Reproducibility of 2D versus 3D radiomics for quantitative assessment of fetal lung development: a retrospective fetal MRI study

Development and validation of a model based on preoperative dual-layer detector spectral computed tomography 3D VOI-based quantitative parameters to predict high Ki-67 proliferation index in pancreatic ductal adenocarcinoma

OBJECTIVE

To develop and validate a model integrating dual-layer detector spectral computed tomography (DLCT) three-dimensional (3D) volume of interest (VOI)-based quantitative parameters and clinical features for predicting Ki-67 proliferation index (PI) in pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

A total of 162 patients with histopathologically confirmed PDAC who underwent DLCT examination were included and allocated to the training (114) and validation (48) sets. 3D VOI-iodine concentration (IC), 3D VOI-slope of the spectral attenuation curves, and 3D VOI-effective atomic number were obtained from the portal venous phase. The significant clinical features and DLCT quantitative parameters were identified through univariate analysis and multivariate logistic regression. The discrimination capability and clinical applicability of the clinical, DLCT, and DLCT-clinical models were quantified by the Receiver Operating Characteristic curve (ROC) and Decision Curve Analysis (DCA), respectively. The optimal model was then used to develop a nomogram, with the goodness-of-fit evaluated through the calibration curve.

RESULTS

The DLCT-clinical model demonstrated superior predictive capability and a satisfactory net benefit for Ki-67 PI in PDAC compared to the clinical and DLCT models. The DLCT-clinical model integrating 3D VOI-IC and CA125 showed area under the ROC curves of 0.939 (95% CI, 0.895-0.982) and 0.915 (95% CI, 0.834-0.996) in the training and validation sets, respectively. The nomogram derived from the DLCT-clinical model exhibited favorable calibration, as depicted by the calibration curve.

CONCLUSIONS

The proposed model based on DLCT 3D VOI-IC and CA125 is a non-invasive and effective preoperative prediction tool demonstrating favorable predictive performance for Ki-67 PI in PDAC.

CRITICAL RELEVANCE STATEMENT

The dual-layer detector spectral computed tomography-clinical model could help predict high Ki-67 PI in pancreatic ductal adenocarcinoma patients, which may help clinicians provide appropriate and individualized treatments.

KEY POINTS

Dual-layer detector spectral CT (DLCT) could predict Ki-67 in pancreatic ductal adenocarcinoma (PDAC). The DLCT-clinical model improved the differential diagnosis of Ki-67. The nomogram showed satisfactory calibration and net benefit for discriminating Ki-67.

Multiparametric prenatal imaging characterization of fetal brain edema in Chiari II malformation might help to select candidates for fetal surgery

OBJECTIVE

To identify brain edema in fetuses with Chiari II malformation using a multiparametric approach including structural T2-weighted, diffusion tensor imaging (DTI) metrics, and MRI-based radiomics.

METHODS

A single-center retrospective review of MRI scans obtained in fetuses with Chiari II was performed. Brain edema cases were radiologically identified using the following MR criteria: brain parenchymal T2 prolongation, blurring of lamination, and effacement of external CSF spaces. Fractional anisotropy (FA) values were calculated from regions of interest (ROI), including hemispheric parenchyma, internal capsule, and corticospinal tract, and compared group-wise. After 1:1 age matching and manual single-slice 2D segmentation of the fetal brain parenchyma using ITK-Snap, radiomics features were extracted using pyradiomics. Areas under the curve (AUCs) of the features regarding discriminating subgroups were calculated.

RESULTS

Ninety-one fetuses with Chiari II underwent a total of 101 MRI scans at a median gestational age of 24.4 weeks and were included. Fifty scans were visually classified as Chiari II with brain edema group and showed significantly reduced external CSF spaces compared to the nonedema group (9.8 vs. 18.3 mm, p < 0.001). FA values of all used ROIs were elevated in the edema group (p < 0.001 for all ROIs). The 10 most important radiomics features showed an AUC of 0.81 (95%CI: 0.71, 0.91) for discriminating between Chiari II fetuses with and without edema.

CONCLUSIONS

Brain edema in fetuses with Chiari II is common and radiologically detectable on T2-weighted fetal MRI sequences, and DTI-based FA values and radiomics features provide further evidence of microstructure differences between subgroups with and without edema.

CLINICAL RELEVANCE STATEMENT

A more severe phenotype of fetuses with Chiari II malformation is characterized by prenatal brain edema and more postnatal clinical morbidity and disability. Fetal brain edema is a promising prenatal MR imaging biomarker candidate for optimizing the risk-benefit evaluation of selection for fetal surgery.

KEY POINTS

Brain edema of fetuses prenatally diagnosed with Chiari II malformation is a common, so far unknown, association. DTI metrics and radiomics confirm microstructural differences between the brains of Chiari II fetuses with and without edema. Fetal brain edema may explain worse motor outcomes in this Chiari II subgroup, who may substantially benefit from fetal surgery.

Different radiomics annotation methods comparison in rectal cancer characterisation and prognosis prediction: a two-centre study

OBJECTIVES

To explore the performance differences of multiple annotations in radiomics analysis and provide a reference for tumour annotation in large-scale medical image analysis.

METHODS

A total of 342 patients from two centres who underwent radical resection for rectal cancer were retrospectively studied and divided into training, internal validation, and external validation cohorts. Three predictive tasks of tumour T-stage (pT), lymph node metastasis (pLNM), and disease-free survival (pDFS) were performed. Twelve radiomics models were constructed using Lasso-Logistic or Lasso-Cox to evaluate and four annotation methods, 2D detailed annotation along tumour boundaries (2D), 3D detailed annotation along tumour boundaries (3D), 2D bounding box (2DBB), and 3D bounding box (3DBB) on T2-weighted images, were compared. Radiomics models were used to establish combined models incorporating clinical risk factors. The DeLong test was performed to compare the performance of models using the receiver operating characteristic curves.

RESULTS

For radiomics models, the area under the curve values ranged from 0.627 (0.518-0.728) to 0.811 (0.705-0.917) in the internal validation cohort and from 0.619 (0.469-0.754) to 0.824 (0.689-0.918) in the external validation cohort. Most radiomics models based on four annotations did not differ significantly, except between the 3D and 3DBB models for pLNM (p = 0.0188) in the internal validation cohort. For combined models, only the 2D model significantly differed from the 2DBB (p = 0.0372) and 3D models (p = 0.0380) for pDFS.

CONCLUSION

Radiomics and combined models constructed with 2D and bounding box annotations showed comparable performances to those with 3D and detailed annotations along tumour boundaries in rectal cancer characterisation and prognosis prediction.

CRITICAL RELEVANCE STATEMENT

For quantitative analysis of radiological images, the selection of 2D maximum tumour area or bounding box annotation is as representative and easy to operate as 3D whole tumour or detailed annotations along tumour boundaries.

KEY POINTS

There is currently a lack of discussion on whether different annotation efforts in radiomics are predictively representative. No significant differences were observed in radiomics and combined models regardless of the annotations (2D, 3D, detailed, or bounding box). Prioritise selecting the more time and effort-saving 2D maximum area bounding box annotation.

Three-dimensional iodine mapping quantified by dual-energy CT for predicting programmed death-ligand 1 expression in invasive pulmonary adenocarcinoma

We examined the association between texture features using three-dimensional (3D) io-dine density histogram on delayed phase of dual-energy CT (DECT) and expression of programmed death-ligand 1 (PD-L1) using immunostaining methods in non-small cell lung cancer. Consecutive 37 patients were scanned by DECT. Unenhanced and enhanced (3 min delay) images were obtained. 3D texture analysis was performed for each nodule to obtain 7 features (max, min, median, mean, standard deviation, skewness, and kurtosis) from iodine density mapping and extracellular volume (ECV). A pathologist evaluated a tumor proportion score (TPS, %) using PD-L1 immunostaining: PD-L1 high (TPS ≥ 50%) and low or negative expression (TPS < 50%). Associations between PD-L1 expression and each 8 parameter were evaluated using logistic regression analysis. The multivariate logistic regression analysis revealed that skewness and ECV were independent indicators associated with high PD-L1 expression (skewness: odds ratio [OR]  7.1 [95% CI 1.1, 45.6], p = 0.039; ECV: OR 6.6 [95% CI 1.1, 38.4], p = 0.037). In the receiver-operating characteristic analysis, the area under the curve of the combination of skewness and ECV was 0.83 (95% CI 0.67, 0.93) with sensitivity of 64% and specificity of 96%. Skewness from 3D iodine density histogram and ECV on dual energy CT were significant factors for predicting PD-L1 expression.

A comparison of 2D and 3D magnetic resonance imaging-based intratumoral and peritumoral radiomics models for the prognostic prediction of endometrial cancer: a pilot study

BACKGROUND

Accurate prognostic assessment is vital for the personalized treatment of endometrial cancer (EC). Although radiomics models have demonstrated prognostic potential in EC, the impact of region of interest (ROI) delineation strategies and the clinical significance of peritumoral features remain uncertain. Our study thereby aimed to explore the predictive performance of varying radiomics models for the prediction of LVSI, DMI, and disease stage in EC.

METHODS

Patients with 174 histopathology-confirmed EC were retrospectively reviewed. ROIs were manually delineated using the 2D and 3D approach on T2-weighted MRI images. Six radiomics models involving intratumoral (2Dintra and 3Dintra), peritumoral (2Dperi and 3Dperi), and combined models (2Dintra + peri and 3Dintra + peri) were developed. Models were constructed using the logistic regression method with five-fold cross-validation. Area under the receiver operating characteristic curve (AUC) was assessed, and was compared using the Delong's test.

RESULTS

No significant differences in AUC were observed between the 2Dintra and 3Dintra models, or the 2Dperi and 3Dperi models in all prediction tasks (P > 0.05). Significant difference was observed between the 3Dintra and 3Dperi models for LVSI (0.738 vs. 0.805) and DMI prediction (0.719 vs. 0.804). The 3Dintra + peri models demonstrated significantly better predictive performance in all 3 prediction tasks compared to the 3Dintra model in both the training and validation cohorts (P < 0.05).

CONCLUSIONS

Comparable predictive performance was observed between the 2D and 3D models. Combined models significantly improved predictive performance, especially with 3D delineation, suggesting that intra- and peritumoral features can provide complementary information for comprehensive prognostication of EC.

Nomograms based on multiparametric MRI radiomics integrated with clinical-radiological features for predicting the response to induction chemotherapy in nasopharyngeal carcinoma

OBJECTIVE

To establish nomograms integrating multiparametric MRI radiomics with clinical-radiological features to identify the responders and non-responders to induction chemotherapy (ICT) in nasopharyngeal carcinoma (NPC).

METHODS

We retrospectively analyzed the clinical and MRI data of 168 NPC patients between December 2015 and April 2022. We used 3D-Slicer to segment the regions of interest (ROIs) and the "Pyradiomic" package to extract radiomics features. We applied the least absolute shrinkage and selection operator regression to select radiomics features. We developed clinical-only, radiomics-only, and the combined clinical-radiomics nomograms using logistic regression analysis. The receiver operating characteristic curves, DeLong test, calibration, and decision curves were used to assess the discriminative performance of the models. The model was internally validated using 10-fold cross-validation.

RESULTS

A total of 14 optimal features were finally selected to develop a radiomic signature, with an AUC of 0.891 (95 % CI, 0.825-0.946) in the training cohort and 0.837 (95 % CI, 0.723-0.932) in the testing cohort. The nomogram based on the Rad-Score and clinical-radiological factors for evaluating tumor response to ICT yielded an AUC of 0.926 (95 % CI, 0.875-0.965) and 0.901 (95 % CI, 0.815-0.979) in the two cohorts, respectively. Decision curves demonstrated that the combined clinical-radiomics nomograms were clinically useful.

CONCLUSION

Nomograms integrating multiparametric MRI-based radiomics and clinical-radiological features could non-invasively discriminate ICT responders from non-responders in NPC patients.

CT-based radiomics for predicting lymph node metastasis in esophageal cancer: a systematic review and meta-analysis

Objective

We aimed to evaluate the diagnostic effectiveness of computed tomography (CT)-based radiomics for predicting lymph node metastasis (LNM) in patients diagnosed with esophageal cancer (EC).

Methods

The present study conducted a comprehensive search by accessing the following databases: PubMed, Embase, Cochrane Library, and Web of Science, with the aim of identifying relevant studies published until July 10th, 2023. The diagnostic accuracy was summarized using the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC). The researchers utilized Spearman's correlation coefficient for assessing the threshold effect, besides performing meta-regression and subgroup analysis for the exploration of possible heterogeneity sources. The quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies-2 and the Radiomics Quality Score (RQS).

Results

The meta-analysis included six studies conducted from 2018 to 2022, with 483 patients enrolled and LNM rates ranging from 27.2% to 59.4%. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC, along with their corresponding 95% CI, were 0.73 (0.67, 0.79), 0.76 (0.69, 0.83), 3.1 (2.3, 4.2), 0.35 (0.28, 0.44), 9 (6, 14), and 0.78 (0.74, 0.81), respectively. The results demonstrated the absence of significant heterogeneity in sensitivity, while significant heterogeneity was observed in specificity; no threshold effect was detected. The observed heterogeneity in the specificity was attributed to the sample size and CT-scan phases (P < 0.05). The included studies exhibited suboptimal quality, with RQS ranging from 14 to 16 out of 36. However, most of the enrolled studies exhibited a low-risk bias and minimal concerns relating to applicability.

Conclusion

The present meta-analysis indicated that CT-based radiomics demonstrated a favorable diagnostic performance in predicting LNM in EC. Nevertheless, additional high-quality, large-scale, and multicenter trials are warranted to corroborate these findings.

Systematic Review Registration

Open Science Framework platform at https://osf.io/5zcnd.

Automated body organ segmentation, volumetry and population-averaged atlas for 3D motion-corrected T2-weighted fetal body MRI

Structural fetal body MRI provides true 3D information required for volumetry of fetal organs. However, current clinical and research practice primarily relies on manual slice-wise segmentation of raw T2-weighted stacks, which is time consuming, subject to inter- and intra-observer bias and affected by motion-corruption. Furthermore, there are no existing standard guidelines defining a universal approach to parcellation of fetal organs. This work produces the first parcellation protocol of the fetal body organs for motion-corrected 3D fetal body MRI. It includes 10 organ ROIs relevant to fetal quantitative volumetry studies. We also introduce the first population-averaged T2w MRI atlas of the fetal body. The protocol was used as a basis for training of a neural network for automated organ segmentation. It showed robust performance for different gestational ages. This solution minimises the need for manual editing and significantly reduces time. The general feasibility of the proposed pipeline was also assessed by analysis of organ growth charts created from automated parcellations of 91 normal control 3T MRI datasets that showed expected increase in volumetry during 22-38 weeks gestational age range.

Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology

Artificial intelligence (AI) has gained prominence in medical imaging, particularly in obstetrics and gynecology (OB/GYN), where ultrasound (US) is the preferred method. It is considered cost effective and easily accessible but is time consuming and hindered by the need for specialized training. To overcome these limitations, AI models have been proposed for automated plane acquisition, anatomical measurements, and pathology detection. This study aims to overview recent literature on AI applications in OB/GYN US imaging, highlighting their benefits and limitations. For the methodology, a systematic literature search was performed in the PubMed and Cochrane Library databases. Matching abstracts were screened based on the PICOS (Participants, Intervention or Exposure, Comparison, Outcome, Study type) scheme. Articles with full text copies were distributed to the sections of OB/GYN and their research topics. As a result, this review includes 189 articles published from 1994 to 2023. Among these, 148 focus on obstetrics and 41 on gynecology. AI-assisted US applications span fetal biometry, echocardiography, or neurosonography, as well as the identification of adnexal and breast masses, and assessment of the endometrium and pelvic floor. To conclude, the applications for AI-assisted US in OB/GYN are abundant, especially in the subspecialty of obstetrics. However, while most studies focus on common application fields such as fetal biometry, this review outlines emerging and still experimental fields to promote further research.

3D T2w fetal body MRI: automated organ volumetry, growth charts and population-averaged atlas

Structural fetal body MRI provides true 3D information required for volumetry of fetal organs. However, current clinical and research practice primarily relies on manual slice-wise segmentation of raw T2-weighted stacks, which is time consuming, subject to inter- and intra-observer bias and affected by motion-corruption. Furthermore, there are no existing standard guidelines defining a universal approach to parcellation of fetal organs. This work produces the first parcellation protocol of the fetal body organs for motion-corrected 3D fetal body MRI. It includes 10 organ ROIs relevant to fetal quantitative volumetry studies. We also introduce the first population-averaged T2w MRI atlas of the fetal body. The protocol was used as a basis for training of a neural network for automated organ segmentation. It showed robust performance for different gestational ages. This solution minimises the need for manual editing and significantly reduces time. The general feasibility of the proposed pipeline was also assessed by analysis of organ growth charts created from automated parcellations of 91 normal control 3T MRI datasets that showed expected increase in volumetry during 22-38 weeks gestational age range. In addition, the results of comparison between 60 normal and 12 fetal growth restriction datasets revealed significant differences in organ volumes.