Development of End-to-End AI-Based MRI Image Analysis System for Predicting IDH Mutation Status of Patients with Gliomas: Multicentric Validation.

Radiogenomics has shown potential to predict genomic phenotypes from medical images. The development of models using standard-of-care pre-operative MRI images, as opposed to advanced MRI images, enables a broader reach of such models. In this work, a radiogenomics model for IDH mutation status prediction from standard-of-care MRIs in patients with glioma was developed and validated using multicentric data. A cohort of 142 (wild-type: 32.4%) patients with glioma retrieved from the TCIA/TCGA was used to train a logistic regression model to predict the IDH mutation status. The model was evaluated using retrospective data collected in two distinct hospitals, comprising 36 (wild-type: 63.9%) and 53 (wild-type: 75.5%) patients. Model development utilized ROC analysis. Model discrimination and calibration were used for validation. The model yielded an AUC of 0.741 vs. 0.716 vs. 0.938, a sensitivity of 0.784 vs. 0.739 vs. 0.875, and a specificity of 0.657 vs. 0.692 vs. 1.000 on the training, test cohort 1, and test cohort 2, respectively. The assessment of model fairness suggested an unbiased model for age and sex, and calibration tests showed a p < 0.05. These results indicate that the developed model allows the prediction of the IDH mutation status in gliomas using standard-of-care MRI images and does not appear to hold sex and age biases.

Augmented Reality in Breast Surgery Education.

Introduction: Augmented reality (AR) has demonstrated a potentially wide range of benefits and educational applications in the virtual health ecosystem. The concept of real-time data acquisition, machine learning-aided processing, and visualization is a foreseen ambition to leverage AR applications in the healthcare sector. This breakthrough with immersive technologies like AR, mixed reality, virtual reality, or extended reality will hopefully initiate a new surgical era: that of the use of the so-called surgical metaverse. Methods: This paper focuses on the future use of AR in breast surgery education describing two potential applications (surgical remote telementoring and impalpable breast cancer localization using AR), along with the technical needs to make it possible. Conclusion: Surgical telementoring and impalpable tumors noninvasive localization are two examples that can have success in the future provided the improvements in both data transformation and infrastructures are capable to overcome the current challenges and limitations.

Performances and variability of CT radiomics for the prediction of microvascular invasion and survival in patients with HCC: a matter of chance or standardisation?

OBJECTIVES: To measure the performance and variability of a radiomics-based model for the prediction of microvascular invasion (MVI) and survival in patients with resected hepatocellular carcinoma (HCC), simulating its sequential development and application. METHODS: This study included 230 patients with 242 surgically resected HCCs who underwent preoperative CT, of which 73/230 (31.7%) were scanned in external centres. The study cohort was split into training set (158 patients, 165 HCCs) and held-out test set (72 patients, 77 HCCs), stratified by random partitioning, which was repeated 100 times, and by a temporal partitioning to simulate the sequential development and clinical use of the radiomics model. A machine learning model for the prediction of MVI was developed with least absolute shrinkage and selection operator (LASSO). The concordance index (C-index) was used to assess the value to predict the recurrence-free (RFS) and overall survivals (OS). RESULTS: In the 100-repetition random partitioning cohorts, the radiomics model demonstrated a mean AUC of 0.54 (range 0.44-0.68) for the prediction of MVI, mean C-index of 0.59 (range 0.44-0.73) for RFS, and 0.65 (range 0.46-0.86) for OS in the held-out test set. In the temporal partitioning cohort, the radiomics model yielded an AUC of 0.50 for the prediction of MVI, a C-index of 0.61 for RFS, and 0.61 for OS, in the held-out test set. CONCLUSIONS: The radiomics models had a poor performance for the prediction of MVI with a large variability in the model performance depending on the random partitioning. Radiomics models demonstrated good performance in the prediction of patient outcomes. CLINICAL RELEVANCE STATEMENT: Patient selection within the training set strongly influenced the performance of the radiomics models for predicting microvascular invasion; therefore, a random approach to partitioning a retrospective cohort into a training set and a held-out set seems inappropriate. KEY POINTS: • The performance of the radiomics models for the prediction of microvascular invasion and survival widely ranged (AUC range 0.44-0.68) in the randomly partitioned cohorts. • The radiomics model for the prediction of microvascular invasion was unsatisfying when trying to simulate its sequential development and clinical use in a temporal partitioned cohort imaged with a variety of CT scanners. • The performance of the radiomics models for the prediction of survival was good with similar performances in the 100-repetition random partitioning and temporal partitioning cohorts.

Value of handcrafted and deep radiomic features towards training robust machine learning classifiers for prediction of prostate cancer disease aggressiveness.

There is a growing piece of evidence that artificial intelligence may be helpful in the entire prostate cancer disease continuum. However, building machine learning algorithms robust to inter- and intra-radiologist segmentation variability is still a challenge. With this goal in mind, several model training approaches were compared: removing unstable features according to the intraclass correlation coefficient (ICC); training independently with features extracted from each radiologist's mask; training with the feature average between both radiologists; extracting radiomic features from the intersection or union of masks; and creating a heterogeneous dataset by randomly selecting one of the radiologists' masks for each patient. The classifier trained with this last resampled dataset presented with the lowest generalization error, suggesting that training with heterogeneous data leads to the development of the most robust classifiers. On the contrary, removing features with low ICC resulted in the highest generalization error. The selected radiomics dataset, with the randomly chosen radiologists, was concatenated with deep features extracted from neural networks trained to segment the whole prostate. This new hybrid dataset was then used to train a classifier. The results revealed that, even though the hybrid classifier was less overfitted than the one trained with deep features, it still was unable to outperform the radiomics model.

Comparison of MRI Features of Fat Fraction and ADC for Early Treatment Response Assessment in Participants with Multiple Myeloma.

Background An imaging-based predictor of response could provide prognostic information early during treatment course in patients with multiple myeloma (MM). Purpose To investigate if very early changes in bone marrow relative fat fraction (rFF) and apparent diffusion coefficient (ADC) histogram metrics, occurring after one cycle of induction therapy in participants with newly diagnosed MM, could help predict overall best response status. Materials and Methods This prospective study included participants with MM who were enrolled between August 2014 and December 2017. Histogram metrics were extracted from ADC and rFF maps from MRI examinations performed before treatment and after the first treatment cycle. Participants were categorized into the very good partial response (VGPR) or better group and the less than VGPR group per the International Myeloma Working Group response criteria. ADC and rFF map metrics for predicting treatment response were compared using the Wilcoxon rank test, and the false discovery rate (FDR) was used to correct for multiple comparisons. Results A total of 23 participants (mean age, 65 years ± 11 [SD]; 13 men) were evaluated. There was no evidence of a difference in ADC metrics between the two responder groups after correcting for multiple comparisons. The rFF histogram changes between pretreatment MRI and MRI after the first treatment cycle (ΔrFF) that provided significant differences between the VGPR or better and less than VGPR groups were as follows: ΔrFF_10th Percentile (median, 0.5 [95% CI: 0, 1] vs -2.5 [95% CI: -5.1, 0.1], respectively), ΔrFF_90th Percentile (median, 2 [95% CI: 1, 6.8] vs -0.5 [95% CI: -1, 0]), ΔrFF_Mean (median, 3.4 [95% CI: 0.3, 7.6] vs -1.1 [95% CI: -1.8, -0.7]), and ΔrFF_Root Mean Squared (median, 3.2 [95% CI: 0.3, 6.1] vs -0.7 [95% CI: -1.3, -0.4]) (FDR-adjusted P = .03 for all), and the latter two also presented mean group increases in the VGPR or better group that were above the upper 95% CI limit for repeatability. Conclusion Very early changes in bone marrow relative fat fraction histogram metrics, calculated from MRI examination at baseline and after only one cycle of induction therapy, may help to predict very good partial response or better in participants with newly diagnosed multiple myeloma. © RSNA, 2022 Online supplemental material is available for this article.

Gamification in Radiology Training Module Developed During the Society for Imaging Informatics in Medicine Annual Meeting Hackathon.

The purpose of this manuscript is to report our experience in the 2021 SIIM Virtual Hackathon, where we developed a proof-of-concept of a radiology training module with elements of gamification. In the 50 h allotted in the hackathon, we proposed an idea, connected with colleagues from five different countries, and completed an operational proof-of-concept, which was demonstrated live at the hackathon showcase, competing with eight other teams. Our prototype involved participants annotating publicly available chest radiographs of patients with tuberculosis. We showed how we could give experience points to trainees based on annotation precision compared to ground truth radiologists' annotation, ranked in a live leaderboard. We believe that gamification elements could provide an engaging solution for radiology education. Our project was awarded first place out of eight participating hackathon teams.

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics.

Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.

Improving performance and generalizability in radiogenomics: a pilot study for prediction of IDH1/2 mutation status in gliomas with multicentric data.

Purpose: Radiogenomics offers a potential virtual and noninvasive biopsy. However, radiogenomics models often suffer from generalizability issues, which cause a performance degradation on unseen data. In MRI, differences in the sequence parameters, manufacturers, and scanners make this generalizability issue worse. Such image acquisition information may be used to define different environments and select robust and invariant radiomic features associated with the clinical outcome that should be included in radiomics/radiogenomics models. Approach: We assessed 77 low-grade gliomas and glioblastomas multiform patients publicly available in TCGA and TCIA. Radiomics features were extracted from multiparametric MRI images (T1-weighted, contrast-enhanced T1-weighted, T2-weighted, and fluid-attenuated inversion recovery) and different regions-of-interest (enhancing tumor, nonenhancing tumor/necrosis, and edema). A method developed to find variables that are part of causal structures was used for feature selection and compared with an embedded feature selection approach commonly used in radiomics/radiogenomics studies, across two different scenarios: (1) leaving data from a center as an independent held-out test set and tuning the model with the data from the remaining centers and (2) use stratified partitioning to obtain the training and the held-out test sets. Results: In scenario (1), the performance of the proposed methodology and the traditional embedded method was AUC: 0.75 [0.25; 1.00] versus 0.83 [0.50; 1.00], Sens.: 0.67 [0.20; 0.93] versus 0.67 [0.20; 0.93], Spec.: 0.75 [0.30; 0.95] versus 0.75 [0.30; 0.95], and MCC: 0.42 [0.19; 0.68] versus 0.42 [0.19; 0.68] for center 1 as the held-out test set. The performance of both methods for center 2 as the held-out test set was AUC: 0.64 [0.36; 0.91] versus 0.55 [0.27; 0.82], Sens.: 0.00 [0.00; 0.73] versus 0.00 [0.00; 0.73], Spec.: 0.82 [0.52; 0.94] versus 0.91 [0.62; 0.98], and MCC: - 0.13 [ - 0.38 ; - 0.04 ] versus - 0.09 [ - 0.38 ; - 0.02 ] , whereas for center 3 was AUC: 0.80 [0.62; 0.95] versus 0.89 [0.56; 0.96], Sens.: 0.86 [0.48; 0.97] versus 0.86 [0.48; 0.97], Spec.: 0.72 [0.54; 0.85] versus 0.79 [0.61; 0.90], and MCC: 0.47 [0.41; 0.53] versus 0.55 [0.48; 0.60]. For center 4, the performance of both methods was AUC: 0.77 [0.51; 1.00] versus 0.75 [0.47; 0.97], Sens.: 0.53 [0.30; 0.75] versus 0.00 [0.00; 0.15], Spec.: 0.71 [0.35; 0.91] versus 0.86 [0.48; 0.97], and MCC: 0.23 [0.16; 0.31] versus. - 0.32 [ - 0.46 ; - 0.20 ] . In scenario (2), the performance of these methods was AUC: 0.89 [0.71; 1.00] versus 0.79 [0.58; 0.94], Sens.: 0.86 [0.80; 0.92] versus 0.43 [0.15; 0.74], Spec.: 0.87 [0.62; 0.96] versus 0.87 [0.62; 0.96], and MCC: 0.70 [0.60; 0.77] versus 0.33 [0.24; 0.42]. Conclusions: This proof-of-concept study demonstrated good performance by the proposed feature selection method in the majority of the studied scenarios, as it promotes robustness of features included in the models and the models' generalizability by making used imaging data of different scanners or with sequence parameters.

A multicenter study on radiomic features from T2 -weighted images of a customized MR pelvic phantom setting the basis for robust radiomic models in clinics.

PURPOSE: To investigate the repeatability and reproducibility of radiomic features extracted from MR images and provide a workflow to identify robust features. METHODS: T2 -weighted images of a pelvic phantom were acquired on three scanners of two manufacturers and two magnetic field strengths. The repeatability and reproducibility of features were assessed by the intraclass correlation coefficient and the concordance correlation coefficient, respectively, and by the within-subject coefficient of variation, considering repeated acquisitions with and without phantom repositioning, and with different scanner and acquisition parameters. The features showing intraclass correlation coefficient or concordance correlation coefficient >0.9 were selected, and their dependence on shape information (Spearman's ρ > 0.8) analyzed. They were classified for their ability to distinguish textures, after shuffling voxel intensities of images. RESULTS: From 944 two-dimensional features, 79.9% to 96.4% showed excellent repeatability in fixed position across all scanners. A much lower range (11.2% to 85.4%) was obtained after phantom repositioning. Three-dimensional extraction did not improve repeatability performance. Excellent reproducibility between scanners was observed in 4.6% to 15.6% of the features, at fixed imaging parameters. In addition, 82.4% to 94.9% of the features showed excellent agreement when extracted from images acquired with echo times 5 ms apart, but decreased with increasing echo-time intervals, and 90.7% of the features exhibited excellent reproducibility for changes in pulse repetition time. Of nonshape features, 2.0% was identified as providing only shape information. CONCLUSION: We showed that radiomic features are affected by MRI protocols and propose a general workflow to identify repeatable, reproducible, and informative radiomic features to ensure robustness of clinical studies.

Diffusion tensor-based fiber tracking of the male urethral sphincter complex in patients undergoing radical prostatectomy: a feasibility study.

OBJECTIVES: To study the diffusion tensor-based fiber tracking feasibility to access the male urethral sphincter complex of patients with prostate cancer undergoing Retzius-sparing robot-assisted laparoscopic radical prostatectomy (RS-RARP). METHODS: Twenty-eight patients (median age of 64.5 years old) underwent 3 T multiparametric-MRI of the prostate, including an additional echo-planar diffusion tensor imaging (DTI) sequence, using 15 diffusion-encoding directions and a b value = 600 s/mm2. Acquisition parameters, together with patient motion and eddy currents corrections, were evaluated. The proximal and distal sphincters, and membranous urethra were reconstructed using the deterministic fiber assignment by continuous tracking (FACT) algorithm, optimizing fiber tracking parameters. Tract length and density, fractional anisotropy (FA), axial diffusivity (AD), mean diffusivity (MD), and radial diffusivity (RD) were computed. Regional differences between structures were accessed by ANOVA, or nonparametric Kruskal-Wallis test, and post-hoc tests were employed, respectively, TukeyHSD or Dunn's. RESULTS: The structures of the male urethral sphincter complex were clearly depicted by fiber tractography using optimized acquisition and fiber tracking parameters. The use of eddy currents and subject motion corrections did not yield statistically significant differences on the reported DTI metrics. Regional differences were found between all structures studied among patients, suggesting a quantitative differentiation on the structures based on DTI metrics. CONCLUSIONS: The current study demonstrates the technical feasibility of the proposed methodology, to study in a preoperative setting the male urethral sphincter complex of prostate cancer patients candidates for surgical treatment. These findings may play a role on a more accurate prediction of the RS-RARP post-surgical urinary continence recovery rate.

Diffusion-weighted imaging and texture analysis: current role for diffuse liver disease.

Multiparametric MRI represents the primary imaging modality to assess diffuse liver disease, both in a qualitative and in a quantitative manner. Diffusion-weighted imaging (DWI) is among the imaging techniques that can be used to assess fibrosis due to its unique capability to assess microstructural changes at the tissue level. DWI is based on water mobility patterns and has the potential to become a non-invasive and non-destructive virtual biopsy to assess diffuse liver disease, overcoming sampling bias errors due to its three-dimensional imaging capabilities. Parallel to DWI, another quantitative method called texture analysis may be used to assess early and advanced diffused liver disease through quantifying spatial relationships in a global and local level, applying to any type of digital imaging technique like MRI or CT. Initial results using texture analysis hold great promise. In the current paper, we will review the role of DWI and texture analysis using MR images in assessing diffuse liver disease.

CT-Based Radiomics Analysis to Predict Malignancy in Patients with Intraductal Papillary Mucinous Neoplasm (IPMN) of the Pancreas.

To assess the performance of CT-based radiomics analysis in differentiating benign from malignant intraductal papillary mucinous neoplasms of the pancreas (IPMN), preoperative scans of 408 resected patients with IPMN were retrospectively analyzed. IPMNs were classified as benign (low-grade dysplasia, n = 181), or malignant (high grade, n = 128, and invasive, n = 99). Clinicobiological data were reported. Patients were divided into a training cohort (TC) of 296 patients and an external validation cohort (EVC) of 112 patients. After semi-automatic tumor segmentation, PyRadiomics was used to extract radiomics features. A multivariate model was developed using a logistic regression approach. In the training cohort, 85/107 radiomics features were significantly different between patients with benign and malignant IPMNs. Unsupervised clustering analysis revealed four distinct clusters of patients with similar radiomics features patterns with malignancy as the most significant association. The multivariate model differentiated benign from malignant tumors in TC with an area under the ROC curve (AUC) of 0.84, sensitivity (Se) of 0.82, specificity (Spe) of 0.74, and in EVC with an AUC of 0.71, Se of 0.69, Spe of 0.57. This large study confirms the high diagnostic performance of preoperative CT-based radiomics analysis to differentiate between benign from malignant IPMNs.

Quantification of tumor burden in multiple myeloma by atlas-based semi-automatic segmentation of WB-DWI.

BACKGROUND: Whole-body diffusion weighted imaging (WB-DWI) has proven value to detect multiple myeloma (MM) lesions. However, the large volume of imaging data and the presence of numerous lesions makes the reading process challenging. The aim of the current study was to develop a semi-automatic lesion segmentation algorithm for WB-DWI images in MM patients and to evaluate this smart-algorithm (SA) performance by comparing it to the manual segmentations performed by radiologists. METHODS: An atlas-based segmentation was developed to remove the high-signal intensity normal tissues on WB-DWI and to restrict the lesion area to the skeleton. Then, an outlier threshold-based segmentation was applied to WB-DWI images, and the segmented area's signal intensity was compared to the average signal intensity of a low-fat muscle on T1-weighted images. This method was validated in 22 whole-body DWI images of patients diagnosed with MM. Dice similarity coefficient (DSC), sensitivity and positive predictive value (PPV) were computed to evaluate the SA performance against the gold standard (GS) and to compare with the radiologists. A non-parametric Wilcoxon test was also performed. Apparent diffusion coefficient (ADC) histogram metrics and lesion volume were extracted for the GS segmentation and for the correctly identified lesions by SA and their correlation was assessed. RESULTS: The mean inter-radiologists DSC was 0.323 ± 0.268. The SA vs GS achieved a DSC of 0.274 ± 0.227, sensitivity of 0.764 ± 0.276 and PPV 0.217 ± 0.207. Its distribution was not significantly different from the mean DSC of inter-radiologist segmentation (p = 0.108, Wilcoxon test). ADC and lesion volume intraclass correlation coefficient (ICC) of the GS and of the correctly identified lesions by the SA was 0.996 for the median and 0.894 for the lesion volume (p < 0.001). The duration of the lesion volume segmentation by the SA was, on average, 10.22 ± 0.86 min, per patient. CONCLUSIONS: The SA provides equally reproducible segmentation results when compared to the manual segmentation of radiologists. Thus, the proposed method offers robust and efficient segmentation of MM lesions on WB-DWI. This method may aid accurate assessment of tumor burden and therefore provide insights to treatment response assessment.

Susceptibility Perturbation MRI Maps Tumor Infiltration into Mesorectal Lymph Nodes.

Noninvasive characterization of lymph node involvement in cancer is an enduring onerous challenge. In rectal cancer, pathologic lymph node status constitutes the most important determinant of local recurrence and overall survival, and patients with involved lymph nodes may benefit from preoperative chemo and/or radiotherapy. However, knowledge of lymph node status before surgery is currently hampered by limited imaging accuracy. Here, we introduce Susceptibility-Perturbation MRI (SPI) as a novel source of contrast to map malignant infiltration into mesorectal lymph nodes. SPI involves multigradient echo (MGE) signal decays presenting a nonmonoexponential nature, which we show is sensitive to the underlying microstructure via susceptibility perturbations. Using numerical simulations, we predicted that the large cell morphology and the high cellularity of tumor within affected mesorectal lymph nodes would induce signature SPI decays. We validated this prediction in mesorectal lymph nodes excised from total mesorectal excision specimens of patients with rectal cancer using ultrahigh field (16.4 T) MRI. SPI signals distinguished benign from malignant nodal tissue, both qualitatively and quantitatively, and our histologic analyses confirmed cellularity and cell size were the likely underlying sources for the differences observed. SPI was then adapted to a clinical 1.5 T scanner, added to patients' staging protocol, and compared with conventional assessment by two expert radiologists. Nonmonoexponential decays, similar to those observed in the ex vivo study, were demonstrated, and SPI classified lymph nodes more accurately than standard high-resolution T2-weighted imaging assessment. These findings suggest this simple, yet highly informative, method can improve rectal cancer patient selection for neoadjuvant therapy. SIGNIFICANCE: These findings introduce an MRI methodology tailored to detect magnetic susceptibility perturbations induced by subtle alterations in tissue microstructure.

Increased cytoplasm viscosity hampers aggregate polar segregation in Escherichia coli.

In Escherichia coli, under optimal conditions, protein aggregates associated with cellular aging are excluded from midcell by the nucleoid. We study the functionality of this process under sub-optimal temperatures from population and time lapse images of individual cells and aggregates and nucleoids within. We show that, as temperature decreases, aggregates become homogeneously distributed and uncorrelated with nucleoid size and location. We present evidence that this is due to increased cytoplasm viscosity, which weakens the anisotropy in aggregate displacements at the nucleoid borders that is responsible for their preference for polar localisation. Next, we show that in plasmolysed cells, which have increased cytoplasm viscosity, aggregates are also not preferentially located at the poles. Finally, we show that the inability of cells with increased viscosity to exclude aggregates from midcell results in enhanced aggregate concentration in between the nucleoids in cells close to dividing. This weakens the asymmetries in aggregate numbers between sister cells of subsequent generations required for rejuvenating cell lineages. We conclude that the process of exclusion of protein aggregates from midcell is not immune to stress conditions affecting the cytoplasm viscosity. The findings contribute to our understanding of E. coli's internal organisation and functioning, and its fragility to stressful conditions.