucose positron-emission tomography (FDG-PET/CT) are preferential sites of local recurrence (LR) in various solid cancers after radiotherapy (RT), becoming potential targets for dose escalation. However, studies conducted on head and neck squamous cell carcinoma (HNSCC) found only a moderate overlap between pre- and post-treatment subvolumes. A limitation of these studies was that scans were not performed in RT treatment position (TP) and were coregistred using a rigid registration (RR) method. We sought to study (i) the influence of FDG-PET/CT acquisition in TP and (ii) the impact of using an elastic registration (ER) method to improve the localization of hotpots in HNSCC.

Methods: Consecutive patients with HNSCC treated by RT between March 2015 and September 2017 who underwent FDG-PET/CT in TP at initial staging (PET_A) and during follow-up (PET_R) were prospectively included. We utilized a control group scanned in non treatment position (NTP) from our previous retrospective study. Scans were registered with both RR and ER methods. Various sub-volumes (A_X; x = 30, 40, 50, 60, 70, 80, and 90%SUVmax) within the initial tumor and in the subsequent LR (R_X; x = 40 and 70%SUVmax) were overlaid on the initial PET/CT for comparison [Dice, Jaccard, overlap fraction = OF, common volume/baseline volume = A_XnR_X/A_X, common volume/recurrent volume = A_XnR_X/R_X].

Results: Of 199 patients included, 43 (21.6%) had LR (TP = 15; NTP = 28). The overlap between A₃₀, A₄₀, and A₅₀ sub-volumes on PET_A and the whole metabolic volume of recurrence R₄₀ and R₇₀ on PET_R showed moderate to good agreements (0.41–0.64) with OF and A_XnR_X/R_X index, regardless of registration method or patient position. Comparison of registration method demonstrated OF and A_XnR_X/R_X indices (x = 30% to 50%SUVmax) were significantly higher with ER vs. RR in NTP (p < 0.03), but not in TP. For patient position, the OF and A_XnR_X/R_X indices were higher in TP than in NTP when RR was used with a trend toward significance, particularly for x=40%SUVmax (0.50±0.22 vs. 0.31 ± 0.13, p = 0.094).

Conclusion: Our study suggested that PET/CT acquired in TP improves results in the localization of FDG hotspots in HNSCC. If TP is not possible, using an ER method is significantly more accurate than RR for overlap estimation.

Radiomic biomarkers for head and neck squamous cell carcinoma

Tumor heterogeneity is a well-known prognostic factor in head and neck squamous cell carcinoma (HNSCC). A major limitation of tissue- and blood-derived tumor markers is the lack of spatial resolution to image tumor heterogeneity. Tissue markers derived from tumor biopsies usually represent only a small tumor subregion at a single timepoint and are therefore often not representative of the tumors' biology or the biological alterations during and after treatment. Similarly, liquid biopsies give an overall picture of the tumors' secreted factors but completely lack any spatial resolution. Radiomics has the potential to give complete three-dimensional information about the tumor. We conducted a comprehensive literature search to assess the correlation of radiomics to tumor biology and treatment outcome in HNSCC and to assess current limitations of the radiomic biomarkers. In total, 25 studies that explored the ability of radiomics to predict tumor biology and phenotype in HNSCC and 28 studies that explored radiomics to predict post-treatment events were identified. Out of these 53 studies, only three failed to show a significant correlation. The major technical challenges are currently artifacts due to metal implants, non-standardized contrast injection, and delineation uncertainties. All studies to date were retrospective and none of the above-mentioned radiomics signatures have been validated in an independent cohort using an independent software implementation, which shows that transferability due to the numerous technical challenges is currently a major limitation. However, radiomics is a very young field and these studies hopefully pave the way for clinical implementation of radiomics for HNSCC in the future.

Computed tomography-derived radiomic signature of head and neck squamous cell carcinoma (peri)tumoral tissue for the prediction of locoregional recurrence and distant metastasis after concurrent chemo-radiotherapy

Introduction

In this study, we investigate the role of radiomics for prediction of overall survival (OS), locoregional recurrence (LRR) and distant metastases (DM) in stage III and IV HNSCC patients treated by chemoradiotherapy. We hypothesize that radiomic analysis of (peri-)tumoral tissue may detect invasion of surrounding tissues indicating a higher chance of locoregional recurrence and distant metastasis.

Methods

Two comprehensive data sources were used: the Dutch Cancer Society Database (Alp 7072, DESIGN) and “Big Data To Decide” (BD2Decide). The gross tumor volumes (GTV) were delineated on contrast-enhanced CT. Radiomic features were extracted using the RadiomiX Discovery Toolbox (OncoRadiomics, Liege, Belgium). Clinical patient features such as age, gender, performance status etc. were collected. Two machine learning methods were chosen for their ability to handle censored data: Cox proportional hazards regression and random survival forest (RSF). Multivariable clinical and radiomic Cox/ RSF models were generated based on significance in univariable cox regression/ RSF analyses on the held out data in the training dataset. Features were selected according to a decreasing hazard ratio for Cox and relative importance for RSF.

Results

A total of 444 patients with radiotherapy planning CT-scans were included in this study: 301 head and neck squamous cell carcinoma (HNSCC) patients in the training cohort (DESIGN) and 143 patients in the validation cohort (BD2DECIDE). We found that the highest performing model was a clinical model that was able to predict distant metastasis in oropharyngeal cancer cases with an external validation C-index of 0.74 and 0.65 with the RSF and Cox models respectively. Peritumoral radiomics based prediction models performed poorly in the external validation, with C-index values ranging from 0.32 to 0.61 utilizing both feature selection and model generation methods.

Conclusion

Our results suggest that radiomic features from the peritumoral regions are not useful for the prediction of time to OS, LR and DM.

Use of Baseline 18 F-FDG PET/CT to Identify Initial Sub-Volumes Associated With Local Failure After Concomitant Chemoradiotherapy in Locally Advanced Cervical Cancer

Introduction: Locally advanced cervical cancer (CC) patients treated by chemoradiotherapy (CRT) have a significant local recurrence rate. The objective of this work was to assess the overlap between the initial high-uptake sub-volume (V1) on baseline 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scans and the metabolic relapse (V2) sites after CRT in locally advanced CC. Methods: PET/CT performed before treatment and at relapse in 21 patients diagnosed with LACC and treated with CRT were retrospectively analyzed. CT images at the time of recurrence were registered to baseline CT using the 3D Slicer TM Expert Automated Registration module. The corresponding PET images were then registered using the corresponding transform. The fuzzy locally adaptive Bayesian (FLAB) algorithm was implemented using 3 classes (one for the background and the other two for tumor) in PET1 to simultaneously define an overall tumor volume and the sub-volume V1. In PET2, FLAB was implemented using 2 classes (one for background, one for tumor), in order to define V2. Four indices were used to determine the overlap between V1 and V2 (Dice coefficients, overlap fraction, X = (V1nV2)/V1 and Y = (V1nV2)/V2). Results: The mean (±standard deviation) follow-up was 26 ± 11 months. The measured overlaps between V1 and V2 were moderate to good according to the four metrics, with 0.62-0.81 (0.72 ± 0.05), 0.72-1.00 (0.85 ± 0.10), 0.55-1.00 (0.73 ± 0.16) and 0.50-1.00 (0.76 ± 0.12) for Dice, overlap fraction, X and Y, respectively. Conclusion: In our study, the overlaps between the initial high-uptake sub-volume and the recurrent metabolic volume showed moderate to good concordance. These results now need to be confirmed in a larger cohort using a more standardized patient repositioning procedure for sequential PET/CT imaging, as there is potential for RT dose escalation exploiting the pre-treatment PET high-uptake sub-volume.