Integrating Multiomics Information in Deep Learning Architectures for Joint Actuarial Outcome Prediction in Non-Small Cell Lung Cancer Patients After Radiation Therapy

A deep learning-informed interpretation of why and when dose metrics outside the PTV can affect the risk of distant metastasis in SBRT NSCLC patients

PURPOSE

Recent papers suggested a correlation between the risk of distant metastasis (DM) and dose outside the PTV, though conclusions in different publications conflicted. This study resolves these conflicts and provides a compelling explanation of prognostic factors.

MATERIALS AND METHODS

A dataset of 478 NSCLC patients treated with SBRT (IMRT or VMAT) was analyzed. We developed a deep learning model for DM prediction and explainable AI was used to identify the most significant prognostic factors. Subsequently, the prognostic power of the extracted features and clinical details were analyzed using conventional statistical methods.

RESULTS

Treatment technique, tumor features, and dosiomic features in a 3 cm wide ring around the PTV (PTV3cm) were identified as the strongest predictors of DM. The Hazard Ratio (HR) for Dmean,PTV3cm was significantly above 1 (p < 0.001). There was no significance of the PTV3cm dose after treatment technique stratification. However, the dose in PTV3cm was found to be a highly significant DM predictor (HR > 1, p = 0.004) when analyzing only VMAT patients with small and spherical tumors (i.e., sphericity > 0.5).

CONCLUSIONS

The main reason for conflicting conclusions in previous papers was inconsistent datasets and insufficient consideration of confounding variables. No causal correlation between the risk of DM and dose outside the PTV was found. However, the mean dose to PTV3cm can be a significant predictor of DM in small spherical targets treated with VMAT, which might clinically imply considering larger PTV margins for smaller, more spherical tumors (e.g., if IGTV > 2 cm, then margin ≤ 7 mm, else margin > 7 mm).

Treatment Response Biomarkers: Working Toward Personalized Radiotherapy for Lung Cancer

Owing to major advances in the field of radiation oncology, patients with lung cancer can now receive technically individualized radiotherapy treatments. Nevertheless, in the era of precision oncology, radiotherapy-based treatment selection needs to be improved as many patients do not benefit or are not offered optimum therapies. Cost-effective robust biomarkers can address this knowledge gap and lead to individuals being offered more bespoke treatments leading to improved outcome. This narrative review discusses some of the current achievements and challenges in the realization of personalized radiotherapy delivery in patients with lung cancer.

Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy

PURPOSE

Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control.

METHODS AND MATERIALS

A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points.

RESULTS

The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51).

CONCLUSIONS

Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

BACKGROUND

Radiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals.

METHODS

Dosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 - (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 - and AST 2 + groups and cutoff value calculations.

RESULTS

Results showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71-0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models.

CONCLUSIONS

This study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.

Improved outcome models with denoising diffusion

PURPOSE

Radiotherapy outcome modelling often suffers from class imbalance in the modelled endpoints. One of the main options to address this issue is by introducing new synthetically generated datapoints, using generative models, such as Denoising Diffusion Probabilistic Models (DDPM). In this study, we implemented DDPM to improve performance of a tumor local control model, trained on imbalanced dataset, and compare this approach with other common techniques.

METHODS

A dataset of 535 NSCLC patients treated with SBRT (50 Gy/5 fractions) was used to train a deep learning outcome model for tumor local control prediction. The dataset included complete treatment planning data (planning CT images, 3D planning dose distribution and patient demographics) with sparsely distributed endpoints (6-7 % experiencing local failure). Consequently, we trained a novel conditional 3D DDPM model to generate synthetic treatment planning data. Synthetically generated treatment planning datapoints were used to supplement the real training dataset and the improvement in the model's performance was studied. Obtained results were also compared to other common techniques for class imbalanced training, such as Oversampling, Undersampling, Augmentation, Class Weights, SMOTE and ADASYN.

RESULTS

Synthetic DDPM-generated data were visually trustworthy, with Fréchet inception distance (FID) below 50. Extending the training dataset with the synthetic data improved the model's performance by more than 10%, while other techniques exhibited only about 4% improvement.

CONCLUSIONS

DDPM introduces a novel approach to class-imbalanced outcome modelling problems. The model generates realistic synthetic radiotherapy planning data, with a strong potential to increase performance and robustness of outcome models.

The global research of artificial intelligence in lung cancer: a 20-year bibliometric analysis

Background

Lung cancer (LC) is the second-highest incidence and the first-highest mortality cancer worldwide. Early screening and precise treatment of LC have been the research hotspots in this field. Artificial intelligence (AI) technology has advantages in many aspects of LC and widely used such as LC early diagnosis, LC differential classification, treatment and prognosis prediction.

Objective

This study aims to analyze and visualize the research history, current status, current hotspots, and development trends of artificial intelligence in the field of lung cancer using bibliometric methods, and predict future research directions and cutting-edge hotspots.

Results

A total of 2931 articles published between 2003 and 2023 were included, contributed by 15,848 authors from 92 countries/regions. Among them, China (40%) with 1173 papers,USA (24.80%) with 727 papers and the India(10.2%) with 299 papers have made outstanding contributions in this field, accounting for 75% of the total publications. The primary research institutions were Shanghai Jiaotong University(n=66),Chinese Academy of Sciences (n=63) and Harvard Medical School (n=52).Professor Qian Wei(n=20) from Northeastern University in China were ranked first in the top 10 authors while Armato SG(n=458 citations) was the most co-cited authors. Frontiers in Oncology(121 publications; IF 2022,4.7; Q2) was the most published journal. while Radiology (3003 citations; IF 2022, 19.7; Q1) was the most co-cited journal. different countries and institutions should further strengthen cooperation between each other. The most common keywords were lung cancer, classification, cancer, machine learning and deep learning. Meanwhile, The most cited papers was Nicolas Coudray et al.2018.NAT MED(1196 Total Citations).

Conclusions

Research related to AI in lung cancer has significant application prospects, and the number of scholars dedicated to AI-related research on lung cancer is continually growing. It is foreseeable that non-invasive diagnosis and precise minimally invasive treatment through deep learning and machine learning will remain a central focus in the future. Simultaneously, there is a need to enhance collaboration not only among various countries and institutions but also between high-quality medical and industrial entities.

Developing a clinical-radiomic prediction model for 3-year cancer-specific survival in lung cancer patients treated with stereotactic body radiation therapy

PURPOSE

The study aims to develop and validate a combined model for predicting 3-year cancer-specific survival (CSS) in lung cancer patients treated with stereotactic body radiation therapy (SBRT) by integrating clinical and radiomic parameters.

METHODS

Clinical data and pre-treatment CT images were collected from 102 patients treated with lung SBRT. Multivariate logistic regression and the least absolute shrinkage and selection operator were used to determine the clinical and radiomic factors associated with 3-year CSS. Three prediction models were developed using clinical factors, radiomic factors, and a combination of both. The performance of the models was assessed using receiver operating characteristic curve and calibration curve. A nomogram was also created to visualize the 3-year CSS prediction.

RESULTS

With a 36-month follow-up, 40 patients (39.2%) died of lung cancer and 62 patients (60.8%) survived. Three clinical factors, including gender, clinical stage, and lymphocyte ratio, along with three radiomic features, were found to be independent factors correlated with 3-year CSS. The area under the curve values for the clinical, radiomic, and combined model were 0.839 (95% CI 0.735-0.914), 0.886 (95% CI 0.790-0.948), and 0.914 (95% CI 0.825-0.966) in the training cohort, and 0.757 (95% CI 0.580-0.887), 0.818 (95% CI 0.648-0.929), and 0.843 (95% CI 0.677-0.944) in the validation cohort, respectively. Additionally, the calibration curve demonstrated good calibration performance and the nomogram created from the combined model showed potential for clinical utility.

CONCLUSION

A clinical-radiomic model was developed to predict the 3-year CSS for lung cancer patients treated with SBRT.

"Under the hood": artificial intelligence in personalized radiotherapy

This review presents and discusses the ways in which artificial intelligence (AI) tools currently intervene, or could potentially intervene in the future, to enhance the diverse tasks involved in the radiotherapy workflow. The radiotherapy framework is presented on 2 different levels for the personalization of the treatment, distinct in tasks and methodologies. The first level is the clinically well-established anatomy-based workflow, known as adaptive radiation therapy. The second level is referred to as biology-driven workflow, explored in the research literature and recently appearing in some preliminary clinical trials for personalized radiation treatments. A 2-fold role for AI is defined according to these 2 different levels. In the anatomy-based workflow, the role of AI is to streamline and improve the tasks in terms of time and variability reductions compared to conventional methodologies. The biology-driven workflow instead fully relies on AI, which introduces decision-making tools opening uncharted frontiers that were in the past deemed challenging to explore. These methodologies are referred to as radiomics and dosiomics, handling imaging and dosimetric information, or multiomics, when complemented by clinical and biological parameters (ie, biomarkers). The review explicitly highlights the methodologies that are currently incorporated into clinical practice or still in research, with the aim of presenting the AI's growing role in personalized radiotherapy.

Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET)

AIM

Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction.

METHODS

A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined.

RESULTS

One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available.

CONCLUSION

Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.

Artificial general intelligence for radiation oncology

The emergence of artificial general intelligence (AGI) is transforming radiation oncology. As prominent vanguards of AGI, large language models (LLMs) such as GPT-4 and PaLM 2 can process extensive texts and large vision models (LVMs) such as the Segment Anything Model (SAM) can process extensive imaging data to enhance the efficiency and precision of radiation therapy. This paper explores full-spectrum applications of AGI across radiation oncology including initial consultation, simulation, treatment planning, treatment delivery, treatment verification, and patient follow-up. The fusion of vision data with LLMs also creates powerful multimodal models that elucidate nuanced clinical patterns. Together, AGI promises to catalyze a shift towards data-driven, personalized radiation therapy. However, these models should complement human expertise and care. This paper provides an overview of how AGI can transform radiation oncology to elevate the standard of patient care in radiation oncology, with the key insight being AGI's ability to exploit multimodal clinical data at scale.

Prediction of Radiation Treatment Response for Locally Advanced Rectal Cancer via a Longitudinal Trend Analysis Framework on Cone-Beam CT

Locally advanced rectal cancer (LARC) presents a significant challenge in terms of treatment management, particularly with regards to identifying patients who are likely to respond to radiation therapy (RT) at an individualized level. Patients respond to the same radiation treatment course differently due to inter- and intra-patient variability in radiosensitivity. In-room volumetric cone-beam computed tomography (CBCT) is widely used to ensure proper alignment, but also allows us to assess tumor response during the treatment course. In this work, we proposed a longitudinal radiomic trend (LRT) framework for accurate and robust treatment response assessment using daily CBCT scans for early detection of patient response. The LRT framework consists of four modules: (1) Automated registration and evaluation of CBCT scans to planning CT; (2) Feature extraction and normalization; (3) Longitudinal trending analyses; and (4) Feature reduction and model creation. The effectiveness of the framework was validated via leave-one-out cross-validation (LOOCV), using a total of 840 CBCT scans for a retrospective cohort of LARC patients. The trending model demonstrates significant differences between the responder vs. non-responder groups with an Area Under the Curve (AUC) of 0.98, which allows for systematic monitoring and early prediction of patient response during the RT treatment course for potential adaptive management.

Interpretable artificial intelligence in radiology and radiation oncology

Artificial intelligence has been introduced to clinical practice, especially radiology and radiation oncology, from image segmentation, diagnosis, treatment planning and prognosis. It is not only crucial to have an accurate artificial intelligence model, but also to understand the internal logic and gain the trust of the experts. This review is intended to provide some insights into core concepts of the interpretability, the state-of-the-art methods for understanding the machine learning models, the evaluation of these methods, identifying some challenges and limits of them, and gives some examples of medical applications.

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis and therapy in the era of precision oncology. Artificial intelligence (AI) including machine learning (ML) and deep learning (DL) techniques combined with the exponential growth of multiomics data may have great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction and clinical decision-making. In this article, we first present different categories of multiomics data and their roles in diagnosis and therapy. Second, AI-based data fusion methods and modeling methods as well as different validation schemes are illustrated. Third, the applications and examples of multiomics research in oncology are demonstrated. Finally, the challenges regarding the heterogeneity data set, availability of omics data, and validation of the research are discussed. The transition of multiomics research to real clinics still requires consistent efforts in standardizing omics data collection and analysis, building computational infrastructure for data sharing and storing, developing advanced methods to improve data fusion and interpretability, and ultimately, conducting large-scale prospective clinical trials to fill the gap between study findings and clinical benefits.

Translation of AI into oncology clinical practice

Artificial intelligence (AI) is a transformative technology that is capturing popular imagination and can revolutionize biomedicine. AI and machine learning (ML) algorithms have the potential to break through existing barriers in oncology research and practice such as automating workflow processes, personalizing care, and reducing healthcare disparities. Emerging applications of AI/ML in the literature include screening and early detection of cancer, disease diagnosis, response prediction, prognosis, and accelerated drug discovery. Despite this excitement, only few AI/ML models have been properly validated and fewer have become regulated products for routine clinical use. In this review, we highlight the main challenges impeding AI/ML clinical translation. We present different clinical use cases from the domains of radiology, radiation oncology, immunotherapy, and drug discovery in oncology. We dissect the unique challenges and opportunities associated with each of these cases. Finally, we summarize the general requirements for successful AI/ML implementation in the clinic, highlighting specific examples and points of emphasis including the importance of multidisciplinary collaboration of stakeholders, role of domain experts in AI augmentation, transparency of AI/ML models, and the establishment of a comprehensive quality assurance program to mitigate risks of training bias and data drifts, all culminating toward safer and more beneficial AI/ML applications in oncology labs and clinics.

Acute coronary event (ACE) prediction following breast radiotherapy by features extracted from 3D CT, dose, and cardiac structures

PURPOSE

Heart toxicity, such as major acute coronary events (ACE), following breast radiation therapy (RT) is of utmost concern. Thus, many studies have been investigating the effect of mean heart dose (MHD) and dose received in heart sub-structures on toxicity. Most studies focused on the dose thresholds in the heart and its sub-structures, while few studies adopted such computational methods as deep neural networks (DNN) and radiomics. This work aims to construct a feature-driven predictive model for ACE after breast RT.

METHODS

A recently proposed two-step predictive model that extracts a number of features from a deep auto-segmentation network and processes the selected features for prediction was adopted. This work refined the auto-segmenting network and feature processing algorithms to enhance performance in cardiac toxicity prediction. In the predictive model, the deep convolutional neural network (CNN) extracted features from 3D computed tomography (CT) images and dose distributions in three automatically segmented heart sub-structures, including the left anterior descending artery (LAD), right coronary artery (RCA), and left ventricle (LV). The optimal feature processing workflow for the extracted features was explored to enhance the prediction accuracy. The regions associated with toxicity were visualized using a class activation map (CAM)-based technique. Our proposed model was validated against a conventional DNN (convolutional and fully connected layers) and radiomics with a patient cohort of 84 cases, including 29 and 55 patient cases with and without ACE. Of the entire 84 cases, 12 randomly chosen cases (5 toxicity and 7 non-toxicity cases) were set aside for independent test, and the remaining 72 cases were applied to 4-fold stratified cross-validation.

RESULTS

Our predictive model outperformed the conventional DNN by 38% and 10% and radiomics-based predictive models by 9% and 10% in AUC for 4-fold cross-validations and independent test, respectively. The degree of enhancement was greater when incorporating dose information and heart sub-structures into feature extraction. The model whose inputs were CT, dose, and three sub-structures (LV, LAD, and RCA) reached 96% prediction accuracy on average and 0.94 area under the curve (AUC) on average in the cross-validation, and also achieved prediction accuracy of 83% and AUC of 0.83 in the independent test. On 10 correctly predicted cases out of 12 for the independent test, the activation maps implied that for cases of ACE toxicity, the higher intensity was more likely to be observed inside the LV.

CONCLUSIONS

The proposed model characterized by modifications in model input with dose distributions and cardiac sub-structures, and serial processing of feature extraction and feature selection techniques can improve the predictive performance in ACE following breast RT.

Comparison of computed tomography image features extracted by radiomics, self-supervised learning and end-to-end deep learning for outcome prediction of oropharyngeal cancer

Background and purpose

To compare the prediction performance of image features of computed tomography (CT) images extracted by radiomics, self-supervised learning and end-to-end deep learning for local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), tumor-specific survival (TSS), overall survival (OS) and disease-free survival (DFS) of oropharyngeal squamous cell carcinoma (OPSCC) patients after (chemo)radiotherapy.

Methods and materials

The OPC-Radiomics dataset was used for model development and independent internal testing and the UMCG-OPC set for external testing. Image features were extracted from the Gross Tumor Volume contours of the primary tumor (GTVt) regions in CT scans when using radiomics or a self-supervised learning-based method (autoencoder). Clinical and combined (radiomics, autoencoder or end-to-end) models were built using multivariable Cox proportional-hazard analysis with clinical features only and both clinical and image features for LC, RC, LRC, DMFS, TSS, OS and DFS prediction, respectively.

Results

In the internal test set, combined autoencoder models performed better than clinical models and combined radiomics models for LC, RC, LRC, DMFS, TSS and DFS prediction (largest improvements in C-index: 0.91 vs. 0.76 in RC and 0.74 vs. 0.60 in DMFS). In the external test set, combined radiomics models performed better than clinical and combined autoencoder models for all endpoints (largest improvements in LC, 0.82 vs. 0.71). Furthermore, combined models performed better in risk stratification than clinical models and showed good calibration for most endpoints.

Conclusions

Image features extracted using self-supervised learning showed best internal prediction performance while radiomics features have better external generalizability.

Prediction of toxicity outcomes following radiotherapy using deep learning-based models: A systematic review

PURPOSE

This study aims to perform a comprehensive systematic review of deep learning (DL) models in predicting RT-induced toxicity.

MATERIALS AND METHODS

A literature review was performed following the PRISMA guidelines. Systematic searches were performed in PubMed, Scopus, Cochrane and Embase databases from the earliest record up to September 2022. Related studies on deep learning models for radiotherapy toxicity prediction were selected based on predefined PICOS criteria.

RESULTS

Fourteen studies of radiotherapy-treated patients on different types of cancer [prostate (n=2), HNC (n=4), liver (n=2), lung (n=4), cervical (n=1), and oesophagus (n=1)] were eligible for inclusion in the systematic review. Information regarding patient characteristics and model development was summarized. Several approaches, such as ensemble learning, data augmentation, and transfer learning, that were utilized by selected studies were discussed.

CONCLUSION

Deep learning techniques are able to produce a consistent performance for toxicity prediction. Future research using large and diverse datasets and standardization of the study methodologies are required to improve the consistency of the research output.

Artificial intelligence predicts lung cancer radiotherapy response: A meta-analysis

BACKGROUND

Artificial intelligence (AI) technology has clustered patients based on clinical features into sub-clusters to stratify high-risk and low-risk groups to predict outcomes in lung cancer after radiotherapy and has gained much more attention in recent years. Given that the conclusions vary considerably, this meta-analysis was conducted to investigate the combined predictive effect of AI models on lung cancer.

METHODS

This study was performed according to PRISMA guidelines. PubMed, ISI Web of Science, and Embase databases were searched for relevant literature. Outcomes, including overall survival (OS), disease-free survival (DFS), progression-free survival (PFS), and local control (LC), were predicted using AI models in patients with lung cancer after radiotherapy, and were used to calculate the pooled effect. Quality, heterogeneity, and publication bias of the included studies were also evaluated.

RESULTS

Eighteen articles with 4719 patients were eligible for this meta-analysis. The combined hazard ratios (HRs) of the included studies for OS, LC, PFS, and DFS of lung cancer patients were 2.55 (95 % confidence interval (CI) = 1.73-3.76), 2.45 (95 % CI = 0.78-7.64), 3.84 (95 % CI = 2.20-6.68), and 2.66 (95 % CI = 0.96-7.34), respectively. The combined area under the receiver operating characteristics curve (AUC) of the included articles on OS and LC in patients with lung cancer was 0.75 (95 % CI = 0.67-0.84), and 0.80 (95%CI = 0.0.68-0.95), respectively.

CONCLUSION

The clinical feasibility of predicting outcomes using AI models after radiotherapy in patients with lung cancer was demonstrated. Large-scale, prospective, multicenter studies should be conducted to more accurately predict the outcomes in patients with lung cancer.

Stereotactic body radiation therapy in unresectable stage III non-small cell lung cancer: A systematic review

In unresectable stage III non-small cell lung cancer (NSCLC), the standard of care for most fit patients is concurrent chemotherapy with normofractionated radiotherapy (NFRT), followed by durvalumab consolidation. Nevertheless, almost half of patients will present locoregional or metastatic intrathoracic relapse. Improving locoregional control thus remains an important objective. For this purpose, stereotactic body radiotherapy (SBRT) may be a relevant treatment modality. We performed a systematic review of the literature that evaluate the efficacy and safety of SBRT in this situation, either instead of or in addition to NFRT. Among 1788 unique reports, 18 met the inclusion criteria. They included 447 patients and were mainly prospective (n = 10, including 5 phase 2 trials). In none, maintenance durvalumab was administered. Most reported SBRT boost after NFRT (n = 8), or definitive tumor and nodal SBRT (n = 7). Median OS varied from 10 to 52 months, due to the heterogeneity of the included populations and according to treatment regimen. The rate of severe side effects was low, with <5 % grade 5 toxicity, and mainly observed when mediastinal SBRT was performed without dose constraints to the proximal bronchovascular tree. It was suggested that a biologically effective dose higher than 112.3 Gy may increase locoregional control. SBRT for selected stage III NSCLC bears potential to improve loco-regional tumor control, but at present, this should only be done in prospective clinical trials.

Virtual clinical trial based on outcome modeling with iteratively redistributed extrapolation data

Virtual clinical trials (VCTs) can potentially simulate clinical trials on a computer, but their application with a limited number of past clinical cases is challenging due to the biased estimation of the statistical population. In this study, we developed ExMixup, a novel training technique based on machine learning, using iteratively redistributed extrapolated data. Information obtained from 100 patients with prostate cancer and 385 patients with oropharyngeal cancer was used to predict the recurrence after radiotherapy. Model performance was evaluated by developing outcome prediction models based on three types of training methods: training with original data (baseline), interpolation data (Mixup), and interpolation + extrapolation data (ExMixup). Two types of VCTs were conducted to predict the treatment response of patients with distinct characteristics compared to the training data obtained from patient cohorts categorized under risk classification or cancer stage. The prediction models developed with ExMixup yielded concordance indices (95% confidence intervals) of 0.751 (0.719-0.818) and 0.752 (0.734-0.785) for VCTs on the prostate and oropharyngeal cancer datasets, respectively, which significantly outperformed the baseline and Mixup models (P < 0.01). The proposed approach could enhance the ability of VCTs to predict treatment results in patients excluded from past clinical trials.

Neural network based ensemble model to predict radiation induced lymphopenia after concurrent chemo-radiotherapy for non-small cell lung cancer from two institutions

The use of adjuvant Immune Checkpoint Inhibitors (ICI) after concurrent chemo-radiation therapy (CCRT) has become the standard of care for locally advanced non-small cell lung cancer (LA-NSCLC). However, prolonged radiotherapy regimens are known to cause radiation-induced lymphopenia (RIL), a long-neglected toxicity that has been shown to correlate with response to ICIs and survival of patients treated with adjuvant ICI after CCRT. In this study, we aim to develop a novel neural network (NN) approach that integrates patient characteristics, treatment related variables, and differential dose volume histograms (dDVH) of lung and heart to predict the incidence of RIL at the end of treatment. Multi-institutional data of 139 LA-NSCLC patients from two hospitals were collected for training and validation of our suggested model. Ensemble learning was combined with a bootstrap strategy to stabilize the model, which was evaluated internally using repeated cross validation. The performance of our proposed model was compared to conventional models using the same input features, such as Logistic Regression (LR) and Random Forests (RF), using the Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) curves. Our suggested model (AUC=0.77) outperformed the comparison models (AUC=0.72, 0.74) in terms of absolute performance, indicating that the convolutional structure of the network successfully abstracts additional information from the differential DVHs, which we studied using Gradient-weighted Class Activation Map. This study shows that clinical factors combined with dDVHs can be used to predict the risk of RIL for an individual patient and shows a path toward preventing lymphopenia using patient-specific modifications of the radiotherapy plan.

Predictive Model of Liver Toxicity to Aid the Personalized Selection of Proton Versus Photon Therapy in Hepatocellular Carcinoma

PURPOSE

Our objective was to develop an externally validated model for predicting liver toxicity after radiation therapy in patients with hepatocellular carcinoma (HCC) that can integrate both photon and proton dose distributions with patient-specific characteristics.

METHODS AND MATERIALS

Training data consisted of all patients with HCC treated between 2008 and 2019 at our institution (n = 117, 60%/40% photon/proton). We developed a shallow convolutional neural network (CNN) to predict posttreatment liver dysfunction from the differential dose-volume histogram (DVH) and baseline liver metrics. To reduce bias and improve robustness, we used ensemble learning (CNNE). After a preregistered study analysis plan, we evaluated stability using internal bootstrap resampling and generalizability using a data set from a different institution (n = 88). Finally, we implemented a class activation map method to characterize the critical DVH subregions and benchmarked the model against logistic regression and XGBoost. The models were evaluated using the area under the receiver operating characteristic curve and area under the precision-recall curve.

RESULTS

The CNNE model showed similar internal performance and robustness compared with the benchmarks. CNNE exceeded the benchmark models in external validation, with an area under the receiver operating characteristic curve of 0.78 versus 0.55 to 0.70, and an area under the precision-recall curve of 0.6 versus 0.43 to 0.52. The model showed improved predictive power in the photon group, excellent specificity in both modalities, and high sensitivity in the photon high-risk group. Models built solely on DVHs confirm outperformance of the CNNE and indicate that the proposed structure efficiently abstracts features from both proton and photon dose distributions. The activation map method demonstrates the importance of the low-dose bath and its interaction with low liver function at baseline.

CONCLUSIONS

We developed and externally validated a patient-specific prediction model for hepatic toxicity based on the entire DVH and clinical factors that can integrate both photon and proton therapy cohorts. This model complements the new American Society for Radiation Oncology clinical practice guidelines and could support value-driven integration of proton therapy into the management of HCC.

Toxicity Prediction in Pelvic Radiotherapy Using Multiple Instance Learning and Cascaded Attention Layers

Modern radiotherapy delivers treatment plans optimised on an individual patient level, using CT-based 3D models of patient anatomy. This optimisation is fundamentally based on simple assumptions about the relationship between radiation dose delivered to the cancer (increased dose will increase cancer control) and normal tissue (increased dose will increase rate of side effects). The details of these relationships are still not well understood, especially for radiation-induced toxicity. We propose a convolutional neural network based on multiple instance learning to analyse toxicity relationships for patients receiving pelvic radiotherapy. A dataset comprising of 315 patients were included in this study; with 3D dose distributions, pre-treatment CT scans with annotated abdominal structures, and patient-reported toxicity scores provided for each participant. In addition, we propose a novel mechanism for segregating the attentions over space and dose/imaging features independently for a better understanding of the anatomical distribution of toxicity. Quantitative and qualitative experiments were performed to evaluate the network performance. The proposed network could predict toxicity with 80% accuracy. Attention analysis over space demonstrated that there was a significant association between radiation dose to the anterior and right iliac of the abdomen and patient-reported toxicity. Experimental results showed that the proposed network had outstanding performance for toxicity prediction, localisation and explanation with the ability of generalisation for an unseen dataset.

A meta-learning approach to improving radiation response prediction in cancers

PURPOSE

Predicting the efficacy of radiotherapy in individual patients has drawn widespread attention, but the limited sample size remains a bottleneck for utilizing high-dimensional multi-omics data to guide personalized radiotherapy. We hypothesize the recently developed meta-learning framework could address this limitation.

METHODS AND MATERIALS

By combining gene expression, DNA methylation, and clinical data of 806 patients who had received radiotherapy from The Cancer Genome Atlas (TCGA), we applied the Model-Agnostic Meta-Learning (MAML) framework to tasks consisting of pan-cancer data, to obtain the best initial parameters of a neural network for a specific cancer with smaller number of samples. The performance of meta-learning framework was compared with four traditional machine learning methods based on two training schemes, and tested on Cancer Cell Line Encyclopedia (CCLE) and Chinese Glioma Genome Atlas (CGGA) datasets. Moreover, biological significance of the models was investigated by survival analysis and feature interpretation.

RESULTS

The mean AUC (Area under the ROC Curve) [95% confidence interval] of our models across nine cancer types was 0.702 [0.691-0.713], which improved by 0.166 on average over other the four machine learning methods on two training schemes. Our models performed significantly better (p < 0.05) in seven cancer types and performed comparable to the other predictors in the rest of two cancer types. The more pan-cancer samples were used to transfer meta-knowledge, the greater the performance improved (p < 0.05). The predicted response scores that our models generated were negatively correlated with cell radiosensitivity index in four cancer types (p < 0.05), while not statistically significant in the other three cancer types. Moreover, the predicted response scores were shown to be prognostic factors in seven cancer types and eight potential radiosensitivity-related genes were identified.

CONCLUSIONS

For the first time, we established the meta-learning approach to improving individual radiation response prediction by transferring common knowledge from pan-cancer data with MAML framework. The results demonstrated the superiority, generalizability, and biological significance of our approach.

Current status and future developments in predicting outcomes in radiation oncology

Advancements in data-driven technologies and the inclusion of information-rich multiomics features have significantly improved the performance of outcomes modeling in radiation oncology. For this current trend to be sustainable, challenges related to robust data modeling such as small sample size, low size to feature ratio, noisy data, as well as issues related to algorithmic modeling such as complexity, uncertainty, and interpretability, need to be mitigated if not resolved. Emerging computational technologies and new paradigms such as federated learning, human-in-the-loop, quantum computing, and novel interpretability methods show great potential in overcoming these challenges and bridging the gap towards precision outcome modeling in radiotherapy. Examples of these promising technologies will be presented and their potential role in improving outcome modeling will be discussed.

Radiomic and Volumetric Measurements as Clinical Trial Endpoints—A Comprehensive Review

Simple Summary

The extraction of quantitative data from standard-of-care imaging modalities offers opportunities to improve the relevance and salience of imaging biomarkers used in drug development. This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers based on radiomic and volumetric assessment in the single-site solid tumor sites: breast cancer, rectal cancer, lung cancer and glioblastoma. Developing approaches to harmonize three essential areas: segmentation, validation and data sharing may expedite regulatory approval and adoption of novel cancer imaging biomarkers.

Abstract

Clinical trials for oncology drug development have long relied on surrogate outcome biomarkers that assess changes in tumor burden to accelerate drug registration (i.e., Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) criteria). Drug-induced reduction in tumor size represents an imperfect surrogate marker for drug activity and yet a radiologically determined objective response rate is a widely used endpoint for Phase 2 trials. With the addition of therapies targeting complex biological systems such as immune system and DNA damage repair pathways, incorporation of integrative response and outcome biomarkers may add more predictive value. We performed a review of the relevant literature in four representative tumor types (breast cancer, rectal cancer, lung cancer and glioblastoma) to assess the preparedness of volumetric and radiomics metrics as clinical trial endpoints. We identified three key areas—segmentation, validation and data sharing strategies—where concerted efforts are required to enable progress of volumetric- and radiomics-based clinical trial endpoints for wider clinical implementation.

Artificial intelligence in lung cancer: Application and future thinking

The availability of medical big data and the rapid development of computer software and hardware have greatly promoted the advancement of intelligent medical healthcare. Artificial intelligence (AI) has been successfully applied in many fields of medicine, especially in lung cancer. The performance of AI in some specific tasks has surpassed that of humans. Several AI software has been deeply used in clinical practice to help decision-making, which is producing a profound influence on clinicians. At present, the application of AI in the field of lung cancer mainly includes detection, segmentation, classification, prognosis prediction, efficacy evaluation, and so on. AI faces certain challenges and opportunities in the era of big data in terms of data acquisition, annotation and interpretability. Researchers have conducted deep and extensive studies using AI in the field of lung cancer, and AI is expected to become a powerful assistant in the prevention and treatment of lung cancer. AI is bringing an unprecedented revolution to radiologists, but the role of radiologists is crucial in the development of AI.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 1, Supradiaphragmatic Cancers

Radiomics is an upcoming field in nuclear oncology, both promising and technically challenging. To summarize the already undertaken work on supradiaphragmatic neoplasia and assess its quality, we performed a literature search in the PubMed database up to 18 February 2022. Inclusion criteria were: studies based on human data; at least one specified tumor type; supradiaphragmatic malignancy; performing radiomics on PET imaging. Exclusion criteria were: studies only based on phantom or animal data; technical articles without a clinically oriented question; fewer than 30 patients in the training cohort. A review database containing PMID, year of publication, cancer type, and quality criteria (number of patients, retrospective or prospective nature, independent validation cohort) was constructed. A total of 220 studies met the inclusion criteria. Among them, 119 (54.1%) studies included more than 100 patients, 21 studies (9.5%) were based on prospectively acquired data, and 91 (41.4%) used an independent validation set. Most studies focused on prognostic and treatment response objectives. Because the textural parameters and methods employed are very different from one article to another, it is complicated to aggregate and compare articles. New contributions and radiomics guidelines tend to help improving quality of the reported studies over the years.

Deep Learning for Radiotherapy Outcome Prediction Using Dose Data - A Review

Artificial intelligence, and in particular deep learning using convolutional neural networks, has been used extensively for image classification and segmentation, including on medical images for diagnosis and prognosis prediction. Use in radiotherapy prognostic modelling is still limited, however, especially as applied to toxicity and tumour response prediction from radiation dose distributions. We review and summarise studies that applied deep learning to radiotherapy dose data, in particular studies that utilised full three-dimensional dose distributions. Ten papers have reported on deep learning models for outcome prediction utilising spatial dose information, whereas four studies used reduced dimensionality (dose volume histogram) information for prediction. Many of these studies suffer from the same issues that plagued early normal tissue complication probability modelling, including small, single-institutional patient cohorts, lack of external validation, poor data and model reporting, use of late toxicity data without taking time-to-event into account, and nearly exclusive focus on clinician-reported complications. They demonstrate, however, how radiation dose, imaging and clinical data may be technically integrated in convolutional neural networks-based models; and some studies explore how deep learning may help better understand spatial variation in radiosensitivity. In general, there are a number of issues specific to the intersection of radiotherapy outcome modelling and deep learning, for example translation of model developments into treatment plan optimisation, which will require further combined effort from the radiation oncology and artificial intelligence communities.

A roadmap for multi-omics data integration using deep learning

High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These data have revolutionized biomedical research by providing a more comprehensive understanding of the biological systems and molecular mechanisms of disease development. Recently, deep learning (DL) algorithms have become one of the most promising methods in multi-omics data analysis, due to their predictive performance and capability of capturing nonlinear and hierarchical features. While integrating and translating multi-omics data into useful functional insights remain the biggest bottleneck, there is a clear trend towards incorporating multi-omics analysis in biomedical research to help explain the complex relationships between molecular layers. Multi-omics data have a role to improve prevention, early detection and prediction; monitor progression; interpret patterns and endotyping; and design personalized treatments. In this review, we outline a roadmap of multi-omics integration using DL and offer a practical perspective into the advantages, challenges and barriers to the implementation of DL in multi-omics data.

OUP accepted manuscript

The recent, rapid advances in immuno-oncology have revolutionized cancer treatment and spurred further research into tumor biology. Yet, cancer patients respond variably to immunotherapy despite mounting evidence to support its efficacy. Current methods for predicting immunotherapy response are unreliable, as these tests cannot fully account for tumor heterogeneity and microenvironment. An improved method for predicting response to immunotherapy is needed. Recent studies have proposed radiomics—the process of converting medical images into quantitative data (features) that can be processed using machine learning algorithms to identify complex patterns and trends—for predicting response to immunotherapy. Because patients undergo numerous imaging procedures throughout the course of the disease, there exists a wealth of radiological imaging data available for training radiomics models. And because radiomic features reflect cancer biology, such as tumor heterogeneity and microenvironment, these models have enormous potential to predict immunotherapy response more accurately than current methods. Models trained on preexisting biomarkers and/or clinical outcomes have demonstrated potential to improve patient stratification and treatment outcomes. In this review, we discuss current applications of radiomics in oncology, followed by a discussion on recent studies that use radiomics to predict immunotherapy response and toxicity.

Regression Analysis of Factors Based on Cluster Analysis of Acute Radiation Pneumonia due to Radiation Therapy for Lung Cancer

We conducted in this paper a regression analysis of factors associated with acute radiation pneumonia due to radiation therapy for lung cancer utilizing cluster analysis to explore the predictive effects of clinical and dosimetry factors on grade ≥2 radiation pneumonia due to radiation therapy for lung cancer and to further refine the effect of the ratio of the volume of the primary foci to the volume of the lung lobes in which they are located on radiation pneumonia, to refine the factors that are clinically effective in predicting the occurrence of grade ≥2 radiation pneumonia. This will provide a basis for better guiding lung cancer radiation therapy, reducing the occurrence of grade ≥2 radiation pneumonia, and improving the safety of radiotherapy. Based on the characteristics of the selected surveillance data, the experimental simulation of the factors of acute radiation pneumonia due to lung cancer radiation therapy was performed based on three signal detection methods using fuzzy mean clustering algorithm with drug names as the target and adverse drug reactions as the characteristics, and the drugs were classified into three categories. The method was then designed and used to determine the classification correctness evaluation function as the best signal detection method. The factor classification and risk feature identification of acute radiation pneumonia due to radiation therapy for lung cancer based on ADR were achieved by using cluster analysis and feature extraction techniques, which provided a referenceable method for establishing the factor classification mechanism of acute radiation pneumonia due to radiation therapy for lung cancer and a new idea for reuse of ADR surveillance report data resources.

Lessons learned in transitioning to AI in the medical imaging of COVID-19

The coronavirus disease 2019 (COVID-19) pandemic has wreaked havoc across the world. It also created a need for the urgent development of efficacious predictive diagnostics, specifically, artificial intelligence (AI) methods applied to medical imaging. This has led to the convergence of experts from multiple disciplines to solve this global pandemic including clinicians, medical physicists, imaging scientists, computer scientists, and informatics experts to bring to bear the best of these fields for solving the challenges of the COVID-19 pandemic. However, such a convergence over a very brief period of time has had unintended consequences and created its own challenges. As part of Medical Imaging Data and Resource Center initiative, we discuss the lessons learned from career transitions across the three involved disciplines (radiology, medical imaging physics, and computer science) and draw recommendations based on these experiences by analyzing the challenges associated with each of the three associated transition types: (1) AI of non-imaging data to AI of medical imaging data, (2) medical imaging clinician to AI of medical imaging, and (3) AI of medical imaging to AI of COVID-19 imaging. The lessons learned from these career transitions and the diffusion of knowledge among them could be accomplished more effectively by recognizing their associated intricacies. These lessons learned in the transitioning to AI in the medical imaging of COVID-19 can inform and enhance future AI applications, making the whole of the transitions more than the sum of each discipline, for confronting an emergency like the COVID-19 pandemic or solving emerging problems in biomedicine.