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

Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study

Purpose.This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) and magnetic resonance imaging (MRI) radiomics features in combination with clinical and dosimetric features in rectal cancer patients.Methods.A total of sixty-three patients with locally advanced rectal cancer who underwent three-dimensional conformal radiation therapy (3D-CRT) were included in this study. Radiomics features were extracted from the rectum and bladder walls in pretreatment CT and MR-T2W-weighted images. Feature selection was performed using various methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and SelectPercentile. Predictive modeling was carried out using machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), and Linear Discriminant Analysis (LDA). The impact of the Laplacian of Gaussian (LoG) filter was investigated with sigma values ranging from 0.5 to 2. Model performance was evaluated in terms of the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, and specificity.Results.A total of 479 radiomics features were extracted, and 59 features were selected. The pre-MRI T2W model exhibited the highest predictive performance with an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, and specificity: 88.09/97.14%. These results were achieved with both original image and LoG filter (sigma = 0.5-1.5) based on LDA/DT-RF classifiers for proctitis and cystitis, respectively. Furthermore, for the CT data, AUC: 90.71/96.0%, accuracy: 90.0/96.92%, precision: 88.14/97.14%, sensitivity: 93.0/96.0%, and specificity: 88.09/97.14% were acquired. The highest values were achieved using XGB/DT-XGB classifiers for proctitis and cystitis with LoG filter (sigma = 2)/LoG filter (sigma = 0.5-2), respectively. MRMR/RFE-Chi2 feature selection methods demonstrated the best performance for proctitis and cystitis in the pre-MRI T2W model. MRMR/MRMR-Lasso yielded the highest model performance for CT.Conclusion.Radiomics features extracted from pretreatment CT and MR images can effectively predict radiation-induced proctitis and cystitis. The study found that LDA, DT, RF, and XGB classifiers, combined with MRMR, RFE, Chi2, and Lasso feature selection algorithms, along with the LoG filter, offer strong predictive performance. With the inclusion of a larger training dataset, these models can be valuable tools for personalized radiotherapy decision-making.

The Crying Need for a Better Response Assessment in Rectal Cancer

OPINION STATEMENT

Since total neoadjuvant treatment achieves almost 30% pathologic complete response, organ preservation has been increasingly debated for good responders after neoadjuvant treatment for patients diagnosed with rectal cancer. Two organ preservation strategies are available: a watch and wait strategy and a local excision strategy including patients with a near clinical complete response. A major issue is the selection of patients according to the initial tumor staging or the response assessment. Despite modern imaging improvement, identifying complete response remains challenging. A better selection could be possible by radiomics analyses, exploiting numerous image features to feed data characterization algorithms. The subsequent step is to include baseline and/or pre-therapeutic MRI, PET-CT, and CT radiomics added to the patients' clinicopathological data, inside machine learning (ML) prediction models, with predictive or prognostic purposes. These models could be further improved by the addition of new biomarkers such as circulating tumor biomarkers, molecular profiling, or pathological immune biomarkers.

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

BACKGROUND

Standardized patient-specific pretreatment dosimetry planning is mandatory in the modern era of nuclear molecular radiotherapy, which may eventually lead to improvements in the final therapeutic outcome. Only a comprehensive definition of a dosage therapeutic window encompassing the range of absorbed doses, that is, helpful without being detrimental can lead to therapy individualization and improved outcomes. As a result, setting absorbed dose safety limits for organs at risk (OARs) requires knowledge of the absorbed dose-effect relationship. Data sets of consistent and reliable inter-center dosimetry findings are required to characterize this relationship.

PURPOSE

We developed and standardized a new pretreatment planning model consisting of a predictive dosimetry procedure for OARs in patients with neuroendocrine tumors (NETs) treated with 177 Lu-DOTATATE (Lutathera). In the retrospective study described herein, we used machine learning (ML) regression algorithms to predict absorbed doses in OARs by exploiting a combination of radiomic and dosiomic features extracted from patients' imaging data.

METHODS

Pretreatment and posttreatment data for 20 patients with NETs treated with 177 Lu-DOTATATE were collected from two clinical centers. A total of 3412 radiomic and dosiomic features were extracted from the patients' computed tomography (CT) scans and dose maps, respectively. All dose maps were generated using Monte Carlo simulations. An ML regression model was designed based on ML algorithms for predicting the absorbed dose in every OAR (liver, left kidney, right kidney, and spleen) before and after the therapy and between each therapy session, thus predicting any possible radiotoxic effects.

RESULTS

We evaluated nine ML regression algorithms. Our predictive model achieved a mean absolute dose error (MAE, in Gy) of 0.61 for the liver, 1.58 for the spleen, 1.30 for the left kidney, and 1.35 for the right kidney between pretherapy 68 Ga-DOTATOC positron emission tomography (PET)/CT and posttherapy 177 Lu-DOTATATE single photon emission (SPECT)/CT scans. Τhe best predictive performance observed was based on the gradient boost for the liver, the left kidney and the right kidney, and on the extra tree regressor for the spleen. Evaluation of the model's performance according to its ability to predict the absorbed dose in each OAR in every possible combination of pretherapy 68 Ga-DOTATOC PET/CT and any posttherapy 177 Lu-DOTATATE treatment cycle SPECT/CT scans as well as any 177 Lu-DOTATATE SPECT/CT treatment cycle and the consequent 177 Lu-DOTATATE SPECT/CT treatment cycle revealed mean absorbed dose differences ranges from -0.55 to 0.68 Gy. Incorporating radiodosiomics features from the 68 Ga-DOTATOC PET/CT and first 177 Lu-DOTATATE SPECT/CT treatment cycle scans further improved the precision and minimized the standard deviation of the predictions in nine out of 12 instances. An average improvement of 57.34% was observed (range: 17.53%-96.12%). However, it's important to note that in three instances (i.e., Ga,C.1 → C3 in spleen and left kidney, and Ga,C.1 → C2 in right kidney) we did not observe an improvement (absolute differences of 0.17, 0.08, and 0.05 Gy, respectively). Wavelet-based features proved to have high correlated predictive value, whereas non-linear-based ML regression algorithms proved to be more capable than the linear-based of producing precise prediction in our case.

CONCLUSIONS

The combination of radiomics and dosiomics has potential utility for personalized molecular radiotherapy (PMR) response evaluation and OAR dose prediction. These radiodosiomic features can potentially provide information on any possible disease recurrence and may be highly useful in clinical decision-making, especially regarding dose escalation issues.

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.

The role of MRI after neochemoradiotherapy in predicting pathological tumor regression grade and clinical outcome in patients with locally advanced rectal adenocarcinoma

Objective

To evaluate the predictive value of tumor regression grade assessed by MRI (mr-TRG) after neoadjuvant chemoradiotherapy (neo-CRT) for postoperative pathological TRG (pTRG) and prognosis in patients with locally advanced rectal adenocarcinoma (LARC).

Materials and methods

This was a retrospective study from a single center experience. The patients who were diagnosed with LARC and received neo-CRT in our department between January 2016 and July 2021 were enrolled. The agreement between mrTRG and pTRG was assessed with the weighted κ test. Overall survival (OS), progress-free survival (PFS), local recurrence-free survival (LRFS), and distant metastasis-free survival (DMFS) were calculated by Kaplan-Meier analysis and log-rank test.

Results

From January 2016 to July 2021, 121 LARC patients received neo-CRT in our department. Among them, 54 patients had complete clinical data, including MRI of pre- and post-neo-CRT, postoperative tumor samples, and follow-up. The median follow-up time was 34.6 months (range: 4.4-70.6 months). The estimated 3-year OS, PFS, LRFS and DMFS were 78.5%, 70.7%, 89.0%, and 75.2%, respectively. The median time from the completion of neo-CRT to preoperative MRI and surgery was 7.1 weeks and 9.7 weeks, respectively. Out of 54 patients, 5 patients achieved mrTRG1 (9.3%), 37 achieved mrTRG2 (68.5%), 8 achieved mrTRG3 (14.8%), 4 achieved mrTRG4 (7.4%), and no patient achieved mrTRG5 after neo-CRT. Regarding pTRG, 12 patients achieved pTRG0 (22.2%), 10 achieved pTRG1 (18.5%), 26 achieved pTRG2 (48.1%), and 6 achieved pTRG3 (11.1%). The agreement between three-tier mrTRG (mrTRG1 vs. mrTRG2-3 vs. mrTRG4-5) and pTRG (pTRG0 vs. pTRG1-2 vs. pTRG3) was fair (weighted kappa=0.287). In a dichotomous classification, the agreement between mrTRG(mrTRG1 vs. mrTRG2-5)and pTRG(pTRG0 vs. pTRG1-3) also resulted in fair agreement (weighted kappa=0.391). The sensitivity, specificity, positive, and negative predictive values of favorable mrTRG (mrTRG 1-2) for pathological complete response (PCR) were 75.0%, 21.4%, 21.4%, and 75.0%, respectively. In univariate analysis, favorable mrTRG (mrTRG1-2) and downstaging N were significantly associated with better OS, while favorable mrTRG (mrTRG1-2), downstaging T, and downstaging N were significantly associated with superior PFS (p<0.05). In multivariate analysis, downstaging N was an independent prognostic factor for OS. Meanwhile, downstaging T and downstaging N remained independent prognostic factors for PFS.

Conclusions

Although the consistency between mrTRG and pTRG is only fair, favorable mrTRG after neo-CRT may be used as a potential prognostic factor for LARC patients.

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.

Role of radiomics in the diagnosis and treatment of gastrointestinal cancer

Gastrointestinal cancer (GIC) has high morbidity and mortality as one of the main causes of cancer death. Preoperative risk stratification is critical to guide patient management, but traditional imaging studies have difficulty predicting its biological behavior. The emerging field of radiomics allows the conversion of potential pathophysiological information in existing medical images that cannot be visually recognized into high-dimensional quantitative image features. Tumor lesion characterization, therapeutic response evaluation, and survival prediction can be achieved by analyzing the relationships between these features and clinical and genetic data. In recent years, the clinical application of radiomics to GIC has increased dramatically. In this editorial, we describe the latest progress in the application of radiomics to GIC and discuss the value of its potential clinical applications, as well as its limitations and future directions.