Applications and limitations of radiomics

Contrast computed tomography-based radiomics is correlation with COG risk stratification of neuroblastoma

PURPOSE

Although a risk stratification strategy for neuroblastoma (NB) has been proposed, precise and convenient clinical risk estimation remains challenging. This study aimed to investigate the correlation of contrast computed tomography (CT)-based radiomics with NB risk stratification.

METHODS

Patients with NB (n = 289) from two centers (244 and 45 patients in the training/testing and external validation cohorts, respectively) were divided into nonhigh- and high-risk groups. A total of 1648 radiomics features were extracted from the arterial phase, and the radiomics signature was constructed using rad scores, whereas the clinical model was established based on clinical factors. Further, a combined nomogram was developed based on the clinical factors and radiomics signatures. Finally, receiver operating characteristic curve and decision curve analyses (DCA) were used to assess the performance of the established models.

RESULTS

Seventeen radiomics features were used to construct the radiomics signature. A significant difference was observed in the rad score between the two groups in the training (0.540 vs. 0.704, P < 0.001) and testing (0.563 vs. 0.969, P < 0.001) cohorts. The nomogram showed a higher area under the curve (AUC) in the training (AUC = 0.87), testing (AUC = 0.83), and external validation (AUC = 0.84) cohorts than other models. The Hosmer-Lemeshow test and calibration curves indicated that the nomogram fit perfectly. DCA demonstrated that the clinical-radiomics nomogram was more beneficial.

CONCLUSIONS

Contrast CT-based radiomics shows correlation with COG risk stratification of NB. Radiomics features combined with clinical factors showed the best performance, which may improve the management of patients with NB.

Colorectal liver metastases patients prognostic assessment: prospects and limits of radiomics and radiogenomics

In this narrative review, we reported un up-to-date on the role of radiomics to assess prognostic features, which can impact on the liver metastases patient treatment choice. In the liver metastases patients, the possibility to assess mutational status (RAS or MSI), the tumor growth pattern and the histological subtype (NOS or mucinous) allows a better treatment selection to avoid unnecessary therapies. However, today, the detection of these features require an invasive approach. Recently, radiomics analysis application has improved rapidly, with a consequent growing interest in the oncological field. Radiomics analysis allows the textural characteristics assessment, which are correlated to biological data. This approach is captivating since it should allow to extract biological data from the radiological images, without invasive approach, so that to reduce costs and time, avoiding any risk for the patients. Several studies showed the ability of Radiomics to identify mutational status, tumor growth pattern and histological type in colorectal liver metastases. Although, radiomics analysis in a non-invasive and repeatable way, however features as the poor standardization and generalization of clinical studies results limit the translation of this analysis into clinical practice. Clear limits are data-quality control, reproducibility, repeatability, generalizability of results, and issues related to model overfitting.

Are deep models in radiomics performing better than generic models? A systematic review

BACKGROUND

Application of radiomics proceeds by extracting and analysing imaging features based on generic morphological, textural, and statistical features defined by formulas. Recently, deep learning methods were applied. It is unclear whether deep models (DMs) can outperform generic models (GMs).

METHODS

We identified publications on PubMed and Embase to determine differences between DMs and GMs in terms of receiver operating area under the curve (AUC).

RESULTS

Of 1,229 records (between 2017 and 2021), 69 studies were included, 61 (88%) on tumours, 68 (99%) retrospective, and 39 (56%) single centre; 30 (43%) used an internal validation cohort; and 18 (26%) applied cross-validation. Studies with independent internal cohort had a median training sample of 196 (range 41-1,455); those with cross-validation had only 133 (43-1,426). Median size of validation cohorts was 73 (18-535) for internal and 94 (18-388) for external. Considering the internal validation, in 74% (49/66), the DMs performed better than the GMs, vice versa in 20% (13/66); no difference in 6% (4/66); and median difference in AUC 0.045. On the external validation, DMs were better in 65% (13/20), GMs in 20% (4/20) cases; no difference in 3 (15%); and median difference in AUC 0.025. On internal validation, fused models outperformed GMs and DMs in 72% (20/28), while they were worse in 14% (4/28) and equal in 14% (4/28); median gain in AUC was + 0.02. On external validation, fused model performed better in 63% (5/8), worse in 25% (2/8), and equal in 13% (1/8); median gain in AUC was + 0.025.

CONCLUSIONS

Overall, DMs outperformed GMs but in 26% of the studies, DMs did not outperform GMs.

Effectiveness of Radiomic ZOT Features in the Automated Discrimination of Oncocytoma from Clear Cell Renal Cancer

Background: Benign renal tumors, such as renal oncocytoma (RO), can be erroneously diagnosed as malignant renal cell carcinomas (RCC), because of their similar imaging features. Computer-aided systems leveraging radiomic features can be used to better discriminate benign renal tumors from the malignant ones. The purpose of this work was to build a machine learning model to distinguish RO from clear cell RCC (ccRCC). Method: We collected CT images of 77 patients, with 30 cases of RO (39%) and 47 cases of ccRCC (61%). Radiomic features were extracted both from the tumor volumes identified by the clinicians and from the tumor’s zone of transition (ZOT). We used a genetic algorithm to perform feature selection, identifying the most descriptive set of features for the tumor classification. We built a decision tree classifier to distinguish between ROs and ccRCCs. We proposed two versions of the pipeline: in the first one, the feature selection was performed before the splitting of the data, while in the second one, the feature selection was performed after, i.e., on the training data only. We evaluated the efficiency of the two pipelines in cancer classification. Results: The ZOT features were found to be the most predictive by the genetic algorithm. The pipeline with the feature selection performed on the whole dataset obtained an average ROC AUC score of 0.87 ± 0.09. The second pipeline, in which the feature selection was performed on the training data only, obtained an average ROC AUC score of 0.62 ± 0.17. Conclusions: The obtained results confirm the efficiency of ZOT radiomic features in capturing the renal tumor characteristics. We showed that there is a significant difference in the performances of the two proposed pipelines, highlighting how some already published radiomic analyses could be too optimistic about the real generalization capabilities of the models.

Ultrasound-based radiomics in the diagnosis of carpal tunnel syndrome: The influence of regions of interest delineation method on mode

BACKGROUND

In the recent years, artificial intelligence (AI) algorithms have been used to accurately diagnose musculoskeletal diseases. However, it is not known whether the particular regions of interest (ROI) delineation method would affect the performance of the AI algorithm.

PURPOSE

The purpose of this study was to investigate the influence of ROI delineation methods on model performance and observer consistency.

METHODS

In this retrospective analysis, ultrasound (US) measures of median nerves affected with carpal tunnel syndrome (CTS) were compared to median nerves in a control group without CTS. Two methods were used for delineation of the ROI: (1) the ROI along the hyperechoic medial edge of the median nerve but not including the epineurium (MN) (ROI1); and (2) the ROI including the hyperechoic epineurium (ROI2), respectively. The intra group correlation coefficient (ICC) was used to compare the observer consistency of ROI features (i.e. the corresponding radiomics parameters). Parameters α₁ and α₂ were obtained based on the ICC of ROI₁ features and ROI₂ features. The ROC analysis was used to determine the area under the curve (AUC) and evaluate the performance of the radiologists and network. In addition, four indices, namely sensitivity, specificity, positive prediction and negative prediction were analyzed too.

RESULTS

A total of 136 wrists of 77 CTS group and 136 wrists of 74 control group were included in the study. Control group was matched to CTS group according to the age and sex. The observer consistency of ROI features delineated by the two schemes was different, and the consistency of ROI₁ features was higher (α1 ˃ α2). The intra-observer consistency was higher than the inter-observer consistency regardless of the scheme, and the intra-observer consistency was higher when chose scheme one. The performances of models based on the two ROI features were different, although the AUC of each model was greater than 0.8.The model performed better when the MN epineurium was included in the ROI. Among five artificial intelligence algorithms, the Forest models (model₁ achieved an AUC of 0.921 in training datasets and 0.830 in testing datasets; model₂ achieved an AUC of 0.967 in training datasets and 0.872 in testing datasets.) obtained the highest performance, followed by the support vector machine (SVM) models and the Logistic models. The performances of the models were significantly better than the inexperienced radiologist (Dr. B. Z. achieved an AUC of 0.702).

CONCLUSION

Different ROI delineation methods may affect the performance of the model and the consistency of observers. Model performance was better when the ROI contained the MN epineurium, and observer consistency was higher when the ROI was delineated along the hyperechoic medial border of the MN.

Influence of Image Processing on Radiomic Features From Magnetic Resonance Imaging

OBJECTIVE

Before implementing radiomics in routine clinical practice, comprehensive knowledge about the repeatability and reproducibility of radiomic features is required. The aim of this study was to systematically investigate the influence of image processing parameters on radiomic features from magnetic resonance imaging (MRI) in terms of feature values as well as test-retest repeatability.

MATERIALS AND METHODS

Utilizing a phantom consisting of 4 onions, 4 limes, 4 kiwifruits, and 4 apples, we acquired a test-retest dataset featuring 3 of the most commonly used MRI sequences on a 3 T scanner, namely, a T1-weighted, a T2-weighted, and a fluid-attenuated inversion recovery sequence, each at high and low resolution. After semiautomatic image segmentation, image processing with systematic variation of image processing parameters was performed, including spatial resampling, intensity discretization, and intensity rescaling. For each respective image processing setting, a total of 45 radiomic features were extracted, corresponding to the following 7 matrices/feature classes: conventional indices, histogram matrix, shape matrix, gray-level zone length matrix, gray-level run length matrix, neighboring gray-level dependence matrix, and gray-level cooccurrence matrix. Systematic differences of individual features between different resampling steps were assessed using 1-way analysis of variance with Tukey-type post hoc comparisons to adjust for multiple testing. Test-retest repeatability of radiomic features was measured using the concordance correlation coefficient, dynamic range, and intraclass correlation coefficient.

RESULTS

Image processing influenced radiological feature values. Regardless of the acquired sequence and feature class, significant differences ( P < 0.05) in feature values were found when the size of the resampled voxels was too large, that is, bigger than 3 mm. Almost all higher-order features depended strongly on intensity discretization. The effects of intensity rescaling were negligible except for some features derived from T1-weighted sequences. For all sequences, the percentage of repeatable features (concordance correlation coefficient and dynamic range ≥ 0.9) varied considerably depending on the image processing settings. The optimal image processing setting to achieve the highest percentage of stable features varied per sequence. Irrespective of image processing, the fluid-attenuated inversion recovery sequence in high-resolution overall yielded the highest number of stable features in comparison with the other sequences (89% vs 64%-78% for the respective optimal image processing settings). Across all sequences, the most repeatable features were generally obtained for a spatial resampling close to the originally acquired voxel size and an intensity discretization to at least 32 bins.

CONCLUSION

Variation of image processing parameters has a significant impact on the values of radiomic features as well as their repeatability. Furthermore, the optimal image processing parameters differ for each MRI sequence. Therefore, it is recommended that these processing parameters be determined in corresponding test-retest scans before clinical application. Extensive repeatability, reproducibility, and validation studies as well as standardization are required before quantitative image analysis and radiomics can be reliably translated into routine clinical care.

Prognostic radiomic signature for head and neck cancer: development and validation on a multi-centric MRI dataset

BACKGROUND AND PURPOSE

Prognosis in locally advanced head and neck cancer (HNC) is currently based on TNM staging system and tumor subsite. However, quantitative imaging features (i.e., radiomic features) from magnetic resonance imaging (MRI) may provide additional prognostic info. The aim of this work is to develop and validate an MRI-based prognostic radiomic signature for locally advanced HNC.

MATERIALS AND METHODS

Radiomic features were extracted from T1- and T2-weighted MRI (T1w and T2w) using the segmentation of the primary tumor as mask. In total 1072 features (536 per image type) were extracted for each tumor. A retrospective multi-centric dataset (n=285) was used for features selection and model training. The selected features were used to fit a Cox proportional hazard regression model for overall survival (OS) that outputs the radiomic signature. The signature was then validated on a prospective multi-centric dataset (n=234). Prognostic performance for OS and disease-free survival (DFS) was evaluated using C-index. Additional prognostic value of the radiomic signature was explored.

RESULTS

The radiomic signature had C-index=0.64 for OS and C-index=0.60 for DFS in the validation set. The addition of the radiomic signature to other clinical features (TNM staging and tumor subsite) increased prognostic ability for both OS (HPV- C-index 0.63 to 0.65; HPV+ C-index 0.75 to 0.80) and DFS (HPV- C-index 0.58 to 0.61; HPV+ C-index 0.64 to 0.65).

CONCLUSION

An MRI-based prognostic radiomic signature was developed and prospectively validated. Such signature can successfully integrate clinical factors in both HPV+ and HPV- tumors. Grant support: European Union Horizon 2020 Framework Programme, Grant/Award, Number: 689715.

Analysis of radiomic features derived from post-contrast T1-weighted images and apparent diffusion coefficient (ADC) maps for breast lesion evaluation: A retrospective study

INTRODUCTION

Breast cancer is the most common malignancy among women, and its diagnosis relies on medical imaging and the invasive, uncomforted biopsy. Recent advances in quantitative imaging and specifically the application of radiomics has proved to be a very promising technique, facilitating both diagnosis and therapy. The purpose of this study is to assess radiomic features derived from post-contrast T1w Magnetic Resonance Imaging (MRI) sequences and Apparent Diffusion Coefficient (ADC) maps for the evaluation of breast pathologies.

METHODS

MRI data from 52 women were retrospectively reviewed, involving 54 breast lesions, both malignant and benign. Diffusion Weighted Imaging (DWI) was applied as a standard MRΙ protocol, including dynamic contrast-enhanced (DCE) MRΙ in all cases. All patients were examined on a 1.5T MRI scanner, and 216 features were initially extracted from DCE-MRI images. Histological analysis of the breast lesions was performed, and a comparative analysis of the results was carried out to assess the accuracy of the method.

RESULTS

Following surgery and histological analysis, 30 lesions were found to be malignant and 24 benign. Implementation of a Machine Learning (ML) classification algorithm with 5-fold cross-validation resulted in a sensitivity of 70%, specificity of 66%, Negative Predictive Value of 82% and overall accuracy of 67% in differentiating malignancy from benevolence.

CONCLUSION

Texture analysis and ML methodology based on the first post-contrast dynamic sequences and ADC maps may be employed to differentiate between malignant and benign breast lesions, offering a promising new tool for diagnostic analysis.

IMPLICATIONS FOR PRACTICE

The results of this study will enhance knowledge around application and performance of radiomics in breast MRI, thus helping MRI radiographers who use AI-enabled technologies to better delineate the pros and cons of these procedures.

Human papilomaviru-related oropharyngeal squamous cell carcinoma and radiomics: A new era?

BACKGROUND

The increase of the incidence of human papillomavirus dependent oropharyngeal squamous cell carcinoma is alarming, although we have greatly progressed in the classification and staging of this disease. We now know that human papillomavirus related oropharyngeal squamous cell carcinoma is a sub-type of head and neck squamous cell carcinoma with favourable prognosis and good response to therapy that needs a proper system of classification and staging. Thus, in routine practice it is essential to test patients for the presence of human papillomavirus. The most popular technique to assess human papillomavirus status is immunohistochemistry on biopsy samples with p16, which is an excellent surrogate for high-risk human papillomavirus infection. Another highly sensitive and specific tissue-based technique for the detection of human papillomavirus is RNAscope In situ hybridization that has a prohibitive cost, limiting its use in routine practice. Radiomics is an artificial intelligence based non-invasive method of computational analysis of computed tomography, magnetic resonance imaging, positron emission tomography, and ultrasound images.

METHODS

In this review, we summarise the last findings of radiomics applied to human papillomavirus associated oropharyngeal squamous cell carcinoma.

RESULTS

A growing body of evidence suggest that radiomics is able to characterise and detect early relapse after treatment, and enable development of tailored therapy of human papillomavirus positive oropharyngeal squamous cell carcinoma.

Exploring the opinion of Spanish medical specialists about the usefulness of radiomics in oncology

AIM

To describe the knowledge and opinion of health professionals regarding the usefulness of radiomics in oncology.

METHODS

A 12-question questionnaire (multiple-choice responses, Likert-type scale, and open response) was developed and sent to professionals related to diagnosis/treatment of oncological diseases (Oncology, Radiodiagnosis, Nuclear Medicine, Radiation Oncology, Hematology-Oncology, Radiophysics and Pathology). Participants were classified into two groups according to their level of training: attending physicians and residents.

RESULTS

114 professionals completed the survey (54% residents, mostly from Nuclear Medicine and Radiodiagnostic specialties). Attending physicians obtained a better performance in the area pf knowledge compared to residents. Both groups of respondents agreed regarding the usefulness of radiomics to help make more accurate diagnoses and promoting the work of medical teams and the most frequent disadvantages were related to the lack of systematization in the acquisition of images and extraction of parameters, the need for the training of professionals and concern about the replacement of human work by technological tools.

CONCLUSIONS

Radiomics is a novel field and the most general aspects are known by health professionals. The professionals surveyed were optimistic about the benefits provided by radiomics and other types of tools. The main problem detected was the lack of systematization in its implementation. The replacement of professionals and job loss is a concern, albeit less prevalent, and may respond to a generational phenomenon.

See Lung Cancer with an AI

A lot has happened in the field of lung cancer screening in recent months. The ongoing discussion and documentation published by the scientific community and policymakers are of great importance to the entire European community and perhaps beyond. Lung cancer is the main worldwide killer. Low-dose computed tomography-based screening, together with smoking cessation, is the only tool to fight lung cancer, as it has already been proven in the United States of America but also European randomized controlled trials. Screening requires a lot of well-organized specialized work, but it can be supported by artificial intelligence (AI). Here we discuss whether and how to use AI for patients, radiologists, pulmonologists, thoracic surgeons, and all hospital staff supporting screening process benefits.

An ordinal radiomic model to predict the differentiation grade of invasive non-mucinous pulmonary adenocarcinoma based on low-dose computed tomography in lung cancer screening

OBJECTIVES

To construct a radiomic model of low-dose CT (LDCT) to predict the differentiation grade of invasive non-mucinous pulmonary adenocarcinoma (IPA) and compare its diagnostic performance with quantitative-semantic model and radiologists.

METHODS

A total of 682 pulmonary nodules were divided into the primary cohort (181 grade 1; 254 grade 2; 64 grade 3) and validation cohort (69 grade 1; 99 grade 2; 15 grade 3) according to scanners. The radiomic and quantitative-semantic models were built using ordinal logistic regression. The diagnostic performance of the models and radiologists was assessed by the area under the curve (AUC) of the receiver operating characteristic curve and accuracy.

RESULTS

The radiomic model demonstrated excellent diagnostic performance in the validation cohort (AUC, 0.900 (95%CI: 0.847-0.939) for Grade 1 vs. Grade 2/Grade 3; AUC, 0.929 (95%CI: 0.882-0.962) for Grade 1/Grade 2 vs. Grade 3; accuracy, 0.803 (95%CI: 0.737-0.857)). No significant difference in diagnostic performance was found between the radiomic model and radiological expert (AUC, 0.840 (95%CI: 0.779-0.890) for Grade 1 vs. Grade 2/Grade 3, p = 0.130; AUC, 0.852 (95%CI: 0.793-0.900) for Grade 1/Grade 2 vs. Grade 3, p = 0.170; accuracy, 0.743 (95%CI: 0.673-0.804), p = 0.079), but the radiomic model outperformed the quantitative-semantic model and inexperienced radiologists (all p < 0.05).

CONCLUSIONS

The radiomic model of LDCT can be used to predict the differentiation grade of IPA in lung cancer screening, and its diagnostic performance is comparable to that of radiological expert.

KEY POINTS

• Early identifying the novel differentiation grade of invasive non-mucinous pulmonary adenocarcinoma may provide guidance for further surveillance, surgical strategy, or more adjuvant treatment. • The diagnostic performance of the radiomic model is comparable to that of a radiological expert and superior to that of the quantitative-semantic model and inexperienced radiologists. • The radiomic model of low-dose CT can be used to predict the differentiation grade of invasive non-mucinous pulmonary adenocarcinoma in lung cancer screening.

Post-Surgical Imaging Assessment in Rectal Cancer: Normal Findings and Complications

Rectal cancer (RC) is one of the deadliest malignancies worldwide. Surgery is the most common treatment for RC, performed in 63.2% of patients. The type of surgical approach chosen aims to achieve maximum residual function with the lowest risk of recurrence. The selection is made by a multidisciplinary team that assesses the characteristics of the patient and the tumor. Total mesorectal excision (TME), including both low anterior resection (LAR) and abdominoperineal resection (APR), is still the standard of care for RC. Radical surgery is burdened by a 31% rate of major complications (Clavien-Dindo grade 3-4), such as anastomotic leaks and a risk of a permanent stoma. In recent years, less-invasive techniques, such as local excision, have been tested. These additional procedures could mitigate the morbidity of rectal resection, while providing acceptable oncologic results. The "watch and wait" approach is not a globally accepted model of care but encouraging results on selected groups of patients make it a promising strategy. In this plethora of treatments, the radiologist is called upon to distinguish a physiological from a pathological postoperative finding. The aim of this narrative review is to identify the main post-surgical complications and the most effective imaging techniques.

Preliminary study on CT contrast-enhanced radiomics for predicting central cervical lymph node status in patients with thyroid nodules

Objective

To explore the feasibility of using a contrast-enhanced CT image-based radiomics model to predict central cervical lymph node status in patients with thyroid nodules.

Methods

Pretreatment clinical and CT imaging data from 271 patients with surgically diagnosed and treated thyroid nodules were retrospectively analyzed. According to the pathological features of the thyroid nodules and central lymph nodes, the patients were divided into three groups: group 1: papillary thyroid carcinoma (PTC) metastatic lymph node group; group 2: PTC nonmetastatic lymph node group; and group 3: benign thyroid nodule reactive lymph node group. Radiomics models were constructed to compare the three groups by pairwise classification (model 1: group 1 vs group 3; model 2: group 1 vs group 2; model 3: group 2 vs group 3; and model 4: group 1 vs groups (2 + 3)). The feature parameters with good generalizability and clinical risk factors were screened. A nomogram was constructed by combining the radiomics features and clinical risk factors. Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) were performed to assess the diagnostic and clinical value of the nomogram.

Results

For radiomics models 1, 2, and 3, the areas under the curve (AUCs) in the training group were 0.97, 0.96, and 0.93, respectively. The following independent clinical risk factors were identified: model 1, arterial phase CT values; model 2, sex and arterial phase CT values; model 3: none. The AUCs for the nomograms of models 1 and 2 in the training group were 0.98 and 0.97, respectively, and those in the test group were 0.95 and 0.87, respectively. The AUCs of the model 4 nomogram in the training and test groups were 0.96 and 0.94, respectively. Calibration curve analysis and DCA revealed the high clinical value of the nomograms of models 1, 2 and 4.

Conclusion

The nomograms based on contrast-enhanced CT images had good predictive efficacy in classifying benign and malignant central cervical lymph nodes of thyroid nodule patients.

Prediction of short-term prognosis of patients with hypertensive intracerebral hemorrhage by radiomic-clinical nomogram

Hypertensive intracerebral hemorrhage (HICH) is the most common type of spontaneous intracerebral hemorrhage in China which is associated with high mortality and disability. We sought to develop and validate a noncontrast computed tomography (NCCT)-based nomogram model to achieve short-term prognostic prediction for patients with HICH. We retrospectively studied 292 patients with HICH from two medical centers, and they were divided into training (n = 151), validation (n = 66), and testing cohorts (n = 75). Based on radiomics, univariate and multivariate, and logistic regression analyses, four models (black hole sign, clinical, radiomics score, and combined models) were established to predict the prognosis of patients with HICH 30 days after the onset. The results suggested that the combined model had the best predictive performance with the area under the receiver operating characteristic curve (AUC) of 0.821, 0.816, and 0.815 in the training, validation, and testing cohorts, respectively. In addition, a radiomics-clinical (R-C) nomogram was visualized. A calibration curve analysis showed that the R-C nomogram had satisfactory calibration in the three cohorts. A decision curve analysis demonstrated that the R-C nomogram was clinically valuable. Our results suggest that the R-C nomogram can accurately and reliably predict the short-term prognosis of patients with HICH and provide a useful evaluation for making individualized treatment plans.

Does radiomics play a role in the diagnosis, staging and re-staging of gastroesophageal junction adenocarcinoma?

Radiomics is an emerging field of investigation in medicine consisting in the extraction of quantitative features from conventional medical images and exploring their potentials in improving diagnosis, prognosis and outcome prediction after therapy. Clinical applications are still limited, mostly due to reproducibility and repeatability issues as well as to limited interpretability of predictive radiomic-based features/signatures. In the specific case of gastroesophageal junction (GEJ) adenocarcinoma, the expectancies are particularly high, mainly due to its increasing incidence and to the limited performance of conventional imaging techniques in assessing correct diagnosis and accurate pre-surgical tumor characterization. Accordingly, current literature was reviewed, emphasizing the methodological quality. In addition, papers were scored according to the Radiomic Quality Score (RQS), weighting more the clinical applicability and generalizability of the resulting models. According to the criteria of the search, only two papers were retained: the resulting technical quality was relatively high for both, while the corresponding RQS were 15 and 19 (on a scale of 31). Although the potentials of radiomics in the setting of GEJ adenocarcinoma are relevant, they remain largely unexplored, warranting an urgent need of high-quality, possibly prospective, multicenter studies.

Multiparametric MRI-based radiomics for the prediction of microvascular invasion in hepatocellular carcinoma

BACKGROUND

Preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is essential in obtaining a successful surgical treatment, in decreasing recurrence, and in improving survival.

PURPOSE

To investigate the value of multiparametric magnetic resonance imaging (MRI)-based radiomics in the prediction of peritumoral MVI in HCC.

MATERIAL AND METHODS

A total of 102 patient with pathologically proven HCC after surgical resection from June 2014 to March 2018 were enrolled in this retrospective study. Histological analysis of resected specimens confirmed positive MVI in 48 patients and negative MVI in 54 patients. Radiomics features were extracted from four MRI sequences and selected with the least absolute shrinkage and selection operator (LASSO) regression and used to analyze the tumoral and peritumoral regions for MVI. Univariate logistic regression was employed to identify the most important clinical factors, which were integrated with the radiomics signature to develop a nomogram.

RESULTS

In total, 11 radiomics features were selected and used to build the radiomics signature. The serum level of alpha-fetoprotein was identified as the clinical factor with the highest predictive value. The developed nomogram achieved the highest AUC in predicting MVI status. The decision curve analysis confirmed the potential clinical utility of the proposed nomogram.

CONCLUSION

The multiparametric MRI-based radiomics nomogram is a promising tool for the preoperative diagnosis of peritumoral MVI in HCCs and helps determine the appropriate medical or surgical therapy.

Sub-regional analysis of the parotid glands: model development for predicting late xerostomia with radiomics features in head and neck cancer patients

BACKGROUND

The irradiation of sub-regions of the parotid has been linked to xerostomia development in patients with head and neck cancer (HNC). In this study, we compared the xerostomia classification performance of radiomics features calculated on clinically relevant and de novo sub-regions of the parotid glands of HNC patients.

MATERIAL AND METHODS

All patients (N = 117) were treated with TomoTherapy in 30-35 fractions of 2-2.167 Gy per fraction with daily mega-voltage-CT (MVCT) acquisition for image-guidance purposes. Radiomics features (N = 123) were extracted from daily MVCTs for the whole parotid gland and nine sub-regions. The changes in feature values after each complete week of treatment were considered as predictors of xerostomia (CTCAEv4.03, grade ≥ 2) at 6 and 12 months. Combinations of predictors were generated following the removal of statistically redundant information and stepwise selection. The classification performance of the logistic regression models was evaluated on train and test sets of patients using the Area Under the Curve (AUC) associated with the different sub-regions at each week of treatment and benchmarked with the performance of models solely using dose and toxicity at baseline.

RESULTS

In this study, radiomics-based models predicted xerostomia better than standard clinical predictors. Models combining dose to the parotid and xerostomia scores at baseline yielded an AUCtest of 0.63 and 0.61 for xerostomia prediction at 6 and 12 months after radiotherapy while models based on radiomics features extracted from the whole parotid yielded a maximum AUCtest of 0.67 and 0.75, respectively. Overall, across sub-regions, maximum AUCtest was 0.76 and 0.80 for xerostomia prediction at 6 and 12 months. Within the first two weeks of treatment, the cranial part of the parotid systematically yielded the highest AUCtest.

CONCLUSION

Our results indicate that variations of radiomics features calculated on sub-regions of the parotid glands can lead to earlier and improved prediction of xerostomia in HNC patients.

Impact of Aggregation Methods for Texture Features on Their Robustness Performance: Application to Nasopharyngeal 18F-FDG PET/CT

PURPOSE

This study aims to investigate the impact of aggregation methods used for the generation of texture features on their robustness of nasopharyngeal carcinoma (NPC) based on ¹⁸F-FDG PET/CT images.

METHODS

128 NPC patients were enrolled and 95 texture features were extracted for each patient including six feature families under different aggregation methods. For GLCM and GLRLM features, six aggregation methods were considered. For GLSZM, GLDZM, NGTDM and NGLDM features, three aggregation methods were considered. The robustness of the features affected by aggregation methods was assessed by the pair-wise intra-class correlation coefficient (ICC). Furthermore, the effects of discretization and partial volume correction (PVC) on the percent of ICC categories of all texture features were evaluated by overall ICC instead of the pair-wise ICC.

RESULTS

There were 12 features with excellent pair-wise ICCs varying aggregation methods, namely joint average, sum average, autocorrelation, long run emphasis, high grey level run emphasis, short run high grey level emphasis, long run high grey level emphasis, run length variance, SZM high grey level emphasis, DZM high grey level emphasis, high grey level count emphasis and dependence count percentage. For GLCM and GLRLM features, 19/25 and 14/16 features showed excellent pair-wise ICCs varying aggregation methods (averaged and merged) on the same dimensional features (2D, 2.5D or 3D). Different discretization levels and partial volume corrections lead to consistent robustness of textural features affected by aggregation methods.

CONCLUSION

Different dimensional features with the same aggregation methods showed worse robustness compared with the same dimensional features with different aggregation methods. Different discretization levels and PVC algorithms had a negligible effect on the percent of ICC categories of all texture features.

Contrast enhanced magnetic resonance imaging-based radiomics nomogram for preoperatively predicting expression status of Ki-67 in meningioma: a two-center study

Background

The aim of this study was to develop and validate a radiomics nomogram for preoperative prediction of Ki-67 proliferative index (Ki-67 PI) expression in patients with meningioma.

Methods

A total of 280 patients from 2 independent hospital centers were enrolled. Patients from center I were randomly divided into a training cohort of 168 patients and a test cohort of 72 patients, and 40 patients from center II served as an external validation cohort. Interoperator reproducibility test, Z-score standardization, analysis of variance (ANOVA), and least absolute shrinkage and selection operator (LASSO) binary logistic regression were used to select radiomics features, which were extracted from contrast-enhanced T1-weighted imaging (CE-T1WI) imaging. The radiomics signature for predicting Ki-67 PI expression was developed and validated using 4 classifiers including logistic regression (LR), decision tree (DT), support vector machine (SVM), and adaptive boost (AdaBoost). Finally, combined radiological characteristics with radiomics signature were used to establish the nomogram to predict the risk of high Ki-67 PI expression in patients with meningioma.

Results

Fourteen radiomics features were used to construct the radiomics signature. The radiomics nomogram that incorporated the radiomics signature and radiological characteristics showed excellent discrimination in the training, test, and validation cohorts with areas under the curve of 0.817 (95% CI: 0.753-0.881), 0.822 (95% CI: 0.727-0.916), and 0.845 (95% CI: 0.708-0.982), respectively. In addition, the calibration curve for the nomogram demonstrated good agreement between prediction and actual observation.

Conclusions

The proposed contrast enhanced magnetic resonance imaging (MRI)-based radiomics nomogram could be an effective tool to predict the risk of Ki-67 high expression in patients with meningioma.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Diffusion radiomics for subtyping and clustering in autism spectrum disorder: A preclinical study

Autism spectrum disorder (ASD) is a highly prevalent, heterogenous neurodevelopmental disorder. Neuroimaging methods such as functional, structural, and diffusion MRI have been used to identify candidate imaging biomarkers for ASD, but current findings remain non-specific and likely arise from the heterogeneity present in ASD. To account for this, efforts to subtype ASD have emerged as a potential strategy for both the study of ASD and advancement of tailored behavioral therapies and therapeutics. Towards these ends, to improve upon current neuroimaging methods, we propose combining biologically sensitive neurite orientation dispersion and density index (NODDI) diffusion MR imaging with radiomics image processing to create a new methodological approach that, we hypothesize, can sensitively and specifically capture neurobiology. We demonstrate this method can sensitively distinguish differences between four genetically distinct rat models of ASD (Fmr1, Pten, Nrxn1, Disc1). Further, we demonstrate diffusion radiomic analyses hold promise for subtyping in ASD as we show unsupervised clustering of NODDI radiomic data generates clusters specific to the underlying genetic differences between the animal models. Taken together, our findings suggest the unique application of radiomic analysis on NODDI diffusion MRI may have the capacity to sensitively and specifically disambiguate the neurobiological heterogeneity present in the ASD population.

Risk Assessment and Cholangiocarcinoma: Diagnostic Management and Artificial Intelligence

Intrahepatic cholangiocarcinoma (iCCA) is the second most common primary liver tumor, with a median survival of only 13 months. Surgical resection remains the only curative therapy; however, at first detection, only one-third of patients are at an early enough stage for this approach to be effective, thus rendering early diagnosis as an efficient approach to improving survival. Therefore, the identification of higher-risk patients, whose risk is correlated with genetic and pre-cancerous conditions, and the employment of non-invasive-screening modalities would be appropriate. For several at-risk patients, such as those suffering from primary sclerosing cholangitis or fibropolycystic liver disease, the use of periodic (6-12 months) imaging of the liver by ultrasound (US), magnetic Resonance Imaging (MRI)/cholangiopancreatography (MRCP), or computed tomography (CT) in association with serum CA19-9 measurement has been proposed. For liver cirrhosis patients, it has been proposed that at-risk iCCA patients are monitored in a similar fashion to at-risk HCC patients. The possibility of using Artificial Intelligence models to evaluate higher-risk patients could favor the diagnosis of these entities, although more data are needed to support the practical utility of these applications in the field of screening. For these reasons, it would be appropriate to develop screening programs in the research protocols setting. In fact, the success of these programs reauires patient compliance and multidisciplinary cooperation.

MRI-derived radiomics to guide post-operative management of glioblastoma: Implication for personalized radiation treatment volume delineation

Background

The glioblastoma's bad prognosis is primarily due to intra-tumor heterogeneity, demonstrated from several studies that collected molecular biology, cytogenetic data and more recently radiomic features for a better prognostic stratification. The GLIFA project (GLIoblastoma Feature Analysis) is a multicentric project planned to investigate the role of radiomic analysis in GB management, to verify if radiomic features in the tissue around the resection cavity may guide the radiation target volume delineation.

Materials and methods

We retrospectively analyze from three centers radiomic features extracted from 90 patients with total or near total resection, who completed the standard adjuvant treatment and for whom we had post-operative images available for features extraction. The Manual segmentation was performed on post gadolinium T1w MRI sequence by 2 radiation oncologists and reviewed by a neuroradiologist, both with at least 10 years of experience. The Regions of interest (ROI) considered for the analysis were: the surgical cavity ± post-surgical residual mass (CTV_cavity); the CTV a margin of 1.5 cm added to CTV_cavity and the volume resulting from subtracting the CTV_cavity from the CTV was defined as CTV_Ring. Radiomic analysis and modeling were conducted in RStudio. Z-score normalization was applied to each radiomic feature. A radiomic model was generated using features extracted from the Ring to perform a binary classification and predict the PFS at 6 months. A 3-fold cross-validation repeated five times was implemented for internal validation of the model.

Results

Two-hundred and seventy ROIs were contoured. The proposed radiomic model was given by the best fitting logistic regression model, and included the following 3 features: F_cm_merged.contrast, F_cm_merged.info.corr.2, F_rlm_merged.rlnu. A good agreement between model predicted probabilities and observed outcome probabilities was obtained (p-value of 0.49 by Hosmer and Lemeshow statistical test). The ROC curve of the model reported an AUC of 0.78 (95% CI: 0.68-0.88).

Conclusion

This is the first hypothesis-generating study which applies a radiomic analysis focusing on healthy tissue ring around the surgical cavity on post-operative MRI. This study provides a preliminary model for a decision support tool for a customization of the radiation target volume in GB patients in order to achieve a margin reduction strategy.

Prediction of myocardial ischemia in coronary heart disease patients using a CCTA-Based radiomic nomogram

Objective

The present study aimed to predict myocardial ischemia in coronary heart disease (CHD) patients based on the radiologic features of coronary computed tomography angiography (CCTA) combined with clinical factors.

Methods

The imaging and clinical data of 110 patients who underwent CCTA scan before DSA or FFR examination in Changzhou Second People's Hospital, Nanjing Medical University (90 patients), and The First Affiliated Hospital of Soochow University (20 patients) from March 2018 to January 2022 were retrospectively analyzed. According to the digital subtraction angiography (DSA) and fractional flow reserve (FFR) results, all patients were assigned to myocardial ischemia (n = 58) and normal myocardial blood supply (n = 52) groups. All patients were further categorized into training (n = 64) and internal validation (n = 26) sets at a ratio of 7:3, and the patients from second site were used as external validation. Clinical indicators of patients were collected, the left ventricular myocardium were segmented from CCTA images using CQK software, and the radiomics features were extracted using pyradiomics software. Independent prediction models and combined prediction models were established. The predictive performance of the model was assessed by calibration curve analysis, receiver operating characteristic (ROC) curve and decision curve analysis.

Results

The combined model consisted of one important clinical factor and eight selected radiomic features. The area under the ROC curve (AUC) of radiomic model was 0.826 in training set, and 0.744 in the internal validation set. For the combined model, the AUCs were 0.873, 0.810, 0.800 in the training, internal validation, and external validation sets, respectively. The calibration curves demonstrated that the probability of myocardial ischemia predicted by the combined model was in good agreement with the observed values in both training and validation sets. The decision curve was within the threshold range of 0.1-1, and the clinical value of nomogram was higher than that of clinical model.

Conclusion

The radiomic characteristics of CCTA combined with clinical factors have a good clinical value in predicting myocardial ischemia in CHD patients.

A novel cascade machine learning pipeline for Alzheimer's disease identification and prediction

Introduction

Alzheimer's disease (AD) is a progressive and irreversible brain degenerative disorder early. Among all diagnostic strategies, hippocampal atrophy is considered a promising diagnostic method. In order to proactively detect patients with early Alzheimer's disease, we built an Alzheimer's segmentation and classification (AL-SCF) pipeline based on machine learning.

Methods

In our study, we collected coronal T1 weighted images that include 187 patients with AD and 230 normal controls (NCs). Our pipeline began with the segmentation of the hippocampus by using a modified U2-net. Subsequently, we extracted 851 radiomics features and selected 37 features most relevant to AD by the Hierarchical clustering method and Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. At last, four classifiers were implemented to distinguish AD from NCs, and the performance of the models was evaluated by accuracy, specificity, sensitivity, and area under the curve.

Results

Our proposed pipeline showed excellent discriminative performance of classification with AD vs NC in the training set (AUC=0.97, 95% CI: (0.96-0.98)). The model was also verified in the validation set with Dice=0.93 for segmentation and accuracy=0.95 for classification.

Discussion

The AL-SCF pipeline can automate the process from segmentation to classification, which may assist doctors with AD diagnosis and develop individualized medical plans for AD in clinical practice.

Immunotherapy Assessment: A New Paradigm for Radiologists

Immunotherapy denotes an exemplar change in an oncological setting. Despite the effective application of these treatments across a broad range of tumors, only a minority of patients have beneficial effects. The efficacy of immunotherapy is affected by several factors, including human immunity, which is strongly correlated to genetic features, such as intra-tumor heterogeneity. Classic imaging assessment, based on computed tomography (CT) or magnetic resonance imaging (MRI), which is useful for conventional treatments, has a limited role in immunotherapy. The reason is due to different patterns of response and/or progression during this kind of treatment which differs from those seen during other treatments, such as the possibility to assess the wide spectrum of immunotherapy-correlated toxic effects (ir-AEs) as soon as possible. In addition, considering the unusual response patterns, the limits of conventional response criteria and the necessity of using related immune-response criteria are clear. Radiomics analysis is a recent field of great interest in a radiological setting and recently it has grown the idea that we could identify patients who will be fit for this treatment or who will develop ir-AEs.

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

PURPOSE

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

METHODS AND MATERIALS

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

RESULTS

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

CONCLUSIONS

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

Collinearity and Dimensionality Reduction in Radiomics: Effect of Preprocessing Parameters in Hypertrophic Cardiomyopathy Magnetic Resonance T1 and T2 Mapping

Radiomics and artificial intelligence have the potential to become a valuable tool in clinical applications. Frequently, radiomic analyses through machine learning methods present issues caused by high dimensionality and multicollinearity, and redundant radiomic features are usually removed based on correlation analysis. We assessed the effect of preprocessing-in terms of voxel size resampling, discretization, and filtering-on correlation-based dimensionality reduction in radiomic features from cardiac T1 and T2 maps of patients with hypertrophic cardiomyopathy. For different combinations of preprocessing parameters, we performed a dimensionality reduction of radiomic features based on either Pearson's or Spearman's correlation coefficient, followed by the computation of the stability index. With varying resampling voxel size and discretization bin width, for both T1 and T2 maps, Pearson's and Spearman's dimensionality reduction produced a slightly different percentage of remaining radiomic features, with a relatively high stability index. For different filters, the remaining features' stability was instead relatively low. Overall, the percentage of eliminated radiomic features through correlation-based dimensionality reduction was more dependent on resampling voxel size and discretization bin width for textural features than for shape or first-order features. Notably, correlation-based dimensionality reduction was less sensitive to preprocessing when considering radiomic features from T2 compared with T1 maps.

Translating Data Science Results into Precision Oncology Decisions: A Mini Review

While reviewing and discussing the potential of data science in oncology, we emphasize medical imaging and radiomics as the leading contextual frameworks to measure the impacts of Artificial Intelligence (AI) and Machine Learning (ML) developments. We envision some domains and research directions in which radiomics should become more significant in view of current barriers and limitations.

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

MRI radiomic features of peritumoral edema may predict the recurrence sites of glioblastoma multiforme

Background and purpose

As one of the most aggressive malignant tumor in the central nervous system, the main cause of poor outcome of glioblastoma (GBM) is recurrence, a non-invasive method which can predict the area of recurrence pre-operation is necessary.To investigate whether there is radiological heterogeneity within peritumoral edema and identify the reproducible radiomic features predictive of the sites of recurrence of glioblastoma(GBM), which may be of value to optimize patients' management.

Materials and methods

The clinical information and MR images (contrast-enhanced T1 weighted and FLAIR sequences) of 22 patients who have been histologically proven glioblastoma, were retrospectively evaluated. Kaplan-Meier methods was used for survival analysis. Oedematous regions were manually segmented by an expert into recurrence region, non-recurrence region. A set of 94 radiomic features were obtained from each region using the function of analyzing MR image of 3D slicer. Paired t test was performed to identify the features existing significant difference. Subsequently, the data of two patients from TCGA database was used to evaluate whether these features have clinical value.

Results

Ten features with significant differences between the recurrence and non-recurrence subregions were identified and verified on two individual patients from the TCGA database with pathologically confirmed diagnosis of GBM.

Conclusions

Our results suggested that heterogeneity does exist in peritumoral edema, indicating that the radiomic features of peritumoral edema from routine MR images can be utilized to predict the sites of GBM recurrence. Our findings may further guide the surgical treatment strategy for GBM.

MRI-based multiregional radiomics for predicting lymph nodes status and prognosis in patients with resectable rectal cancer

Purpose

To establish and evaluate multiregional T2-weighted imaging (T2WI)-based clinical-radiomics model for predicting lymph node metastasis (LNM) and prognosis in patients with resectable rectal cancer.

Methods

A total of 346 patients with pathologically confirmed rectal cancer from two hospitals between January 2019 and December 2021 were prospectively enrolled. Intra- and peritumoral features were extracted separately, and least absolute shrinkage and selection operator regression was applied for feature selection. Radiomics signatures were built using the selected features from different regions. The clinical-radiomic nomogram was developed by combining the intratumoral and peritumoral radiomics signatures score (radscore) and the most predictive clinical parameters. The diagnostic performances of the nomogram and clinical model were evaluated using the area under the receiver operating characteristic curve (AUC). The prognostic model for 3-year recurrence-free survival (RFS) was constructed using univariate and multivariate Cox analysis.

Results

The intratumoral radscore (radscore 1) included four features, the peritumoral radscore (radscore 2) included five features, and the combined intratumoral and peritumoural radscore (radscore 3) included ten features. The AUCs for radscore 3 were higher than that of radscore 1 in training cohort (0.77 vs. 0.71, P=0.182) and internal validation cohort (0.76 vs. 0.64, P=0.041). The AUCs for radscore 3 were higher than that of radscore 2 in training cohort (0.77 vs. 0.74, P=0.215) and internal validation cohort (0.76 vs. 0.68, P=0.083). A clinical-radiomic nomogram showed a higher AUC compared with the clinical model in training cohort (0.84 vs. 0.67, P<0.001) and internal validation cohort (0.78 vs. 0.64, P=0.038) but not in external validation (0.72 vs. 0.76, P=0.164). Multivariate Cox analysis showed MRI-reported extramural vascular invasion (EMVI) (HR=1.099, 95%CI: 0.462-2.616; P=0.031) and clinical-radiomic nomogram-based LNM (HR=2.232, 95%CI:1.238-7.439; P=0.017) were independent risk factors for assessing 3-year RFS. Combined clinical-radiomic nomogram based LNM and MRI-reported EMVI showed good performance in training cohort (AUC=0.748), internal validation cohort (AUC=0.706) and external validation (AUC=0.688) for predicting 3-year RFS.

Conclusion

A clinical-radiomics nomogram exhibits good performance for predicting preoperative LNM. Combined clinical-radiomic nomogram based LNM and MRI-reported EMVI showed clinical potential for assessing 3-year RFS.

Preoperative radiomic signature based on CT images for noninvasive evaluation of localized nephroblastoma in pediatric patients

Background

Nephron sparing nephrectomy may not reduce the prognosis of nephroblastoma in the absence of involvement of the renal capsule, sinus vessels, and lymph nodes, However, there is no accurate preoperative noninvasive evaluation method at present.

Materials and methods

105 nephroblastoma patients underwent contrast-enhanced CT scan between 2013 and 2020 in our hospital were retrospectively collected, including 59 cases with localized stage and 46 cases with non-localized stage, and then were divided into training cohort (n= 73) and validation cohort (n= 32) according to the order of CT scanning time. After lesion segmentation and data preprocessing, radiomic features were extracted from each volume of interest. The multi-step procedure including Pearson correlation analysis and sequential forward floating selection was performed to produce radiomic signature. Prediction model was constructed using the radiomic signature and Logistic Regression classifier for predicting the localized nephroblastoma in the training cohort. Finally, the model performance was validated in the validation cohort.

Results

A total of 1652 radiomic features have been extracted, from which TOP 10 features were selected as the radiomic signature. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity of the prediction model were 0.796, 0.795, 0.732 and 0.875 for the training cohort respectively, and 0.710, 0.719, 0.611 and 0.857 for the validation cohort respectively. The result comparison with prediction models composed of different machine learning classifiers and different parameters also manifest the effectiveness of our radiomic model.

Conclusion

A logistic regression model based on radiomic features extracted from preoperative CT images had good ability to noninvasively predict nephroblastoma without renal capsule, sinus vessel, and lymph node involvement.

Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes

Background

MRI radiomic features and machine learning have been used to predict brain metastasis (BM) stereotactic radiosurgery (SRS) outcomes. Previous studies used only single-center datasets, representing a significant barrier to clinical translation and further research. This study, therefore, presents the first dual-center validation of these techniques.

Methods

SRS datasets were acquired from 2 centers (n = 123 BMs and n = 117 BMs). Each dataset contained 8 clinical features, 107 pretreatment T1w contrast-enhanced MRI radiomic features, and post-SRS BM progression endpoints determined from follow-up MRI. Random decision forest models were used with clinical and/or radiomic features to predict progression. 250 bootstrap repetitions were used for single-center experiments.

Results

Training a model with one center's dataset and testing it with the other center's dataset required using a set of features important for outcome prediction at both centers, and achieved area under the receiver operating characteristic curve (AUC) values up to 0.70. A model training methodology developed using the first center's dataset was locked and externally validated with the second center's dataset, achieving a bootstrap-corrected AUC of 0.80. Lastly, models trained on pooled data from both centers offered balanced accuracy across centers with an overall bootstrap-corrected AUC of 0.78.

Conclusions

Using the presented validated methodology, radiomic models trained at a single center can be used externally, though they must utilize features important across all centers. These models' accuracies are inferior to those of models trained using each individual center's data. Pooling data across centers shows accurate and balanced performance, though further validation is required.

Predictive value of magnetic resonance imaging radiomics-based machine learning for disease progression in patients with high-grade glioma

Background

Accurately predicting the prognosis of patients with high-grade glioma (HGG) is potentially important for treatment. However, the predictive value of images of various magnetic resonance imaging (MRI) sequences for prognosis at different time points is unknown. We established predictive machine learning models of HGG disease progression and recurrence using MRI radiomics and explored the factors influencing prediction accuracy.

Methods

Radiomics features were extracted from T1-weighted (T1WI), contrast-enhanced T1-weighted (CE-T1WI), T2-weighted (T2WI), and fluid-attenuated inversion recovery (FLAIR) images (postoperative radiotherapy planning MRI images) obtained from 162 patients with HGG. The Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) algorithm were used for feature selection. Machine learning models were used to build prediction models to estimate disease progression or recurrence. The influence of different MRI sequences, regions of interest (ROIs), and prediction time points was also explored. The receiver operating characteristic (ROC) curve was used to evaluate the discriminative performance of each model, and the DeLong test was employed to compare the ROC curves.

Results

Radiomics features from T2WI and FLAIR demonstrated greater predictive value for disease progression compared with T1WI or CE-TIWI. The best predictive models, with areas under the ROC curves (AUCs) of 0.70, 0.68, 0.78, 0.78, and 0.78 for predicting disease progression at the 6th, 9th, 12th, 15th, and 18th month after radiotherapy, respectively, were obtained by combining clinical features with gross tumor volume (GTV) and clinical target volume (CTV) features extracted from T2WI and FLAIR.

Conclusions

Structural MRI obtained before radiotherapy can be used to predict the disease progression or posttreatment recurrence of HGG. When using MRI radiomics to predict long-term outcomes as opposed to short-term outcomes, better predictive results may be obtained.

Radiomics approach to the condylar head for legal age classification using cone-beam computed tomography: A pilot study

Legal age estimation of living individuals is a critically important issue, and radiomics is an emerging research field that extracts quantitative data from medical images. However, no reports have proposed age-related radiomics features of the condylar head or an age classification model using those features. This study aimed to introduce a radiomics approach for various classifications of legal age (18, 19, 20, and 21 years old) based on cone-beam computed tomography (CBCT) images of the mandibular condylar head, and to evaluate the usefulness of the radiomics features selected by machine learning models as imaging biomarkers. CBCT images from 85 subjects were divided into eight age groups for four legal age classifications: ≤17 and ≥18 years old groups (18-year age classification), ≤18 and ≥19 years old groups (19-year age classification), ≤19 and ≥20 years old groups (20-year age classification) and ≤20 and ≥21 years old groups (21-year age classification). The condylar heads were manually segmented by an expert. In total, 127 radiomics features were extracted from the segmented area of each condylar head. The random forest (RF) method was utilized to select features and develop the age classification model for four legal ages. After sorting features in descending order of importance, the top 10 extracted features were used. The 21-year age classification model showed the best performance, with an accuracy of 91.18%, sensitivity of 80%, and specificity of 95.83%. Radiomics features of the condylar head using CBCT showed the possibility of age estimation, and the selected features were useful as imaging biomarkers.

Radiomics analysis of [18F]-fluoro-2-deoxyglucose positron emission tomography for the prediction of cervical lymph node metastasis in tongue squamous cell carcinoma

OBJECTIVES

This study aimed to create a predictive model for cervical lymph node metastasis (CLNM) in patients with tongue squamous cell carcinoma (SCC) based on radiomics features detected by [¹⁸F]-fluoro-2-deoxyglucose (¹⁸F-FDG) positron emission tomography (PET).

METHODS

A total of 40 patients with tongue SCC who underwent ¹⁸F-FDG PET imaging during their first medical examination were enrolled. During the follow-up period (mean 28 months), 20 patients had CLNM, including six with late CLNM, whereas the remaining 20 patients did not have CLNM. Radiomics features were extracted from ¹⁸F-FDG PET images of all patients irrespective of metal artifact, and clinicopathological factors were obtained from the medical records. Late CLNM was defined as the CLNM that occurred after major treatment. The least absolute shrinkage and selection operator (LASSO) model was used for radiomics feature selection and sequential data fitting. The receiver operating characteristic curve analysis was used to assess the predictive performance of the ¹⁸F-FDG PET-based model and clinicopathological factors model (CFM) for CLNM.

RESULTS

Six radiomics features were selected from LASSO analysis. The average values of the area under the curve (AUC), accuracy, sensitivity, and specificity of radiomics analysis for predicting CLNM from ¹⁸F-FDG PET images were 0.79, 0.68, 0.65, and 0.70, respectively. In contrast, those of the CFM were 0.54, 0.60, 0.60, and 0.60, respectively. The ¹⁸F-FDG PET-based model showed significantly higher AUC than that of the CFM.

CONCLUSIONS

The ¹⁸F-FDG PET-based model has better potential for diagnosing CLNM and predicting late CLNM in patients with tongue SCC than the CFM.

Radiomic and clinical nomogram for cognitive impairment prediction in Wilson's disease

Objective

To investigate potential biomarkers for the early detection of cognitive impairment in patients with Wilson's disease (WD), we developed a computer-assisted radiomics model to distinguish between WD and WD cognitive impairment.

Methods

Overall, 136 T1-weighted MR images were retrieved from the First Affiliated Hospital of Anhui University of Chinese Medicine, including 77 from patients with WD and 59 from patients with WD cognitive impairment. The images were divided into training and test groups at a ratio of 70:30. The radiomic features of each T1-weighted image were extracted using 3D Slicer software. R software was used to establish clinical and radiomic models based on clinical characteristics and radiomic features, respectively. The receiver operating characteristic profiles of the three models were evaluated to assess their diagnostic accuracy and reliability in distinguishing between WD and WD cognitive impairment. We combined relevant neuropsychological test scores of prospective memory to construct an integrated predictive model and visual nomogram to effectively assess the risk of cognitive decline in patients with WD.

Results

The area under the curve values for distinguishing WD and WD cognitive impairment for the clinical, radiomic, and integrated models were 0.863, 0.922, and 0.935 respectively, indicative of excellent performance. The nomogram based on the integrated model successfully differentiated between WD and WD cognitive impairment.

Conclusion

The nomogram developed in the current study may assist clinicians in the early identification of cognitive impairment in patients with WD. Early intervention following such identification may help improve long-term prognosis and quality of life of these patients.

Joint EANM/SNMMI guideline on radiomics in nuclear medicine : Jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council

PURPOSE

The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses for both hand-crafted and deep learning-based approaches.

METHODS

In a cooperative effort between the EANM and SNMMI, we agreed upon current best practices and recommendations for relevant aspects of radiomics analyses, including study design, quality assurance, data collection, impact of acquisition and reconstruction, detection and segmentation, feature standardization and implementation, as well as appropriate modelling schemes, model evaluation, and interpretation. We also offer an outlook for future perspectives.

CONCLUSION

Radiomics is a very quickly evolving field of research. The present guideline focused on established findings as well as recommendations based on the state of the art. Though this guideline recognizes both hand-crafted and deep learning-based radiomics approaches, it primarily focuses on the former as this field is more mature. This guideline will be updated once more studies and results have contributed to improved consensus regarding the application of deep learning methods for radiomics. Although methodological recommendations in the present document are valid for most medical image modalities, we focus here on nuclear medicine, and specific recommendations when necessary are made for PET/CT, PET/MR, and quantitative SPECT.

Prognostic value of textural features obtained from F-fluorodeoxyglucose (F-18 FDG) positron emission tomography/computed tomography (PET/CT) in patients with locally advanced cervical cancer undergoing concurrent chemoradiotherapy

OBJECTIVE

To evaluate whether textural features obtained from F-18 FDG PET/CT offer clinical value that can predict the outcome of patients with locally advanced cervical cancer (LACC) receiving concurrent chemoradiotherapy (CCRT).

METHODS

We reviewed the records of 68 patients with stage IIB-IVA LACC who underwent PET/CT before CCRT. Conventional metabolic parameters, shape indices, and textural features of the primary tumor were measured on PET/CT. A Cox regression model was used to examine the effects of variables on overall survival (OS) and progression-free survival (PFS).

RESULTS

The patients included in this study were classified into two groups based on median value of PET/CT parameters. The high group of GLNU derived from GLRLM is only independent prognostic factor for PFS (HR 7.142; 95% CI 1.656-30.802; p = 0.008) and OS (HR 9,780; 95% CI 1.222-78.286; p = 0.031). In addition, GLNU derived from GLRLM (AUC 0.846, 95% CI 0.738-0.923) was the best predictor for recurrence among clinical prognostic factors and PET/CT parameters.

CONCLUSION

Our results demonstrated that high GLNU from GLRLM on pretreatment F-18 FDG PET/CT images, were significant prognostic factors for recurrence and death in patients with LACC receiving CCRT.

Machine Learning Model to Predict Diagnosis of Mild Cognitive Impairment by Using Radiomic and Amyloid Brain PET

PURPOSE

The study aimed to develop a deep learning model for predicting amnestic mild cognitive impairment (aMCI) diagnosis using radiomic features and amyloid brain PET.

PATIENTS AND METHODS

Subjects (n = 328) from the Alzheimer's Disease Neuroimaging Initiative database and the EudraCT 2015-001184-39 trial (159 males, 169 females), with a mean age of 72 ± 7.4 years, underwent PET/CT with 18 F-florbetaben. The study cohort consisted of normal controls (n = 149) and subjects with aMCI (n = 179). Thirteen gray-level run-length matrix radiomic features and amyloid loads were extracted from 27 cortical brain areas. The least absolute shrinkage and selection operator regression was used to select features with the highest predictive value. A feed-forward neural multilayer network was trained, validated, and tested on 70%, 15%, and 15% of the sample, respectively. Accuracy, precision, F1-score, and area under the curve were used to assess model performance. SUV performance in predicting the diagnosis of aMCI was also assessed and compared with that obtained from the machine learning model.

RESULTS

The machine learning model achieved an area under the receiver operating characteristic curve of 90% (95% confidence interval, 89.4-90.4) on the test set, with 80% and 78% for accuracy and F1-score, respectively. The deep learning model outperformed SUV performance (area under the curve, 71%; 95% confidence interval, 69.7-71.4; 57% accuracy, 48% F1-score).

CONCLUSIONS

Using radiomic and amyloid PET load, the machine learning model identified MCI subjects with 84% specificity at 81% sensitivity. These findings show that a deep learning algorithm based on radiomic data and amyloid load obtained from brain PET images improves the prediction of MCI diagnosis compared with SUV alone.

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

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

A Dosiomics Analysis Based on Linear Energy Transfer and Biological Dose Maps to Predict Local Recurrence in Sacral Chordomas after Carbon-Ion Radiotherapy

Carbon Ion Radiotherapy (CIRT) is one of the most promising therapeutic options to reduce Local Recurrence (LR) in Sacral Chordomas (SC). The aim of this work is to compare the performances of survival models fed with dosiomics features and conventional DVH metrics extracted from relative biological effectiveness (RBE)-weighted dose (D_RBE) and dose-averaged Linear Energy Transfer (LET_d) maps, towards the identification of possible prognostic factors for LR in SC patients treated with CIRT. This retrospective study included 50 patients affected by SC with a focus on patients that presented a relapse in a high-dose region. Survival models were built to predict both LR and High-Dose Local Recurrencies (HD-LR). The models were evaluated through Harrell Concordance Index (C-index) and patients were stratified into high/low-risk groups. Local Recurrence-free Kaplan-Meier curves were estimated and evaluated through log-rank tests. The model with highest performance (median(interquartile-range) C-index of 0.86 (0.22)) was built on features extracted from LET_d maps, with D_RBE models showing promising but weaker results (C-index of 0.83 (0.21), 0.80 (0.21)). Although the study should be extended to a wider patient population, LET_d maps show potential as a prognostic factor for SC HD-LR in CIRT, and dosiomics appears to be the most promising approach against more conventional methods (e.g., DVH-based).

The Role of Radiomics and AI Technologies in the Segmentation, Detection, and Management of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the most common primary hepatic neoplasm. Thanks to recent advances in computed tomography (CT) and magnetic resonance imaging (MRI), there is potential to improve detection, segmentation, discrimination from HCC mimics, and monitoring of therapeutic response. Radiomics, artificial intelligence (AI), and derived tools have already been applied in other areas of diagnostic imaging with promising results. In this review, we briefly discuss the current clinical applications of radiomics and AI in the detection, segmentation, and management of HCC. Moreover, we investigate their potential to reach a more accurate diagnosis of HCC and to guide proper treatment planning.

Performance sensitivity analysis of brain metastasis stereotactic radiosurgery outcome prediction using MRI radiomics

Recent studies have used T1w contrast-enhanced (T1w-CE) magnetic resonance imaging (MRI) radiomic features and machine learning to predict post-stereotactic radiosurgery (SRS) brain metastasis (BM) progression, but have not examined the effects of combining clinical and radiomic features, BM primary cancer, BM volume effects, and using multiple scanner models. To investigate these effects, a dataset of n = 123 BMs from 99 SRS patients with 12 clinical features, 107 pre-treatment T1w-CE radiomic features, and BM progression determined by follow-up MRI was used with a random decision forest model and 250 bootstrapped repetitions. Repeat experiments assessed the relative accuracy across primary cancer sites, BM volume groups, and scanner model pairings. Correction for accuracy imbalances across volume groups was investigated by removing volume-correlated features. We found that using clinical and radiomic features together produced the most accurate model with a bootstrap-corrected area under the receiver operating characteristic curve of 0.77. Accuracy also varied by primary cancer site, BM volume, and scanner model pairings. The effect of BM volume was eliminated by removing features at a volume-correlation coefficient threshold of 0.25. These results show that feature type, primary cancer, volume, and scanner model are all critical factors in the accuracy of radiomics-based prognostic models for BM SRS that must be characterised and controlled for before clinical translation.

Early prediction of pathological complete response to neoadjuvant chemotherapy combining DCE-MRI and apparent diffusion coefficient values in breast Cancer

INTRODUCTION

Improving the early prediction of neoadjuvant chemotherapy (NAC) efficacy in breast cancer can lead to an improved prediction of the final prognosis of patients, which would be useful for promoting individualized treatment. This study aimed to explore the value of the combination of dynamic contrast-enhanced (DCE)-MRI parameters and apparent diffusion coefficient (ADC) values in the early prediction of pathological complete response (pCR) to NAC for breast cancer.

METHODS

A total of 119 (range, 28-69 years) patients with biopsy-proven breast cancer who received two cycles of NAC before breast surgery were retrospectively enrolled from our hospital database. Patients were divided into pCR and non pCR groups according to their pathological responses; a total of 24 patients achieved pCR, while 95 did not. The quantitative (K^trans; K_ep; V_e; IAUC) and semiquantitative parameters (W-in; W-out; TTP) of DCE-MRI that were significantly different between groups were combined with ADC values to explore their value in the early prediction of pCR to NAC for breast cancer. The independent T test was performed to compare the differences in DCE-MRI parameters and ADC values between the two groups. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC), sensitivity and specificity were calculated to evaluate the performance of the prediction.

RESULTS

The K^trans, K_ep, IAUC, ADC, W-in and TTP values were significantly different between the pCR and non pCR groups after NAC. The AUC (0.845) and specificity (95.79%) of the combined K^trans, K_ep, IAUC and ADC values were both higher than those of the individual parameters. The combination of W-in, TTP and ADC values had the highest AUC value (0.886) in predicting pCR, with a sensitivity and specificity of 87.5% and 82.11%, respectively.

CONCLUSIONS

The results suggested that the combination of ADC values and quantitative and semiquantitative DCE-MRI parameters, especially the combination of W-in, TTP, and ADC values, may improve the early prediction of pCR in breast cancer.

Radiomics model based on features of axillary lymphatic nodes to predict axillary lymphatic node metastasis in breast cancer

BACKGROUND

Breast cancer (BC) is among the most common cancers worldwide. Machine learning-based radiomics model could predict axillary lymph node metastasis (ALNM) of BC accurately.

PURPOSE

The purpose is to develop a machine learning model to predict ALNM of BC by focusing on the radiomics features of axillary lymphatic node (ALN).

METHODS

A group of 398 BC patients with 800 ALNs were retrospectively collected. A set of patient characteristics were obtained to form clinical factors. Three hundred and twenty-six radiomics features were extracted from each region of interest for ALN in contrast-enhanced computed tomography (CECT) image. A framework composed of four feature selection methods and 14 machine learning classification algorithms was systematically applied. A clinical model, a radiomics model, and a combined model were developed using a cross-validation approach and compared. Metrics of the area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the performance of these models in the prediction of ALNM in BC.

RESULTS

Among the 800 cases of ALNs, there were 388 cases of positive metastasis (48.50%) and 412 cases of negative metastasis (51.50%). The baseline clinical model achieved the performance with an AUC = 0.8998 (95% CI [0.8540, 0.9457]). The radiomics model achieved an AUC = 0.9081 (95% CI [0.8640, 0.9523]). The combined model using the clinical factors and radiomics features achieved the best results with an AUC = 0.9305 (95% CI [0.8928, 0.9682]).

CONCLUSIONS

Combinations of feature selection methods and machine learning-based classification algorithms can develop promising predictive models to predict ALNM in BC using CECT features. The combined model of clinical factors and radiomics features outperforms both the clinical model and the radiomic model.