Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features

Cone-beam computed-tomography-based delta-radiomic analysis for investigating prognostic power for esophageal squamous cell cancer patients undergoing concurrent chemoradiotherapy

PURPOSE

To investigate the prognostic power of cone-beam computed-tomography (CBCT)-based delta-radiomics in esophageal squamous cell cancer (ESCC) patients treated with concurrent chemoradiotherapy (CCRT).

METHODS

We collected data from 26 ESCC patients treated with CCRT. CBCT images acquired at five time points (1st-5th week) per patient during CCRT were used in this study. Radiomic features were extracted from the five CBCT images on the gross tumor volumes. Then, 17 delta-radiomic feature sets derived from five types of calculations were obtained for all the cases. Leave-one-out cross-validation was applied to investigate the prognostic power of CBCT-based delta-radiomic features. Feature selection and construction of a prediction model using Coxnet were performed using training samples. Then, the test sample was classified into high or low risk in each cross-validation fold. Survival analysis for the two groups were performed to evaluate the prognostic power of the extracted CBCT-based delta-radiomic features.

RESULTS

Four delta-radiomic feature sets indicated significant differences between the high- and low-risk groups (p < 0.05). The highest C-index in the 17 delta-radiomic feature sets was 0.821 (95 % confidence interval, 0.735-0.907). That feature set had p-value of the log-rank test and hazard ratio of 0.003 and 4.940 (95 % confidence interval, 1.391-17.544), respectively.

CONCLUSIONS

We investigated the potential of using CBCT-based delta-radiomics for prognosis of ESCC patients treated with CCRT. It was demonstrated that delta-radiomic feature sets based on the absolute value of relative difference obtained from the early to the middle treatment stages have high prognostic power for ESCC.

Artificial intelligence applied to image-guided radiation therapy (IGRT): a systematic review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (yAIRO)

INTRODUCTION

The advent of image-guided radiation therapy (IGRT) has recently changed the workflow of radiation treatments by ensuring highly collimated treatments. Artificial intelligence (AI) and radiomics are tools that have shown promising results for diagnosis, treatment optimization and outcome prediction. This review aims to assess the impact of AI and radiomics on modern IGRT modalities in RT.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to investigate the impact of radiomics and AI to modern IGRT modalities. The search strategy was "Radiomics" AND "Cone Beam Computed Tomography"; "Radiomics" AND "Magnetic Resonance guided Radiotherapy"; "Radiomics" AND "on board Magnetic Resonance Radiotherapy"; "Artificial Intelligence" AND "Cone Beam Computed Tomography"; "Artificial Intelligence" AND "Magnetic Resonance guided Radiotherapy"; "Artificial Intelligence" AND "on board Magnetic Resonance Radiotherapy" and only original articles up to 01.11.2022 were considered.

RESULTS

A total of 402 studies were obtained using the previously mentioned search strategy on PubMed and Embase. The analysis was performed on a total of 84 papers obtained following the complete selection process. Radiomics application to IGRT was analyzed in 23 papers, while a total 61 papers were focused on the impact of AI on IGRT techniques.

DISCUSSION

AI and radiomics seem to significantly impact IGRT in all the phases of RT workflow, even if the evidence in the literature is based on retrospective data. Further studies are needed to confirm these tools' potential and provide a stronger correlation with clinical outcomes and gold-standard treatment strategies.

The Promise and Future of Radiomics for Personalized Radiotherapy Dosing and Adaptation

Quantitative image analysis, also known as radiomics, aims to analyze large-scale quantitative features extracted from acquired medical images using hand-crafted or machine-engineered feature extraction approaches. Radiomics has great potential for a variety of clinical applications in radiation oncology, an image-rich treatment modality that utilizes computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) for treatment planning, dose calculation, and image guidance. A promising application of radiomics is in predicting treatment outcomes after radiotherapy such as local control and treatment-related toxicity using features extracted from pretreatment and on-treatment images. Based on these individualized predictions of treatment outcomes, radiotherapy dose can be sculpted to meet the specific needs and preferences of each patient. Radiomics can aid in tumor characterization for personalized targeting, especially for identifying high-risk regions within a tumor that cannot be easily discerned based on size or intensity alone. Radiomics-based treatment response prediction can aid in developing personalized fractionation and dose adjustments. In order to make radiomics models more applicable across different institutions with varying scanners and patient populations, further efforts are needed to harmonize and standardize the acquisition protocols by minimizing uncertainties within the imaging data.

Image Guided Radiotherapy (IGRT) and Delta (Δ) Radiomics-An Urgent Alliance for the Front Line of the War against Head and Neck Cancers

The identification of a biomarker that is response predictive could offer a solution for the stratification of the treatment of head and neck cancers (HNC) in the context of high recurrence rates, especially those associated with loco-regional failure. Delta (Δ) radiomics, a concept based on the variation of parameters extracted from medical imaging using artificial intelligence (AI) algorithms, demonstrates its potential as a predictive biomarker of treatment response in HNC. The concept of image-guided radiotherapy (IGRT), including computer tomography simulation (CT) and position control imaging with cone-beam-computed tomography (CBCT), now offers new perspectives for radiomics applied in radiotherapy. The use of Δ features of texture, shape, and size, both from the primary tumor and from the tumor-involved lymph nodes, demonstrates the best predictive accuracy. If, in the case of treatment response, promising Δ radiomics results could be obtained, even after 24 h from the start of treatment, for radiation-induced xerostomia, the evaluation of Δ radiomics in the middle of treatment could be recommended. The fused models (clinical and Δ radiomics) seem to offer benefits, both in comparison to the clinical model and to the radiomic model. The selection of patients who benefit from induction chemotherapy is underestimated in Δ radiomic studies and may be an unexplored territory with major potential. The advantage offered by "in house" simulation CT and CBCT favors the rapid implementation of Δ radiomics studies in radiotherapy departments. Positron emission tomography (PET)-CT Δ radiomics could guide the new concepts of dose escalation on radio-resistant sub-volumes based on radiobiological criteria, but also guide the "next level" of HNC adaptive radiotherapy (ART).

Towards reliable head and neck cancers locoregional recurrence prediction using delta-radiomics and learning with rejection option

PURPOSE

A reliable locoregional recurrence (LRR) prediction model is important for the personalized management of head and neck cancers (HNC) patients who received radiotherapy. This work aims to develop a delta-radiomics feature-based multi-classifier, multi-objective, and multi-modality (Delta-mCOM) model for post-treatment HNC LRR prediction. Furthermore, we aim to adopt a learning with rejection option (LRO) strategy to boost the reliability of Delta-mCOM model by rejecting prediction for samples with high prediction uncertainties.

METHODS

In this retrospective study, we collected PET/CT image and clinical data from 224 HNC patients who received radiotherapy (RT) at our institution. We calculated the differences between radiomics features extracted from PET/CT images acquired before and after radiotherapy and used them in conjunction with pre-treatment radiomics features as the input features. Using clinical parameters, PET radiomics features, and CT radiomics features, we built and optimized three separate single-modality models. We used multiple classifiers for model construction and employed sensitivity and specificity simultaneously as the training objectives for each of them. Then, for testing samples, we fused the output probabilities from all these single-modality models to obtain the final output probabilities of the Delta-mCOM model. In the LRO strategy, we estimated the epistemic and aleatoric uncertainties when predicting with a trained Delta-mCOM model and identified patients associated with prediction of higher reliability (low uncertainty estimates). The epistemic and aleatoric uncertainties were estimated using an AutoEncoder-style anomaly detection model and test-time augmentation (TTA) with predictions made from the Delta-mCOM model, respectively. Predictions with higher epistemic uncertainty or higher aleatoric uncertainty than given thresholds were deemed unreliable, and they were rejected before providing a final prediction. In this study, different thresholds corresponding to different low-reliability prediction rejection ratios were applied. Their values are based on the estimated epistemic and aleatoric uncertainties distribution of the validation data.

RESULTS

The Delta-mCOM model performed significantly better than the single-modality models, whether trained with pre-, post-treatment radiomics features or concatenated BaseLine and Delta-Radiomics Features (BL-DRFs). It was numerically superior to the PET and CT fused BL-DRF model (nonstatistically significant). Using the LRO strategy for the Delta-mCOM model, most of the evaluation metrics improved as the rejection ratio increased from 0% to around 25%. Utilizing both epistemic and aleatoric uncertainty for rejection yielded nonstatistically significant improved metrics compared to each alone at approximately a 25% rejection ratio. Metrics were significantly better than the no-rejection method when the reject ratio was higher than 50%.

CONCLUSIONS

The inclusion of the delta-radiomics feature improved the accuracy of HNC LRR prediction, and the proposed Delta-mCOM model can give more reliable predictions by rejecting predictions for samples of high uncertainty using the LRO strategy.

Current Role of Delta Radiomics in Head and Neck Oncology

The latest developments in the management of head and neck cancer show an increasing trend in the implementation of novel approaches using artificial intelligence for better patient stratification and treatment-related risk evaluation. Radiomics, or the extraction of data from various imaging modalities, is a tool often used to evaluate specific features related to the tumour or normal tissue that are not identifiable by the naked eye and which can add value to existing clinical data. Furthermore, the assessment of feature variations from one time point to another based on subsequent images, known as delta radiomics, was shown to have even higher value for treatment-outcome prediction or patient stratification into risk categories. The information gathered from delta radiomics can, further, be used for decision making regarding treatment adaptation or other interventions found to be beneficial to the patient. The aim of this work is to collate the existing studies on delta radiomics in head and neck cancer and evaluate its role in tumour response and normal-tissue toxicity predictions alike. Moreover, this work also highlights the role of holomics, which brings under the same umbrella clinical and radiomic features, for a more complex patient characterization and treatment optimisation.

Current Applications of Deep Learning and Radiomics on CT and CBCT for Maxillofacial Diseases

The increasing use of computed tomography (CT) and cone beam computed tomography (CBCT) in oral and maxillofacial imaging has driven the development of deep learning and radiomics applications to assist clinicians in early diagnosis, accurate prognosis prediction, and efficient treatment planning of maxillofacial diseases. This narrative review aimed to provide an up-to-date overview of the current applications of deep learning and radiomics on CT and CBCT for the diagnosis and management of maxillofacial diseases. Based on current evidence, a wide range of deep learning models on CT/CBCT images have been developed for automatic diagnosis, segmentation, and classification of jaw cysts and tumors, cervical lymph node metastasis, salivary gland diseases, temporomandibular (TMJ) disorders, maxillary sinus pathologies, mandibular fractures, and dentomaxillofacial deformities, while CT-/CBCT-derived radiomics applications mainly focused on occult lymph node metastasis in patients with oral cancer, malignant salivary gland tumors, and TMJ osteoarthritis. Most of these models showed high performance, and some of them even outperformed human experts. The models with performance on par with human experts have the potential to serve as clinically practicable tools to achieve the earliest possible diagnosis and treatment, leading to a more precise and personalized approach for the management of maxillofacial diseases. Challenges and issues, including the lack of the generalizability and explainability of deep learning models and the uncertainty in the reproducibility and stability of radiomic features, should be overcome to gain the trust of patients, providers, and healthcare organizers for daily clinical use of these models.

Identification of biomarkers for hepatocellular carcinoma based on single cell sequencing and machine learning algorithms

Hepatocellular carcinoma (HCC) remains one of the most lethal cancers around the world. Precision oncology will be crucial for further improving the prognosis of HCC patients. Compared with traditional bulk RNA-seq, single-cell RNA sequencing (scRNA-seq) enables the transcriptomes of a great deal of individual cells assayed in an unbiased manner, showing the potential to deeply reveal tumor heterogeneity. In this study, based on the scRNA-seq results of primary neoplastic cells and paired normal liver cells from eight HCC patients, a new strategy of machine learning algorithms was applied to screen core biomarkers that distinguished HCC tumor tissues from the adjacent normal liver. Expression profiles of HCC cells and normal liver cells were first analyzed by maximum relevance minimum redundancy (mRMR) to get a top 50 signature gene feature. For further analysis, the incremental feature selection (IFS) method and leave-one-out cross validation (LOOCV) were conducted to build an optimal classification model and to extract 21 potentially essential biomarkers for HCC cells. Our results provided new insights into HCC pathogenesis that might be valuable for HCC diagnosis and therapy.