Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients

End-to-end [18F]PSMA-1007 PET/CT radiomics-based pipeline for predicting ISUP grade group in prostate cancer

OBJECTIVES

To develop an end-to-end radiomics-based pipeline for the prediction of International Society of Urological Pathology grade group (ISUP GG) in prostate cancer (PCa).

METHODS

This retrospective study includes 356 patients (241 in training set and 115 in independent test set) with histopathologically confirmed PCa who underwent [18F]PSMA-1007 PET/CT scan. Patients were classified into two groups according to their ISUP GG (1-3 vs. 4-5). Radiomics features were extracted from the whole, automatically segmented prostate on PET/CT images, 30 models were constructed by combining 6 feature selection algorithms and 5 machine learning classifiers. The clinical model incorporated age, total prostate-specific antigen (tPSA), maximum standardized uptake value (SUVmax), and prostate volume. The predictive performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC), balanced accuracy (bAcc), and decision curve analysis (DCA).

RESULTS

The best-performing radiomics model significantly outperformed clinical model (AUC 0.879 ± 0.041 vs. 0.799 ± 0.051, bAcc 0.745 ± 0.074 vs. 0.629 ± 0.045). On an external independent test set, best-performing radiomics model perform better than clinical model, with an AUC of 0.861 vs. 0.750, p = 0.002 (Delong), and bAcc of 0.764 vs. 0.582, p = 0.043 (McNemar). The learning curve, calibration curve and DCA demonstrated goodness-of-fit and improved benefits in clinical practice.

CONCLUSION

The end-to-end radiomics-based pipeline is an effective non-invasive tool to predict ISUP GG in PCa.

MRI-Based Radiomics Features for Prediction of Pathological Deterioration Upgrading in Rectal Tumor

PURPOSE

Our aim is to develop and validate an MRI-based diagnostic model for predicting pathological deterioration upgrading in rectal tumor.

METHODS

This retrospective study included 158 eligible patients from January 2017 to November 2023. The patients were divided into a training group (n = 110) and a validation group (n = 48). Radiomics features were extracted from T2-weighted images to create a radiomics score model. Significant factors identified through multifactor analysis were used to develop the final clinical feature model. By combining these two models, an combined radiomics-clinical model was established. The model's performance was evaluated using Receiver Operating Characteristic (ROC) analysis and the Area Under the ROC Curve (AUC).

RESULTS

A total of 1197 features were extracted, with 11 features selected for calculating the radiomics score to establish the radiomics model. This model demonstrated good predictive performance for pathological upgrading in both the training and validation groups (AUC of 0.863 and 0.861, respectively). Clinical factors such as chief complaint and differential carcinoembryonic antigen levels showed statistical significance (P < 0.05). The clinical model, incorporating these factors, yielded AUC values of 0.669 and 0.651 for the training and validation groups, respectively. Furthermore, the radiomics-clinical combined model outperformed the individual models in predicting preoperative pathological upgrading in both the training and validation groups (AUC of 0.932 and 0.907, respectively).

CONCLUSIONS

A radiomics-clinical model, which combines clinical features with radiomics features based on MRI, can predict pathological deterioration upgrading in patients with rectal tumor and provide valuable insights for personalized treatment strategies.

Integrating PET/CT, radiomics and clinical data: An advanced multi-modal approach for lymph node metastasis prediction in prostate cancer

The involvement of lymph nodes critically affects patient outcomes in prostate cancer. While traditional risk models use factors like stage and PSA levels, the detection of lymph node involvement through modalities like PET targeting PSMA with 68Ga radiotracer plays a pivotal role in guiding treatments ranging from prostatectomy to pelvic radiotherapy. This study aims to create a deep learning model to predict lymph node involvement in intermediate to high-risk prostate cancer patients using 68Ga-PSMA PET/CT imagery, radiomics features, and various clinical parameters. For this study, 68Ga-PSMA PET/CT scans and corresponding clinical data from 229 prostate cancer patients were retrospectively collected. An artificial intelligence model, integrating PET/CT fusion images, clinical data, and radiomics features, was developed using a slice-wise feature extractor and MNASNet for spatial feature extraction. The model was trained on 181 cases and tested on 48 cases. To assess the model's performance, a reader study was conducted on a balanced subset of the test data with five radiation oncologists. Among the 229 intermediate to high-risk patients with localized prostate cancer evaluated, 67 (30%) had lymph node metastasis, while 162 were non-metastatic. The proposed AI model achieved a mean accuracy of 0.85±0.03 and an F1 score of 0.73±0.03. In the reader study, radiation oncologists' mean evaluations showed lower metrics (accuracy 0.71±0.08, F1 score 0.70±0.07), compared to the AI model's mean accuracy of 0.79±0.02 and F1 score of 0.76±0.02. Our findings demonstrate the potential benefits of the proposed model in the clinical setting, particularly in enhancing decision-making by doctors in scenarios with high variability between readers, such as lymph node metastasis prediction.

Enhancing the Opportunistic Bone Status Assessment Using Radiomics Based on Dual-Energy Spectral CT Material Decomposition Images

The dual-energy spectral CT (DEsCT) employs material decomposition (MD) technology, opening up novel avenues for the opportunistic assessment of bone status. Radiomics, a powerful tool for elucidating the structural and textural characteristics of bone, aids in the detection of mineral loss. Therefore, this study aims to compare the efficacy of bone status assessment using both bone density measurements and radiomics models derived from MD images and to further explore the clinical value of radiomics models.

METHODS

Retrospective data were collected from 307 patients who underwent both quantitative computed tomography (QCT) and full-abdomen DEsCT scans at our institution. Based on QCT measurements, patients were divided into three categories: normal bone mineral density (BMD), osteopenia, and osteoporosis. Using the abdominal DEsCT data, six types of MD images were reconstructed, including HAP (Water), HAP (Fat), Ca (Water), Ca (Fat), Fat (Ca), and Fat (HAP). Patients were randomly divided into a training cohort (n = 214) and a validation cohort (n = 93) at a ratio of 7:3. Focusing on the L1 to L3 vertebrae, density values from the six MD images were measured. Six density value models and six radiomics models were constructed using a random forest (RF) classifier. The performance of these models in assessing bone status was evaluated using the receiver operating characteristic (ROC) curves, and the DeLong test was employed to compare performance differences between the models.

RESULTS

The macro-area under the curve (AUC) values for the density value models based on HAP (Water), HAP (Fat), Ca (Water), and Ca (Fat) MD images were 0.870, 0.870, 0.847, and 0.765, respectively, which outperformed those of Fat (Ca) (AUC = 0.623) and Fat (HAP) (AUC = 0.618) density value models. In the comparison of radiomics models, the trends of model performance were consistent with the density value models across the six MD images. However, the models based on HAP (Water), Ca (Water), HAP (Fat), Ca (Fat), Fat (Ca), and Fat (HAP) images exhibited superior performance than those of the density value models with the corresponding MD images, with values of 0.946, 0.941, 0.934, 0.926, 0.831, and 0.824, respectively.

CONCLUSIONS

Bone status assessment can be accurately conducted using density values from HAP (Water), HAP (Fat), Ca (Water), and Ca (Fat) MD images. However, radiomics models derived from MD images surpass traditional density measurement methods in evaluating bone status, highlighting their superior diagnostic potential.

Biology-guided radiotherapy in metastatic prostate cancer: time to push the envelope?

The therapeutic landscape of metastatic prostate cancer has undergone a profound revolution in recent years. In addition to the introduction of novel molecules in the clinics, the field has witnessed a tremendous development of functional imaging modalities adding new biological insights which can ultimately inform tailored treatment strategies, including local therapies. The evolution and rise of Stereotactic Body Radiotherapy (SBRT) have been particularly notable in patients with oligometastatic disease, where it has been demonstrated to be a safe and effective treatment strategy yielding favorable results in terms of disease control and improved oncological outcomes. The possibility of debulking all sites of disease, matched with the ambition of potentially extending this treatment paradigm to polymetastatic patients in the not-too-distant future, makes Biology-guided Radiotherapy (BgRT) an attractive paradigm which can be used in conjunction with systemic therapy in the management of patients with metastatic prostate cancer.

Radiomic Pipelines for Prostate Cancer in External Beam Radiation Therapy: A Review of Methods and Future Directions

Background: Prostate Cancer (PCa) is asymptomatic at an early stage and often painless, requiring only active surveillance. External Beam Radiotherapy (EBRT) is currently a curative option for localised and locally advanced diseases and a palliative option for metastatic low-volume disease. Although highly effective, especially in a hypofractionation scheme, 17.4% to 39.4% of all patients suffer from cancer recurrence after EBRT. But, radiographic findings also correlate with significant differences in protein expression patterns. In the PCa EBRT workflow, several imaging modalities are available for grading, staging and contouring. Using image data characterisation algorithms (radiomics), one can provide a quantitative analysis of prognostic and predictive treatment outcomes. Methods: This literature review searched for original studies in radiomics for PCa in the context of EBRT. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this review includes 73 new studies and analyses datasets, imaging modality, segmentation technique, feature extraction, selection and model building methods. Results: Magnetic Resonance Imaging (MRI) is the preferred imaging modality for radiomic studies in PCa but Computed Tomography (CT), Positron Emission Tomography (PET) and Ultrasound (US) may offer valuable insights on tumour characterisation and treatment response prediction. Conclusions: Most radiomic studies used small, homogeneous and private datasets lacking external validation and variability. Future research should focus on collaborative efforts to create large, multicentric datasets and develop standardised methodologies, ensuring the full potential of radiomics in clinical practice.

Prostate-specific membrane antigen-PET/CT may result in stage migration in prostate cancer: performances, quantitative analysis, and potential criticism in the clinical practice

AIM

The early detection of prostate cancer (PCa) metastatic disease with PET imaging leads to stage migration and change of disease management. We aimed to assess the impact on clinical management deriving from prostate-specific membrane antigen (PSMA) imaging with a digital PET/CT during the routine application in the staging and restaging process of PCa.

MATERIAL AND METHODS

Eighty consecutive PCa patients underwent 18F-PSMA-1007. Digital PET/CT were retrospectively evaluated and discussed with oncologists to evaluate the impact on clinical management. Performances analysis, correlation among variables also considering semiquantitative parameters have been conducted.

RESULTS

In the whole group of 80 patients at staging (N = 31) and restaging (N = 49), the detection rate of PSMA PET was 85% for all lesions. At staging, the performance analysis resulted in sensitivity 77.6%, specificity 89.5%, negative predictive value (NPV) 77.6%, positive predictive value (PPV) 89.5%, accuracy 85.7%, and area under curve (AUC) 0.87%. The performance of restaging PET in the group of patients with PSA values <1 ng/ml resulted in the following values: sensitivity 66.7%, specificity 92.9%, NPV 85.7%, PPV 81.3%, accuracy 82.6%, and AUC 0.79. Semiquantitative analysis revealed a mean value of SUVmax, metabolic tumor volume, and total lesion PSMA expression with differences in patients with high risk compared to low intermediate. At restaging PET, semiquantitative values of patients with total prostate specific antigen (tPSA) ≤ 1 ng/ml were significantly less than those of the tPSA > 1 ng/ml. A significant impact on clinical management was reported in 46/80 patients (57.5%) based on PSMA PET findings at staging and restaging.

CONCLUSION

Although PSMA-PET provides optimal performances, its current role in redefining a better staging should be translated in the current clinical scenario about potential improvement in clinical/survival outcomes.

Machine learning-based analysis of 68Ga-PSMA-11 PET/CT images for estimation of prostate tumor grade

Early diagnosis of prostate cancer, the most common malignancy in men, can improve patient outcomes. Since the tissue sampling procedures are invasive and sometimes inconclusive, an alternative image-based method can prevent possible complications and facilitate treatment management. We aim to propose a machine-learning model for tumor grade estimation based on 68 Ga-PSMA-11 PET/CT images in prostate cancer patients. This study included 90 eligible participants out of 244 biopsy-proven prostate cancer patients who underwent staging 68Ga-PSMA-11 PET/CT imaging. The patients were divided into high and low-intermediate groups based on their Gleason scores. The PET-only images were manually segmented, both lesion-based and whole prostate, by two experienced nuclear medicine physicians. Four feature selection algorithms and five classifiers were applied to Combat-harmonized and non-harmonized datasets. To evaluate the model's generalizability across different institutions, we performed leave-one-center-out cross-validation (LOOCV). The metrics derived from the receiver operating characteristic curve were used to assess model performance. In the whole prostate segmentation, combining the ANOVA algorithm as the feature selector with Random Forest (RF) and Extra Trees (ET) classifiers resulted in the highest performance among the models, with an AUC of 0.78 and 083, respectively. In the lesion-based segmentation, the highest AUC was achieved by MRMR feature selector + Linear Discriminant Analysis (LDA) and Logistic Regression (LR) classifiers (0.76 and 0.79, respectively). The LOOCV results revealed that both the RF_ANOVA and ET_ANOVA models showed high levels of accuracy and generalizability across different centers, with an average AUC value of 0.87 for the ET_ANOVA combination. Machine learning-based analysis of radiomics features extracted from 68Ga-PSMA-11 PET/CT scans can accurately classify prostate tumors into low-risk and intermediate- to high-risk groups.

Prostate-Specific Membrane Antigen Positron Emission Tomography/Computed Tomography-Derived Radiomic Models in Prostate Cancer Prognostication

The clinical integration of prostate membrane specific antigen (PSMA) positron emission tomography and computed tomography (PET/CT) scans represents potential for advanced data analysis techniques in prostate cancer (PC) prognostication. Among these tools is the use of radiomics, a computer-based method of extracting and quantitatively analyzing subvisual features in medical imaging. Within this context, the present review seeks to summarize the current literature on the use of PSMA PET/CT-derived radiomics in PC risk stratification. A stepwise literature search of publications from 2017 to 2023 was performed. Of 23 articles on PSMA PET/CT-derived prostate radiomics, PC diagnosis, prediction of biopsy Gleason score (GS), prediction of adverse pathology, and treatment outcomes were the primary endpoints of 4 (17.4%), 5 (21.7%), 7 (30.4%), and 7 (30.4%) studies, respectively. In predicting PC diagnosis, PSMA PET/CT-derived models performed well, with receiver operator characteristic curve area under the curve (ROC-AUC) values of 0.85-0.925. Similarly, in the prediction of biopsy and surgical pathology results, ROC-AUC values had ranges of 0.719-0.84 and 0.84-0.95, respectively. Finally, prediction of recurrence, progression, or survival following treatment was explored in nine studies, with ROC-AUC ranging 0.698-0.90. Of the 23 studies included in this review, 2 (8.7%) included external validation. While explorations of PSMA PET/CT-derived radiomic models are immature in follow-up and experience, these results represent great potential for future investigation and exploration. Prior to consideration for clinical use, however, rigorous validation in feature reproducibility and biologic validation of radiomic signatures must be prioritized.

The Application of Radiomics and AI to Molecular Imaging for Prostate Cancer

Molecular imaging is a key tool in the diagnosis and treatment of prostate cancer (PCa). Magnetic Resonance (MR) plays a major role in this respect with nuclear medicine imaging, particularly, Prostate-Specific Membrane Antigen-based, (PSMA-based) positron emission tomography with computed tomography (PET/CT) also playing a major role of rapidly increasing importance. Another key technology finding growing application across medicine and specifically in molecular imaging is the use of machine learning (ML) and artificial intelligence (AI). Several authoritative reviews are available of the role of MR-based molecular imaging with a sparsity of reviews of the role of PET/CT. This review will focus on the use of AI for molecular imaging for PCa. It will aim to achieve two goals: firstly, to give the reader an introduction to the AI technologies available, and secondly, to provide an overview of AI applied to PET/CT in PCa. The clinical applications include diagnosis, staging, target volume definition for treatment planning, outcome prediction and outcome monitoring. ML and AL techniques discussed include radiomics, convolutional neural networks (CNN), generative adversarial networks (GAN) and training methods: supervised, unsupervised and semi-supervised learning.

An Informative Review of Radiomics Studies on Cancer Imaging: The Main Findings, Challenges and Limitations of the Methodologies

The aim of this informative review was to investigate the application of radiomics in cancer imaging and to summarize the results of recent studies to support oncological imaging with particular attention to breast cancer, rectal cancer and primitive and secondary liver cancer. This review also aims to provide the main findings, challenges and limitations of the current methodologies. Clinical studies published in the last four years (2019-2022) were included in this review. Among the 19 studies analyzed, none assessed the differences between scanners and vendor-dependent characteristics, collected images of individuals at additional points in time, performed calibration statistics, represented a prospective study performed and registered in a study database, conducted a cost-effectiveness analysis, reported on the cost-effectiveness of the clinical application, or performed multivariable analysis with also non-radiomics features. Seven studies reached a high radiomic quality score (RQS), and seventeen earned additional points by using validation steps considering two datasets from two distinct institutes and open science and data domains (radiomics features calculated on a set of representative ROIs are open source). The potential of radiomics is increasingly establishing itself, even if there are still several aspects to be evaluated before the passage of radiomics into routine clinical practice. There are several challenges, including the need for standardization across all stages of the workflow and the potential for cross-site validation using real-world heterogeneous datasets. Moreover, multiple centers and prospective radiomics studies with more samples that add inter-scanner differences and vendor-dependent characteristics will be needed in the future, as well as the collecting of images of individuals at additional time points, the reporting of calibration statistics and the performing of prospective studies registered in a study database.

Artificial intelligence applied to image-guided radiation therapy (IGRT): a systematic review by the Young Group of the Italian Association of Radiotherapy and Clinical Oncology (yAIRO)

INTRODUCTION

The advent of image-guided radiation therapy (IGRT) has recently changed the workflow of radiation treatments by ensuring highly collimated treatments. Artificial intelligence (AI) and radiomics are tools that have shown promising results for diagnosis, treatment optimization and outcome prediction. This review aims to assess the impact of AI and radiomics on modern IGRT modalities in RT.

METHODS

A PubMed/MEDLINE and Embase systematic review was conducted to investigate the impact of radiomics and AI to modern IGRT modalities. The search strategy was "Radiomics" AND "Cone Beam Computed Tomography"; "Radiomics" AND "Magnetic Resonance guided Radiotherapy"; "Radiomics" AND "on board Magnetic Resonance Radiotherapy"; "Artificial Intelligence" AND "Cone Beam Computed Tomography"; "Artificial Intelligence" AND "Magnetic Resonance guided Radiotherapy"; "Artificial Intelligence" AND "on board Magnetic Resonance Radiotherapy" and only original articles up to 01.11.2022 were considered.

RESULTS

A total of 402 studies were obtained using the previously mentioned search strategy on PubMed and Embase. The analysis was performed on a total of 84 papers obtained following the complete selection process. Radiomics application to IGRT was analyzed in 23 papers, while a total 61 papers were focused on the impact of AI on IGRT techniques.

DISCUSSION

AI and radiomics seem to significantly impact IGRT in all the phases of RT workflow, even if the evidence in the literature is based on retrospective data. Further studies are needed to confirm these tools' potential and provide a stronger correlation with clinical outcomes and gold-standard treatment strategies.

Application of Artificial Intelligence in Oncologic Molecular PET-Imaging: A Narrative Review on Beyond [18F]F-FDG Tracers - Part I. PSMA, Choline, and DOTA Radiotracers

Artificial intelligence (AI) has evolved significantly in the past few decades. This thriving trend has also been seen in medicine in recent years, particularly in the field of imaging. Machine learning (ML), deep learning (DL), and their methods (eg, SVM, CNN), as well as radiomics, are the terminologies that have been introduced to this field and, to some extent, become familiar to the expert clinicians. PET is one of the modalities that has been enhanced via these state-of-the-art algorithms. This robust imaging technique further merged with anatomical modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), to provide reliable hybrid modalities, PET/CT and PET/MRI. Applying AI-based algorithms on the different components (PET, CT, and MRI) has resulted in promising results, maximizing the value of PET imaging. However, [18F]F-FDG, the most commonly utilized tracer in molecular imaging, has been mainly in the spotlight. Thus, we aimed to look into the less discussed tracers in this review, moving beyond [18F]F-FDG. The novel non-[18F]F-FDG agents also showed to be valuable in various clinical tasks, including lesion detection and tumor characterization, accurate delineation, and prognostic impact. Regarding prostate patients, PSMA-based models were highly accurate in determining tumoral lesions' location and delineating them, particularly within the prostate gland. However, they also could assess whole-body images to detect extra-prostatic lesions in a patient automatically. Considering the prognostic value of prostate-specific membrane antigen (PSMA) PET using AI, it could predict response to treatment and patient survival, which are crucial in patient management. Choline imaging, another non-[18F]F-FDG tracer, similarly showed acceptable results that may be of benefit in the clinic, though the current evidence is significantly more limited than PSMA. Lastly, different subtypes of DOTA ligands were found to be valuable. They could diagnose tumoral lesions in challenging sites and even predict histopathology grade, being a highly advantageous noninvasive tool. In conclusion, the current limited investigations have shown promising results, leading us to a bright future for AI in molecular imaging beyond [18F]F-FDG.

Analysis of preoperative computed tomography radiomics and clinical factors for predicting postsurgical recurrence of papillary thyroid carcinoma

BACKGROUND

Postsurgical recurrence is of great concern for papillary thyroid carcinoma (PTC). We aim to investigate the value of computed tomography (CT)-based radiomics features and conventional clinical factors in predicting the recurrence of PTC.

METHODS

Two-hundred and eighty patients with PTC were retrospectively enrolled and divided into training and validation cohorts at a 6:4 ratio. Recurrence was defined as cytology/pathology-proven disease or morphological evidence of lesions on imaging examinations within 5 years after surgery. Radiomics features were extracted from manually segmented tumor on CT images and were then selected using four different feature selection methods sequentially. Multivariate logistic regression analysis was conducted to identify clinical features associated with recurrence. Radiomics, clinical, and combined models were constructed separately using logistic regression (LR), support vector machine (SVM), k-nearest neighbor (KNN), and neural network (NN), respectively. Receiver operating characteristic analysis was performed to evaluate the model performance in predicting recurrence. A nomogram was established based on all relevant features, with its reliability and reproducibility verified using calibration curves and decision curve analysis (DCA).

RESULTS

Eighty-nine patients with PTC experienced recurrence. A total of 1218 radiomics features were extracted from each segmentation. Five radiomics and six clinical features were related to recurrence. Among the 4 radiomics models, the LR-based and SVM-based radiomics models outperformed the NN-based radiomics model (P = 0.032 and 0.026, respectively). Among the 4 clinical models, only the difference between the area under the curve (AUC) of the LR-based and NN-based clinical model was statistically significant (P = 0.035). The combined models had higher AUCs than the corresponding radiomics and clinical models based on the same classifier, although most differences were not statistically significant. In the validation cohort, the combined models based on the LR, SVM, KNN, and NN classifiers had AUCs of 0.746, 0.754, 0.669, and 0.711, respectively. However, the AUCs of these combined models had no significant differences (all P > 0.05). Calibration curves and DCA indicated that the nomogram have potential clinical utility.

CONCLUSIONS

The combined model may have potential for better prediction of PTC recurrence than radiomics and clinical models alone. Further testing with larger cohort may help reach statistical significance.

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.

Computed Tomography-Based Radiomics for Long-Term Prognostication of High-Risk Localized Prostate Cancer Patients Received Whole Pelvic Radiotherapy

Given the high death rate caused by high-risk prostate cancer (PCa) (>40%) and the reliability issues associated with traditional prognostic markers, the purpose of this study is to investigate planning computed tomography (pCT)-based radiomics for the long-term prognostication of high-risk localized PCa patients who received whole pelvic radiotherapy (WPRT). This is a retrospective study with methods based on best practice procedures for radiomics research. Sixty-four patients were selected and randomly assigned to training (n = 45) and testing (n = 19) cohorts for radiomics model development with five major steps: pCT image acquisition using a Philips Big Bore CT simulator; multiple manual segmentations of clinical target volume for the prostate (CTVprostate) on the pCT images; feature extraction from the CTVprostate using PyRadiomics; feature selection for overfitting avoidance; and model development with three-fold cross-validation. The radiomics model and signature performances were evaluated based on the area under the receiver operating characteristic curve (AUC) as well as accuracy, sensitivity and specificity. This study's results show that our pCT-based radiomics model was able to predict the six-year progression-free survival of the high-risk localized PCa patients who received the WPRT with highly consistent performances (mean AUC: 0.76 (training) and 0.71 (testing)). These are comparable to findings of other similar studies including those using magnetic resonance imaging (MRI)-based radiomics. The accuracy, sensitivity and specificity of our radiomics signature that consisted of two texture features were 0.778, 0.833 and 0.556 (training) and 0.842, 0.867 and 0.750 (testing), respectively. Since CT is more readily available than MRI and is the standard-of-care modality for PCa WPRT planning, pCT-based radiomics could be used as a routine non-invasive approach to the prognostic prediction of WPRT treatment outcomes in high-risk localized PCa.

Multicentric 68Ga-PSMA PET radiomics for treatment response assessment of 177Lu-PSMA-617 radioligand therapy in patients with metastatic castration-resistant prostate cancer

Objective

The treatment with 177Lutetium PSMA (177Lu-PSMA) in patients with metastatic castration-resistant prostate cancer (mCRPC) has recently been approved by the FDA and EMA. Since treatment success is highly variable between patients, the prediction of treatment response and identification of short- and long-term survivors after treatment could help tailor mCRPC diagnosis and treatment accordingly. The aim of this study is to investigate the value of radiomic parameters extracted from pretreatment 68Ga-PSMA PET images for the prediction of treatment response.

Methods

A total of 45 mCRPC patients treated with 177Lu-PSMA-617 from two university hospital centers were retrospectively reviewed for this study. Radiomic features were extracted from the volumetric segmentations of metastases in the bone. A random forest model was trained and validated to predict treatment response based on age and conventionally used PET parameters, radiomic features and combinations thereof. Further, overall survival was predicted by using the identified radiomic signature and compared to a Cox regression model based on age and PET parameters.

Results

The machine learning model based on a combined radiomic signature of three features and patient age achieved an AUC of 0.82 in 5-fold cross-validation and outperformed models based on age and PET parameters or radiomic features (AUC, 0.75 and 0.76, respectively). A Cox regression model based on this radiomic signature showed the best performance to predict overall survival (C-index, 0.67).

Conclusion

Our results demonstrate that a machine learning model to predict response to 177Lu-PSMA treatment based on a combination of radiomics and patient age outperforms a model based on age and PET parameters. Moreover, the identified radiomic signature based on pretreatment 68Ga-PSMA PET images might be able to identify patients with an improved outcome and serve as a supportive tool in clinical decision making.

Phenotyping the Histopathological Subtypes of Non-Small-Cell Lung Carcinoma: How Beneficial Is Radiomics?

The aim of this study was to investigate the usefulness of radiomics in the absence of well-defined standard guidelines. Specifically, we extracted radiomics features from multicenter computed tomography (CT) images to differentiate between the four histopathological subtypes of non-small-cell lung carcinoma (NSCLC). In addition, the results that varied with the radiomics model were compared. We investigated the presence of the batch effects and the impact of feature harmonization on the models' performance. Moreover, the question on how the training dataset composition influenced the selected feature subsets and, consequently, the model's performance was also investigated. Therefore, through combining data from the two publicly available datasets, this study involves a total of 152 squamous cell carcinoma (SCC), 106 large cell carcinoma (LCC), 150 adenocarcinoma (ADC), and 58 no other specified (NOS). Through the matRadiomics tool, which is an example of Image Biomarker Standardization Initiative (IBSI) compliant software, 1781 radiomics features were extracted from each of the malignant lesions that were identified in CT images. After batch analysis and feature harmonization, which were based on the ComBat tool and were integrated in matRadiomics, the datasets (the harmonized and the non-harmonized) were given as an input to a machine learning modeling pipeline. The following steps were articulated: (i) training-set/test-set splitting (80/20); (ii) a Kruskal-Wallis analysis and LASSO linear regression for the feature selection; (iii) model training; (iv) a model validation and hyperparameter optimization; and (v) model testing. Model optimization consisted of a 5-fold cross-validated Bayesian optimization, repeated ten times (inner loop). The whole pipeline was repeated 10 times (outer loop) with six different machine learning classification algorithms. Moreover, the stability of the feature selection was evaluated. Results showed that the batch effects were present even if the voxels were resampled to an isotropic form and whether feature harmonization correctly removed them, even though the models' performances decreased. Moreover, the results showed that a low accuracy (61.41%) was reached when differentiating between the four subtypes, even though a high average area under curve (AUC) was reached (0.831). Further, a NOS subtype was classified as almost completely correct (true positive rate ~90%). The accuracy increased (77.25%) when only the SCC and ADC subtypes were considered, as well as when a high AUC (0.821) was obtained-although harmonization decreased the accuracy to 58%. Moreover, the features that contributed the most to models' performance were those extracted from wavelet decomposed and Laplacian of Gaussian (LoG) filtered images and they belonged to the texture feature class.. In conclusion, we showed that our multicenter data were affected by batch effects, that they could significantly alter the models' performance, and that feature harmonization correctly removed them. Although wavelet features seemed to be the most informative features, an absolute subset could not be identified since it changed depending on the training/testing splitting. Moreover, performance was influenced by the chosen dataset and by the machine learning methods, which could reach a high accuracy in binary classification tasks, but could underperform in multiclass problems. It is, therefore, essential that the scientific community propose a more systematic radiomics approach, focusing on multicenter studies, with clear and solid guidelines to facilitate the translation of radiomics to clinical practice.

Clinical application of AI-based PET images in oncological patients

Based on the advantages of revealing the functional status and molecular expression of tumor cells, positron emission tomography (PET) imaging has been performed in numerous types of malignant diseases for diagnosis and monitoring. However, insufficient image quality, the lack of a convincing evaluation tool and intra- and interobserver variation in human work are well-known limitations of nuclear medicine imaging and restrict its clinical application. Artificial intelligence (AI) has gained increasing interest in the field of medical imaging due to its powerful information collection and interpretation ability. The combination of AI and PET imaging potentially provides great assistance to physicians managing patients. Radiomics, an important branch of AI applied in medical imaging, can extract hundreds of abstract mathematical features of images for further analysis. In this review, an overview of the applications of AI in PET imaging is provided, focusing on image enhancement, tumor detection, response and prognosis prediction and correlation analyses with pathology or specific gene mutations in several types of tumors. Our aim is to describe recent clinical applications of AI-based PET imaging in malignant diseases and to focus on the description of possible future developments.

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays

Before the recent success of deep learning methods for automated medical image analysis, practitioners used handcrafted radiomic features to quantitatively describe local patches of medical images. However, extracting discriminative radiomic features relies on accurate pathology localization, which is difficult to acquire in real-world settings. Despite advances in disease classification and localization from chest X-rays, many approaches fail to incorporate clinically-informed domainspecific radiomic features. For these reasons, we propose a Radiomics-Guided Transformer (RGT) that fuses global image information with local radiomics-guided auxiliary information to provide accurate cardiopulmonary pathology localization and classification without any bounding box annotations. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomics information. Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers. Thus, RGT utilizes a novel end-to-end feedback loop that can bootstrap accurate pathology localization only using image-level disease labels. Experiments on the NIH ChestXRay dataset demonstrate that RGT outperforms prior works in weakly supervised disease localization (by an average margin of 3.6% over various intersection-over-union thresholds) and classification (by 1.1% in average area under the receiver operating characteristic curve). We publicly release our codes and pre-trained models at https://github.com/VITAGroup/chext.

CT-based machine learning radiomics predicts CCR5 expression level and survival in ovarian cancer

OBJECTIVE

We aimed to evaluate the prognostic value of C-C motif chemokine receptor type 5 (CCR5) expression level for patients with ovarian cancer and to establish a radiomics model that can predict CCR5 expression level using The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) database.

METHODS

A total of 343 cases of ovarian cancer from the TCGA were used for the gene-based prognostic analysis. Fifty seven cases had preoperative computed tomography (CT) images stored in TCIA with genomic data in TCGA were used for radiomics feature extraction and model construction. 89 cases with both TCGA and TCIA clinical data were used for radiomics model evaluation. After feature extraction, a radiomics signature was constructed using the least absolute shrinkage and selection operator (LASSO) regression analysis. A prognostic scoring system incorporating radiomics signature based on CCR5 expression level and clinicopathologic risk factors was proposed for survival prediction.

RESULTS

CCR5 was identified as a differentially expressed prognosis-related gene in tumor and normal sample, which were involved in the regulation of immune response and tumor invasion and metastasis. Four optimal radiomics features were selected to predict overall survival. The performance of the radiomics model for predicting the CCR5 expression level with 10-fold cross- validation achieved Area Under Curve (AUCs) of 0.770 and of 0.726, respectively, in the training and validation sets. A predictive nomogram was generated based on the total risk score of each patient, the AUCs of the time-dependent receiver operating characteristic (ROC) curve of the model was 0.8, 0.673 and 0.792 for 1-year, 3-year and 5-year, respectively. Along with clinical features, important imaging biomarkers could improve the overall survival accuracy of the prediction model.

CONCLUSION

The expression levels of CCR5 can affect the prognosis of patients with ovarian cancer. CT-based radiomics could serve as a new tool for prognosis prediction.

A CT based radiomics nomogram for differentiation between focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma

Objectives

The purpose of this study was to develop and validate an CT-based radiomics nomogram for the preoperative differentiation of focal-type autoimmune pancreatitis from pancreatic ductal adenocarcinoma.

Methods

96 patients with focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma have been enrolled in the study (32 and 64 cases respectively). All cases have been confirmed by imaging, clinical follow-up and/or pathology. The imaging data were considered as: 70% training cohort and 30% test cohort. Pancreatic lesions have been manually delineated by two radiologists and image segmentation was performed to extract radiomic features from the CT images. Independent-sample T tests and LASSO regression were used for feature selection. The training cohort was classified using a variety of machine learning-based classifiers, and 5-fold cross-validation has been performed. The classification performance was evaluated using the test cohort. Multivariate logistic regression analysis was then used to develop a radiomics nomogram model, containing the CT findings and Rad-Score. Calibration curves have been plotted showing the agreement between the predicted and actual probabilities of the radiomics nomogram model. Different patients have been selected to test and evaluate the model prediction process. Finally, receiver operating characteristic curves and decision curves were plotted, and the radiomics nomogram model was compared with a single model to visually assess its diagnostic ability.

Results

A total of 158 radiomics features were extracted from each image. 7 features were selected to construct the radiomics model, then a variety of classifiers were used for classification and multinomial logistic regression (MLR) was selected to be the optimal classifier. Combining CT findings with radiomics model, a prediction model based on CT findings and radiomics was finally obtained. The nomogram model showed a good sensitivity and specificity with AUCs of 0.87 and 0.83 in training and test cohorts, respectively. The areas under the curve and decision curve analysis showed that the radiomics nomogram model may provide better diagnostic performance than the single model and achieve greater clinical net benefits than the CT finding model and radiomics signature model individually.

Conclusions

The CT image-based radiomics nomogram model can accurately distinguish between focal-type autoimmune pancreatitis and pancreatic ductal adenocarcinoma patients and provide additional clinical benefits.

Predicting clinically significant prostate cancer with a deep learning approach: a multicentre retrospective study

PURPOSE

This study aimed to develop deep learning (DL) models based on multicentre biparametric magnetic resonance imaging (bpMRI) for the diagnosis of clinically significant prostate cancer (csPCa) and compare the performance of these models with that of the Prostate Imaging and Reporting and Data System (PI-RADS) assessment by expert radiologists based on multiparametric MRI (mpMRI).

METHODS

We included 1861 consecutive male patients who underwent radical prostatectomy or biopsy at seven hospitals with mpMRI. These patients were divided into the training (1216 patients in three hospitals) and external validation cohorts (645 patients in four hospitals). PI-RADS assessment was performed by expert radiologists. We developed DL models for the classification between benign and malignant lesions (DL-BM) and that between csPCa and non-csPCa (DL-CS). An integrated model combining PI-RADS and the DL-CS model, abbreviated as PIDL-CS, was developed. The performances of the DL models and PIDL-CS were compared with that of PI-RADS.

RESULTS

In each external validation cohort, the area under the receiver operating characteristic curve (AUC) values of the DL-BM and DL-CS models were not significantly different from that of PI-RADS (P > 0.05), whereas the AUC of PIDL-CS was superior to that of PI-RADS (P < 0.05), except for one external validation cohort (P > 0.05). The specificity of PIDL-CS for the detection of csPCa was much higher than that of PI-RADS (P < 0.05).

CONCLUSION

Our proposed DL models can be a potential non-invasive auxiliary tool for predicting csPCa. Furthermore, PIDL-CS greatly increased the specificity of csPCa detection compared with PI-RADS assessment by expert radiologists, greatly reducing unnecessary biopsies and helping radiologists achieve a precise diagnosis of csPCa.

A comparative study between deep learning and radiomics models in grading liver tumors using hepatobiliary phase contrast-enhanced MR images

Purpose

To compare a deep learning model with a radiomics model in differentiating high-grade (LR-3, LR-4, LR-5) liver imaging reporting and data system (LI-RADS) liver tumors from low-grade (LR-1, LR-2) LI-RADS tumors based on the contrast-enhanced magnetic resonance images.

Methods

Magnetic resonance imaging scans of 361 suspected hepatocellular carcinoma patients were retrospectively reviewed. Lesion volume segmentation was manually performed by two radiologists, resulting in 426 lesions from the training set and 83 lesions from the test set. The radiomics model was constructed using a support vector machine (SVM) with pre-defined features, which was first selected using Chi-square test, followed by refining using binary least absolute shrinkage and selection operator (LASSO) regression. The deep learning model was established based on the DenseNet. Performance of the models was quantified by area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity and F1-score.

Results

A set of 8 most informative features was selected from 1049 features to train the SVM classifier. The AUCs of the radiomics model were 0.857 (95% confidence interval [CI] 0.816–0.888) for the training set and 0.879 (95% CI 0.779–0.935) for the test set. The deep learning method achieved AUCs of 0.838 (95% CI 0.799–0.871) for the training set and 0.717 (95% CI 0.601–0.814) for the test set. The performance difference between these two models was assessed by t-test, which showed the results in both training and test sets were statistically significant.

Conclusion

The deep learning based model can be trained end-to-end with little extra domain knowledge, while the radiomics model requires complex feature selection. However, this process makes the radiomics model achieve better performance in this study with smaller computational cost and more potential on model interpretability.

Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT images

PURPOSE

This study aimed to develop and assess an automated segmentation framework based on deep learning for metastatic prostate cancer (mPCa) lesions in whole-body [68Ga]Ga-PSMA-11 PET/CT images for the purpose of extracting patient-level prognostic biomarkers.

METHODS

Three hundred thirty-seven [68Ga]Ga-PSMA-11 PET/CT images were retrieved from a cohort of biochemically recurrent PCa patients. A fully 3D convolutional neural network (CNN) is proposed which is based on the self-configuring nnU-Net framework, and was trained on a subset of these scans, with an independent test set reserved for model evaluation. Voxel-level segmentation results were assessed using the dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity. Sensitivity and PPV were calculated to assess lesion level detection; patient-level classification results were assessed by the accuracy, PPV, and sensitivity. Whole-body biomarkers total lesional volume (TLVauto) and total lesional uptake (TLUauto) were calculated from the automated segmentations, and Kaplan-Meier analysis was used to assess biomarker relationship with patient overall survival.

RESULTS

At the patient level, the accuracy, sensitivity, and PPV were all > 90%, with the best metric being the PPV (97.2%). PPV and sensitivity at the lesion level were 88.2% and 73.0%, respectively. DSC and PPV measured at the voxel level performed within measured inter-observer variability (DSC, median = 50.7% vs. second observer = 32%, p = 0.012; PPV, median = 64.9% vs. second observer = 25.7%, p < 0.005). Kaplan-Meier analysis of TLVauto and TLUauto showed they were significantly associated with patient overall survival (both p < 0.005).

CONCLUSION

The fully automated assessment of whole-body [68Ga]Ga-PSMA-11 PET/CT images using deep learning shows significant promise, yielding accurate scan classification, voxel-level segmentations within inter-observer variability, and potentially clinically useful prognostic biomarkers associated with patient overall survival.

TRIAL REGISTRATION

This study was registered with the Australian New Zealand Clinical Trials Registry (ACTRN12615000608561) on 11 June 2015.

68Ga-PSMA-11 PET/CT Features Extracted from Different Radiomic Zones Predict Response to Androgen Deprivation Therapy in Patients with Advanced Prostate Cancer

Purpose: Prediction of treatment response to androgen deprivation therapy (ADT) prior to treatment initiation remains difficult. This study was undertaken to investigate whether 68Ga-PSMA-11 PET/CT features extracted from different radiomic zones within the prostate gland might predict response to ADT in patients with advanced prostate cancer (PCa). Methods: A total of 35 patients with prostate adenocarcinoma underwent two 68Ga-PSMA-11 PET/CT scans—termed PET-1 and PET-2—before and after 3 months of ADT, respectively. The prostate was divided into three radiomic zones, with zone-1 being the metabolic tumor zone, zone-2 the proximal peripheral tumor zone, and zone-3 the extended peripheral tumor zone. Patients in the response group were those who showed a reduction ratio > 30% for PET-derived parameters measured at PET-1 and PET-2. The remaining patients were classified as non-responders. Results: Seven features (glcm_idmn, glcm_idn, glcm_imc1, ngtdm_Contrast, glrlm_rln, gldm_dn, and shape_MeshVolume) from zone-1, two features (gldm_sdlgle and shape_MinorAxisLength) from zone-2, and two features (diagnostics_Mask-interpolated_Minimum and shape_Sphericity) from zone-3 successfully distinguished responders from non-responders to ADT. One predictive feature (shape_SurfaceVolumeRatio) was consistently identified in all of the three zones. Conclusions: this study demonstrates the potential usefulness of radiomic features extracted from different prostatic zones in distinguishing responders from non-responders prior to ADT initiation.

A diagnosis model in nasopharyngeal carcinoma based on PET/MRI radiomics and semiquantitative parameters

BACKGROUND

The staging of nasopharyngeal carcinoma (NPC) is of great value in treatment and prognosis. We explored whether a positron emission tomography/ magnetic resonance imaging (PET/MRI) based comprehensive model of radiomics features and semiquantitative parameters was useful for clinical evaluation of NPC staging.

MATERIALS AND METHODS

A total of 100 NPC patients diagnosed with non-keratinized undifferentiated carcinoma were divided into early-stage group (I-II) and advanced-stage group (III-IV) and divided into the training set (n = 70) and the testing set (n = 30). Radiomics features (n = 396 × 2) of the primary site of NPC were extracted from MRI and PET images, respectively. Three major semiquantitative parameters of primary sites including maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) in all NPC patients were measured. After feature selection, three diagnostic models including the radiomics model, the metabolic parameter model, and the combined model were established using logistic regression model. Finally, internal validation was performed, and a nomogram for NPC comprehensive diagnosis has been made.

RESULTS

The radiomics model and metabolic parameter model showed an area under the curve (AUC) of 0.83 and 0.80 in the testing set, respectively. The combined model based on radiomics and semiquantitative parameters showed an AUC of 0.90 in the testing set, with the best performance among the three models.

CONCLUSION

The combined model based on PET/MRI radiomics and semiquantitative parameters is of great value in the evaluation of clinical stage (early-stage group and advanced-stage group) of NPC.

matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model

Radiomics aims to support clinical decisions through its workflow, which is divided into: (i) target identification and segmentation, (ii) feature extraction, (iii) feature selection, and (iv) model fitting. Many radiomics tools were developed to fulfill the steps mentioned above. However, to date, users must switch different software to complete the radiomics workflow. To address this issue, we developed a new free and user-friendly radiomics framework, namely matRadiomics, which allows the user: (i) to import and inspect biomedical images, (ii) to identify and segment the target, (iii) to extract the features, (iv) to reduce and select them, and (v) to build a predictive model using machine learning algorithms. As a result, biomedical images can be visualized and segmented and, through the integration of Pyradiomics into matRadiomics, radiomic features can be extracted. These features can be selected using a hybrid descriptive–inferential method, and, consequently, used to train three different classifiers: linear discriminant analysis, k-nearest neighbors, and support vector machines. Model validation is performed using k-fold cross-Validation and k-fold stratified cross-validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In this study, we discuss the workflow, architecture, application, future development of matRadiomics, and demonstrate its working principles in a real case study with the aim of establishing a reference standard for the whole radiomics analysis, starting from the image visualization up to the predictive model implementation.

18F-Fluoroethylcholine PET/CT Radiomic Analysis for Newly Diagnosed Prostate Cancer Patients: A Monocentric Study

Aim: The aim of this study is to assess whether there are some correlations between radiomics and baseline clinical-biological data of prostate cancer (PC) patients using Fluorine-18 Fluoroethylcholine (¹⁸F-FECh) PET/CT. Methods: Digital rectal examination results (DRE), Prostate-Specific Antigen (PSA) serum levels, and bioptical-Gleason Score (GS) were retrospectively collected in newly diagnosed PC patients and considered as outcomes of PC. Thereafter, Volumes of interest (VOI) encompassing the prostate of each patient were drawn to extract conventional and radiomic PET features. Radiomic bivariate models were set up using the most statistically relevant features and then trained/tested with a cross-fold validation test. The best bivariate models were expressed by mean and standard deviation to the normal area under the receiver operating characteristic curves (mAUC, sdAUC). Results: Semiquantitative and radiomic analyses were performed on 67 consecutive patients. tSUVmean and tSkewness were significant DRE predictors at univariate analysis (OR 1.52 [1.01; 2.29], p = 0.047; OR 0.21 [0.07; 0.65], p = 0.007, respectively); moreover, tKurtosis was an independent DRE predictor at multivariate analysis (OR 0.64 [0.42; 0.96], p = 0.03) Among the most relevant bivariate models, szm_2.5D.z.entr + cm.clust.tend was a predictor of PSA levels (mAUC 0.83 ± 0.19); stat.kurt + stat.entropy predicted DRE (mAUC 0.79 ± 0.10); cm.info.corr.1 + szm_2.5D.szhge predicted GS (mAUC 0.78 ± 0.16). Conclusions: tSUVmean, tSkewness, and tKurtosis were predictors of DRE results only, while none of the PET parameters predicted PSA or GS significantly; ¹⁸F-FECh PET/CT radiomic models should be tested in larger cohort studies of newly diagnosed PC patients.

Development and validation of a machine learning-derived radiomics model for diagnosis of osteoporosis and osteopenia using quantitative computed tomography

Background

To develop and validate a quantitative computed tomography (QCT) based radiomics model for discriminating osteoporosis and osteopenia.

Methods

A total of 635 patients underwent QCT were retrospectively included from November 2016 to November 2019. The patients with osteopenia or osteoporosis (N = 590) were divided into a training cohort (N = 414) and a test cohort (N = 176). Radiomics features were extracted from the QCT images of the third lumbar vertebra. Minimum redundancy and maximum relevance and least absolute shrinkage and selection operator were used for data dimensional reduction, features selection and radiomics model building. Multivariable logistic regression was applied to construct the combined clinical-radiomic model that incorporated radiomics signatures and clinical characteristics. The performance of the combined clinical-radiomic model was evaluated by the area under the curve of receiver operator characteristic curve (ROC–AUC), accuracy, specificity, sensitivity, positive predictive value, and negative predictive value.

Results

The patients with osteopenia or osteoporosis were randomly divided into training and test cohort with a ratio of 7:3. Six more predictive radiomics signatures, age, alkaline phosphatase and homocysteine were selected to construct the combined clinical-radiomic model for diagnosis of osteoporosis and osteopenia. The AUC of the combined clinical-radiomic model was 0.96 (95% confidence interval (CI), 0.95 to 0.98) in the training cohort and 0.96 (95% CI 0.92 to 1.00) in the test cohort, which were superior to the clinical model alone (training-AUC = 0.81, test-AUC = 0.79). The calibration curve demonstrated that the radiomics nomogram had good agreement between prediction and observation and decision curve analysis confirmed clinically useful.

Conclusions

The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors, can serve as a reliable and powerful tool for discriminating osteoporosis and osteopenia.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00868-5.

PET-CT in Clinical Adult Oncology-IV. Gynecologic and Genitourinary Malignancies

Simple Summary

Positron emission tomography (PET), typically combined with computed tomography (CT), has become a critical advanced imaging technique in oncology. With concurrently acquired positron emission tomography and computed tomography (PET-CT), a radioactive molecule (radiotracer) is injected in the bloodstream and localizes to sites of tumor because of specific cellular features of the tumor that accumulate the targeting radiotracer. The CT scan provides information to allow better visualization of radioactivity from deep or dense structures and to provide detailed anatomic information. PET-CT has a variety of applications in oncology, including staging, therapeutic response assessment, restaging and surveillance. This series of six review articles provides an overview of the value, applications, and imaging interpretive strategies for PET-CT in the more common adult malignancies. The fourth report in this series provides a review of PET-CT imaging in gynecologic and genitourinary malignancies.

Abstract

Concurrently acquired positron emission tomography and computed tomography (PET-CT) is an advanced imaging modality with diverse oncologic applications, including staging, therapeutic assessment, restaging and longitudinal surveillance. This series of six review articles focuses on providing practical information to providers and imaging professionals regarding the best use and interpretative strategies of PET-CT for oncologic indications in adult patients. In this fourth article of the series, the more common gynecological and adult genitourinary malignancies encountered in clinical practice are addressed, with an emphasis on Food and Drug Administration (FDA)-approved and clinically available radiopharmaceuticals. The advent of new FDA-approved radiopharmaceuticals for prostate cancer imaging has revolutionized PET-CT imaging in this important disease, and these are addressed in this report. However, [¹⁸F]F-fluoro-2-deoxy-d-glucose (FDG) remains the mainstay for PET-CT imaging of gynecologic and many other genitourinary malignancies. This information will serve as a guide for the appropriate role of PET-CT in the clinical management of gynecologic and genitourinary cancer patients for health care professionals caring for adult cancer patients. It also addresses the nuances and provides guidance in the accurate interpretation of FDG PET-CT in gynecological and genitourinary malignancies for imaging providers, including radiologists, nuclear medicine physicians and their trainees.

Radiomics and artificial intelligence in prostate cancer: new tools for molecular hybrid imaging and theragnostics

In prostate cancer (PCa), the use of new radiopharmaceuticals has improved the accuracy of diagnosis and staging, refined surveillance strategies, and introduced specific and personalized radioreceptor therapies. Nuclear medicine, therefore, holds great promise for improving the quality of life of PCa patients, through managing and processing a vast amount of molecular imaging data and beyond, using a multi-omics approach and improving patients’ risk-stratification for tailored medicine. Artificial intelligence (AI) and radiomics may allow clinicians to improve the overall efficiency and accuracy of using these “big data” in both the diagnostic and theragnostic field: from technical aspects (such as semi-automatization of tumor segmentation, image reconstruction, and interpretation) to clinical outcomes, improving a deeper understanding of the molecular environment of PCa, refining personalized treatment strategies, and increasing the ability to predict the outcome. This systematic review aims to describe the current literature on AI and radiomics applied to molecular imaging of prostate cancer.

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.

Radiomics Analysis of Brain [18F]FDG PET/CT to Predict Alzheimer's Disease in Patients with Amyloid PET Positivity: A Preliminary Report on the Application of SPM Cortical Segmentation, Pyradiomics and Machine-Learning Analysis

BACKGROUND

Early in-vivo diagnosis of Alzheimer's disease (AD) is crucial for accurate management of patients, in particular, to select subjects with mild cognitive impairment (MCI) that may evolve into AD, and to define other types of MCI non-AD patients. The application of artificial intelligence to functional brain [18F]fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography(CT) aiming to increase diagnostic accuracy in the diagnosis of AD is still undetermined. In this field, we propose a radiomics analysis on advanced imaging segmentation method Statistical Parametric Mapping (SPM)-based completed with a Machine-Learning (ML) application to predict the diagnosis of AD, also by comparing the results with following Amyloid-PET and final clinical diagnosis.

METHODS

From July 2016 to September 2017, 43 patients underwent PET/CT scans with FDG and Florbetaben brain PET/CT and at least 24 months of clinical/instrumental follow-up. Patients were retrospectively evaluated by a multidisciplinary team (MDT = Neurologist, Psychologist, Radiologist, Nuclear Medicine Physician, Laboratory Clinic) at the G. Giglio Institute in Cefalù, Italy. Starting from the cerebral segmentations applied by SPM on the main cortical macro-areas of each patient, Pyradiomics was used for the feature extraction process; subsequently, an innovative descriptive-inferential mixed sequential approach and a machine learning algorithm (i.e., discriminant analysis) were used to obtain the best diagnostic performance in prediction of amyloid deposition and the final diagnosis of AD.

RESULTS

A total of 11 radiomics features significantly predictive of cortical beta-amyloid deposition (n = 6) and AD (n = 5) were found. Among them, two higher-order features (original_glcm_Idmn and original_glcm_Id), extracted from the limbic enthorinal cortical area (ROI-1) in the FDG-PET/CT images, predicted the positivity of Amyloid-PET/CT scans with maximum values of sensitivity (SS), specificity (SP), precision (PR) and accuracy (AC) of 84.92%, 75.13%, 73.75%, and 79.56%, respectively. Conversely, for the prediction of the clinical-instrumental final diagnosis of AD, the best performance was obtained by two higher-order features (original_glcm_MCC and original_glcm_Maximum Probability) extracted from ROI-2 (frontal cortex) with a SS, SP, PR and AC of 75.16%, 80.50%, 77.68%, and 78.05%, respectively, and by one higher-order feature (original_glcm_Idmn) extracted from ROI-3 (medial Temporal cortex; SS = 80.88%, SP = 76.85%, PR = 75.63%, AC = 78.76%.

CONCLUSIONS

The results obtained in this preliminary study support advanced segmentation of cortical areas typically involved in early AD on FDG PET/CT brain images, and radiomics analysis for the identification of specific high-order features to predict Amyloid deposition and final diagnosis of AD.

A New Preclinical Decision Support System Based on PET Radiomics: A Preliminary Study on the Evaluation of an Innovative 64Cu-Labeled Chelator in Mouse Models

The 64Cu-labeled chelator was analyzed in vivo by positron emission tomography (PET) imaging to evaluate its biodistribution in a murine model at different acquisition times. For this purpose, nine 6-week-old female Balb/C nude strain mice underwent micro-PET imaging at three different time points after 64Cu-labeled chelator injection. Specifically, the mice were divided into group 1 (acquisition 1 h after [64Cu] chelator administration, n = 3 mice), group 2 (acquisition 4 h after [64Cu]chelator administration, n = 3 mice), and group 3 (acquisition 24 h after [64Cu] chelator administration, n = 3 mice). Successively, all PET studies were segmented by means of registration with a standard template space (3D whole-body Digimouse atlas), and 108 radiomics features were extracted from seven organs (namely, heart, bladder, stomach, liver, spleen, kidney, and lung) to investigate possible changes over time in [64Cu]chelator biodistribution. The one-way analysis of variance and post hoc Tukey Honestly Significant Difference test revealed that, while heart, stomach, spleen, kidney, and lung districts showed a very low percentage of radiomics features with significant variations (p-value < 0.05) among the three groups of mice, a large number of features (greater than 60% and 50%, respectively) that varied significantly between groups were observed in bladder and liver, indicating a different in vivo uptake of the 64Cu-labeled chelator over time. The proposed methodology may improve the method of calculating the [64Cu]chelator biodistribution and open the way towards a decision support system in the field of new radiopharmaceuticals used in preclinical imaging trials.

Artificial Intelligence Applications on Restaging [18F]FDG PET/CT in Metastatic Colorectal Cancer: A Preliminary Report of Morpho-Functional Radiomics Classification for Prediction of Disease Outcome

The aim of this study was to investigate the application of [18F]FDG PET/CT images-based textural features analysis to propose radiomics models able to early predict disease progression (PD) and survival outcome in metastatic colorectal cancer (MCC) patients after first adjuvant therapy. For this purpose, 52 MCC patients who underwent [18F]FDGPET/CT during the disease restaging process after the first adjuvant therapy were analyzed. Follow-up data were recorded for a minimum of 12 months after PET/CT. Radiomics features from each avid lesion in PET and low-dose CT images were extracted. A hybrid descriptive-inferential method and the discriminant analysis (DA) were used for feature selection and for predictive model implementation, respectively. The performance of the features in predicting PD was performed for per-lesion analysis, per-patient analysis, and liver lesions analysis. All lesions were again considered to assess the diagnostic performance of the features in discriminating liver lesions. In predicting PD in the whole group of patients, on PET features radiomics analysis, among per-lesion analysis, only the GLZLM_GLNU feature was selected, while three features were selected from PET/CT images data set. The same features resulted more accurately by associating CT features with PET features (AUROC 65.22%). In per-patient analysis, three features for stand-alone PET images and one feature (i.e., HUKurtosis) for the PET/CT data set were selected. Focusing on liver metastasis, in per-lesion analysis, the same analysis recognized one PET feature (GLZLM_GLNU) from PET images and three features from PET/CT data set. Similarly, in liver lesions per-patient analysis, we found three PET features and a PET/CT feature (HUKurtosis). In discrimination of liver metastasis from the rest of the other lesions, optimal results of stand-alone PET imaging were found for one feature (SUVbwmin; AUROC 88.91%) and two features for merged PET/CT features analysis (AUROC 95.33%). In conclusion, our machine learning model on restaging [18F]FDGPET/CT was demonstrated to be feasible and potentially useful in the predictive evaluation of disease progression in MCC.

[68Ga]DOTATOC PET/CT Radiomics to Predict the Response in GEP-NETs Undergoing [177Lu]DOTATOC PRRT: The “Theragnomics” Concept

Despite impressive results, almost 30% of NET do not respond to PRRT and no well-established criteria are suitable to predict response. Therefore, we assessed the predictive value of radiomics [68Ga]DOTATOC PET/CT images pre-PRRT in metastatic GEP NET. We retrospectively analyzed the predictive value of radiomics in 324 SSTR-2-positive lesions from 38 metastatic GEP-NET patients (nine G1, 27 G2, and two G3) who underwent restaging [68Ga]DOTATOC PET/CT before complete PRRT with [177Lu]DOTATOC. Clinical, laboratory, and radiological follow-up data were collected for at least six months after the last cycle. Through LifeX, we extracted 65 PET features for each lesion. Grading, PRRT number of cycles, and cumulative activity, pre- and post-PRRT CgA values were also considered as additional clinical features. [68Ga]DOTATOC PET/CT follow-up with the same scanner for each patient determined the disease status (progression vs. response in terms of stability/reduction/disappearance) for each lesion. All features (PET and clinical) were also correlated with follow-up data in a per-site analysis (liver, lymph nodes, and bone), and for features significantly associated with response, the Δradiomics for each lesion was assessed on follow-up [68Ga]DOTATOC PET/CT performed until nine months post-PRRT. A statistical system based on the point-biserial correlation and logistic regression analysis was used for the reduction and selection of the features. Discriminant analysis was used, instead, to obtain the predictive model using the k-fold strategy to split data into training and validation sets. From the reduction and selection process, HISTO_Skewness and HISTO_Kurtosis were able to predict response with an area under the receiver operating characteristics curve (AUC ROC), sensitivity, and specificity of 0.745, 80.6%, 67.2% and 0.722, 61.2%, 75.9%, respectively. Moreover, a combination of three features (HISTO_Skewness; HISTO_Kurtosis, and Grading) did not improve the AUC significantly with 0.744. SUVmax. However, it could not predict response to PRRT (p = 0.49, AUC 0.523). The presented preliminary “theragnomics” model proved to be superior to conventional quantitative parameters to predict the response of GEP-NET lesions in patients treated with complete [177Lu]DOTATOC PRRT, regardless of the lesion site.

Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients

After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate-specific antigen (PSA) elevation during follow-up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naïve Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason's score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models' performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow-up when disease progression was suspected.

Deep Learning Networks for Automatic Retroperitoneal Sarcoma Segmentation in Computerized Tomography

The volume estimation of retroperitoneal sarcoma (RPS) is often difficult due to its huge dimensions and irregular shape; thus, it often requires manual segmentation, which is time-consuming and operator-dependent. This study aimed to evaluate two fully automated deep learning networks (ENet and ERFNet) for RPS segmentation. This retrospective study included 20 patients with RPS who received an abdominal computed tomography (CT) examination. Forty-nine CT examinations, with a total of 72 lesions, were included. Manual segmentation was performed by two radiologists in consensus, and automatic segmentation was performed using ENet and ERFNet. Significant differences between manual and automatic segmentation were tested using the analysis of variance (ANOVA). A set of performance indicators for the shape comparison (namely sensitivity), positive predictive value (PPV), dice similarity coefficient (DSC), volume overlap error (VOE), and volumetric differences (VD) were calculated. There were no significant differences found between the RPS volumes obtained using manual segmentation and ENet (p-value = 0.935), manual segmentation and ERFNet (p-value = 0.544), or ENet and ERFNet (p-value = 0.119). The sensitivity, PPV, DSC, VOE, and VD for ENet and ERFNet were 91.54% and 72.21%, 89.85% and 87.00%, 90.52% and 74.85%, 16.87% and 36.85%, and 2.11% and -14.80%, respectively. By using a dedicated GPU, ENet took around 15 s for segmentation versus 13 s for ERFNet. In the case of CPU, ENet took around 2 min versus 1 min for ERFNet. The manual approach required approximately one hour per segmentation. In conclusion, fully automatic deep learning networks are reliable methods for RPS volume assessment. ENet performs better than ERFNet for automatic segmentation, though it requires more time.

Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis

Objectives

To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG).

Methods

Patients with histologically confirmed TET in the years 2000–2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance.

Results

105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22–82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3–94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9–93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8–79.5).

Conclusions

CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.

Machine learning-based prediction of invisible intraprostatic prostate cancer lesions on 68 Ga-PSMA-11 PET/CT in patients with primary prostate cancer

PURPOSE

⁶⁸ Ga-PSMA PET/CT has high specificity and sensitivity for the detection of both intraprostatic tumor focal lesions and metastasis. However, approximately 10% of primary prostate cancer are invisible on PSMA-PET (exhibit no or minimal uptake). In this work, we investigated whether machine learning-based radiomics models derived from PSMA-PET images could predict invisible intraprostatic lesions on ⁶⁸ Ga-PSMA-11 PET in patients with primary prostate cancer.

METHODS

In this retrospective study, patients with or without prostate cancer who underwent ⁶⁸ Ga-PSMA PET/CT and presented negative on PSMA-PET image at either of two different institutions were included: institution 1 (between 2017 and 2020) for the training set and institution 2 (between 2019 and 2020) for the external test set. Three random forest (RF) models were built using selected features extracted from standard PET images, delayed PET images, and both standard and delayed PET images. Then, subsequent tenfold cross-validation was performed. In the test phase, the three RF models and PSA density (PSAD, cut-off value: 0.15 ng/ml/ml) were tested with the external test set. The area under the receiver operating characteristic curve (AUC) was calculated for the models and PSAD. The AUCs of the radiomics model and PSAD were compared.

RESULTS

A total of 64 patients (39 with prostate cancer and 25 with benign prostate disease) were in the training set, and 36 (21 with prostate cancer and 15 with benign prostate disease) were in the test set. The average AUCs of the three RF models from tenfold cross-validation were 0.87 (95% CI: 0.72, 1.00), 0.86 (95% CI: 0.63, 1.00), and 0.91 (95% CI: 0.69, 1.00), respectively. In the test set, the AUCs of the three trained RF models and PSAD were 0.903 (95% CI: 0.830, 0.975), 0.856 (95% CI: 0.748, 0.964), 0.925 (95% CI:0.838, 1.00), and 0.662 (95% CI: 0.510, 0.813). The AUCs of the three radiomics models were higher than that of PSAD (0.903, 0.856, and 0.925 vs. 0.662, respectively; P = .007, P = .045, and P = .005, respectively).

CONCLUSION

Random forest models developed by ⁶⁸ Ga-PSMA-11 PET-based radiomics features were proven useful for accurate prediction of invisible intraprostatic lesion on ⁶⁸ Ga-PSMA-11 PET in patients with primary prostate cancer and showed better diagnostic performance compared with PSAD.