Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer

Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis

OBJECTIVES

To investigate the usefulness of machine learning (ML) models using pretreatment 18F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS).

MATERIALS AND METHODS

This retrospective study included 47 patients with CS who underwent 18F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 18F-FDG-PET-based radiomic features and the visibility of right ventricle 18F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances.

RESULTS

Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm.

CONCLUSION

ML analyses using 18F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

Retrospective analysis of the 18F-FDG PET/CT cutoff value for metabolic parameters was performed as a prediction model to evaluate risk factors for endometrial cancer

PURPOSE

The study retrospectively analyzed the accuracy and predictive ability of preoperative integrated whole-body 18F-FDG PET/CT for the assessment of high-risk factors in patients with endometrial carcinoma (EC).

MATERIALS AND METHODS

A total of 205 patients with endometrial cancer who underwent preoperative PET/CT at Shanghai General Hospital from January 2018 to December 2021 were retrospectively evaluated and last follow-up was June 2023. Our study evaluated the ability and optimal cutoff values of three metabolic and volumetric parameters-standardized uptake value (SUV), metabolic tumor volume (MTV) and total lesion glycolysis (TLG)-to predict deep myometrial invasion (DMI), endocervical stroma invasion (ESI) and lymph node metastases (LNM) in endometrial cancer. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of PET/CT were used to assess the diagnostic performance for the prediction.

RESULTS

Our study demonstrated a significant relationship between SUVmax (11.29, 17.38, 9.47), SUVmean (5.20, 6.12, 4.49), MTV (38.15, 36.28, 33.79 ml), and TLG (199.30, 225.10, 156.40 g) on PET/CT and histologically confirmed DMI, ESI and LNM in endometrial carcinoma (EC), with sensitivity, specificity, accuracy, PPV, and NPV of 100%/100%/100%, 96.53%/98.89%/87.14%, 97.56%/99.02%/91.22%, 92.42%/92.85%/78.31%, and 100%/100%/100%, respectively. Our study showed a risk model based on optimal cutoff values for MTV and TLG of 19.6 ml/126.3 g, 20.54 ml/84.80 g and 24 ml/49.83 g to preoperatively predict DMI, ESI, and LNM, respectively, in endometrial carcinoma. The 4-year OS (HR) for Stage IA, IB, II, III and IV according to 2009 FIGO was 98.00% (0.22), 95.20% (0.04), 83.90% (0.18), 90.50% (0.09) and 60% (0.51). Accordingly, estimated 4-year DFS (HR) for the stage IA-III was 98% (0.02), 95.20% (0.05), 76.90% (0.27) and 76.30% (0.35), all the patients in stage IV occurred recurrence and progression.

CONCLUSION

The present study showed patients with MTV > = 19.6 ml of MI and PET- positive LN with MTV cutoff > = 24 ml tended to predict poor OS and PFS in endometrial carcinoma. The cutoff of MTV and TLG in PET/CT assessment could be an independent prognostic factors to predict aggressive forms of EC.

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

AIM

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

METHODS

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

RESULTS

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

CONCLUSION

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

Prognostic 18F-FDG Radiomic Features in Advanced High-Grade Serous Ovarian Cancer

High-grade serous ovarian cancer (HGSOC) is an aggressive disease with different clinical outcomes and poor prognosis. This could be due to tumor heterogeneity. The 18F-FDG PET radiomic parameters permit addressing tumor heterogeneity. Nevertheless, this has been not well studied in ovarian cancer. The aim of our work was to assess the prognostic value of pretreatment 18F-FDG PET radiomic features in patients with HGSOC. A review of 36 patients diagnosed with advanced HGSOC between 2016 and 2020 in our center was performed. Radiomic features were obtained from pretreatment 18F-FDGPET. Disease-free survival (DFS) and overall survival (OS) were calculated. Optimal cutoff values with receiver operating characteristic curve/median values were used. A correlation between radiomic features and DFS/OS was made. The mean DFS was 19.6 months and OS was 37.1 months. Total Lesion Glycolysis (TLG), GLSZM_ Zone Size Non-Uniformity (GLSZM_ZSNU), and GLRLM_Run Length Non-Uniformity (GLRLM_RLNU) were significantly associated with DFS. The survival-curves analysis showed a significant difference of DSF in patients with GLRLM_RLNU > 7388.3 versus patients with lower values (19.7 months vs. 31.7 months, p = 0.035), maintaining signification in the multivariate analysis (p = 0.048). Moreover, Intensity-based Kurtosis was associated with OS (p = 0.027). Pretreatment 18F-FDG PET radiomic features GLRLM_RLNU, GLSZM_ZSNU, and Kurtosis may have prognostic value in patients with advanced HGSOC.

An ultrasound-based radiomics model for survival prediction in patients with endometrial cancer

PURPOSE

To establish a nomogram integrating radiomics features based on ultrasound images and clinical parameters for predicting the prognosis of patients with endometrial cancer (EC).

MATERIALS AND METHODS

A total of 175 eligible patients with ECs were enrolled in our study between January 2011 and April 2018. They were divided into a training cohort (n = 122) and a validation cohort (n = 53). Least absolute shrinkage and selection operator (LASSO) regression were applied for selection of key features, and a radiomics score (rad-score) was calculated. Patients were stratified into high risk and low-risk groups according to the rad-score. Univariate and multivariable COX regression analysis was used to select independent clinical parameters for disease-free survival (DFS). A combined model based on radiomics features and clinical parameters was ultimately established, and the performance was quantified with respect to discrimination and calibration.

RESULTS

Nine features were selected from 1130 features using LASSO regression in the training cohort, which yielded an area under the curve (AUC) of 0.823 and 0.792 to predict DFS in the training and validation cohorts, respectively. Patients with a higher rad-score were significantly associated with worse DFS. The combined nomogram, which was composed of clinically significant variables and radiomics features, showed a calibration and favorable performance for DFS prediction (AUC 0.893 and 0.885 in the training and validation cohorts, respectively).

CONCLUSION

The combined nomogram could be used as a tool in predicting DFS and may assist individualized decision making and clinical treatment.

Application of Machine Learning Analyses Using Clinical and [18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer

PURPOSE

To develop and identify machine learning (ML) models using pretreatment clinical and 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic characteristics to predict disease recurrences in patients with breast cancers who underwent surgery.

PROCEDURES

This retrospective study included 112 patients with 118 breast cancer lesions who underwent [18F]-FDG-PET/ X-ray computed tomography (CT) preoperatively, and these lesions were assigned to training (n=95) and testing (n=23) cohorts. A total of 12 clinical and 40 [18F]-FDG-PET-based radiomic characteristics were used to predict recurrences using 7 different ML algorithms, namely, decision tree, random forest (RF), neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine (SVM) with a 10-fold cross-validation and synthetic minority over-sampling technique. Three different ML models were created using clinical characteristics (clinical ML models), radiomic characteristics (radiomic ML models), and both clinical and radiomic characteristics (combined ML models). Each ML model was constructed using the top ten characteristics ranked by the decrease in Gini impurity. The areas under ROC curves (AUCs) and accuracies were used to compare predictive performances.

RESULTS

In training cohorts, all 7 ML algorithms except for logistic regression algorithm in the radiomics ML model (AUC = 0.760) achieved AUC values of >0.80 for predicting recurrences with clinical (range, 0.892-0.999), radiomic (range, 0.809-0.984), and combined (range, 0.897-0.999) ML models. In testing cohorts, the RF algorithm of combined ML model achieved the highest AUC and accuracy (95.7% (22/23)) with similar classification performance between training and testing cohorts (AUC: training cohort, 0.999; testing cohort, 0.992). The important characteristics for modeling process of this RF algorithm were radiomic GLZLM_ZLNU and AJCC stage.

CONCLUSIONS

ML analyses using both clinical and [18F]-FDG-PET-based radiomic characteristics may be useful for predicting recurrence in patients with breast cancers who underwent surgery.

A Radiomic-Based Machine Learning Model Predicts Endometrial Cancer Recurrence Using Preoperative CT Radiomic Features: A Pilot Study

BACKGROUND

Current prognostic models lack the use of pre-operative CT images to predict recurrence in endometrial cancer (EC) patients. Our study aimed to investigate the potential of radiomic features extracted from pre-surgical CT scans to accurately predict disease-free survival (DFS) among EC patients.

METHODS

Contrast-Enhanced CT (CE-CT) scans from 81 EC cases were used to extract the radiomic features from semi-automatically contoured volumes of interest. We employed a 10-fold cross-validation approach with a 6:4 training to test set and utilized data augmentation and balancing techniques. Univariate analysis was applied for feature reduction leading to the development of three distinct machine learning (ML) models for the prediction of DFS: LASSO-Cox, CoxBoost and Random Forest (RFsrc).

RESULTS

In the training set, the ML models demonstrated AUCs ranging from 0.92 to 0.93, sensitivities from 0.96 to 1.00 and specificities from 0.77 to 0.89. In the test set, AUCs ranged from 0.86 to 0.90, sensitivities from 0.89 to 1.00 and specificities from 0.73 to 0.90. Patients classified as having a high recurrence risk prediction by ML models exhibited significantly worse DSF (p-value < 0.001) across all models.

CONCLUSIONS

Our findings demonstrate the potential of radiomics in predicting EC recurrence. While further validation studies are needed, our results underscore the promising role of radiomics in forecasting EC outcomes.

The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer

OBJECTIVE

To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer.

METHODS

This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index).

RESULTS

Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808).

CONCLUSION

ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer.

ADVANCES IN KNOWLEDGE

ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.

A systematic review and meta-analysis of predictive and prognostic models for outcome prediction using positron emission tomography radiomics in head and neck squamous cell carcinoma patients

BACKGROUND

Positron emission tomography (PET) images of head and neck squamous cell carcinoma (HNSCC) patients can assess the functional and biochemical processes at cellular levels. Therefore, PET radiomics-based prediction and prognostic models have the potentials to understand tumour heterogeneity and assist clinicians with diagnosis, prognosis and management of the disease. We conducted a systematic review of published modelling information to evaluate the usefulness of PET radiomics in the prediction and prognosis of HNSCC patients.

METHODS

We searched bibliographic databases (MEDLINE, Embase, Web of Science) from 2010 to 2021 and considered 31 studies with pre-defined inclusion criteria. We followed the CHARMS checklist for data extraction and performed quality assessment using the PROBAST tool. We conducted a meta-analysis to estimate the accuracy of the prediction and prognostic models using the diagnostic odds ratio (DOR) and average C-statistic, respectively.

RESULTS

Manual segmentation method followed by 40% of the maximum standardised uptake value (SUVmax ) thresholding is a commonly used approach. The area under the receiver operating curves of externally validated prediction models ranged between 0.60-0.87, 0.65-0.86 and 0.62-0.75 for overall survival, distant metastasis and recurrence, respectively. Most studies highlighted an overall high risk of bias (outcome definition, statistical methodologies and external validation of models) and high unclear concern in terms of applicability. The meta-analysis showed the estimated pooled DOR of 6.75 (95% CI: 4.45, 10.23) for prediction models and the C-statistic of 0.71 (95% CI: 0.67, 0.74) for prognostic models.

CONCLUSIONS

Both prediction and prognostic models using clinical variables and PET radiomics demonstrated reliable accuracy for detecting adverse outcomes in HNSCC, suggesting the prospect of PET radiomics in clinical settings for diagnosis, prognosis and management of HNSCC patients. Future studies of prediction and prognostic models should emphasise the quality of reporting, external model validation, generalisability to real clinical scenarios and enhanced reproducibility of results.

Magnetic resonance imaging-radiomics in endometrial cancer: a systematic review and meta-analysis

OBJECTIVE

Endometrial carcinoma is the most common gynecological tumor in developed countries. Clinicopathological factors and molecular subtypes are used to stratify the risk of recurrence and to tailor adjuvant treatment. The present study aimed to assess the role of radiomics analysis in pre-operatively predicting molecular or clinicopathological prognostic factors in patients with endometrial carcinoma.

METHODS

Literature was searched for publications reporting radiomics analysis in assessing diagnostic performance of MRI for different outcomes. Diagnostic accuracy performance of risk prediction models was pooled using the metandi command in Stata.

RESULTS

A search of MEDLINE (PubMed) resulted in 153 relevant articles. Fifteen articles met the inclusion criteria, for a total of 3608 patients. MRI showed pooled sensitivity and specificity 0.785 and 0.814, respectively, in predicting high-grade endometrial carcinoma, deep myometrial invasion (pooled sensitivity and specificity 0.743 and 0.816, respectively), lymphovascular space invasion (pooled sensitivity and specificity 0.656 and 0.753, respectively), and nodal metastasis (pooled sensitivity and specificity 0.831 and 0.736, respectively).

CONCLUSIONS

Pre-operative MRI-radiomics analyses in patients with endometrial carcinoma is a good predictor of tumor grading, deep myometrial invasion, lymphovascular space invasion, and nodal metastasis.

The Usefulness of Machine Learning-Based Evaluation of Clinical and Pretreatment [18F]-FDG-PET/CT Radiomic Features for Predicting Prognosis in Hypopharyngeal Cancer

PURPOSE

To examine whether the machine learning (ML) analyses using clinical and pretreatment 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography ([¹⁸F]-FDG-PET)-based radiomic features were useful for predicting prognosis in patients with hypopharyngeal cancer.

PROCEDURES

This retrospective study included 100 patients with hypopharyngeal cancer who underwent [¹⁸F]-FDG-PET/X-ray computed tomography (CT) before treatment, and these patients were allocated to the training (n=80) and validation (n=20) cohorts. Eight clinical (age, sex, histology, T stage, N stage, M stage, UICC stage, and treatment) and 40 [¹⁸F]-FDG-PET-based radiomic features were used to predict disease progression. A feature reduction procedure based on the decrease of the Gini impurity was applied. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were compared using the area under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis.

RESULTS

The five most important features for predicting disease progression were UICC stage, N stage, gray level co-occurrence matrix entropy (GLCM_Entropy), gray level run length matrix run length non-uniformity (GLRLM_RLNU), and T stage. Patients who experienced disease progression displayed significantly higher UICC stage, N stage, GLCM_Entropy, GLRLM_RLNU, and T stage than those without progression (each, p<0.001). In both cohorts, the logistic regression model constructed by these 5 features was the best performing classifier (training: AUC=0.860, accuracy=0.800; validation: AUC=0.803, accuracy=0.700). In the logistic regression model, 5-year PFS was significantly higher in patients with predicted non-progression than those with predicted progression (75.8% vs. 8.3%, p<0.001), and this model was only the independent factor for PFS in multivariate analysis (hazard ratio = 3.22; 95% confidence interval = 1.03-10.11; p=0.045).

CONCLUSIONS

The logistic regression model constructed by UICC, T and N stages and pretreatment [¹⁸F]-FDG-PET-based radiomic features, GLCM_Entropy, and GLRLM_RLNU may be the most important predictor of prognosis in patients with hypopharyngeal cancer.

Prognostic analysis of curatively resected pancreatic cancer using harmonized positron emission tomography radiomic features

BACKGROUND

Texture features reflecting tumour heterogeneity enable us to investigate prognostic factors. The R package ComBat can harmonize the quantitative texture features among several positron emission tomography (PET) scanners. We aimed to identify prognostic factors among harmonized PET radiomic features and clinical information from pancreatic cancer patients who underwent curative surgery.

METHODS

Fifty-eight patients underwent preoperative enhanced dynamic computed tomography (CT) scanning and fluorodeoxyglucose PET/CT using four PET scanners. Using LIFEx software, we measured PET radiomic parameters including texture features with higher order and harmonized these PET parameters. For progression-free survival (PFS) and overall survival (OS), we evaluated clinical information, including age, TNM stage, and neural invasion, and the harmonized PET radiomic features based on univariate Cox proportional hazard regression. Next, we analysed the prognostic indices by multivariate Cox proportional hazard regression (1) by using either significant (p < 0.05) or borderline significant (p = 0.05-0.10) indices in the univariate analysis (first multivariate analysis) or (2) by using the selected features with random forest algorithms (second multivariate analysis). Finally, we checked these multivariate results by log-rank test.

RESULTS

Regarding the first multivariate analysis for PFS after univariate analysis, age was the significant prognostic factor (p = 0.020), and MTV and GLCM contrast were borderline significant (p = 0.051 and 0.075, respectively). Regarding the first multivariate analysis of OS, neural invasion, Shape sphericity and GLZLM LZLGE were significant (p = 0.019, 0.042 and 0.0076). In the second multivariate analysis, only MTV was significant (p = 0.046) for PFS, whereas GLZLM LZLGE was significant (p = 0.047), and Shape sphericity was borderline significant (p = 0.088) for OS. In the log-rank test, age, MTV and GLCM contrast were borderline significant for PFS (p = 0.08, 0.06 and 0.07, respectively), whereas neural invasion and Shape sphericity were significant (p = 0.03 and 0.04, respectively), and GLZLM LZLGE was borderline significant for OS (p = 0.08).

CONCLUSIONS

Other than the clinical factors, MTV and GLCM contrast for PFS and Shape sphericity and GLZLM LZLGE for OS may be prognostic PET parameters. A prospective multicentre study with a larger sample size may be warranted.

Gynecological cancer prognosis using machine learning techniques: A systematic review of last three decades (1990–2022)

OBJECTIVE

Many Computer Aided Prognostic (CAP) systems based on machine learning techniques have been proposed in the field of oncology. The objective of this systematic review was to assess and critically appraise the methodologies and approaches used in predicting the prognosis of gynecological cancers using CAPs.

METHODS

Electronic databases were used to systematically search for studies utilizing machine learning methods in gynecological cancers. Study risk of bias (ROB) and applicability were assessed using the PROBAST tool. 139 studies met the inclusion criteria, of which 71 predicted outcomes for ovarian cancer patients, 41 predicted outcomes for cervical cancer patients, 28 predicted outcomes for uterine cancer patients, and 2 predicted outcomes for gynecological malignancies broadly.

RESULTS

Random forest (22.30 %) and support vector machine (21.58 %) classifiers were used most commonly. Use of clinicopathological, genomic and radiomic data as predictors was observed in 48.20 %, 51.08 % and 17.27 % of studies, respectively, with some studies using multiple modalities. 21.58 % of studies were externally validated. Twenty-three individual studies compared ML and non-ML methods. Study quality was highly variable and methodologies, statistical reporting and outcome measures were inconsistent, preventing generalized commentary or meta-analysis of performance outcomes.

CONCLUSION

There is significant variability in model development when prognosticating gynecological malignancies with respect to variable selection, machine learning (ML) methods and endpoint selection. This heterogeneity prevents meta-analysis and conclusions regarding the superiority of ML methods. Furthermore, PROBAST-mediated ROB and applicability analysis demonstrates concern for the translatability of existing models. This review identifies ways that this can be improved upon in future works to develop robust, clinically translatable models within this promising field.

Role of Machine Learning (ML)-Based Classification Using Conventional 18F-FDG PET Parameters in Predicting Postsurgical Features of Endometrial Cancer Aggressiveness

PURPOSE

to investigate the preoperative role of ML-based classification using conventional ¹⁸F-FDG PET parameters and clinical data in predicting features of EC aggressiveness.

METHODS

retrospective study, including 123 EC patients who underwent ¹⁸F-FDG PET (2009-2021) for preoperative staging. Maximum standardized uptake value (SUVmax), SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were computed on the primary tumour. Age and BMI were collected. Histotype, myometrial invasion (MI), risk group, lymph-nodal involvement (LN), and p53 expression were retrieved from histology. The population was split into a train and a validation set (80-20%). The train set was used to select relevant parameters (Mann-Whitney U test; ROC analysis) and implement ML models, while the validation set was used to test prediction abilities.

RESULTS

on the validation set, the best accuracies obtained with individual parameters and ML were: 61% (TLG) and 87% (ML) for MI; 71% (SUVmax) and 79% (ML) for risk groups; 72% (TLG) and 83% (ML) for LN; 45% (SUVmax; SUVmean) and 73% (ML) for p53 expression.

CONCLUSIONS

ML-based classification using conventional ¹⁸F-FDG PET parameters and clinical data demonstrated ability to characterize the investigated features of EC aggressiveness, providing a non-invasive way to support preoperative stratification of EC patients.

An Applicable Machine Learning Model Based on Preoperative Examinations Predicts Histology, Stage, and Grade for Endometrial Cancer

Purpose

To build a machine learning model to predict histology (type I and type II), stage, and grade preoperatively for endometrial carcinoma to quickly give a diagnosis and assist in improving the accuracy of the diagnosis, which can help patients receive timely, appropriate, and effective treatment.

Materials and Methods

This study used a retrospective database of preoperative examinations (tumor markers, imaging, diagnostic curettage, etc.) in patients with endometrial carcinoma. Three algorithms (random forest, logistic regression, and deep neural network) were used to build models. The AUC and accuracy were calculated. Furthermore, the performance of machine learning models, doctors’ prediction, and doctors with the assistance of models were compared.

Results

A total of 329 patients were included in this study with 16 features (age, BMI, stage, grade, histology, etc.). A random forest algorithm had the highest AUC and Accuracy. For histology prediction, AUC and accuracy was 0.69 (95% CI=0.67-0.70) and 0.81 (95%CI=0.79-0.82). For stage they were 0.66 (95% CI=0.64-0.69) and 0.63 (95% CI=0.61-0.65) and for differentiation grade 0.64 (95% CI=0.63-0.65) and 0.43 (95% CI=0.41-0.44). The average accuracy of doctors for histology, stage, and grade was 0.86 (with AI) and 0.79 (without AI), 0.64 and 0.53, 0.5 and 0.45, respectively. The accuracy of doctors’ prediction with AI was higher than that of Random Forest alone and doctors’ prediction without AI.

Conclusion

A random forest model can predict histology, stage, and grade of endometrial cancer preoperatively and can help doctors in obtaining a better diagnosis and predictive results.

The efficacy of 18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors

OBJECTIVE

To examine whether the machine-learning approach using 18-fludeoxyglucose positron emission tomography (18F-FDG-PET)-based radiomic and deep-learning features is useful for predicting the pathological risk subtypes of thymic epithelial tumors (TETs).

METHODS

This retrospective study included 79 TET [27 low-risk thymomas (types A, AB and B1), 31 high-risk thymomas (types B2 and B3) and 21 thymic carcinomas] patients who underwent pre-therapeutic 18F-FDG-PET/CT. High-risk TETs (high-risk thymomas and thymic carcinomas) were 52 patients. The 107 PET-based radiomic features, including SUV-related parameters [maximum SUV (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG)] and 1024 deep-learning features extracted from the convolutional neural network were used to predict the pathological risk subtypes of TETs using six different machine-learning algorithms. The area under the curves (AUCs) were calculated to compare the predictive performances.

RESULTS

SUV-related parameters yielded the following AUCs for predicting thymic carcinomas: SUVmax 0.713, MTV 0.442, and TLG 0.479 or high-risk TETs: SUVmax 0.673, MTV 0.533, and TLG 0.539. The best-performing algorithm was the logistic regression model for predicting thymic carcinomas (AUC 0.900, accuracy 81.0%), and the random forest (RF) model for high-risk TETs (AUC 0.744, accuracy 72.2%). The AUC was significantly higher in the logistic regression model than three SUV-related parameters for predicting thymic carcinomas, and in the RF model than MTV and TLG for predicting high-risk TETs (each; p < 0.05).

CONCLUSION

18F-FDG-PET-based radiomic analysis using a machine-learning approach may be useful for predicting the pathological risk subtypes of TETs.

ADVANCES IN KNOWLEDGE

Machine-learning approach using 18F-FDG-PET-based radiomic features has the potential to predict the pathological risk subtypes of TETs.

Clinical parameters combined with radiomics features of PET/CT can predict recurrence in patients with high-risk pediatric neuroblastoma

Background

This retrospective study aimed to develop and validate a combined model based [¹⁸F]FDG PET/CT radiomics and clinical parameters for predicting recurrence in high-risk pediatric neuroblastoma patients.

Methods

Eighty-four high-risk neuroblastoma patients were retrospectively enrolled and divided into training and test sets according to the ratio of 3:2. [¹⁸F]FDG PET/CT images of the tumor were segmented by 3D Slicer software and the radiomics features were extracted. The effective features were selected by the least absolute shrinkage and selection operator to construct the radiomics score (Rad_score). And the radiomics model (R_model) was constructed based on Rad_score for prediction of recurrence. Then, univariate and multivariate analyses were used to screen out the independent clinical risk parameters and construct the clinical model (C_model). A combined model (RC_model) was developed based on the Rad_score and independent clinical risk parameters and presented as radiomics nomogram. The performance of the above three models was assessed by the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).

Results

Seven radiomics features were selected for building the R_model. The AUCs of the C_model in training and test sets were 0.744 (95% confidence interval [CI], 0.595–0.874) and 0.750 (95% CI, 0.577–0.904), respectively. The R_model yielded AUCs of 0.813 (95% CI, 0.685–0.916) and 0.869 (95% CI, 0.715–0.985) in the training and test sets, respectively. The RC_model demonstrated the largest AUCs of 0.889 (95% CI, 0.794–0.963) and 0.892 (95% CI, 0.758–0.992) in the training and test sets, respectively. DCA demonstrated that RC_model added more net benefits than either the C_model or the R_model for predicting recurrence in high-risk pediatric neuroblastoma.

Conclusions

The combined model performed well for predicting recurrence in high-risk pediatric neuroblastoma, which can facilitate disease follow-up and management in clinical practice.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers

The objective of this review was to summarize published radiomics studies dealing with infradiaphragmatic cancers, blood malignancies, melanoma, and musculoskeletal cancers, and assess their quality. PubMed database was searched from January 1990 to February 2022 for articles performing radiomics on PET imaging of at least 1 specified tumor type. Exclusion criteria includd: non-oncological studies; supradiaphragmatic tumors; reviews, comments, cases reports; phantom or animal studies; technical articles without a clinically oriented question; studies including <30 patients in the training cohort. The review database contained PMID, first author, year of publication, cancer type, number of patients, study design, independent validation cohort and objective. This database was completed twice by the same person; discrepant results were resolved by a third reading of the articles. A total of 162 studies met inclusion criteria; 61 (37.7%) studies included >100 patients, 13 (8.0%) were prospective and 61 (37.7%) used an independent validation set. The most represented cancers were esophagus, lymphoma, and cervical cancer (n = 24, n = 24 and n = 19 articles, respectively). Most studies focused on 18F-FDG, and prognostic and response to treatment objectives. Although radiomics and artificial intelligence are technically challenging, new contributions and guidelines help improving research quality over the years and pave the way toward personalized medicine.

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).

Outcome Prediction at Patient Level Derived from Pre-Treatment 18F-FDG PET Due to Machine Learning in Metastatic Melanoma Treated with Anti-PD1 Treatment

(1) Background: As outcome of patients with metastatic melanoma treated with anti-PD1 immunotherapy can vary in success, predictors are needed. We aimed to predict at the patients’ levels, overall survival (OS) and progression-free survival (PFS) after one year of immunotherapy, based on their pre-treatment 18F-FDG PET; (2) Methods: Fifty-six metastatic melanoma patients—without prior systemic treatment—were retrospectively included. Forty-five 18F-FDG PET-based radiomic features were computed and the top five features associated with the patient’s outcome were selected. The analyzed machine learning classifiers were random forest (RF), neural network, naive Bayes, logistic regression and support vector machine. The receiver operating characteristic curve was used to compare model performances, which were validated by cross-validation; (3) Results: The RF model obtained the best performance after validation to predict OS and PFS and presented AUC, sensitivities and specificities (IC95%) of 0.87 ± 0.1, 0.79 ± 0.11 and 0.95 ± 0.06 for OS and 0.9 ± 0.07, 0.88 ± 0.09 and 0.91 ± 0.08 for PFS, respectively. (4) Conclusion: A RF classifier, based on pretreatment 18F-FDG PET radiomic features may be useful for predicting the survival status for melanoma patients, after one year of a first line systemic treatment by immunotherapy.

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.

FDG PET biomarkers for prediction of survival in metastatic melanoma prior to anti-PD1 immunotherapy

Our aim was to analyse whether biomarkers extracted from baseline ¹⁸F-FDG PET before anti-PD1 treatment contribute to prognostic survival information for early risk stratification in metastatic melanoma. Fifty-six patients, without prior systemic treatment, BRAF wild type, explored using ¹⁸F-FDG PET were included retrospectively. Our primary endpoint was overall survival (OS). Total metabolic tumoral volume (MTV) and forty-one IBSI compliant parameters were extracted from PET. Parameters associated with outcome were evaluated by a cox regression model and when significant helped build a prognostic score. Median follow-up was 22.1 months and 21 patients died. Total MTV and long zone emphasis (LZE) correlated with shorter OS and served to define three risk categories for the prognostic score. For low, intermediate and high risk groups, survival rates were respectively 91.1% (IC 95 80–1), 56.1% (IC 95 37.1–85) and 19% (IC 95 0.06–60.2) and hazard ratios were respectively 0.11 (IC 95 0.025–0.46), P = 0.0028, 1.2 (IC 95 0.48–2.8), P = 0.74 and 5.9 (IC 95 2.5–14), P < 0.0001. To conclude, a prognostic score based on total MTV and LZE separated metastatic melanoma patients in 3 categories with dramatically different outcomes. Innovative therapies should be tested in the group with the lowest prognosis score for future clinical trials.

A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets

PURPOSE

To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the "center-effect". The goal of the present work was to integrate a transfer learning (TL) technique within ComBat-and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)-to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center.

MATERIAL AND METHODS

The proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines.

RESULTS

The proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available.

CONCLUSION

The proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data.