The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups

CQENet: A segmentation model for nasopharyngeal carcinoma based on confidence quantitative evaluation

Accurate segmentation of the tumor regions of nasopharyngeal carcinoma (NPC) is of significant importance for radiotherapy of NPC. However, the precision of existing automatic segmentation methods for NPC remains inadequate, primarily manifested in the difficulty of tumor localization and the challenges in delineating blurred boundaries. Additionally, the black-box nature of deep learning models leads to insufficient quantification of the confidence in the results, preventing users from directly understanding the model's confidence in its predictions, which severely impacts the clinical application of deep learning models. This paper proposes an automatic segmentation model for NPC based on confidence quantitative evaluation (CQENet). To address the issue of insufficient confidence quantification in NPC segmentation results, we introduce a confidence assessment module (CAM) that enables the model to output not only the segmentation results but also the confidence in those results, aiding users in understanding the uncertainty risks associated with model outputs. To address the difficulty in localizing the position and extent of tumors, we propose a tumor feature adjustment module (FAM) for precise tumor localization and extent determination. To address the challenge of delineating blurred tumor boundaries, we introduce a variance attention mechanism (VAM) to assist in edge delineation during fine segmentation. We conducted experiments on a multicenter NPC dataset, validating that our proposed method is effective and superior to existing state-of-the-art models, possessing considerable clinical application value.

Magnetic Resonance Imaging Liver Segmentation Protocol Enables More Consistent and Robust Annotations, Paving the Way for Advanced Computer-Assisted Analysis

BACKGROUND/OBJECTIVES

Recent advancements in artificial intelligence (AI) have spurred interest in developing computer-assisted analysis for imaging examinations. However, the lack of high-quality datasets remains a significant bottleneck. Labeling instructions are critical for improving dataset quality but are often lacking. This study aimed to establish a liver MRI segmentation protocol and assess its impact on annotation quality and inter-reader agreement.

METHODS

This retrospective study included 20 patients with chronic liver disease. Manual liver segmentations were performed by a radiologist in training and a radiology technician on T2-weighted imaging (wi) and T1wi at the portal venous phase. Based on the inter-reader discrepancies identified after the first segmentation round, a segmentation protocol was established, guiding the second round of segmentation, resulting in a total of 160 segmentations. The Dice Similarity Coefficient (DSC) assessed inter-reader agreement pre- and post-protocol, with a Wilcoxon signed-rank test for per-volume analysis and an Aligned-Rank Transform (ART) for repeated measures analyses of variance (ANOVA) for per-slice analysis. Slice selection at extreme cranial or caudal liver positions was evaluated using the McNemar test.

RESULTS

The per-volume DSC significantly increased after protocol implementation for both T2wi (p < 0.001) and T1wi (p = 0.03). Per-slice DSC also improved significantly for both T2wi and T1wi (p < 0.001). The protocol reduced the number of liver segmentations with a non-annotated slice on T1wi (p = 0.04), but the change was not significant on T2wi (p = 0.16).

CONCLUSIONS

Establishing a liver MRI segmentation protocol improves annotation robustness and reproducibility, paving the way for advanced computer-assisted analysis. Moreover, segmentation protocols could be extended to other organs and lesions and incorporated into guidelines, thereby expanding the potential applications of AI in daily clinical practice.

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

Enhancing Nasopharyngeal Carcinoma Survival Prediction: Integrating Pre- and Post-Treatment MRI Radiomics with Clinical Data

Recurrences are frequent in nasopharyngeal carcinoma (NPC) despite high remission rates with treatment, leading to considerable morbidity. This study aimed to develop a prediction model for NPC survival by harnessing both pre- and post-treatment magnetic resonance imaging (MRI) radiomics in conjunction with clinical data, focusing on 3-year progression-free survival (PFS) as the primary outcome. Our comprehensive approach involved retrospective clinical and MRI data collection of 276 eligible NPC patients from three independent hospitals (180 in the training cohort, 46 in the validation cohort, and 50 in the external cohort) who underwent MRI scans twice, once within 2 months prior to treatment and once within 10 months after treatment. From the contrast-enhanced T1-weighted images before and after treatment, 3404 radiomics features were extracted. These features were not only derived from the primary lesion but also from the adjacent lymph nodes surrounding the tumor. We conducted appropriate feature selection pipelines, followed by Cox proportional hazards models for survival analysis. Model evaluation was performed using receiver operating characteristic (ROC) analysis, the Kaplan-Meier method, and nomogram construction. Our study unveiled several crucial predictors of NPC survival, notably highlighting the synergistic combination of pre- and post-treatment data in both clinical and radiomics assessments. Our prediction model demonstrated robust performance, with an accuracy of AUCs of 0.66 (95% CI: 0.536-0.779) in the training cohort, 0.717 (95% CI: 0.536-0.883) in the testing cohort, and 0.827 (95% CI: 0.684-0.948) in validation cohort in prognosticating patient outcomes. Our study presented a novel and effective prediction model for NPC survival, leveraging both pre- and post-treatment clinical data in conjunction with MRI features. Its constructed nomogram provides potentially significant implications for NPC research, offering clinicians a valuable tool for individualized treatment planning and patient counseling.

Characterization of renal masses with MRI-based radiomics: assessment of inter-package and inter-observer reproducibility in a prospective pilot study

OBJECTIVES

To evaluate radiomics features' reproducibility using inter-package/inter-observer measurement analysis in renal masses (RMs) based on MRI and to employ machine learning (ML) models for RM characterization.

METHODS

32 Patients (23M/9F; age 61.8 ± 10.6 years) with RMs (25 renal cell carcinomas (RCC)/7 benign masses; mean size, 3.43 ± 1.73 cm) undergoing resection were prospectively recruited. All patients underwent 1.5 T MRI with T2-weighted (T2-WI), diffusion-weighted (DWI)/apparent diffusion coefficient (ADC), and pre-/post-contrast-enhanced T1-weighted imaging (T1-WI). RMs were manually segmented using volume of interest (VOI) on T2-WI, DWI/ADC, and T1-WI pre-/post-contrast imaging (1-min, 3-min post-injection) by two independent observers using two radiomics software packages for inter-package and inter-observer assessments of shape/histogram/texture features common to both packages (104 features; n = 26 patients). Intra-class correlation coefficients (ICCs) were calculated to assess inter-observer and inter-package reproducibility of radiomics measurements [good (ICC ≥ 0.8)/moderate (ICC = 0.5-0.8)/poor (ICC < 0.5)]. ML models were employed using reproducible features (between observers and packages, ICC > 0.8) to distinguish RCC from benign RM.

RESULTS

Inter-package comparisons demonstrated that radiomics features from T1-WI-post-contrast had the highest proportion of good/moderate ICCs (54.8-58.6% for T1-WI-1 min), while most features extracted from T2-WI, T1-WI-pre-contrast, and ADC exhibited poor ICCs. Inter-observer comparisons found that radiomics measurements from T1-WI pre/post-contrast and T2-WI had the greatest proportion of features with good/moderate ICCs (95.3-99.1% T1-WI-post-contrast 1-min), while ADC measurements yielded mostly poor ICCs. ML models generated an AUC of 0.71 [95% confidence interval = 0.67-0.75] for diagnosis of RCC vs. benign RM.

CONCLUSION

Radiomics features extracted from T1-WI-post-contrast demonstrated greater inter-package and inter-observer reproducibility compared to ADC, with fair accuracy for distinguishing RCC from benign RM.

CLINICAL RELEVANCE

Knowledge of reproducibility of MRI radiomics features obtained on renal masses will aid in future study design and may enhance the diagnostic utility of radiomics models for renal mass characterization.

Stability of Radiomic Features against Variations in Lesion Segmentations Computed on Apparent Diffusion Coefficient Maps of Breast Lesions

Diffusion-weighted imaging (DWI) combined with radiomics can aid in the differentiation of breast lesions. Segmentation characteristics, however, might influence radiomic features. To evaluate feature stability, we implemented a standardized pipeline featuring shifts and shape variations of the underlying segmentations. A total of 103 patients were retrospectively included in this IRB-approved study after multiparametric diagnostic breast 3T MRI with a spin-echo diffusion-weighted sequence with echoplanar readout (b-values: 50, 750 and 1500 s/mm2). Lesion segmentations underwent shifts and shape variations, with >100 radiomic features extracted from apparent diffusion coefficient (ADC) maps for each variation. These features were then compared and ranked based on their stability, measured by the Overall Concordance Correlation Coefficient (OCCC) and Dynamic Range (DR). Results showed variation in feature robustness to segmentation changes. The most stable features, excluding shape-related features, were FO (Mean, Median, RootMeanSquared), GLDM (DependenceNonUniformity), GLRLM (RunLengthNonUniformity), and GLSZM (SizeZoneNonUniformity), which all had OCCC and DR > 0.95 for both shifting and resizing the segmentation. Perimeter, MajorAxisLength, MaximumDiameter, PixelSurface, MeshSurface, and MinorAxisLength were the most stable features in the Shape category with OCCC and DR > 0.95 for resizing. Considering the variability in radiomic feature stability against segmentation variations is relevant when interpreting radiomic analysis of breast DWI data.

A comparative analysis of preclinical computed tomography radiomics using cone-beam and micro-computed tomography scanners

Background and purpose

Radiomics analysis extracts quantitative data (features) from medical images. These features could potentially reflect biological characteristics and act as imaging biomarkers within precision medicine. However, there is a lack of cross-comparison and validation of radiomics outputs which is paramount for clinical implementation. In this study, we compared radiomics outputs across two computed tomography (CT)-based preclinical scanners.

Materials and methods

Cone beam CT (CBCT) and µCT scans were acquired using different preclinical CT imaging platforms. The reproducibility of radiomics features on each scanner was assessed using a phantom across imaging energies (40 & 60 kVp) and segmentation volumes (44-238 mm3). Retrospective mouse scans were used to compare feature reliability across varying tissue densities (lung, heart, bone), scanners and after voxel size harmonisation. Reliable features had an intraclass correlation coefficient (ICC) > 0.8.

Results

First order and GLCM features were the most reliable on both scanners across different volumes. There was an inverse relationship between tissue density and feature reliability, with the highest number of features in lung (CBCT=580, µCT=734) and lowest in bone (CBCT=110, µCT=560). Comparable features for lung and heart tissues increased when voxel sizes were harmonised. We have identified tissue-specific preclinical radiomics signatures in mice for the lung (133), heart (35), and bone (15).

Conclusions

Preclinical CBCT and µCT scans can be used for radiomics analysis to support the development of meaningful radiomics signatures. This study demonstrates the importance of standardisation and emphasises the need for multi-centre studies.

Radiomics-based lymph nodes prognostic models from three MRI regions in nasopharyngeal carcinoma

Accurate prediction of the prognosis of nasopharyngeal carcinoma (NPC) is important for treatment. Lymph nodes metastasis is an important predictor for distant failure and regional recurrence in patients with NPC. Traditionally, subjective radiological evaluation increases concerns regarding the accuracy and consistency of predictions. Radiomics is an objective and quantitative evaluation algorithm for medical images. This retrospective analysis was conducted based on the data of 729 patients newly diagnosed with NPC without distant metastases to evaluate the performance of radiomics pretreatment using magnetic resonance imaging (MRI)-determined metastatic lymph nodes models to predict NPC prognosis with three delineation methods. Radiomics features were extracted from all lymph nodes (ALN), largest lymph node (LLN), and largest slice of the largest lymph node (LSLN) to generate three radiomics signatures. The radiomics signatures, clinical model, and radiomics-clinic merged models were developed in training cohort for predicting overall survival (OS). The results showed that LSLN signature with clinical factors predicted OS with high accuracy and robustness using pretreatment MR-determined metastatic lymph nodes (C-index [95 % confidence interval]: 0.762[0.760-0.763]), providing a new tool for treatment planning in NPC.

Radiomics and Deep Learning in Nasopharyngeal Carcinoma: A Review

Nasopharyngeal carcinoma is a common head and neck malignancy with distinct clinical management compared to other types of cancer. Precision risk stratification and tailored therapeutic interventions are crucial to improving the survival outcomes. Artificial intelligence, including radiomics and deep learning, has exhibited considerable efficacy in various clinical tasks for nasopharyngeal carcinoma. These techniques leverage medical images and other clinical data to optimize clinical workflow and ultimately benefit patients. In this review, we provide an overview of the technical aspects and basic workflow of radiomics and deep learning in medical image analysis. We then conduct a detailed review of their applications to seven typical tasks in the clinical diagnosis and treatment of nasopharyngeal carcinoma, covering various aspects of image synthesis, lesion segmentation, diagnosis, and prognosis. The innovation and application effects of cutting-edge research are summarized. Recognizing the heterogeneity of the research field and the existing gap between research and clinical translation, potential avenues for improvement are discussed. We propose that these issues can be gradually addressed by establishing standardized large datasets, exploring the biological characteristics of features, and technological upgrades.

Application of CT and MRI images based on an artificial intelligence algorithm for predicting lymph node metastasis in breast cancer patients: a meta-analysis

BACKGROUND

This study aimed to comprehensively evaluate the accuracy and effect of computed tomography (CT) and magnetic resonance imaging (MRI) based on artificial intelligence (AI) algorithms for predicting lymph node metastasis in breast cancer patients.

METHODS

We systematically searched the PubMed, Embase and Cochrane Library databases for literature from inception to June 2023 using keywords that included 'artificial intelligence', 'CT,' 'MRI', 'breast cancer' and 'lymph nodes'. Studies that met the inclusion criteria were screened and their data were extracted for analysis. The main outcome measures included sensitivity, specificity, positive likelihood ratio, negative likelihood ratio and area under the curve (AUC).

RESULTS

A total of 16 studies were included in the final meta-analysis, covering 4,764 breast cancer patients. Among them, 11 studies used the manual algorithm MRI to calculate breast cancer risk, which had a sensitivity of 0.85 (95% confidence interval [CI] 0.79-0.90; p < 0.001; I2 = 75.3%), specificity of 0.81 (95% CI 0.66-0.83; p < 0.001; I2 = 0%), a positive likelihood ratio of 4.6 (95% CI 4.0-4.8), a negative likelihood ratio of 0.18 (95% CI 0.13-0.26) and a diagnostic odds ratio of 25 (95% CI 17-38). Five studies used manual algorithm CT to calculate breast cancer risk, which had a sensitivity of 0.88 (95% CI 0.79-0.94; p < 0.001; I2 = 87.0%), specificity of 0.80 (95% CI 0.69-0.88; p < 0.001; I2 = 91.8%), a positive likelihood ratio of 4.4 (95% CI 2.7-7.0), a negative likelihood ratio of 0.15 (95% CI 0.08-0.27) and a diagnostic odds ratio of 30 (95% CI 12-72). For MRI and CT, the AUC after study pooling was 0.85 (95% CI 0.82-0.88) and 0.91 (95% CI 0.88-0.93), respectively.

CONCLUSION

Computed tomography and MRI images based on an AI algorithm have good diagnostic accuracy in predicting lymph node metastasis in breast cancer patients and have the potential for clinical application.

Segmentation methods applied to MRI-derived radiomic analysis for the prediction of placenta accreta spectrum in patients with placenta previa

PURPOSE

To retrospectively evaluate the performance of different manual segmentation methods of placenta MR images for predicting Placenta Accreta Spectrum (PAS) disorders in patients with placenta previa (PP) using a Machine Learning (ML) Radiomics analysis.

METHODS

64 patients (n=41 with PAS and n= 23 without PAS) with PP who underwent MRI examination for suspicion of PAS were retrospectively selected. All MRI examinations were acquired on a 1.5 T using T2-weighted (T2w) sequences on axial, sagittal and coronal planes. Ten different manual segmentation methods were performed on sagittal placental T2-weighted images obtaining five sets of 2D regions of interest (ROIs) and five sets of 3D volumes of interest (VOIs) from each patient. In detail, ROIs and VOIs were positioned on the following areas: placental tissue, retroplacental myometrium, cervix, placenta with underneath myometrium, placenta with underneath myometrium and cervix. For feature stability testing, the same process was repeated on 30 randomly selected placental MRI examinations by two additional radiologists, working independently and blinded to the original segmentation. Radiomic features were extracted from all available ROIs and VOIs. 100 iterations of 5-fold cross-validation with nested feature selection, based on recursive feature elimination, were subsequently run on each ROI/VOI to identify the best-performing method to classify instances correctly.

RESULTS

Among the segmentation methods, the best performance in predicting PAS was obtained by the VOIs covering the retroplacental myometrium (Mean validation score: 0.761, standard deviation: 0.116).

CONCLUSION

Our preliminary results show that the VOI including the retroplacental myometrium using T2w images seems to be the best method when segmenting images for the development of ML radiomics predictive models to identify PAS in patients with PP.

A radiomics-based logistic regression model for the assessment of emphysema severity

Introduction

The aim of this study is to develop a model that differentiates between the radiological patterns of severe and mild emphysema using radiomics parameters, as well as to examine the parameters included in the model.

Materials and Methods

Over the last 12 months, a total of 354 patients were screened based on the presence of terms such as “Fleischner”, “CLE”, and “centriacinar” in their thoracic CT reports, culminating in a study population of 82 patients. The study population was divided into Group 1 (Fleischner mild and moderate; n= 45) and Group 2 (Fleischner confluent and advanced destructive; n= 37). Volumetric segmentation was performed, focusing on the upper lobe segments of both lungs. From these segmented volumes, radiomics parameters including shape, size, first-order, and second-order features were calculated. The best model parameters were selected based on the Bayesian Information Criterion and further optimized through grid search. The final model was tested using 1000 iterations of bootstrap resampling.

Results

In the training set, performance metrics were calculated with a sensitivity of 0.862, specificity of 0.870, accuracy of 0.863, and AUC of 0.910. Correspondingly, in the test set, these values were sensitivity= 0.848; specificity= 0.865; accuracy= 0.857; and AUC= 0.907.

Conclusion

The logistic regression model, composed of radiomics parameters and trained on a limited number of cases, effectively differentiated between mild and severe radiological patterns of emphysema using computed tomography images.

Development and optimisation of a preclinical cone beam computed tomography-based radiomics workflow for radiation oncology research

Background and purpose

Radiomics features derived from medical images have the potential to act as imaging biomarkers to improve diagnosis and predict treatment response in oncology. However, the complex relationships between radiomics features and the biological characteristics of tumours are yet to be fully determined. In this study, we developed a preclinical cone beam computed tomography (CBCT) radiomics workflow with the aim to use in vivo models to further develop radiomics signatures.

Materials and methods

CBCT scans of a mouse phantom were acquired using onboard imaging from a small animal radiotherapy research platform (SARRP, Xstrahl). The repeatability and reproducibility of radiomics outputs were compared across different imaging protocols, segmentation sizes, pre-processing parameters and materials. Robust features were identified and used to compare scans of two xenograft mouse tumour models (A549 and H460).

Results

Changes to the radiomics workflow significantly impact feature robustness. Preclinical CBCT radiomics analysis is feasible with 119 stable features identified from scans imaged at 60 kV, 25 bin width and 0.26 mm slice thickness. Large variation in segmentation volumes reduced the number of reliable radiomics features for analysis. Standardization in imaging and analysis parameters is essential in preclinical radiomics analysis to improve accuracy of outputs, leading to more consistent and reproducible findings.

Conclusions

We present the first optimised workflow for preclinical CBCT radiomics to identify imaging biomarkers. Preclinical radiomics has the potential to maximise the quantity of data captured in in vivo experiments and could provide key information supporting the wider application of radiomics.

External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study

OBJECTIVES

The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers' discriminative performance for pCR prediction.

METHODS

This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve.

RESULTS

Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models.

CONCLUSIONS

The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients.

KEY POINTS

• A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC. • The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer. • The RF classifier performed best in the current study.

AI-based MRI auto-segmentation of brain tumor in rodents, a multicenter study

Automatic segmentation of rodent brain tumor on magnetic resonance imaging (MRI) may facilitate biomedical research. The current study aims to prove the feasibility for automatic segmentation by artificial intelligence (AI), and practicability of AI-assisted segmentation. MRI images, including T2WI, T1WI and CE-T1WI, of brain tumor from 57 WAG/Rij rats in KU Leuven and 46 mice from the cancer imaging archive (TCIA) were collected. A 3D U-Net architecture was adopted for segmentation of tumor bearing brain and brain tumor. After training, these models were tested with both datasets after Gaussian noise addition. Reduction of inter-observer disparity by AI-assisted segmentation was also evaluated. The AI model segmented tumor-bearing brain well for both Leuven and TCIA datasets, with Dice similarity coefficients (DSCs) of 0.87 and 0.85 respectively. After noise addition, the performance remained unchanged when the signal-noise ratio (SNR) was higher than two or eight, respectively. For the segmentation of tumor lesions, AI-based model yielded DSCs of 0.70 and 0.61 for Leuven and TCIA datasets respectively. Similarly, the performance is uncompromised when the SNR was over two and eight respectively. AI-assisted segmentation could significantly reduce the inter-observer disparities and segmentation time in both rats and mice. Both AI models for segmenting brain or tumor lesions could improve inter-observer agreement and therefore contributed to the standardization of the following biomedical studies.

Radiomics model of diffusion-weighted whole-body imaging with background signal suppression (DWIBS) for predicting axillary lymph node status in breast cancer

BACKGROUND

In breast cancer diagnosis and treatment, non-invasive prediction of axillary lymph node (ALN) metastasis can help avoid complications related to sentinel lymph node biopsy.

OBJECTIVE

This study aims to develop and evaluate machine learning models using radiomics features extracted from diffusion-weighted whole-body imaging with background signal suppression (DWIBS) examination for predicting the ALN status.

METHODS

A total of 100 patients with histologically proven, invasive, clinically N0 breast cancer who underwent DWIBS examination consisting of short tau inversion recovery (STIR) and DWIBS sequences before surgery were enrolled. Radiomic features were calculated using segmented primary lesions in DWIBS and STIR sequences and were divided into training (n = 75) and test (n = 25) datasets based on the examination date. Using the training dataset, optimal feature selection was performed using the least absolute shrinkage and selection operator algorithm, and the logistic regression model and support vector machine (SVM) classifier model were constructed with DWIBS, STIR, or a combination of DWIBS and STIR sequences to predict ALN status. Receiver operating characteristic curves were used to assess the prediction performance of radiomics models.

RESULTS

For the test dataset, the logistic regression model using DWIBS, STIR, and a combination of both sequences yielded an area under the curve (AUC) of 0.765 (95% confidence interval: 0.548-0.982), 0.801 (0.597-1.000), and 0.779 (0.567-0.992), respectively, whereas the SVM classifier model using DWIBS, STIR, and a combination of both sequences yielded an AUC of 0.765 (0.548-0.982), 0.757 (0.538-0.977), and 0.779 (0.567-0.992), respectively.

CONCLUSIONS

Use of machine learning models incorporating with the quantitative radiomic features derived from the DWIBS and STIR sequences can potentially predict ALN status.

CT-based morphologic and radiomics features for the classification of MYCN gene amplification status in pediatric neuroblastoma

PURPOSE

MYCN onco-gene amplification in neuroblastoma confers patients to the high-risk disease category for which prognosis is poor and more aggressive multimodal treatment is indicated. This retrospective study leverages machine learning techniques to develop a computed tomography (CT)-based model incorporating semantic and non-semantic features for non-invasive prediction of MYCN amplification status in pediatric neuroblastoma.

METHODS

From 2009 to 2020, 54 pediatric patients treated for neuroblastoma at a specialized children's hospital with pre-treatment contrast-enhanced CT and MYCN status were identified (training cohort, n = 44; testing cohort, n = 10). Six morphologic features and 107 quantitative gray-level texture radiomics features extracted from manually drawn volume-of-interest were analyzed. Following feature selection and class balancing, the final predictive model was developed with eXtreme Gradient Boosting (XGBoost) algorithm. Accumulated local effects (ALE) plots were used to explore main effects of the predictive features. Tumor texture maps were also generated for visualization of radiomics features.

RESULTS

One morphologic and 2 radiomics features were selected for model building. The XGBoost model from the training cohort yielded an area under the receiver operating characteristics curve (AUC-ROC) of 0.930 (95% CI, 0.85-1.00), optimized F1-score of 0.878, and Matthews correlation coefficient (MCC) of 0.773. Evaluation on the testing cohort returned AUC-ROC of 0.880 (95% CI, 0.64-1.00), optimized F1-score of 0.933, and MCC of 0.764. ALE plots and texture maps showed higher "GreyLevelNonUniformity" values, lower "Strength" values, and higher number of image-defined risk factors contribute to higher predicted probability of MYCN amplification.

CONCLUSION

The machine learning model reliably classified MYCN amplification in pediatric neuroblastoma and shows potential as a surrogate imaging biomarker.

Largest diameter delineations can substitute 3D tumor volume delineations for radiomics prediction of human papillomavirus status on MRI's of oropharyngeal cancer

PURPOSE

Laborious and time-consuming tumor segmentations are one of the factors that impede adoption of radiomics in the clinical routine. This study investigates model performance using alternative tumor delineation strategies in models predictive of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC).

METHODS

Of 153 OPSCC patients, HPV status was determined using p16/p53 immunohistochemistry. MR-based radiomic features were extracted within 3D delineations by an inexperienced observer, experienced radiologist or radiation oncologist, and within a 2D delineation of the largest axial tumor diameter and 3D spheres within the tumor. First, logistic regression prediction models were constructed and tested separately for each of these six delineation strategies. Secondly, the model trained on experienced delineations was tested using these delineation strategies. The latter methodology was repeated with the omission of shape features. Model performance was evaluated using area under the curve (AUC), sensitivity and specificity.

RESULTS

Models constructed and tested using single-slice delineations (AUC/Sensitivity/Specificity: 0.84/0.75/0.84) perform better compared to 3D experienced observer delineations (AUC/Sensitivity/Specificity: 0.76/0.76/0.71), where models based on 4 mm sphere delineations (AUC/Sensitivity/Specificity: 0.77/0.59/0.71) show similar performance. Similar performance was found when experienced and largest diameter delineations (AUC/Sens/Spec: 0.76/0.75/0.65 vs 0.76/0.69/0.69) was used to test the model constructed using experienced delineations without shape features.

CONCLUSION

Alternative delineations can substitute labor and time intensive full tumor delineations in a model that predicts HPV status in OPSCC. These faster delineations may improve adoption of radiomics in the clinical setting. Future research should evaluate whether these alternative delineations are valid in other radiomics models.

MRI-based random survival Forest model improves prediction of progression-free survival to induction chemotherapy plus concurrent Chemoradiotherapy in Locoregionally Advanced nasopharyngeal carcinoma

Background

The present study aimed to explore the application value of random survival forest (RSF) model and Cox model in predicting the progression-free survival (PFS) among patients with locoregionally advanced nasopharyngeal carcinoma (LANPC) after induction chemotherapy plus concurrent chemoradiotherapy (IC + CCRT).

Methods

Eligible LANPC patients underwent magnetic resonance imaging (MRI) scan before treatment were subjected to radiomics feature extraction. Radiomics and clinical features of patients in the training cohort were subjected to RSF analysis to predict PFS and were tested in the testing cohort. The performance of an RSF model with clinical and radiologic predictors was assessed with the area under the receiver operating characteristic (ROC) curve (AUC) and Delong test and compared with Cox models based on clinical and radiologic parameters. Further, the Kaplan-Meier method was used for risk stratification of patients.

Results

A total of 294 LANPC patients (206 in the training cohort; 88 in the testing cohort) were enrolled and underwent magnetic resonance imaging (MRI) scans before treatment. The AUC value of the clinical Cox model, radiomics Cox model, clinical + radiomics Cox model, and clinical + radiomics RSF model in predicting 3- and 5-year PFS for LANPC patients was [0.545 vs 0.648 vs 0.648 vs 0.899 (training cohort), and 0.566 vs 0.736 vs 0.730 vs 0.861 (testing cohort); 0.556 vs 0.604 vs 0.611 vs 0.897 (training cohort), and 0.591 vs 0.661 vs 0.676 vs 0.847 (testing cohort), respectively]. Delong test showed that the RSF model and the other three Cox models were statistically significant, and the RSF model markedly improved prediction performance (P < 0.001). Additionally, the PFS of the high-risk group was lower than that of the low-risk group in the RSF model (P < 0.001), while comparable in the Cox model (P > 0.05).

Conclusion

The RSF model may be a potential tool for prognostic prediction and risk stratification of LANPC patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09832-6.

Higher volume growth rate is associated with development of worrisome features in patients with branch duct-intraductal papillary mucinous neoplasms

BACKGROUND

Branch duct-intraductal papillary mucinous neoplasms (BD-IPMNs) are the most common pancreatic cystic tumours and have a low risk of malignant transformation. Current guidelines only evaluate cyst diameter as an important risk factor but it is not always easy to measure, especially when comparing different methods. On the other side, cyst volume is a new parameter with low inter-observer variability and is highly reproducible over time.

AIM

To assess both diameter and volume growth rate of BD-IPMNs and evaluate their correlation with the development of malignant characteristics.

METHODS

Computed tomography scans and magnetic resonance imaging exams were retrospectively reviewed. The diameter was measured on three planes, while the volume was calculated by segmentation: The volume of the entire cyst was determined by manually drawing a region of interest along the edge of the neoplasm on each consecutive slice covering the whole lesion; therefore, a three-dimensional volume of interest was finally obtained with the calculated value expressed in cm³. Changes in size over time were measured. The development of worrisome features was evaluated.

RESULTS

We evaluated exams of 98 patients across a 40.5-mo median follow-up time. Ten patients developed worrisome features. Cysts at baseline were significantly larger in patients who developed worrisome features (diameters P = 0.0035, P = 0.00652, P = 0.00424; volume P = 0.00222). Volume growth rate was significantly higher in patients who developed worrisome features (1.12 cm³/year vs 0 cm³/year, P = 0.0001); diameter growth rate was higher as well, but the difference did not always reach statistical significance. Volume but not diameter growth rate in the first year of follow-up was higher in patients who developed worrisome features (0.46 cm³/year vs 0 cm³/year, P = 0.00634).

CONCLUSION

The measurement of baseline volume and its variation over time is a reliable tool for the follow-up of BD-IPMNs. Volume measurement could be a better tool than diameter measurement to predict the development of worrisome features.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Although CT radiomics has shown promising results in the evaluation of vertebral fractures, the need for manual segmentation of fractured vertebrae limited the routine clinical implementation of radiomics. Therefore, automated segmentation of fractured vertebrae is needed for successful clinical use of radiomics. In this study, we aimed to develop and validate an automated algorithm for segmentation of fractured vertebral bodies on CT, and to evaluate the applicability of the algorithm in a radiomics prediction model to differentiate benign and malignant fractures. A convolutional neural network was trained to perform automated segmentation of fractured vertebral bodies using 341 vertebrae with benign or malignant fractures from 158 patients, and was validated on independent test sets (internal test, 86 vertebrae [59 patients]; external test, 102 vertebrae [59 patients]). Then, a radiomics model predicting fracture malignancy on CT was constructed, and the prediction performance was compared between automated and human expert segmentations. The algorithm achieved good agreement with human expert segmentation at testing (Dice similarity coefficient, 0.93-0.94; cross-sectional area error, 2.66-2.97%; average surface distance, 0.40-0.54 mm). The radiomics model demonstrated good performance in the training set (AUC, 0.93). In the test sets, automated and human expert segmentations showed comparable prediction performances (AUC, internal test, 0.80 vs 0.87, p = 0.044; external test, 0.83 vs 0.80, p = 0.37). In summary, we developed and validated an automated segmentation algorithm that showed comparable performance to human expert segmentation in a CT radiomics model to predict fracture malignancy, which may enable more practical clinical utilization of radiomics.

A systematic review and quality of reporting checklist for repeatability and reproducibility of radiomic features

•

Main factors impacting feature stability: Image acquisition, reconstruction, tumor segmentation, and interpolation.

•

Textural features are less robust than morphological or statistical features.

•

A checklist is provided including items that should be reported in a radiomic study.

Purpose

Although quantitative image biomarkers (radiomics) show promising value for cancer diagnosis, prognosis, and treatment assessment, these biomarkers still lack reproducibility. In this systematic review, we aimed to assess the progress in radiomics reproducibility and repeatability in the recent years.

Methods and materials

Four hundred fifty-one abstracts were retrieved according to the original PubMed search pattern with the publication dates ranging from 2017/05/01 to 2020/12/01. Each abstract including the keywords was independently screened by four observers. Forty-two full-text articles were selected for further analysis. Patient population data, radiomic feature classes, feature extraction software, image preprocessing, and reproducibility results were extracted from each article. To support the community with a standardized reporting strategy, we propose a specific reporting checklist to evaluate the feasibility to reproduce each study.

Results

Many studies continue to under-report essential reproducibility information: all but one clinical and all but two phantom studies missed to report at least one important item reporting image acquisition. The studies included in this review indicate that all radiomic features are sensitive to image acquisition, reconstruction, tumor segmentation, and interpolation. However, the amount of sensitivity is feature dependent, for instance, textural features were, in general, less robust than statistical features.

Conclusions

Radiomics repeatability, reproducibility, and reporting quality can substantially be improved regarding feature extraction software and settings, image preprocessing and acquisition, cutoff values for stable feature selection. Our proposed radiomics reporting checklist can serve to simplify and improve the reporting and, eventually, guarantee the possibility to fully replicate and validate radiomic studies.

A meta-analysis of the diagnostic performance of machine learning-based MRI in the prediction of axillary lymph node metastasis in breast cancer patients

Background

Despite that machine learning (ML)-based MRI has been evaluated for diagnosis of axillary lymph node metastasis (ALNM) in breast cancer patients, diagnostic values they showed have been variable. In this study, we aimed to assess the use of ML to classify ALNM on MRI and to identify potential covariates that might influence the diagnostic performance of ML.

Methods

A systematic research of PubMed, Embase, Web of Science, and the Cochrane Library was conducted until 27 December 2020 to collect the included articles. Subgroup analysis was also performed.

Findings

Fourteen studies assessing a total of 2247 breast cancer patients were included in the analysis. The overall AUC for ML in the validation set was 0.80 (95% confidence interval [CI] 0.76–0.83) with a negative predictive value of 0.83. The pooled sensitivity and specificity were 0.79 (95% CI 0.74–0.84) and 0.77 (95% CI 0.73–0.81), respectively. In the subgroup analysis of the validation set, T1-weighted contrast-enhanced (T1CE) imaging with ML yielded a higher sensitivity (0.80 vs. 0.67 vs. 0.76) than the T2-weighted fat-suppressed (T2-FS) imaging and diffusion-weighted imaging (DWI). Support vector machines (SVMs) had a higher specificity than linear regression (LR) and linear discriminant analysis (LDA) (0.79 vs. 0.78 vs. 0.75), whereas LDA showed a higher sensitivity than LR and SVM (0.83 vs. 0.70 vs. 0.77).

Interpretation

MRI sequences and algorithms were the main factors that affect the diagnostic performance of ML. Although its results were encouraging with the pooled sensitivity of around 0.80, it meant that 1 in 5 women that would go with undetected metastases, which may have a detrimental effect on the overall survival for 20% of patients with positive SLN status. Despite that a high NPV of 0.83 meant that ML could potentially benefit those with negative SLN, it might also translate to 1 in 5 tests being false negative. We would like to suggest that ML may not be yet usable in clinical routine especially when patient survival is used as a primary measurement of its outcome.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01034-1.

Radiomic Features on Multiparametric MRI for Preoperative Evaluation of Pituitary Macroadenomas Consistency: Preliminary Findings

BACKGROUND

Preoperative assessment of the consistency of pituitary macroadenomas (PMA) might be needed for surgical planning.

PURPOSE

To investigate the diagnostic performance of radiomics models based on multiparametric magnetic resonance imaging (mpMRI) for preoperatively evaluating the tumor consistency of PMA.

STUDY TYPE

Retrospective.

POPULATION

One hundred and fifty-six PMA patients (soft consistency, N = 104 vs. hard consistency, N = 52), divided into training (N = 108) and test (N = 48) cohorts. The tumor consistency was determined on surgical findings.

FIELD STRENGTH/SEQUENCE

T1-weighted imaging (T1WI), contrast-enhanced T1WI (T1CE), and T2-weighted imaging (T2WI) using spin-echo sequences with a 3.0-T scanner.

ASSESSMENT

An automated three-dimensional (3D) segmentation was performed to generate the volume of interest (VOI) on T2WI, then T1WI/T1CE were coregistered to T2WI. A total of 388 radiomic features were extracted on each VOI of mpMRI. The top-discriminative features were identified using the minimum-redundancy maximum-relevance method and 0.632+ bootstrapping. The radiomics models based on each sequence and their combinations were established via the random forest (RF) and support vector machine (SVM), and independently evaluated for their ability in distinguishing PMA consistency.

STATISTICAL TESTS

Mann-Whitney U-test and Chi-square test were used for comparison analysis. The area under the receiver operating characteristic curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), and relative standard deviation (RSD) were calculated to evaluate each model's performance. ACC with P-value<0.05 was considered statistically significant.

RESULTS

Eleven mpMRI-based features exhibited statistically significant differences between soft and hard PMA in the training cohort. The radiomics model built on combined T1WI/T1CE/T2WI demonstrated the best performance among all the radiomics models with an AUC of 0.90 (95% confidence interval [CI]: 0.87-0.92), ACC of 0.87 (CI: 0.84-0.89), SEN of 0.83 (CI: 0.81-0.85), and SPE of 0.87 (CI: 0.85-0.99) in the test cohort.

DATA CONCLUSION

Radiomic features based on mpMRI have good performance in the presurgical evaluation of PMA consistency.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

A Comprehensive Review on Radiomics and Deep Learning for Nasopharyngeal Carcinoma Imaging

Nasopharyngeal carcinoma (NPC) is one of the most common malignant tumours of the head and neck, and improving the efficiency of its diagnosis and treatment strategies is an important goal. With the development of the combination of artificial intelligence (AI) technology and medical imaging in recent years, an increasing number of studies have been conducted on image analysis of NPC using AI tools, especially radiomics and artificial neural network methods. In this review, we present a comprehensive overview of NPC imaging research based on radiomics and deep learning. These studies depict a promising prospect for the diagnosis and treatment of NPC. The deficiencies of the current studies and the potential of radiomics and deep learning for NPC imaging are discussed. We conclude that future research should establish a large-scale labelled dataset of NPC images and that studies focused on screening for NPC using AI are necessary.

Assessment of MRI-Based Radiomics in Preoperative T Staging of Rectal Cancer: Comparison between Minimum and Maximum Delineation Methods

The manual delineation of the lesion is mainly used as a conventional segmentation method, but it is subjective and has poor stability and repeatability. The purpose of this study is to validate the effect of a radiomics model based on MRI derived from two delineation methods in the preoperative T staging of patients with rectal cancer (RC). A total of 454 consecutive patients with pathologically confirmed RC who underwent preoperative MRI between January 2018 and December 2019 were retrospectively analyzed. RC patients were grouped according to whether the muscularis propria was penetrated. Two radiologists segmented lesions, respectively, by minimum delineation (Method 1) and maximum delineation (Method 2), after which radiomics features were extracted. Inter- and intraclass correlation coefficient (ICC) of all features was evaluated. After feature reduction, the support vector machine (SVM) was trained to build a prediction model. The diagnostic performances of models were determined by receiver operating characteristic (ROC) curves. Then, the areas under the curve (AUCs) were compared by the DeLong test. Decision curve analysis (DCA) was performed to evaluate clinical benefit. Finally, 317 patients were assessed, including 152 cases in the training set and 165 cases in the validation set. Moreover, 1288/1409 (91.4%) features of Method 1 and 1273/1409 (90.3%) features of Method 2 had good robustness (P < 0.05). The AUCs of Model 1 and Model 2 were 0.808 and 0.903 in the validation set, respectively (P = 0.035). DCA showed that the maximum delineation yielded more net benefit. MRI-based radiomics models derived from two segmentation methods demonstrated good performance in the preoperative T staging of RC. The minimum delineation had better stability in feature selection, while the maximum delineation method was more clinically beneficial.

MRI based radiomics in nasopharyngeal cancer: Systematic review and perspectives using radiomic quality score (RQS) assessment

BACKGROUND

MRI based radiomics has the potential to better define tumor biology compared to qualitative MRI assessment and support decisions in patients affected by nasopharyngeal carcinoma. Aim of this review was to systematically evaluate the methodological quality of studies using MRI- radiomics for nasopharyngeal cancer patient evaluation.

METHODS

A systematic search was performed in PUBMED, WEB OF SCIENCE and SCOPUS using "MRI, magnetic resonance imaging, radiomic, texture analysis, nasopharyngeal carcinoma, nasopharyngeal cancer" in all possible combinations. The methodological quality of study included ( = 24) was evaluated according to the RQS (Radiomic quality score). Subgroup, for journal type (imaging/clinical) and biomarker (prognostic/predictive), and correlation, between RQS and journal Impact Factor, analyses were performed. Mann-Whitney U test and Spearman's correlation were performed. P value < .05 were defined as statistically significant.

RESULTS

Overall, no studies reported a phantom study or a test re-test for assessing stability in image, biological correlation or open science data. Only 8% of them included external validation. Almost half of articles (45 %) performed multivariable analysis with non-radiomics features. Only 1 study was prospective (4%). The mean RQS was 7.5 ± 5.4. No significant differences were detected between articles published in clinical/imaging journal and between studies with a predictive or prognostic biomarker. No significant correlation was found between total RQS and Impact Factor of the year of publication (p always > 0.05).

CONCLUSIONS

Radiomic articles in nasopharyngeal cancer are mostly of low methodological quality. The greatest limitations are the lack of external validation, biological correlates, prospective design and open science.

Krizsan A, Forgács A, Berényi E, Balkay L. Effect of grey-level discretization on texture feature on different weighted MRI images of diverse disease groups

PURPOSE

Many studies of MRI radiomics do not include the discretization method used for the analyses, which might indicate that the discretization methods used are considered irrelevant. Our goals were to compare three frequently used discretization methods (lesion relative resampling (LRR), lesion absolute resampling (LAR) and absolute resampling (AR)) applied to the same data set, along with two different lesion segmentation approaches.

METHODS

We analyzed the effects of altering bin widths or bin numbers for the three different sampling methods using 40 texture indices (TIs). The impact was evaluated on brain MRI studies obtained for 71 patients divided into three different disease groups: multiple sclerosis (MS, N = 22), ischemic stroke (IS, N = 22), cancer patients (N = 27). Two different MRI acquisition protocols were considered for all patients, a T2- and a post-contrast 3D T1-weighted MRI sequence. Elliptical and manually drawn VOIs were employed for both imaging series. Three different types of gray-level discretization methods were used: LRR, LAR and AR. Hypothesis tests were done among all diseased and control areas to compare the TI values in these areas. We also did correlation analyses between TI values and lesion volumes.

RESULTS

In general, no significant differences were reported in the results when employing the AR and LAR discretization methods. It was found that employing 38 TIs introduced variation in the results when the number of bin parameters was altered, suggesting that both the degree and direction of monotonicity between each TI value and binning parameters were characteristic for each TI. Furthermore, while TIs were changing with altering binning values, no changes correlated to neither disease nor the MRI sequence. We found that most indices correlated weakly with the volume, while the correlation coefficients were independent of both diseases analyzed and MR contrast. Several cooccurrence-matrix based texture parameters show a definite higher correlation when employing the LRR discretization method However, with the best correlations obtained for the manually drawn VOI. Hypothesis tests among all disease and control areas (co-lateral hemisphere) revealed that the AR or LAR discretization techniques provide more suitable texture features than LRR. In addition, the manually drawn segmentation gave fewer significantly different TIs than the ellipsoid segmentations. In addition, the amount of TIs with significant differences was increasing with increasing the number of bins, or decreasing bin widths.

CONCLUSION

Our findings indicate that the AR discretization method may offer the best texture analysis in MR image assessments. Employing too many bins or too large bin widths might reduce the selection of TIs that can be used for differential diagnosis. In general, more statistically different TIs were observed for elliptical segmentations when compared to the manually drawn VOIs. In the texture analysis of MR studies, studies and publications should report on all important parameters and methods related to data collection, corrections, normalization, discretization, and segmentation.

Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting

Purpose

In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics.

Methods

In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing).

Results

The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training.

Conclusion

The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05244-z.

Evaluation of a multiparametric MRI radiomic-based approach for stratification of equivocal PI-RADS 3 and upgraded PI-RADS 4 prostatic lesions

Despite the key-role of the Prostate Imaging and Reporting and Data System (PI-RADS) in the diagnosis and characterization of prostate cancer (PCa), this system remains to be affected by several limitations, primarily associated with the interpretation of equivocal PI-RADS 3 lesions and with the debated role of Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI), which is only used to upgrade peripheral PI-RADS category 3 lesions to PI-RADS category 4 if enhancement is focal. We aimed at investigating the usefulness of radiomics for detection of PCa lesions (Gleason Score ≥ 6) in PI-RADS 3 lesions and in peripheral PI-RADS 3 upgraded to PI-RADS 4 lesions (upPI-RADS 4). Multiparametric MRI (mpMRI) data of patients who underwent prostatic mpMRI between April 2013 and September 2018 were retrospectively evaluated. Biopsy results were used as gold standard. PI-RADS 3 and PI-RADS 4 lesions were re-scored according to the PI-RADS v2.1 before and after DCE-MRI evaluation. Radiomic features were extracted from T2-weighted MRI (T2), Apparent diffusion Coefficient (ADC) map and DCE-MRI subtracted images using PyRadiomics. Feature selection was performed using Wilcoxon-ranksum test and Minimum Redundancy Maximum Relevance (mRMR). Predictive models were constructed for PCa detection in PI-RADS 3 and upPI-RADS 4 lesions using at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. 41 PI-RADS 3 and 32 upPI-RADS 4 lesions were analyzed. Among 293 radiomic features, the top selected features derived from T2 and ADC. For PI-RADS 3 stratification, second order model showed higher performances (Area Under the Receiver Operating Characteristic Curve-AUC- = 80%), while for upPI-RADS 4 stratification, first order model showed higher performances respect to superior order models (AUC = 89%). Our results support the significant role of T2 and ADC radiomic features for PCa detection in lesions scored as PI-RADS 3 and upPI-RADS 4. Radiomics models showed high diagnostic efficacy in classify PI-RADS 3 and upPI-RADS 4 lesions, outperforming PI-RADS v2.1 performance.

Prognostic value of CT radiomics in evaluating lymphovascular invasion in rectal cancer: Diagnostic performance based on different volumes of interest

OBJECTIVES

This study aims to evaluate diagnostic performance of radiomic analysis using computed tomography (CT) to identify lymphovascular invasion (LVI) in patients diagnosed with rectal cancer and assess diagnostic performance of different lesion segmentations.

METHODS

The study is applied to 169 pre-treatment CT images and the clinical features of patients with rectal cancer. Radiomic features are extracted from two different volumes of interest (VOIs) namely, gross tumor volume and peri-tumor tissue volume. The maximum relevance and the minimum redundancy, and the least absolute shrinkage selection operator based logistic regression analyses are performed to select the optimal feature subset on the training cohort. Then, Rad and Rad-clinical combined models for LVI prediction are built and compared. Finally, the models are externally validated.

RESULTS

Eighty-three patients had positive LVI on pathology, while 86 had negative LVI. An optimal multi-mode radiology nomogram for LVI estimation is established. The area under the receiver operating characteristic curves of the Rad and Rad-clinical combined model in the peri-tumor VOI group are significantly higher than those in the tumor VOI group (Rad: peri-tumor vs. tumor: 0.85 vs. 0.68; Rad-clinical: peri-tumor vs. tumor: 0.90 vs 0.82) in the validation cohort. Decision curve analysis shows that the peri-tumor-based Rad-clinical combined model has the best performance in identifying LVI than other models.

CONCLUSIONS

CT radiomics model based on peri-tumor volumes improves prediction performance of LVI in rectal cancer compared with the model based on tumor volumes.

Radiomics in medical imaging-"how-to" guide and critical reflection

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.