Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer

Do treated rectal tumors appear differently on MRI after chemotherapy versus chemoradiotherapy?

PURPOSE

Increasing studies have focused on neoadjuvant chemotherapy (NCT) in rectal cancer. However, few studies explored the differences in radiographic variation between patients treated with NCT and neoadjuvant chemoradiotherapy (NCRT).

METHODS

Stage II/III rectal cancer patients from March 2016 to December 2019 meeting the criteria treated with NCRT or NCT were included. MRI features, including tumor location, longitudinal length, DWI signal, MRI tumor regression grade (mrTRG), and radiomic texture features, before and after neoadjuvant treatments were reviewed.

RESULTS

116 patients with NCRT and 61 with NCT were analyzed. Among these patients, 46 patients in the NCRT group and 18 in the NCT group were responders with pathological TRG0-1. Within these responders, the mean tumor longitudinal length regression rate (TLRR) of the NCT group was 60.08 ± 11.17%, which was significantly higher than the 50.73 ± 15.28% of the NCRT group (p = 0.010). The proportion of high signal in the DWI image after NCT was higher than that of the NCRT group (88.89% vs 50.00%, p = 0.004). NCT responders had significantly higher median change rates than those of NCRT responders in 11 radiomic features, especially those shape features.

CONCLUSION

MRI images change differently between responders treated with NCRT and those with NCT in rectal cancer. The tumor volumetry and some radiomic features change more obviously in NCT responders, and the tumor signal changes more obviously in NCRT responders. During the evaluation of the response of the tumor to the neoadjuvant treatments, images of patients should be treated differently.

Artificial intelligence for dementia prevention

INTRODUCTION

A wide range of modifiable risk factors for dementia have been identified. Considerable debate remains about these risk factors, possible interactions between them or with genetic risk, and causality, and how they can help in clinical trial recruitment and drug development. Artificial intelligence (AI) and machine learning (ML) may refine understanding.

METHODS

ML approaches are being developed in dementia prevention. We discuss exemplar uses and evaluate the current applications and limitations in the dementia prevention field.

RESULTS

Risk-profiling tools may help identify high-risk populations for clinical trials; however, their performance needs improvement. New risk-profiling and trial-recruitment tools underpinned by ML models may be effective in reducing costs and improving future trials. ML can inform drug-repurposing efforts and prioritization of disease-modifying therapeutics.

DISCUSSION

ML is not yet widely used but has considerable potential to enhance precision in dementia prevention.

HIGHLIGHTS

Artificial intelligence (AI) is not widely used in the dementia prevention field. Risk-profiling tools are not used in clinical practice. Causal insights are needed to understand risk factors over the lifespan. AI will help personalize risk-management tools for dementia prevention. AI could target specific patient groups that will benefit most for clinical trials.

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.

Is It Really Gone? Assessing Response to Neoadjuvant Therapy in Rectal Cancer

PURPOSE

Non-operative management of rectal cancer is a feasible and appealing treatment option for patients who develop a complete response after neoadjuvant therapy. However, identifying patients who are complete responders is often a challenge. This review aims to present and discuss current evidence and recommendations regarding the assessment of treatment response in rectal cancer.

METHODS

A review of the current literature on rectal cancer restaging was performed. Studies included in this review explored the optimal interval between the end of neoadjuvant therapy and restaging, as well as modalities of assessment and their diagnostic performance.

RESULTS

The current standard for restaging rectal cancer is a multimodal assessment with the digital rectal examination, endoscopy, and T2-weighted MRI with diffusion-weighted imaging. Other diagnostic procedures under investigation are PET/MRI, radiomics, confocal laser endomicroscopy, artificial intelligence-assisted endoscopy, cell-free DNA, and prediction models incorporating one or more of the above-mentioned exams.

CONCLUSION

Non-operative management of rectal cancer requires a multidisciplinary approach. Understanding of the robustness and limitations of each exam is critical to inform patient selection for that treatment strategy.

Myocardial Perfusion SPECT Imaging Radiomic Features and Machine Learning Algorithms for Cardiac Contractile Pattern Recognition

A U-shaped contraction pattern was shown to be associated with a better Cardiac resynchronization therapy (CRT) response. The main goal of this study is to automatically recognize left ventricular contractile patterns using machine learning algorithms trained on conventional quantitative features (ConQuaFea) and radiomic features extracted from Gated single-photon emission computed tomography myocardial perfusion imaging (GSPECT MPI). Among 98 patients with standard resting GSPECT MPI included in this study, 29 received CRT therapy and 69 did not (also had CRT inclusion criteria but did not receive treatment yet at the time of data collection, or refused treatment). A total of 69 non-CRT patients were employed for training, and the 29 were employed for testing. The models were built utilizing features from three distinct feature sets (ConQuaFea, radiomics, and ConQuaFea + radiomics (combined)), which were chosen using Recursive feature elimination (RFE) feature selection (FS), and then trained using seven different machine learning (ML) classifiers. In addition, CRT outcome prediction was assessed by different treatment inclusion criteria as the study's final phase. The MLP classifier had the highest performance among ConQuaFea models (AUC, SEN, SPE = 0.80, 0.85, 0.76). RF achieved the best performance in terms of AUC, SEN, and SPE with values of 0.65, 0.62, and 0.68, respectively, among radiomic models. GB and RF approaches achieved the best AUC, SEN, and SPE values of 0.78, 0.92, and 0.63 and 0.74, 0.93, and 0.56, respectively, among the combined models. A promising outcome was obtained when using radiomic and ConQuaFea from GSPECT MPI to detect left ventricular contractile patterns by machine learning.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Radiomics in Hypopharyngeal Cancer Management: A State-of-the-Art Review

(1) Background: Hypopharyngeal squamous cell carcinomas usually present with locally advanced disease and a correspondingly poor prognosis. Currently, efforts are being made to improve tumor characterization and provide insightful information for outcome prediction. Radiomics is an emerging area of study that involves the conversion of medical images into mineable data; these data are then used to extract quantitative features based on shape, intensity, texture, and other parameters; (2) Methods: A systematic review of the peer-reviewed literature was conducted; (3) Results: A total of 437 manuscripts were identified. Fifteen manuscripts met the inclusion criteria. The main targets described were the evaluation of textural features to determine tumor-programmed death-ligand 1 expression; a surrogate for microvessel density and heterogeneity of perfusion; patient stratification into groups at high and low risk of progression; prediction of early recurrence, 1-year locoregional failure and survival outcome, including progression-free survival and overall survival, in patients with locally advanced HPSCC; thyroid cartilage invasion, early disease progression, recurrence, induction chemotherapy response, treatment response, and prognosis; and (4) Conclusions: our findings suggest that radiomics represents a potentially useful tool in the diagnostic workup as well as during the treatment and follow-up of patients with HPSCC. Large prospective studies are essential to validate this technology in these patients.

MRI-based pre-Radiomics and delta-Radiomics models accurately predict the post-treatment response of rectal adenocarcinoma to neoadjuvant chemoradiotherapy

Objectives

To develop and validate magnetic resonance imaging (MRI)-based pre-Radiomics and delta-Radiomics models for predicting the treatment response of local advanced rectal cancer (LARC) to neoadjuvant chemoradiotherapy (NCRT).

Methods

Between October 2017 and August 2022, 105 LARC NCRT-naïve patients were enrolled in this study. After careful evaluation, data for 84 patients that met the inclusion criteria were used to develop and validate the NCRT response models. All patients received NCRT, and the post-treatment response was evaluated by pathological assessment. We manual segmented the volume of tumors and 105 radiomics features were extracted from three-dimensional MRIs. Then, the eXtreme Gradient Boosting algorithm was implemented for evaluating and incorporating important tumor features. The predictive performance of MRI sequences and Synthetic Minority Oversampling Technique (SMOTE) for NCRT response were compared. Finally, the optimal pre-Radiomics and delta-Radiomics models were established respectively. The predictive performance of the radionics model was confirmed using 5-fold cross-validation, 10-fold cross-validation, leave-one-out validation, and independent validation. The predictive accuracy of the model was based on the area under the receiver operator characteristic (ROC) curve (AUC).

Results

There was no significant difference in clinical factors between patients with good and poor reactions. Integrating different MRI modes and the SMOTE method improved the performance of the radiomics model. The pre-Radiomics model (train AUC: 0.93 ± 0.06; test AUC: 0.79) and delta-Radiomcis model (train AUC: 0.96 ± 0.03; test AUC: 0.83) all have high NCRT response prediction performance by LARC. Overall, the delta-Radiomics model was superior to the pre-Radiomics model.

Conclusion

MRI-based pre-Radiomics model and delta-Radiomics model all have good potential to predict the post-treatment response of LARC to NCRT. Delta-Radiomics analysis has a huge potential for clinical application in facilitating the provision of personalized therapy.

Role of Machine Learning in Precision Oncology: Applications in Gastrointestinal Cancers

Gastrointestinal (GI) cancers, consisting of a wide spectrum of pathologies, have become a prominent health issue globally. Despite medical imaging playing a crucial role in the clinical workflow of cancers, standard evaluation of different imaging modalities may provide limited information. Accurate tumor detection, characterization, and monitoring remain a challenge. Progress in quantitative imaging analysis techniques resulted in "radiomics", a promising methodical tool that helps to personalize diagnosis and treatment optimization. Radiomics, a sub-field of computer vision analysis, is a bourgeoning area of interest, especially in this era of precision medicine. In the field of oncology, radiomics has been described as a tool to aid in the diagnosis, classification, and categorization of malignancies and to predict outcomes using various endpoints. In addition, machine learning is a technique for analyzing and predicting by learning from sample data, finding patterns in it, and applying it to new data. Machine learning has been increasingly applied in this field, where it is being studied in image diagnosis. This review assesses the current landscape of radiomics and methodological processes in GI cancers (including gastric, colorectal, liver, pancreatic, neuroendocrine, GI stromal, and rectal cancers). We explain in a stepwise fashion the process from data acquisition and curation to segmentation and feature extraction. Furthermore, the applications of radiomics for diagnosis, staging, assessment of tumor prognosis and treatment response according to different GI cancer types are explored. Finally, we discussed the existing challenges and limitations of radiomics in abdominal cancers and investigate future opportunities.

Construction of machine learning-based models for cancer outcomes in low and lower-middle income countries: A scoping review

Background

The impact and utility of machine learning (ML)-based prediction tools for cancer outcomes including assistive diagnosis, risk stratification, and adjunctive decision-making have been largely described and realized in the high income and upper-middle-income countries. However, statistical projections have estimated higher cancer incidence and mortality risks in low and lower-middle-income countries (LLMICs). Therefore, this review aimed to evaluate the utilization, model construction methods, and degree of implementation of ML-based models for cancer outcomes in LLMICs.

Methods

PubMed/Medline, Scopus, and Web of Science databases were searched and articles describing the use of ML-based models for cancer among local populations in LLMICs between 2002 and 2022 were included. A total of 140 articles from 22,516 citations that met the eligibility criteria were included in this study.

Results

ML-based models from LLMICs were often based on traditional ML algorithms than deep or deep hybrid learning. We found that the construction of ML-based models was skewed to particular LLMICs such as India, Iran, Pakistan, and Egypt with a paucity of applications in sub-Saharan Africa. Moreover, models for breast, head and neck, and brain cancer outcomes were frequently explored. Many models were deemed suboptimal according to the Prediction model Risk of Bias Assessment tool (PROBAST) due to sample size constraints and technical flaws in ML modeling even though their performance accuracy ranged from 0.65 to 1.00. While the development and internal validation were described for all models included (n=137), only 4.4% (6/137) have been validated in independent cohorts and 0.7% (1/137) have been assessed for clinical impact and efficacy.

Conclusion

Overall, the application of ML for modeling cancer outcomes in LLMICs is increasing. However, model development is largely unsatisfactory. We recommend model retraining using larger sample sizes, intensified external validation practices, and increased impact assessment studies using randomized controlled trial designs

Systematic review registration

https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=308345, identifier CRD42022308345.

Application of Radiomics in Predicting Treatment Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: Strategies and Challenges

Neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision is the standard treatment for locally advanced rectal cancer (LARC). A noninvasive preoperative prediction method should greatly assist in the evaluation of response to nCRT and for the development of a personalized strategy for patients with LARC. Assessment of nCRT relies on imaging and radiomics can extract valuable quantitative data from medical images. In this review, we examined the status of radiomic application for assessing response to nCRT in patients with LARC and indicated a potential direction for future research.

CT-based radiomics signature analysis for evaluation of response to induction chemotherapy and progression-free survival in locally advanced hypopharyngeal carcinoma

OBJECTIVES

To establish and validate a CT radiomics model for prediction of induction chemotherapy (IC) response and progression-free survival (PFS) among patients with locally advanced hypopharyngeal carcinoma (LAHC).

METHODS

One hundred twelve patients with LAHC (78 in training cohort and 34 in validation cohort) who underwent contrast-enhanced CT (CECT) scans prior to IC were enrolled. Least absolute shrinkage and selection operator (LASSO) was used to select the crucial radiomic features in the training cohort. Radiomics signature and clinical data were used to build a radiomics nomogram to predict individual response to IC. Kaplan-Meier analysis and log-rank test were used to evaluate ability of radiomics signature in progression-free survival risk stratification.

RESULTS

The radiomics signature consisted of 6 selected features from the arterial and venous phases of CECT images and demonstrated good performance in predicting the IC response in both two cohorts. The radiomics nomogram showed good discriminative performance, and the C-index of nomogram was 0.899 (95% confidence interval (CI), 0.831-0.967) and 0.775 (95% CI, 0.591-0.959) in the training and validation cohorts, respectively. Survival analysis indicated that low-risk and high-risk groups defined by the value of radiomics signature had significant difference in PFS (3-year PFS 66.4% vs 29.7%, p < 0.001).

CONCLUSIONS

Multiparametric CT-based radiomics model could be useful for predicting treatment response and PFS in patients with LAHC who underwent IC.

KEY POINTS

• CT radiomics can predict IC response and progression-free survival in hypopharyngeal carcinoma. • We combined significant radiomics signature with clinical predictors to establish a nomogram to predict individual response to IC. • Radiomics signature could divide patients into the high-risk and low-risk groups based on the PFS.

A Tumoral and Peritumoral CT-Based Radiomics and Machine Learning Approach to Predict the Microsatellite Instability of Rectal Carcinoma

Objective

To predict the status of microsatellite instability (MSI) of rectal carcinoma (RC) using different machine learning algorithms based on tumoral and peritumoral radiomics combined with clinicopathological characteristics.

Methods

There were 497 RC patients enrolled in this retrospective study. The tumoral and peritumoral CT-based radiomic features were calculated after tumor segmentation. The radiomic features from two radiologists were compared by way of inter-observer correlation coefficient (ICC). After methods of variance, correlation, and dimension reduction, six machine learning algorithms of logistic regression (LR), Bayes, support vector machine, random forest, k-nearest neighbor, and decision tree were conducted to develop models for predicting MSI status of RC. The relative standard deviation (RSD) was quantified. The radiomics and significant clinicopathological variables constituted the radiomics-clinicopathological nomogram. The receiver operator curve (ROC) was made by DeLong test, and the area under curve (AUC) with 95% confidence interval (95% CI) was calculated to evaluate the performance of the model.

Results

The venous phase of CT examination was selected for further analysis because the proportion of radiomic features with ICC greater than 0.75 was higher. The tumoral and peritumoral model by LR algorithm (M-LR) with minimal RSD showed good performance in predicting MSI status of RC with the AUCs of 0.817 and 0.726 in the training and validation set. The radiomic-clinicopathological nomogram performed better in both the training and validation set with AUCs of 0.843 and 0.737.

Conclusion

The radiomics-clinicopathological nomogram demonstrated better predictive performance in evaluating the MSI status of RC.

Radiomics-guided radiation therapy: opportunities and challenges

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

Ability of Delta Radiomics to Predict a Complete Pathological Response in Patients with Loco-Regional Rectal Cancer Addressed to Neoadjuvant Chemo-Radiation and Surgery

Simple Summary

The present study aimed to investigate the possible use of MRI delta texture analysis (D-TA) in order to predict the extent of pathological response in patients with locally advanced rectal cancer addressed to neoadjuvant chemo-radiotherapy (C-RT) followed by surgery. We found that D-TA may really predict the frequency of pCR in this patient setting and, thus, it may be investigated as a potential item to identify candidate patients who may benefit from an aggressive radical surgery.

Abstract

We performed a pilot study to evaluate the use of MRI delta texture analysis (D-TA) as a methodological item able to predict the frequency of complete pathological responses and, consequently, the outcome of patients with locally advanced rectal cancer addressed to neoadjuvant chemoradiotherapy (C-RT) and subsequently, to radical surgery. In particular, we carried out a retrospective analysis including 100 patients with locally advanced rectal adenocarcinoma who received C-RT and then radical surgery in three different oncological institutions between January 2013 and December 2019. Our experimental design was focused on the evaluation of the gross tumor volume (GTV) at baseline and after C-RT by means of MRI, which was contoured on T2, DWI, and ADC sequences. Multiple texture parameters were extracted by using a LifeX Software, while D-TA was calculated as percentage of variations in the two time points. Both univariate and multivariate analysis (logistic regression) were, therefore, carried out in order to correlate the above-mentioned TA parameters with the frequency of pathological responses in the examined patients’ population focusing on the detection of complete pathological response (pCR, with no viable cancer cells: TRG 1) as main statistical endpoint. ROC curves were performed on three different datasets considering that on the 21 patients, only 21% achieved an actual pCR. In our training dataset series, pCR frequency significantly correlated with ADC GLCM-Entropy only, when univariate and binary logistic analysis were performed (AUC for pCR was 0.87). A confirmative binary logistic regression analysis was then repeated in the two remaining validation datasets (AUC for pCR was 0.92 and 0.88, respectively). Overall, these results support the hypothesis that D-TA may have a significant predictive value in detecting the occurrence of pCR in our patient series. If confirmed in prospective and multicenter trials, these results may have a critical role in the selection of patients with locally advanced rectal cancer who may benefit form radical surgery after neoadjuvant chemoradiotherapy.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients

BACKGROUND

We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients.

METHODS

Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported.

RESULTS

In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance.

CONCLUSION

Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.

Threat Matrix: A Fast Algorithm for Human–Machine Chinese Ludo Gaming

Chinese Ludo, also known as Aeroplan Chess, has been a very popular board game for several decades. However, there is no mature algorithm existing for human–machine gambling. The major challenge is the high randomness of the dice rolls, where the algorithm must ensure that the machine is smarter than a human in order to guarantee that the owner of the game machines makes a profit. This paper presents a fast Chinese Ludo algorithm (named “Threat Matrix”) that we have recently developed. Unlike from most chess programs, which rely on high performance computing machines, the evaluation function in our program is only a linear sum of four factors. For fast and low-cost computation, we innovatively construct the concept of the threat matrix, by which we can easily obtain the threat between any two dice on any two positions. The threat matrix approach greatly reduces the required amount of calculations, enabling the program to run on a 32-bit 80 × 86 SCM with a 100 MHz CPU while supporting a recursive algorithms to search plies. Statistics compiled from matches against human game players show that our threat matrix has an average win rate of 92% with no time limit, 95% with a time limit of 10 s, and 98% with a time limit of 5 s. Furthermore, the threat matrix can reduce the computation cost by nearly 90% compared to real-time computing; memory consumption drops and is stable, which increases the evaluation speed by 58% compared to real-time computing.

Prediction of Response to Induction Chemotherapy Plus Concurrent Chemoradiotherapy for Nasopharyngeal Carcinoma Based on MRI Radiomics and Delta Radiomics: A Two-Center Retrospective Study

Objective

We aimed to establish an MRI radiomics model and a Delta radiomics model to predict tumor retraction after induction chemotherapy (IC) combined with concurrent chemoradiotherapy (CCRT) for primary nasopharyngeal carcinoma (NPC) in non-endemic areas and to validate its efficacy.

Methods

A total of 272 patients (155 in the training set, 66 in the internal validation set, and 51 in the external validation set) with biopsy pathologically confirmed primary NPC who were screened for pretreatment MRI were retrospectively collected. The NPC tumor was delineated as a region of interest in the two sequenced images of MRI before treatment and after IC, followed by radiomics feature extraction. With the use of maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithms, logistic regression was performed to establish pretreatment MRI radiomics and pre- and post-IC Delta radiomics models. The optimal Youden’s index was taken; the receiver operating characteristic (ROC) curve, calibration curve, and decision curve were drawn to evaluate the predictive efficacy of different models.

Results

Seven optimal feature subsets were selected from the pretreatment MRI radiomics model, and twelve optimal subsets were selected from the Delta radiomics model. The area under the ROC curve, accuracy, sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV) of the MRI radiomics model were 0.865, 0.827, 0.837, 0.813, 0.776, and 0.865, respectively; the corresponding indicators of the Delta radiomics model were 0.941, 0.883, 0.793, 0.968, 0.833, and 0.958, respectively.

Conclusion

The pretreatment MRI radiomics model and pre- and post-IC Delta radiomics models could predict the IC-CCRT response of NPC in non-epidemic areas.

Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation

We evaluate radiomic phenotypes derived from CT scans as early predictors of overall survival (OS) after chemoradiation in stage III primary lung adenocarcinoma. We retrospectively analyzed 110 thoracic CT scans acquired between April 2012-October 2018. Patients received a median radiation dose of 66.6 Gy at 1.8 Gy/fraction delivered with proton (55.5%) and photon (44.5%) beam treatment, as well as concurrent chemotherapy (89%) with carboplatin-based (55.5%) and cisplatin-based (36.4%) doublets. A total of 56 death events were recorded. Using manual tumor segmentations, 107 radiomic features were extracted. Feature harmonization using ComBat was performed to mitigate image heterogeneity due to the presence or lack of intravenous contrast material and variability in CT scanner vendors. A binary radiomic phenotype to predict OS was derived through the unsupervised hierarchical clustering of the first principal components explaining 85% of the variance of the radiomic features. C-scores and likelihood ratio tests (LRT) were used to compare the performance of a baseline Cox model based on ECOG status and age, with a model integrating the radiomic phenotype with such clinical predictors. The model integrating the radiomic phenotype (C-score = 0.69, 95% CI = (0.62, 0.77)) significantly improved (p<0.005) upon the baseline model (C-score = 0.65, CI = (0.57, 0.73)). Our results suggest that harmonized radiomic phenotypes can significantly improve OS prediction in stage III NSCLC after chemoradiation.

Non-contrast Cine Cardiac Magnetic Resonance image radiomics features and machine learning algorithms for myocardial infarction detection

OBJECTIVE

Robust differentiation between infarcted and normal tissue is important for clinical diagnosis and precision medicine. The aim of this work is to investigate the radiomic features and to develop a machine learning algorithm for the differentiation of myocardial infarction (MI) and viable tissues/normal cases in the left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.

METHODS

Seventy-two patients (52 with MI and 20 healthy control patients) were enrolled in this study. MR imaging was performed on a 1.5 T MRI using the following parameters: TR = 43.35 ms, TE = 1.22 ms, flip angle = 65°, temporal resolution of 30-40 ms. N4 bias field correction algorithm was applied to correct the inhomogeneity of images. All images were segmented and verified simultaneously by two cardiac imaging experts in consensus. Subsequently, features extraction was performed within the whole left ventricular myocardium (3D volume) in end-diastolic volume phase. Re-sampling to 1 × 1 × 1 mm³ voxels was performed for MR images. All intensities within the VOI of MR images were discretized to 64 bins. Radiomic features were normalized to obtain Z-scores, followed by Student's t-test statistical analysis for comparison. A p-value < 0.05 was used as a threshold for statistically significant differences and false discovery rate (FDR) correction performed to report q-value (FDR adjusted p-value). The extracted features were ranked using the MSVM-RFE algorithm, then Spearman correlation between features was performed to eliminate highly correlated features (R2 > 0.80). Ten different machine learning algorithms were used for classification and different metrics used for evaluation and various parameters used for models' evaluation.

RESULTS

In univariate analysis, the highest area under the curve (AUC) of receiver operating characteristic (ROC) value was achieved for the Maximum 2D diameter slice (M2DS) shape feature (AUC = 0.88, q-value = 1.02E-7), while the average of univariate AUCs was 0.62 ± 0.08. In multivariate analysis, Logistic Regression (AUC = 0.93 ± 0.03, Accuracy = 0.86 ± 0.05, Recall = 0.87 ± 0.1, Precision = 0.93 ± 0.03 and F1 Score = 0.90 ± 0.04) and SVM (AUC = 0.92 ± 0.05, Accuracy = 0.85 ± 0.04, Recall = 0.92 ± 0.01, Precision = 0.88 ± 0.04 and F1 Score = 0.90 ± 0.02) yielded optimal performance as the best machine learning algorithm for this radiomics analysis.

CONCLUSION

This study demonstrated that using radiomics analysis on non-contrast Cine-CMR images enables to accurately detect MI, which could potentially be used as an alternative diagnostic method for Late Gadolinium Enhancement Cardiac Magnetic Resonance (LGE-CMR).

Delta radiomics: a systematic review

BACKGROUND

Radiomics can provide quantitative features from medical imaging that can be correlated with various biological features and clinical endpoints. Delta radiomics, on the other hand, consists in the analysis of feature variation at different acquisition time points, usually before and after therapy. The aim of this study was to provide a systematic review of the different delta radiomics approaches.

METHODS

Eligible articles were searched in Embase, PubMed, and ScienceDirect using a search string that included free text and/or Medical Subject Headings (MeSH) with three key search terms: "radiomics", "texture", and "delta". Studies were analysed using QUADAS-2 and the RQS tool.

RESULTS

Forty-eight studies were finally included. The studies were divided into preclinical/methodological (five studies, 10.4%); rectal cancer (six studies, 12.5%); lung cancer (twelve studies, 25%); sarcoma (five studies, 10.4%); prostate cancer (three studies, 6.3%), head and neck cancer (six studies, 12.5%); gastrointestinal malignancies excluding rectum (seven studies, 14.6%), and other disease sites (four studies, 8.3%). The median RQS of all studies was 25% (mean 21% ± 12%), with 13 studies (30.2%) achieving a quality score < 10% and 22 studies (51.2%) < 25%.

CONCLUSIONS

Delta radiomics shows potential benefit for several clinical endpoints in oncology (differential diagnosis, prognosis and prediction of treatment response, and evaluation of side effects). Nevertheless, the studies included in this systematic review suffer from the bias of overall low quality, so that the conclusions are currently heterogeneous, not robust, and not replicable. Further research with prospective and multicentre studies is needed for the clinical validation of delta radiomics approaches.

AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging:: Towards Radiophenomics

Artificial intelligence (AI) techniques have significant potential to enable effective, robust, and automated image phenotyping including the identification of subtle patterns. AI-based detection searches the image space to find the regions of interest based on patterns and features. There is a spectrum of tumor histologies from benign to malignant that can be identified by AI-based classification approaches using image features. The extraction of minable information from images gives way to the field of "radiomics" and can be explored via explicit (handcrafted/engineered) and deep radiomics frameworks. Radiomics analysis has the potential to be used as a noninvasive technique for the accurate characterization of tumors to improve diagnosis and treatment monitoring. This work reviews AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks. We also discuss needed efforts to enable the translation of AI techniques to routine clinical workflows, and potential improvements and complementary techniques such as the use of natural language processing on electronic health records and neuro-symbolic AI techniques.

Overall Survival Prediction in Renal Cell Carcinoma Patients Using Computed Tomography Radiomic and Clinical Information

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p < 0.002, < 0.02, and < 0.018, respectively). The most significant predictors of OS among the selected radiomic features were flatness, area density, and median (p < 0.02, < 0.02, and < 0.05, respectively). Along with important clinical features, such as tumor heterogeneity and tumor grade, imaging biomarkers such as tumor flatness, area density, and median are significantly correlated with OS of RCC patients.

Non-small cell lung carcinoma histopathological subtype phenotyping using high-dimensional multinomial multiclass CT radiomics signature

OBJECTIVE

The aim of this study was to identify the most important features and assess their discriminative power in the classification of the subtypes of NSCLC.

METHODS

This study involved 354 pathologically proven NSCLC patients including 134 squamous cell carcinoma (SCC), 110 large cell carcinoma (LCC), 62 not other specified (NOS), and 48 adenocarcinoma (ADC). In total, 1433 radiomics features were extracted from 3D volumes of interest drawn on the malignant lesion identified on CT images. Wrapper algorithm and multivariate adaptive regression splines were implemented to identify the most relevant/discriminative features. A multivariable multinomial logistic regression was employed with 1000 bootstrapping samples based on the selected features to classify four main subtypes of NSCLC.

RESULTS

The results revealed that the texture features, specifically gray level size zone matrix features (GLSZM), were the significant indicators of NSCLC subtypes. The optimized classifier achieved an average precision, recall, F1-score, and accuracy of 0.710, 0.703, 0.706, and 0.865, respectively, based on the selected features by the wrapper algorithm.

CONCLUSIONS

Our CT radiomics approach demonstrated impressive potential for the classification of the four main histological subtypes of NSCLC, It is anticipated that CT radiomics could be useful in treatment planning and precision medicine.

A clinical-radiomics model incorporating T2-weighted and diffusion-weighted magnetic resonance images predicts the existence of lymphovascular invasion / perineural invasion in patients with colorectal cancer

PURPOSE

Lymphovascular invasion (LVI) and perineural invasion (PNI) are independent prognostic factors in patients with colorectal cancer (CRC). In this study, we aimed to develop and validate a preoperative predictive model based on high-throughput radiomic features and clinical factors for accurate prediction of LVI/PNI in these patients.

METHODS

Two hundred and sixty-three patients who underwent colorectal resection for histologically confirmed CRC between 1 February 2011 and 30 June 2020 were retrospectively enrolled. Between 1 February 2011 and 30 September 2018, 213 patients were randomly divided into a training cohort (n = 149) and a validation cohort (n = 64) by a ratio of 7:3. We used a 10000-iteration bootstrap analysis to estimate the prediction error and confidence interval for two cohorts. The independent test cohort consisted of 50 patients between 1 October 2018 and 30 June 2020. Regions of interest (ROIs) were manually delineated in high-resolution T2-weighted and diffusion-weighted images using ITK-SNAP software on each CRC tumor slice. In total, 3356 radiomic features were extracted from each ROI. Next, we used the maximum relevance minimum redundancy and least absolute shrinkage and selection operator algorithms to select the strongest of these features to establish a clinical-radiomics model for predicting LVI/PNI. Receiver-operating characteristic and calibration curves were then plotted to evaluate the predictive performance of the model in the training, validation, and independent test cohorts.

RESULTS

A multiparametric clinical-radiomics model combining MRI-reported extramural vascular invasion (EMVI) status and a Radiomics score for the LVI/PNI estimation was established. This model had significant predictive power in the training cohort (area under the curve [AUC] 0.91; 95% confidence interval [CI]: 0.85-0.97), validation cohort (AUC: 0.88; 95% CI: 0.79-89), and independent test cohorts (AUC 0.83, 95% CI 0.72-0.95). The model performed well in the independent test cohort with sensitivity of 0.818, specificity of 0.714, and accuracy of 0.760. Calibration curve and decision curve analysis demonstrated clinical benefits.

CONCLUSION

Multiparametric clinical-radiomics models can accurately predict LVI/PNI in patients with CRC. Our model has predictive ability that should improve preoperative diagnostic performance and allow more individualized treatment decisions.