Multi-view radiomics and dosiomics analysis with machine learning for predicting acute-phase weight loss in lung cancer patients treated with radiotherapy

Machine Learning Approaches to Predict Symptoms in People With Cancer: Systematic Review

BACKGROUND

People with cancer frequently experience severe and distressing symptoms associated with cancer and its treatments. Predicting symptoms in patients with cancer continues to be a significant challenge for both clinicians and researchers. The rapid evolution of machine learning (ML) highlights the need for a current systematic review to improve cancer symptom prediction.

OBJECTIVE

This systematic review aims to synthesize the literature that has used ML algorithms to predict the development of cancer symptoms and to identify the predictors of these symptoms. This is essential for integrating new developments and identifying gaps in existing literature.

METHODS

We conducted this systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist. We conducted a systematic search of CINAHL, Embase, and PubMed for English records published from 1984 to August 11, 2023, using the following search terms: cancer, neoplasm, specific symptoms, neural networks, machine learning, specific algorithm names, and deep learning. All records that met the eligibility criteria were individually reviewed by 2 coauthors, and key findings were extracted and synthesized. We focused on studies using ML algorithms to predict cancer symptoms, excluding nonhuman research, technical reports, reviews, book chapters, conference proceedings, and inaccessible full texts.

RESULTS

A total of 42 studies were included, the majority of which were published after 2017. Most studies were conducted in North America (18/42, 43%) and Asia (16/42, 38%). The sample sizes in most studies (27/42, 64%) typically ranged from 100 to 1000 participants. The most prevalent category of algorithms was supervised ML, accounting for 39 (93%) of the 42 studies. Each of the methods-deep learning, ensemble classifiers, and unsupervised ML-constituted 3 (3%) of the 42 studies. The ML algorithms with the best performance were logistic regression (9/42, 17%), random forest (7/42, 13%), artificial neural networks (5/42, 9%), and decision trees (5/42, 9%). The most commonly included primary cancer sites were the head and neck (9/42, 22%) and breast (8/42, 19%), with 17 (41%) of the 42 studies not specifying the site. The most frequently studied symptoms were xerostomia (9/42, 14%), depression (8/42, 13%), pain (8/42, 13%), and fatigue (6/42, 10%). The significant predictors were age, gender, treatment type, treatment number, cancer site, cancer stage, chemotherapy, radiotherapy, chronic diseases, comorbidities, physical factors, and psychological factors.

CONCLUSIONS

This review outlines the algorithms used for predicting symptoms in individuals with cancer. Given the diversity of symptoms people with cancer experience, analytic approaches that can handle complex and nonlinear relationships are critical. This knowledge can pave the way for crafting algorithms tailored to a specific symptom. In addition, to improve prediction precision, future research should compare cutting-edge ML strategies such as deep learning and ensemble methods with traditional statistical models.

Dosiomics for intensity-modulated radiotherapy in patients with prostate cancer: survival analysis stratified by baseline prostate-specific antigen and Gleason grade group in a 2-institutional retrospective study

OBJECTIVE

This study evaluated the prognostic impact of the quality of dose distribution using dosiomics in patients with prostate cancer, stratified by pretreatment prostate-specific antigen (PSA) levels and Gleason grade (GG) group.

METHODS

A total of 721 patients (Japanese Foundation for Cancer Research [JFCR] cohort: N = 489 and Tokyo Radiation Oncology Clinic [TROC] cohort: N = 232) with localized prostate cancer treated by intensity-modulated radiation therapy were enrolled. Two predictive dosiomic features for biochemical recurrence (BCR) were selected and patients were divided into certain groups stratified by pretreatment PSA levels and GG. Freedom from biochemical failure (FFBF) was estimated using the Kaplan-Meier method based on each dosiomic feature and univariate discrimination was evaluated using the log-rank test. As an exploratory analysis, a dosiomics hazard (DH) score was developed and its prognostic power for BCR was examined.

RESULTS

The dosiomic feature extracted from planning target volume (PTV) significantly distinguished the high- and low-risk groups in patients with PSA levels >10 ng/mL (7-year FFBF: 86.7% vs 76.1%, P < .01), GG 4 (92.2% vs 76.9%, P < .01), and GG 5 (83.1% vs 77.8%, P = .04). The DH score showed significant association with BCR (hazard score: 2.04; 95% confidence interval: 1.38-3.01; P < .001).

CONCLUSION

The quality of planned dose distribution on PTV may affect the prognosis of patients with poor prognostic factors, such as PSA levels >10 ng/mL and higher GGs.

ADVANCES IN KNOWLEDGE

The effects of planned dose distribution on prognosis differ depending on the patient's clinical background.

Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study

BACKGROUND

This study aimed to investigate the value of clinical, radiomic features extracted from gross tumor volumes (GTVs) delineated on CT images, dose distributions (Dosiomics), and fusion of CT and dose distributions to predict outcomes in head and neck cancer (HNC) patients.

METHODS

A cohort of 240 HNC patients from five different centers was obtained from The Cancer Imaging Archive. Seven strategies, including four non-fusion (Clinical, CT, Dose, DualCT-Dose), and three fusion algorithms (latent low-rank representation referred (LLRR),Wavelet, weighted least square (WLS)) were applied. The fusion algorithms were used to fuse the pre-treatment CT images and 3-dimensional dose maps. Overall, 215 radiomics and Dosiomics features were extracted from the GTVs, alongside with seven clinical features incorporated. Five feature selection (FS) methods in combination with six machine learning (ML) models were implemented. The performance of the models was quantified using the concordance index (CI) in one-center-leave-out 5-fold cross-validation for overall survival (OS) prediction considering the time-to-event.

RESULTS

The mean CI and Kaplan-Meier curves were used for further comparisons. The CoxBoost ML model using the Minimal Depth (MD) FS method and the glmnet model using the Variable hunting (VH) FS method showed the best performance with CI = 0.73 ± 0.15 for features extracted from LLRR fused images. In addition, both glmnet-Cindex and Coxph-Cindex classifiers achieved a CI of 0.72 ± 0.14 by employing the dose images (+ incorporated clinical features) only.

CONCLUSION

Our results demonstrated that clinical features, Dosiomics and fusion of dose and CT images by specific ML-FS models could predict the overall survival of HNC patients with acceptable accuracy. Besides, the performance of ML methods among the three different strategies was almost comparable.

Radiomics and dosiomics for predicting radiation-induced hypothyroidism and guiding intensity-modulated radiotherapy

To guide individualized intensity-modulated radiotherapy (IMRT), we developed and prospectively validated a multiview radiomics risk model for predicting radiation-induced hypothyroidism in patients with nasopharyngeal carcinoma. And simulated radiotherapy plans with same dose-volume-histogram (DVH) but different dose distributions were redesigned to explore the clinical application of the multiview radiomics risk model. The radiomics and dosiomics were built based on selected radiomics and dosiomics features from planning computed tomography and dose distribution, respectively. The multiview radiomics risk model that integrated radiomics, dosiomics, DVH parameters, and clinical factors had better performance than traditional normal tissue complication probability models. And multiview radiomics risk model could identify differences of patient hypothyroidism-free survival that cannot be stratified by traditional models. Besides, two redesigned simulated plans further verified the clinical application and advantage of the multiview radiomics risk model. The multiview radiomics risk model was a promising method to predict radiation-induced hypothyroidism and guide individualized IMRT.

Prediction of radiation pneumonia after radiotherapy for esophageal cancer using a unified fractional dosiomics combined model

OBJECTIVE

This study aimed to construct an optimal model to predict radiation pneumonia (RP) after radiotherapy for esophageal cancer using unified fractional dosiomics and to investigate the improvements in the prediction efficiency of each model for RP.

METHODS

The clinical data, DVH, pre-treatment CT, and dose distribution of 182 patients were retrospectively analyzed.The independent risk factors were screened using univariate and multivariate logistic regression. The mutual information (MI),least absolute shrinkage and selection operator (LASSO), and recursive feature elimination (RFE) methods were used to screen the omics features. The AUC values of ROC, calibration curves, and clinical decision curves were calculated to evaluate the efficacy and trends of each model.

RESULTS

The AUC of dosiomics model were 0.783 and 0.760 in the training and test cohorts, higher than 0.585 and 0.579 in the training and test cohorts of the DVH model. The AUC value of the R + D combination was the highest, reaching 0.833. The combined R + D model had a better calibration degree than the other models (mean absolute error = 0.018) and better net benefit in clinical decision-making.

CONCLUSIONS

The radiomics combined dosiomics model was the best combined model to predict RP after radiotherapy for esophageal cancer. The dosiomics model could cover the efficiency of the DVH model and significantly improve the efficiency of the combined model.In the future, we will include other centers for further verification.

ADVANCES IN KNOWLEDGE

For the first time, this study used CT images combined dose distribution to predict the occurrence of radiation pneumonitis after radiotherapy for esophageal cancer.

Immunotherapy Efficacy Prediction for Non-Small Cell Lung Cancer Using Multi-View Adaptive Weighted Graph Convolutional Networks

Immunotherapy is an effective way to treat non-small cell lung cancer (NSCLC). The efficacy of immunotherapy differs from person to person and may cause side effects, making it important to predict the efficacy of immunotherapy before surgery. Radiomics based on machine learning has been successfully used to predict the efficacy of NSCLC immunotherapy. However, most studies only considered the radiomic features of the individual patient, ignoring the inter-patient correlations. Besides, they usually concatenated different features as the input of a single-view model, failing to consider the complex correlation among features of multiple types. To this end, we propose a multi-view adaptive weighted graph convolutional network (MVAW-GCN) for the prediction of NSCLC immunotherapy efficacy. Specifically, we group the radiomic features into several views according to the type of the fitered images they extracted from. We construct a graph in each view based on the radiomic features and phenotypic information. An attention mechanism is introduced to automatically assign weights to each view. Considering the view-shared and view-specific knowledge of radiomic features, we propose separable graph convolution that decomposes the output of the last convolution layer into two components, i.e., the view-shared and view-specific outputs. We maximize the consistency and enhance the diversity among different views in the learning procedure. The proposed MVAW-GCN is evaluated on 107 NSCLC patients, including 52 patients with valid efficacy and 55 patients with invalid efficacy. Our method achieved an accuracy of 77.27% and an area under the curve (AUC) of 0.7780, indicating its effectiveness in NSCLC immunotherapy efficacy prediction.

Enhanced prediction of postoperative radiotherapy-induced esophagitis in non-small cell lung cancer: Dosiomic model development in a real-world cohort and validation in the PORT-C randomized controlled trial

BACKGROUND

Radiotherapy-induced esophagitis (RE) diminishes the quality of life and interrupts treatment in patients with non-small cell lung cancer (NSCLC) undergoing postoperative radiotherapy. Dosimetric models showed limited capability in predicting RE. We aimed to develop dosiomic models to predict RE.

METHODS

Models were trained with a real-world cohort and validated with PORT-C randomized controlled trial cohort. Patients with NSCLC undergoing resection followed by postoperative radiotherapy between 2004 and 2015 were enrolled. The endpoint was grade ≥2 RE. Esophageal three-dimensional dose distribution features were extracted using handcrafted and convolutional neural network (CNN) methods, screened using an entropy-based method, and selected using minimum redundancy and maximum relevance. Prediction models were built using logistic regression. The areas under the receiver operating characteristic curve (AUC) and precision-recall curve were used to evaluate prediction model performance. A dosimetric model was built for comparison.

RESULTS

A total of 190 and 103 patients were enrolled in the training and validation sets, respectively. Using handcrafted and CNN methods, 107 and 4096 features were derived, respectively. Three handcrafted, four CNN-extracted and three dosimetric features were selected. AUCs of training and validation sets were 0.737 and 0.655 for the dosimetric features, 0.730 and 0.724 for handcrafted features, and 0.812 and 0.785 for CNN-extracted features, respectively. Precision-recall curves revealed that CNN-extracted features outperformed dosimetric and handcrafted features.

CONCLUSIONS

Prediction models may identify patients at high risk of developing RE. Dosiomic models outperformed the dosimetric-feature model in predicting RE. CNN-extracted features were more predictive but less interpretable than handcrafted features.

Analysis of the risk factors of radiation pneumonitis and the predictive ability of dosiomics in non-small-cell lung cancer

Purpose: This prospective study investigated the incidence of radiation pneumonitis (RP) after immunotherapy followed by radiotherapy in non-small-cell lung cancer, analyzed the risk factors for RP, and explored the predictive performance of dosimetry and dosiomics. Methods & materials: Risk factors for grade ≥2 RP were calculated by using a logistic regression model. Predictive performance was compared on the basis of area under the curve values. Results: Grade ≥2 RP occurred in 16 cases (26.7%). The AUC values of V5 Gy, gray-level dependence matrix-small dependence high gray-level emphasis (GLDM-SDHGLE) and combined features were 0.685, 0.724 and 0.734, respectively. Conclusion: Smoking history, bilateral lung V5 Gy and GLDM-SDHGLE were independent risk factors for RP. Dosiomics can effectively predict RP.

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.

Multi-view radiomics and deep learning modeling for prostate cancer detection based on multi-parametric MRI

Introduction

This study aims to develop an imaging model based on multi-parametric MR images for distinguishing between prostate cancer (PCa) and prostate hyperplasia.

Methods

A total of 236 subjects were enrolled and divided into training and test sets for model construction. Firstly, a multi-view radiomics modeling strategy was designed in which different combinations of radiomics feature categories (original, LoG, and wavelet) were compared to obtain the optimal input feature sets. Minimum-redundancy maximum-relevance (mRMR) selection and least absolute shrinkage selection operator (LASSO) were used for feature reduction, and the next logistic regression method was used for model construction. Then, a Swin Transformer architecture was designed and trained using transfer learning techniques to construct the deep learning models (DL). Finally, the constructed multi-view radiomics and DL models were combined and compared for model selection and nomogram construction. The prediction accuracy, consistency, and clinical benefit were comprehensively evaluated in the model comparison.

Results

The optimal input feature set was found when LoG and wavelet features were combined, while 22 and 17 radiomic features in this set were selected to construct the ADC and T2 multi-view radiomic models, respectively. ADC and T2 DL models were built by transferring learning from a large number of natural images to a relatively small sample of prostate images. All individual and combined models showed good predictive accuracy, consistency, and clinical benefit. Compared with using only an ADC-based model, adding a T2-based model to the combined model would reduce the model's predictive performance. The ADCCombinedScore model showed the best predictive performance among all and was transformed into a nomogram for better use in clinics.

Discussion

The constructed models in our study can be used as a predictor in differentiating PCa and BPH, thus helping clinicians make better clinical treatment decisions and reducing unnecessary prostate biopsies.

Prediction of plan adaptation in head and neck cancer proton therapy using clinical, radiographic, and dosimetric features

PURPOSE

Because proton head and neck (HN) treatments are sensitive to anatomical changes, plan adaptation (re-plan) during the treatment course is needed for a significant portion of patients. We aim to predict re-plan at plan review stage for HN proton therapy with a neural network (NN) model trained with patients' dosimetric and clinical features. The model can serve as a valuable tool for planners to assess the probability of needing to revise the current plan.

METHODS AND MATERIALS

Mean beam dose heterogeneity index (BHI), defined as the ratio of the maximum beam dose to the prescription dose, plan robustness features (clinical target volume (CTV), V100 changes, and V100 > 95% passing rates in 21 robust evaluation scenarios), as well as clinical features (e.g., age, tumor site, and surgery/chemotherapy status) were gathered from 171 patients treated at our proton center in 2020, with a median age of 64 and stages from I-IVc across 13 HN sites. Statistical analyses of dosimetric parameters and clinical features were conducted between re-plan and no-replan groups. A NN was trained and tested using these features. Receiver operating characteristic (ROC) analysis was conducted to evaluate the performance of the prediction model. A sensitivity analysis was done to determine feature importance.

RESULTS

Mean BHI in the re-plan group was significantly higher than the no-replan group (p < .01). Tumor site (p < .01), chemotherapy status (p < .01), and surgery status (p < .01) were significantly correlated to re-plan. The model had sensitivities/specificities of 75.0%/77.4%, respectively, and an area under the ROC curve of .855.

CONCLUSION

There are several dosimetric and clinical features that correlate to re-plans, and NNs trained with these features can be used to predict HN re-plans, which can be used to reduce re-plan rate by improving plan quality.

Multi-omics to predict acute radiation esophagitis in patients with lung cancer treated with intensity-modulated radiation therapy

PURPOSE

The study aimed to predict acute radiation esophagitis (ARE) with grade  ≥ 2 for patients with locally advanced lung cancer (LALC) treated with intensity-modulated radiation therapy (IMRT) using multi-omics features, including radiomics and dosiomics.

METHODS

161 patients with stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT with a prescribed dose from 45 to 70 Gy from 2015 to 2019 were enrolled retrospectively. All the toxicity gradings were given following the Common Terminology Criteria for Adverse Events V4.0. Multi-omics features, including radiomics, dosiomics (including dose-volume histogram dosimetric parameters), were extracted based on the planning CT image and three-dimensional dose distribution. All data were randomly divided into training cohorts (N = 107) and testing cohorts (N = 54). In the training cohorts, features with reliably high outcome relevance and low redundancy were selected under random patient subsampling. Four classification models (using clinical factors (CF) only, using radiomics features (RFs) only, dosiomics features (DFs) only, and the hybrid features (HFs) containing clinical factors, radiomics and dosiomics) were constructed employing the Ridge classifier using two-thirds of randomly selected patients as the training cohort. The remaining patient was treated as the testing cohort. A series of models were built with 30 times training-testing splits. Their performances were assessed using the area under the ROC curve (AUC) and accuracy.

RESULTS

Among all patients, 51 developed ARE grade  ≥ 2, with an incidence of 31.7%. Next, 8990 radiomics and 213 dosiomics features were extracted, and 3, 6, 12, and 13 features remained after feature selection in the CF, DF, RF and DF models, respectively. The RF and HF models achieved similar classification performance, with the training and testing AUCs of 0.796 ± 0.023 (95% confidence interval (CI [0.79, 0.80])/0.744 ± 0.044 (95% CI [0.73, 0.76]) and 0.801 ± 0.022 (95% CI [0.79, 0.81]) (p = 0.74), respectively. The model performances using CF and DF features were poorer, with training and testing AUCs of 0.573 ± 0.026 (95% CI [0.56, 0.58])/ 0.509 ± 0.072 (95% CI [0.48, 0.53]) and 0.679 ± 0.027 (95% CI [0.67, 0.69])/0.604 ± 0.041 (95% CI [0.53, 0.63]) compared with the above two models (p < 0.001), respectively.

CONCLUSIONS

In LALC patients treated with CRT IMRT, the ARE grade  ≥ 2 can be predicted using the pretreatment radiotherapy image features. To predict ARE, the multi-omics features had similar predictability with radiomics features; however, the dosiomics features and clinical factors had a limited classification performance.

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

OBJECTIVES

By comparing the prognostic performance of ¹⁸F-FDG PET/CT-based radiomics combining dose features [Includes Dosiomics feature and the dose volume histogram (DVH) features] with that of conventional radiomics in head and neck cancer (HNC), multidimensional prognostic models were constructed to investigate the overall survival (OS) in HNC.

MATERIALS AND METHODS

A total of 220 cases from four centres based on the Cancer Imaging Archive public dataset were used in this study, 2260 radiomics features and 1116 dosiomics features and 8 DVH features were extracted for each case, and classified into seven different models of PET, CT, Dose, PET+CT, PET+Dose, CT+Dose and PET+CT+Dose. Features were selected by univariate Cox and Spearman correlation coefficients, and the selected features were brought into the least absolute shrinkage and selection operator (LASSO)-Cox model. A nomogram was constructed to visually analyse the prognostic impact of the incorporated dose features. C-index and Kaplan-Meier curves (log-rank analysis) were used to evaluate and compare these models.

RESULTS

The cases from the four centres were divided into three different training and validation sets according to the hospitals. The PET+CT+Dose model had C-indexes of 0.873 (95% CI 0.812-0.934), 0.759 (95% CI 0.663-0.855) and 0.835 (95% CI 0.745-0.925) in the validation set respectively, outperforming the rest models overall. The PET+CT+Dose model did well in classifying patients into high- and low-risk groups under all three different sets of experiments (p < 0.05).

CONCLUSION

Multidimensional model of radiomics features combining dosiomics features and DVH features showed high prognostic performance for predicting OS in patients with HNC.

Integrating Preoperative Computed Tomography and Clinical Factors for Lymph Node Metastasis Prediction in Esophageal Squamous Cell Carcinoma by Feature-Wise Attentional Graph Neural Network

PURPOSE

This study aimed to propose a regional lymph node (LN) metastasis prediction model for patients with esophageal squamous cell carcinoma (ESCC) that can learn and adaptively integrate preoperative computed tomography (CT) image features and nonimaging clinical parameters.

METHODS AND MATERIALS

Contrast-enhanced CT scans taken 2 weeks before surgery and 20 clinical factors, including general, pathologic, hematological, and diagnostic information, were collected from 357 patients with ESCC between October 2013 and November 2018. There were 999 regional LNs (857 negative, 142 positive) with pathologically confirmed status after surgery. All LNs were randomly divided into a training set (n = 738) and a validation set (n = 261) for testing. The feature-wise attentional graph neural network (FAGNN) was composed of (1) deep image feature extraction by the encoder of 3-dimensional UNet and high-level nonimaging factor representation by the clinical parameter encoder; (2) a feature-wise attention module for feature embedding with learnable adaptive weights; and (3) a graph attention layer to integrate the embedded features for final LN level metastasis prediction.

RESULTS

Among the 4 models we constructed, FAGNN using both CT and clinical parameters as input is the model with the best performance, and the area under the curve (AUC) reaches 0.872, which is better than manual CT diagnosis method, multivariable model using CT only (AUC = 0.797), multivariable model with combined CT and clinical parameters (AUC = 0.846), and our FAGNN using CT only (AUC = 0.853).

CONCLUSIONS

Our adaptive integration model improved the metastatic LN prediction performance based on CT and clinical parameters. Our model has the potential to foster effective fusion of multisourced parameters and to support early prognosis and personalized surgery or radiation therapy planning in patients with ESCC.

Prediction of Cobb Angle Using Deep Learning Algorithm with Three-Dimensional Depth Sensor Considering the Influence of Garment in Idiopathic Scoliosis

Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal deformity. Early detection of deformity and timely intervention, such as brace treatment, can help inhibit progressive changes. A three-dimensional (3D) depth-sensor imaging system with a convolutional neural network was previously developed to predict the Cobb angle. The purpose of the present study was to (1) evaluate the performance of the deep learning algorithm (DLA) in predicting the Cobb angle and (2) assess the predictive ability depending on the presence or absence of clothing in a prospective analysis. We included 100 subjects with suspected AIS. The correlation coefficient between the actual and predicted Cobb angles was 0.87, and the mean absolute error and root mean square error were 4.7° and 6.0°, respectively, for Adam's forward bending without underwear. There were no significant differences in the correlation coefficients between the groups with and without underwear in the forward-bending posture. The performance of the DLA with a 3D depth sensor was validated using an independent external validation dataset. Because the psychological burden of children and adolescents on naked body imaging is an unignorable problem, scoliosis examination with underwear is a valuable alternative in clinics or schools.

Predicting N2 lymph node metastasis in presurgical stage I-II non-small cell lung cancer using multiview radiomics and deep learning method

BACKGROUND

Accurate diagnosis of N2 lymph node status of the resectable stage I-II non-small cell lung cancer (NSCLC) before surgery is crucial, while there is lack of corresponding method clinically.

PURPOSE

To develop and validate a model to quantitively predict the N2 lymph node metastasis in presurgical clinical stage I-II NSCLC using multiview radiomics and deep learning method.

METHODS

In this study, 140 NSCLC patients were enrolled and randomly divided into training and test sets. Univariate and multiple analysis method were used step by step to establish the clinical model; Then a multiview radiomics modeling scheme was designed, in which the optimal input feature set was determined by subcategorizing radiomics features (C1: original; C2: LoG and C3: wavelet) and comparison of corresponding radiomics model. The minimum-redundancy maximum-relevance (mRMR) selection and the least absolute shrinkage and selection operator (LASSO) algorithm were used for the feature selection and construction of each radiomics model (Rad). Next, an end-to-end ResNet18 architecture and transfer learning techniques were designed to construct a deep learning model (DL). Subsequently, the screened clinical risk factors and constructed Rad and DL models were combined and compared and a nomogram was constructed. Finally, the diagnostic performance of all constructed models were evaluated and compared using receiver operating characteristic curve (ROC) analysis, Delong test, Calibration analysis, Hosmer-Lemeshow test, and decision curves, respectively.

RESULTS

Carcinoma embryonic antigen (CEA) level and spiculation were screened to make up the Clinical model, while seven radiomics features in the optimal input feature set C2 + C3 were selected to construct the Rad. DL was constructed by training on 1.8 million natural images and small sample data of our N2 lymph node volume of interest (VOI) images. Except for the Clinical model, all other models showed good predictive accuracy and consistency in both training set and test set. DL (area under curve (AUC): 0.83) was better than Rad (AUC: 0.76) in predictive accuracy, but their difference was not significant (p = 0.45). The combined models showed better diagnostic performance than the model only clinical or image risk factors were used (AUC for Clinical, Rad + DL, Rad + Clinical, DL + Clinical, and Rad + DL + Clinical were respectively 0.66, 0.86, 0.82, 0.86, and 0.88). Finally, the Rad + DL + Clinical model with the best diagnostic performance was selected to draw the final nomogram for clinical use.

CONCLUSION

This study proposes a nomogram based on multiview radiomics, deep learning, and clinical features that can be efficiently used to quantitively predict presurgical N2 diseases in patients with clinical stage I-II NSCLC.

Review of Radiomics- and Dosiomics-based Predicting Models for Rectal Cancer

By breaking the traditional medical image analysis framework, precision medicine–radiomics has attracted much attention in the past decade. The use of various mathematical algorithms offers radiomics the ability to extract vast amounts of detailed features from medical images for quantitative analysis and analyzes the confidential information related to the tumor in the image, which can establish valuable disease diagnosis and prognosis models to support personalized clinical decisions. This article summarizes the application of radiomics and dosiomics in radiation oncology. We focus on the application of radiomics in locally advanced rectal cancer and also summarize the latest research progress of dosiomics in radiation tumors to provide ideas for the treatment of future related diseases, especially ¹²⁵I CT-guided radioactive seed implant brachytherapy.

Multi-view learning for lymph node metastasis prediction using tumor and nodal radiomics in gastric cancer

Purpose. This study aims to develop and validate a multi-view learning method by the combination of primary tumor radiomics and lymph node (LN) radiomics for the preoperative prediction of LN status in gastric cancer (GC). Methods. A total of 170 contrast-enhanced abdominal CT images from GC patients were enrolled in this retrospective study. After data preprocessing, two-step feature selection approach including Pearson correlation analysis and supervised feature selection method based on test-time budget (FSBudget) was performed to remove redundance of tumor and LN radiomics features respectively. Two types of discriminative features were then learned by an unsupervised multi-view partial least squares (UMvPLS) for a latent common space on which a logistic regression classifier is trained. Five repeated random hold-out experiments were employed. Results. On 20-dimensional latent common space, area under receiver operating characteristic curve (AUC), precision, accuracy, recall and F1-score are 0.9531 ± 0.0183, 0.9260 ± 0.0184, 0.9136 ± 0.0174, 0.9468 ± 0.0106 and 0.9362 ± 0.0125 for the training cohort respectively, and 0.8984 ± 0.0536, 0.8671 ± 0.0489, 0.8500 ± 0.0599, 0.9118 ± 0.0550 and 0.8882 ± 0.0440 for the validation cohort respectively (reported as mean ± standard deviation). It shows a better discrimination capability than single-view methods, our previous method, and eight baseline methods. When the dimension was reduced to 2, the model not only has effective prediction performance, but also is convenient for data visualization. Conclusions. Our proposed method by integrating radiomics features of primary tumor and LN can be helpful in predicting lymph node metastasis in patients of GC. It shows multi-view learning has great potential for guiding the prognosis and treatment decision-making in GC.

Rapid Progress in Intelligent Radiotherapy and Future Implementation

Radiotherapy is one of the major approaches to cancer treatment. Artificial intelligence in radiotherapy (shortly, Intelligent radiotherapy) mainly involves big data, deep learning, extended reality, digital twin, radiomics, Internet plus and Internet of Things (IoT), which establish an automatic and intelligent network platform consisting of radiotherapy preparation, target volume delineation, treatment planning, radiation delivery, quality assurance (QA) and quality control (QC), prognosis judgment and post-treatment follow-up. Intelligent radiotherapy is an interdisciplinary frontier discipline in infancy. The review aims to summary the important implements of intelligent radiotherapy in various areas and put forward the future of unmanned radiotherapy center.

Multi-Organ Omics-Based Prediction for Adaptive Radiation Therapy Eligibility in Nasopharyngeal Carcinoma Patients Undergoing Concurrent Chemoradiotherapy

Purpose

To investigate the role of different multi-organ omics-based prediction models for pre-treatment prediction of Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC).

Methods and Materials

Pre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose and contour data of 135 NPC patients treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed for extraction of multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), and Contouromics (C), from a total of eight organ structures. During model development, patient cohort was divided into a training set and a hold-out test set in a ratio of 7 to 3 via 20 iterations. Four single-omics models (R, M, D, C) and four multi-omics models (RD, RC, RM, RMDC) were developed on the training data using Ridge and Multi-Kernel Learning (MKL) algorithm, respectively, under 10-fold cross validation, and evaluated on hold-out test data using average area under the receiver-operator-characteristics curve (AUC). The best-performing single-omics model was first determined by comparing the AUC distribution across the 20 iterations among the four single-omics models using two-sided student t-test, which was then retrained using MKL algorithm for a fair comparison with the four multi-omics models.

Results

The R model significantly outperformed all other three single-omics models (all p-value<0.0001), achieving an average AUC of 0.942 (95%CI: 0.938-0.946) and 0.918 (95%CI: 0.903-0.933) in training and hold-out test set, respectively. When trained with MKL, the R model (R_MKL) yielded an increased AUC of 0.984 (95%CI: 0.981-0.988) and 0.927 (95%CI: 0.905-0.948) in training and hold-out test set respectively, while demonstrating no significant difference as compared to all studied multi-omics models in the hold-out test sets. Intriguingly, Radiomic features accounted for the majority of the final selected features, ranging from 64% to 94%, in all the studied multi-omics models.

Conclusions

Among all the studied models, the Radiomic model was found to play a dominant role for ART eligibility in NPC patients, and Radiomic features accounted for the largest proportion of features in all the multi-omics models.

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

The high-throughput extraction of quantitative imaging features from medical images for the purpose of radiomic analysis, i.e., radiomics in a broad sense, is a rapidly developing and emerging research field that has been attracting increasing interest, particularly in multimodality and multi-omics studies. In this context, the quantitative analysis of multidimensional data plays an essential role in assessing the spatio-temporal characteristics of different tissues and organs and their microenvironment. Herein, recent developments in this method, including manually defined features, data acquisition and preprocessing, lesion segmentation, feature extraction, feature selection and dimension reduction, statistical analysis, and model construction, are reviewed. In addition, deep learning-based techniques for automatic segmentation and radiomic analysis are being analyzed to address limitations such as rigorous workflow, manual/semi-automatic lesion annotation, and inadequate feature criteria, and multicenter validation. Furthermore, a summary of the current state-of-the-art applications of this technology in disease diagnosis, treatment response, and prognosis prediction from the perspective of radiology images, multimodality images, histopathology images, and three-dimensional dose distribution data, particularly in oncology, is presented. The potential and value of radiomics in diagnostic and therapeutic strategies are also further analyzed, and for the first time, the advances and challenges associated with dosiomics in radiotherapy are summarized, highlighting the latest progress in radiomics. Finally, a robust framework for radiomic analysis is presented and challenges and recommendations for future development are discussed, including but not limited to the factors that affect model stability (medical big data and multitype data and expert knowledge in medical), limitations of data-driven processes (reproducibility and interpretability of studies, different treatment alternatives for various institutions, and prospective researches and clinical trials), and thoughts on future directions (the capability to achieve clinical applications and open platform for radiomics analysis).

Interpretable machine learning for predicting pathologic complete response in patients treated with chemoradiation therapy for rectal adenocarcinoma

Purpose

Pathologic complete response (pCR) is a critical factor in determining whether patients with rectal cancer (RC) should have surgery after neoadjuvant chemoradiotherapy (nCRT). Currently, a pathologist's histological analysis of surgical specimens is necessary for a reliable assessment of pCR. Machine learning (ML) algorithms have the potential to be a non-invasive way for identifying appropriate candidates for non-operative therapy. However, these ML models' interpretability remains challenging. We propose using explainable boosting machine (EBM) to predict the pCR of RC patients following nCRT.

Methods

A total of 296 features were extracted, including clinical parameters (CPs), dose-volume histogram (DVH) parameters from gross tumor volume (GTV) and organs-at-risk, and radiomics (R) and dosiomics (D) features from GTV. R and D features were subcategorized into shape (S), first-order (L1), second-order (L2), and higher-order (L3) local texture features. Multi-view analysis was employed to determine the best set of input feature categories. Boruta was used to select all-relevant features for each input dataset. ML models were trained on 180 cases from our institution, with 37 cases from RTOG 0822 clinical trial serving as the independent dataset for model validation. The performance of EBM in predicting pCR on the test dataset was evaluated using ROC AUC and compared with that of three state-of-the-art black-box models: extreme gradient boosting (XGB), random forest (RF) and support vector machine (SVM). The predictions of all black-box models were interpreted using Shapley additive explanations.

Results

The best input feature categories were CP+DVH+S+R_L1+R_L2 for all models, from which Boruta-selected features enabled the EBM, XGB, RF, and SVM models to attain the AUCs of 0.820, 0.828, 0.828, and 0.774, respectively. Although EBM did not achieve the best performance, it provided the best capability for identifying critical turning points in response scores at distinct feature values, revealing that the bladder with maximum dose >50 Gy, and the tumor with maximum2DDiameterColumn >80 mm, elongation <0.55, leastAxisLength >50 mm and lower variance of CT intensities were associated with unfavorable outcomes.

Conclusions

EBM has the potential to enhance the physician's ability to evaluate an ML-based prediction of pCR and has implications for selecting patients for a "watchful waiting" strategy to RC therapy.

On dose cube pixel spacing pre-processing for features extraction stability in dosiomic studies

PURPOSE

Dosiomics allows to parameterize regions of interest (ROIs) and to produce quantitative dose features encoding the spatial and statistical distribution of radiotherapy dose. The stability of dosiomics features extraction on dose cube pixel spacing variation has been investigated in this study.

MATERIAL AND METHODS

Based on 17 clinical delivered dose distributions (P_n), dataset has been generated considering all the possible combinations of four dose grid resolutions and two calculation algorithms. Each dose voxel cube has been post-processed considering 4 different dose cube pixel spacing values: 1x1x1, 2x2x2, 3x3x3 mm³ and the one equal to the planning CT. Dosiomics features extraction has been performed from four different ROIs. The stability of each extracted dosiomic feature has been analyzed in terms of coefficient of variation (CV) intraclass correlation coefficient (ICC).

RESULTS

The highest CV mean values were observed for PTV ROI and for the grey level size zone matrix features family. On the other hand, the lowest CV mean values have been found for RING ROI for the grey level co-occurrence matrix features family. P₃ showed the highest percentage of CV >1 (1.14%) followed by P₁₅ (0.41%), P₁ (0.29%) and P13 (0.19%). ICC analysis leads to identify features with an ICC >0.95 that could be considered stable to use in dosiomic studies when different dose cube pixel spacing are considered, especially the features in common among the seventeen plans.

CONCLUSION

Considering the observed variability, dosiomic studies should always provide a report not only on grid resolution and algorithm dose calculation, but also on dose cube pixel spacing.

Improving Early Identification of Significant Weight Loss Using Clinical Decision Support System in Lung Cancer Radiation Therapy

PURPOSE

Early identification of patients who may be at high risk of significant weight loss (SWL) is important for timely clinical intervention in lung cancer radiotherapy (RT). A clinical decision support system (CDSS) for SWL prediction was implemented within the routine clinical workflow and assessed on a prospective cohort of patients.

MATERIALS AND METHODS

CDSS incorporated a machine learning prediction model on the basis of radiomics and dosiomics image features and was connected to a web-based dashboard for streamlined patient enrollment, feature extraction, SWL prediction, and physicians' evaluation processes. Patients with lung cancer (N = 37) treated with definitive RT without prior RT were prospectively enrolled in the study. Radiomics and dosiomics features were extracted from CT and 3D dose volume, and SWL probability (≥ 0.5 considered as SWL) was predicted. Two physicians predicted whether the patient would have SWL before and after reviewing the CDSS prediction. The physician's prediction performance without and with CDSS and prediction changes before and after using CDSS were compared.

RESULTS

CDSS showed significantly better prediction accuracy than physicians (0.73 v 0.54) with higher specificity (0.81 v 0.50) but with lower sensitivity (0.55 v 0.64). Physicians changed their original prediction after reviewing CDSS prediction for four cases (three correctly and one incorrectly), for all of which CDSS prediction was correct. Physicians' prediction was improved with CDSS in accuracy (0.54-0.59), sensitivity (0.64-0.73), specificity (0.50-0.54), positive predictive value (0.35-0.40), and negative predictive value (0.76-0.82).

CONCLUSION

Machine learning-based CDSS showed the potential to improve SWL prediction in lung cancer RT. More investigation on a larger patient cohort is needed to properly interpret CDSS prediction performance and its benefit in clinical decision making.

Dosiomics-based prediction of radiation-induced hypothyroidism in nasopharyngeal carcinoma patients

PURPOSE

To predict the incidence of radiation-induced hypothyroidism (RHT) in nasopharyngeal carcinoma (NPC) patients, dosiomics features based prediction models were established.

MATERIALS AND METHODS

A total of 145 NPC patients treated with radiotherapy from January 2012 to January 2015 were included. Dosiomics features of the dose distribution within thyroid gland were extracted. The minimal-redundancy-maximal-relevance (mRMR) criterion was used to rank the extracted features and selected the most relevant features. Machine learning (ML) algorithms including logistic regression (LR), support vector machine (SVM), random forest (RF), and k-nearest neighbor (KNN) were utilized to establish prediction models, respectively. Nested sampling and hyper-tuning methods were adopted to train and validate the prediction models. The dosiomics-based (DO) prediction models were evaluated through comparing with the dose-volume factor-based (DV) models in terms of the area under the receiver operating characteristic (ROC) curve (AUC). The demographics factors (age and gender) were included in both DO model and DV model.

RESULTS

Age, V45 and 37 dosiomics features exhibited significant correlations with RHT in univariate analysis. For prediction performance, DO prediction models exhibited better results with the best AUC value 0.7 while DV prediction models 0.61. In DO prediction models, the AUC values displayed a trend from ascending to descending with the increasing of selected features. The highest AUC value was achieved when the number of selected features was 3. In DV prediction model, similar trend was not observed.

CONCLUSION

This study established a prediction model based on the dosiomics features with better performance than conventional dose-volume factors, leading to early predict the possible RHT among NPC patients who had received radiotherapy and take precaution measures for NPC patients.

Dose-based radiomic analysis (dosiomics) for intensity-modulated radiotherapy in patients with prostate cancer: Correlation between planned dose distribution and biochemical failure

PURPOSE

Although radiotherapy is one of the most significant modalities for localized prostate cancer, the prognostic factors for biochemical recurrence (BCR) regarding the treatment plan are unclear. We aimed to develop a novel dosiomics-based prediction model for BCR in patients with prostate cancer and clarify the correlations between the dosimetric factors and BCR.

METHODS AND MATERIALS

This study included 489 patients with localized prostate cancer (BCR: 96, No-BCR: 393) who received intensity-modulated radiation therapy. A total of 2,475 dosiomic features were extracted from the dose distributions on the prostate, clinical target volume (CTV), and planning target volume. A prediction model for BCR was trained on a training cohort of 342 patients. The performance of this model was validated using the concordance index (C-index) in a validation cohort of 147 patients. Another model was constructed using clinical variables, dosimetric parameters, and radiomic features for comparisons. Kaplan-Meier curves with log-rank analysis were used to assess the univariate discrimination based on the predictive dosiomic features.

RESULTS

The dosiomic feature derived from the CTV was significantly associated with BCR (hazard ratio: 0.73; 95% confidence interval [CI]: 0.57-0.93; P = .01). Although the dosiomics model outperformed the dosimetric and radiomics models, it did not outperform the clinical model. The performance significantly improved by combining the clinical variables and dosiomic features (C-index: 0.67; 95% CI: 0.65-0.68; P < .0001). The predictive dosiomic features were used to distinguish high-risk and low-risk patients (P < .05).

CONCLUSIONS

The dosiomic feature extracted from the CTV was significantly correlated with BCR in patients with prostate cancer, and the dosiomics model outperformed the model with conventional dose indices. Hence, new metrics for evaluating the quality of a treatment plan are warranted. Moreover, further research should be conducted to determine whether dosiomics can be incorporated in a clinical workflow or clinical trial.

Multiblock Discriminant Analysis of Integrative 18F-FDG-PET/CT Radiomics for Predicting Circulating Tumor Cells in Early-Stage Non-small Cell Lung Cancer Treated With Stereotactic Body Radiation Therapy

PURPOSE

The main objective of the present study was to integrate 18F-FDG-PET/CT radiomics with multiblock discriminant analysis for predicting circulating tumor cells (CTCs) in early-stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic body radiation therapy (SBRT).

METHODS

Fifty-six patients with stage I NSCLC treated with SBRT underwent 18F-FDG-PET/CT imaging pre-SBRT and post-SBRT (median, 5 months; range, 3-10 months). CTCs were assessed via a telomerase-based assay before and within 3 months after SBRT and dichotomized at 5 and 1.3 CTCs/mL. Pre-SBRT, post-SBRT, and delta PET/CT radiomics features (n = 1548 × 3/1562 × 3) were extracted from gross tumor volume. Seven feature blocks were constructed including clinical parameters (n = 12). Multiblock data integration was performed using block sparse partial least squares-discriminant analysis (sPLS-DA) referred to as Data Integration Analysis for Biomarker Discovery Using Latent Components (DIABLO) for identifying key signatures by maximizing common information between different feature blocks while discriminating CTC levels. Optimal input blocks were identified using a pairwise combination method. DIABLO performance for predicting pre-SBRT and post-SBRT CTCs was evaluated using combined AUC (area under the curve, averaged across different blocks) analysis with 20 × 5-fold cross-validation (CV) and compared with that of concatenation-based sPLS-DA that consisted of combining all features into 1 block. CV prediction scores between 1 class versus the other were compared using the Wilcoxon rank sum test.

RESULTS

For predicting pre-SBRT CTCs, DIABLO achieved the best performance with combined pre-SBRT PET radiomics and clinical feature blocks, showing CV AUC of 0.875 (P = .009). For predicting post-SBRT CTCs, DIABLO achieved the best performance with combined post-SBRT CT and delta CT radiomics feature blocks, showing CV AUCs of 0.883 (P = .001). In contrast, all single-block sPLS-DA models could not attain CV AUCs higher than 0.7.

CONCLUSIONS

Multiblock integration with discriminant analysis of 18F-FDG-PET/CT radiomics has the potential for predicting pre-SBRT and post-SBRT CTCs. Radiomics and CTC analysis may complement and together help guide the subsequent management of patients with ES-NSCLC.

Incorporating radiomics into clinical trials: expert consensus endorsed by the European Society of Radiology on considerations for data-driven compared to biologically driven quantitative biomarkers

Existing quantitative imaging biomarkers (QIBs) are associated with known biological tissue characteristics and follow a well-understood path of technical, biological and clinical validation before incorporation into clinical trials. In radiomics, novel data-driven processes extract numerous visually imperceptible statistical features from the imaging data with no a priori assumptions on their correlation with biological processes. The selection of relevant features (radiomic signature) and incorporation into clinical trials therefore requires additional considerations to ensure meaningful imaging endpoints. Also, the number of radiomic features tested means that power calculations would result in sample sizes impossible to achieve within clinical trials. This article examines how the process of standardising and validating data-driven imaging biomarkers differs from those based on biological associations. Radiomic signatures are best developed initially on datasets that represent diversity of acquisition protocols as well as diversity of disease and of normal findings, rather than within clinical trials with standardised and optimised protocols as this would risk the selection of radiomic features being linked to the imaging process rather than the pathology. Normalisation through discretisation and feature harmonisation are essential pre-processing steps. Biological correlation may be performed after the technical and clinical validity of a radiomic signature is established, but is not mandatory. Feature selection may be part of discovery within a radiomics-specific trial or represent exploratory endpoints within an established trial; a previously validated radiomic signature may even be used as a primary/secondary endpoint, particularly if associations are demonstrated with specific biological processes and pathways being targeted within clinical trials. KEY POINTS: • Data-driven processes like radiomics risk false discoveries due to high-dimensionality of the dataset compared to sample size, making adequate diversity of the data, cross-validation and external validation essential to mitigate the risks of spurious associations and overfitting. • Use of radiomic signatures within clinical trials requires multistep standardisation of image acquisition, image analysis and data mining processes. • Biological correlation may be established after clinical validation but is not mandatory.

A Multicentre Evaluation of Dosiomics Features Reproducibility, Stability and Sensitivity

Simple Summary

Dosiomics is born directly as an extension of radiomics: it entails extracting features from the patients’ three-dimensional (3D) radiotherapy dose distribution rather than from conventional medical images to obtain specific spatial and statistical information. Dosiomic studies, in a multicentre setting, require assessing the features’ stability to dose calculation settings and the features’ capability in distinguishing different dose distributions. This study provides the first multicentre evaluation of the dosiomic features in terms of reproducibility, stability and sensitivity across various dose distributions obtained from multiple technologies and techniques and considering different dose calculation algorithms of TPS and two different resolutions of the dose grid. Harmonisation strategies to account for a possible variation in the dose distribution due to these confounding factors should be adopted when investigating a correlation between dosiomic features and clinical outcomes in multicentre studies.

Abstract

Dosiomics is a texture analysis method to produce dose features that encode the spatial 3D distribution of radiotherapy dose. Dosiomic studies, in a multicentre setting, require assessing the features’ stability to dose calculation settings and the features’ capability in distinguishing different dose distributions. Dose distributions were generated by eight Italian centres on a shared image dataset acquired on a dedicated phantom. Treatment planning protocols, in terms of planning target volume coverage and dose–volume constraints to the organs at risk, were shared among the centres to produce comparable dose distributions for measuring reproducibility/stability and sensitivity of dosiomic features. In addition, coefficient of variation (CV) was employed to evaluate the dosiomic features’ variation. We extracted 38,160 features from 30 different dose distributions from six regions of interest, grouped by four features’ families. A selected group of features (CV < 3 for the reproducibility/stability studies, CV > 1 for the sensitivity studies) were identified to support future multicentre studies, assuring both stable features when dose distributions variation is minimal and sensitive features when dose distribution variations need to be clearly identified. Dosiomic is a promising tool that could support multicentre studies, especially for predictive models, and encode the spatial and statistical characteristics of the 3D dose distribution.

Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations

For decades, dose-volume information for segmented anatomy has provided the essential data for correlating radiotherapy dosimetry with treatment-induced complications. Dose-volume information has formed the basis for modelling those associations via normal tissue complication probability (NTCP) models and for driving treatment planning. Limitations to this approach have been identified. Many studies have emerged demonstrating that the incorporation of information describing the spatial nature of the dose distribution, and potentially its correlation with anatomy, can provide more robust associations with toxicity and seed more general NTCP models. Such approaches are culminating in the application of computationally intensive processes such as machine learning and the application of neural networks. The opportunities these approaches have for individualising treatment, predicting toxicity and expanding the solution space for radiation therapy are substantial and have clearly widespread and disruptive potential. Impediments to reaching that potential include issues associated with data collection, model generalisation and validation. This review examines the role of spatial models of complication and summarises relevant published studies. Sources of data for these studies, appropriate statistical methodology frameworks for processing spatial dose information and extracting relevant features are described. Spatial complication modelling is consolidated as a pathway to guiding future developments towards effective, complication-free radiotherapy treatment.

An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection

BACKGROUND CONTEXT

Timely intervention in growing individuals, such as brace treatment, relies on early detection of adolescent idiopathic scoliosis (AIS). To this end, several screening methods have been implemented. However, these methods have limitations in predicting the Cobb angle.

PURPOSE

This study aimed to evaluate the performance of a three-dimensional depth sensor imaging system with a deep learning algorithm, in predicting the Cobb angle in AIS.

STUDY DESIGN

Retrospective analysis of prospectively collected, consecutive, nonrandomized series of patients at five scoliosis centers in Japan.

PATIENT SAMPLE

One hundred and-sixty human subjects suspected to have AIS were included.

OUTCOME MEASURES

Patient demographics, radiographic measurements, and predicted Cobb angle derived from the deep learning algorithm were the outcome measures for this study.

METHODS

One hundred and sixty data files were shuffled into five datasets with 32 data files at random (dataset 1, 2, 3, 4, and 5) and five-fold cross validation was performed. The relationships between the actual and predicted Cobb angles were calculated using Pearson's correlation coefficient analyses. The prediction performances of the network models were evaluated using mean absolute error and root mean square error between the actual and predicted Cobb angles. The shuffling into five datasets and five-fold cross validation was conducted ten times. There were no study-specific biases related to conflicts of interest.

RESULTS

The correlation between the actual and the mean predicted Cobb angles was 0.91. The mean absolute error and root mean square error were 4.0° and 5.4°, respectively. The accuracy of the mean predicted Cobb angle was 94% for identifying a Cobb angle of ≥10° and 89% for that of ≥20°.

CONCLUSIONS

The three-dimensional depth sensor imaging system with its newly innovated convolutional neural network for regression is objective and has significant ability to predict the Cobb angle in children and adolescents. This system is expected to be used for screening scoliosis in clinics or physical examination at schools.

Radiomics and Dosiomics for Predicting Local Control after Carbon-Ion Radiotherapy in Skull-Base Chordoma

Skull-base chordoma (SBC) can be treated with carbon ion radiotherapy (CIRT) to improve local control (LC). The study aimed to explore the role of multi-parametric radiomic, dosiomic and clinical features as prognostic factors for LC in SBC patients undergoing CIRT. Before CIRT, 57 patients underwent MR and CT imaging, from which tumour contours and dose maps were obtained. MRI and CT-based radiomic, and dosiomic features were selected and fed to two survival models, singularly or by combining them with clinical factors. Adverse LC was given by in-field recurrence or tumour progression. The dataset was split in development and test sets and the models' performance evaluated using the concordance index (C-index). Patients were then assigned a low- or high-risk score. Survival curves were estimated, and risk groups compared through log-rank tests (after Bonferroni correction α = 0.0083). The best performing models were built on features describing tumour shape and dosiomic heterogeneity (median/interquartile range validation C-index: 0.80/024 and 0.79/0.26), followed by combined (0.73/0.30 and 0.75/0.27) and CT-based models (0.77/0.24 and 0.64/0.28). Dosiomic and combined models could consistently stratify patients in two significantly different groups. Dosiomic and multi-parametric radiomic features showed to be promising prognostic factors for LC in SBC treated with CIRT.

What is plan quality in radiotherapy? The importance of evaluating dose metrics, complexity, and robustness of treatment plans

Plan evaluation is a key step in the radiotherapy treatment workflow. Central to this step is the assessment of treatment plan quality. Hence, it is important to agree on what we mean by plan quality and to be fully aware of which parameters it depends on. We understand plan quality in radiotherapy as the clinical suitability of the delivered dose distribution that can be realistically expected from a treatment plan. Plan quality is commonly assessed by evaluating the dose distribution calculated by the treatment planning system (TPS). Evaluating the 3D dose distribution is not easy, however; it is hard to fully evaluate its spatial characteristics and we still lack the knowledge for personalising the prediction of the clinical outcome based on individual patient characteristics. This advocates for standardisation and systematic collection of clinical data and outcomes after radiotherapy. Additionally, the calculated dose distribution is not exactly the dose delivered to the patient due to uncertainties in the dose calculation and the treatment delivery, including variations in the patient set-up and anatomy. Consequently, plan quality also depends on the robustness and complexity of the treatment plan. We believe that future work and consensus on the best metrics for quality indices are required. Better tools are needed in TPSs for the evaluation of dose distributions, for the robust evaluation and optimisation of treatment plans, and for controlling and reporting plan complexity. Implementation of such tools and a better understanding of these concepts will facilitate the handling of these characteristics in clinical practice and be helpful to increase the overall quality of treatment plans in radiotherapy.