Training radiology residents to evaluate deep myometrial invasion in endometrial cancer patients on MRI: A learning curve study.

PURPOSE: To evaluate the impact of a four-month training program on radiology residents' diagnostic accuracy in assessing deep myometrial invasion (DMI) in endometrial cancer (EC) using MRI. METHOD: Three radiology residents with limited EC MRI experience participated in the training program, which included conventional didactic sessions, case-centric workshops, and interactive classes. Utilizing a training dataset of 120 EC MRI scans, trainees independently assessed subsets of cases over five reading sessions. Each subset consisted of 30 scans, the first and the last with the same cases, for a total of 150 reads. Diagnostic accuracy metrics, assessment time (rounded to the nearest minute), and confidence levels (using a 5-point Likert scale) were recorded. The learning curve was obtained plotting the diagnostic accuracy of the three trainees and the average over the subsets. Anatomopathological results served as the reference standard for DMI presence. RESULTS: The three trainees exhibited heterogeneous starting point, with a learning curve and a trend to more homogeneous performance with training. The diagnostic accuracy of the average trainee raised from 64 % (56 %-76 %) to 88 % (80 %-94 %) across the five subsets (p < 0.001). Reductions in assessment time (5.92 to 4.63 min, p < 0.018) and enhanced confidence levels (3.58 to 3.97, p = 0.12) were observed. Improvements in sensitivity, specificity, positive predictive value, and negative predictive value were noted, particularly for specificity which raised from 56 % (41 %-68 %) in the first to 86 % (74 %-94 %) in the fifth subset (p = 0.16). Although not reaching statistical significance, these advancements aligned the trainees with literature performance benchmarks. CONCLUSIONS: The structured training program significantly enhanced radiology residents' diagnostic accuracy in assessing DMI for EC on MRI, emphasizing the effectiveness of active case-based training in refining oncologic imaging skills within radiology residency curricula.

Tumor Burden of Iodine-Avid Bone Metastatic Thyroid Cancer Identified via 18F-Sodium Fluoride PET/CT Imaging.

BACKGROUND: Patients with differentiated thyroid cancer (DTC) are referred to radioactive 131I (RAI) therapy and post-therapy 131I whole-body scintigraphy (WBS) to identify local and/or remote metastases. Positron emission tomography (PET)/computed tomography (CT) imaging with 18F-fluoro-D-glucose (FDG) or 18F-sodium fluoride (NaF) may also be used with these patients for the evaluation of bone metastases. We compared the role of 18F-NaF PET/CT and 18F-FDG-PET/CT in patients with DTC and documented bone metastases at post-therapy WBS. METHODS: Ten consecutive DTC patients with iodine avid bone metastasis at post-therapy WBS referred to 18F-NaF PET/CT and 18F-FDG PET/CT were studied. The findings of the three imaging procedures were compared for abnormal detection rates and concordance. RESULTS: At post-therapy 131I WBS, all patients had skeletal involvement with a total of 21 bone iodine avid lesions. At 18F-FDG PET/TC, 19 bone lesions demonstrated increased tracer uptake and CT pathological alterations, while 2 lesions did not show any pathological finding. At 18F-NaF PET/CT, the 19 bone lesions detected at 18F-FDG PET/TC also demonstrated abnormal tracer uptake, and the other 2 bone iodine avid foci did not show any pathological finding. CONCLUSIONS: In patients with DTC, 18F-NaF PET/CT did not obtain more information on the metastatic skeletal involvement than post-therapy 131I WBS and 18F-FDG PET/CT.

Thyroid Cancer Radiomics: Navigating Challenges in a Developing Landscape.

In a review from 2021 by Cao et al [...].

Prediction of placenta accreta spectrum in patients with placenta previa using a clinical, US and MRI combined model: A retrospective study with external validation.

PURPOSE: To build and validate a predictive model of placental accreta spectrum (PAS) in patients with placenta previa (PP) combining clinical risk factors (CRF) with US and MRI signs. METHOD: Our retrospective study included patients with PP from two institutions. All patients underwent US and MRI examinations for suspicion of PAS. CRF consisting of maternal age, cesarean section number, smoking and hypertension were retrieved. US and MRI signs suggestive of PAS were evaluated. Logistic regression analysis was performed to identify CRF and/or US and MRI signs associated with PAS considering histology as the reference standard. A nomogram was created using significant CRF and imaging signs at multivariate analysis, and its diagnostic accuracy was measured using the area under the binomial ROC curve (AUC), and the cut-off point was determined by Youden's J statistic. RESULTS: A total of 171 patients were enrolled from two institutions. Independent predictors of PAS included in the nomogram were: 1) smoking and number of previous CS among CRF; 2) loss of the retroplacental clear space at US; 3) intraplacental dark bands, focal interruption of the myometrial border and placental bulging at MRI. A PAS-prediction nomogram was built including these parameters and an optimal cut-off of 14.5 points was identified, showing the highest sensitivity (91%) and specificity (88%) with an AUC value of 0.95 (AUC of 0.80 in the external validation cohort). CONCLUSION: A nomogram-based model combining CRF with US and MRI signs might help to predict PAS in PP patients, with MRI contributing more than US as imaging evaluation.

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.

Prediction of 2-[18F]FDG PET-CT SUVmax for Adrenal Mass Characterization: A CT Radiomics Feasibility Study.

BACKGROUND: Indeterminate adrenal masses (AM) pose a diagnostic challenge, and 2-[18F]FDG PET-CT serves as a problem-solving tool. Aim of this study was to investigate whether CT radiomics features could be used to predict the 2-[18F]FDG SUVmax of AM. METHODS: Patients with AM on 2-[18F]FDG PET-CT scan were grouped based on iodine contrast injection as CT contrast-enhanced (CE) or CT unenhanced (NCE). Two-dimensional segmentations of AM were manually obtained by multiple operators on CT images. Image resampling and discretization (bin number = 16) were performed. 919 features were calculated using PyRadiomics. After scaling, unstable, redundant, and low variance features were discarded. Using linear regression and the Uniform Manifold Approximation and Projection technique, a CT radiomics synthetic value (RadSV) was obtained. The correlation between CT RadSV and 2-[18F]FDG SUVmax was assessed with Pearson test. RESULTS: A total of 725 patients underwent PET-CT from April 2020 to April 2021. In 150 (21%) patients, a total of 179 AM (29 bilateral) were detected. Group CE consisted of 84 patients with 108 AM (size = 18.1 ± 4.9 mm) and Group NCE of 66 patients with 71 AM (size = 18.5 ± 3.8 mm). In both groups, 39 features were selected. No statisticallyf significant correlation between CT RadSV and 2-[18F]FDG SUVmax was found (Group CE, r = 0.18 and p = 0.058; Group NCE, r = 0.13 and p = 0.27). CONCLUSIONS: It might not be feasible to predict 2-[18F]FDG SUVmax of AM using CT RadSV. Its role as a problem-solving tool for indeterminate AM remains fundamental.

Autoimmune liver diseases and SARS-CoV-2.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), causing coronavirus disease 2019 (COVID-19), can trigger autoimmunity in genetically predisposed individuals through hyperstimulation of immune response and molecular mimicry. Here we summarise the current knowledge about auto-immune liver diseases (AILDs) and SARS-CoV-2, focusing on: (1) The risk of SARS-CoV-2 infection and the course of COVID-19 in patients affected by AILDs; (2) the role of SARS-CoV-2 in inducing liver damage and triggering AILDs; and (3) the ability of vaccines against SARS-CoV-2 to induce autoimmune responses in the liver. Data derived from the literature suggest that patients with AILDs do not carry an increased risk of SARS-Cov-2 infection but may develop a more severe course of COVID-19 if on treatment with steroids or thiopurine. Although SARS-CoV-2 infection can lead to the development of several autoimmune diseases, few reports correlate it to the appearance of de novo manifestation of immune-mediated liver diseases such as autoimmune hepatitis (AIH), primary biliary cholangitis (PBC) or AIH/PBC overlap syndrome. Different case series of an AIH-like syndrome with a good prognosis after SARS-CoV-2 vaccination have been described. Although the causal link between SARS-CoV-2 vaccines and AIH cannot be definitively established, these reports suggest that this association could be more than coincidental.

MRI Liver Imaging Integrated with Texture Analysis in Native Liver Survivor Patients with Biliary Atresia after Kasai Portoenterostomy: Correlation with Medical Outcome after Surgical Treatment.

Kasai portoenterostomy (KP) plays a crucial role in the treatment of biliary atresia (BA). The aim is to correlate MRI quantitative findings of native liver survivor BA patients after KP with a medical outcome. Thirty patients were classified as having ideal medical outcomes (Group 1; n = 11) if laboratory parameter values were in the normal range and there was no evidence of chronic liver disease complications; otherwise, they were classified as having nonideal medical outcomes (Group 2; n = 19). Liver and spleen volumes, portal vein diameter, liver mean, and maximum and minimum ADC values were measured; similarly, ADC and T2-weighted textural parameters were obtained using ROI analysis. The liver volume was significantly (p = 0.007) lower in Group 2 than in Group 1 (954.88 ± 218.31 cm3 vs. 1140.94 ± 134.62 cm3); conversely, the spleen volume was significantly (p < 0.001) higher (555.49 ± 263.92 cm3 vs. 231.83 ± 70.97 cm3). No differences were found in the portal vein diameter, liver ADC values, or ADC and T2-weighted textural parameters. In conclusion, significant quantitative morpho-volumetric liver and spleen abnormalities occurred in BA patients with nonideal medical outcomes after KP, but no significant microstructural liver abnormalities detectable by ADC values and ADC and T2-weighted textural parameters were found between the groups.

MRI Radiomics and Machine Learning for the Prediction of Oncotype Dx Recurrence Score in Invasive Breast Cancer.

AIM: To non-invasively predict Oncotype DX recurrence scores (ODXRS) in patients with ER+ HER2- invasive breast cancer (IBC) using dynamic contrast-enhanced (DCE) MRI-derived radiomics features extracted from primary tumor lesions and a ML algorithm. MATERIALS AND METHODS: Pre-operative DCE-MRI of patients with IBC, no history of neoadjuvant therapy prior to MRI, and for which the ODXRS was available, were retrospectively selected from a public dataset. ODXRS was obtained on histological tumor samples and considered as positive if greater than 16 and 26 in patients aged under and over 50 years, respectively. Tumor lesions were manually annotated by three independent operators on DCE-MRI images through 3D ROIs positioning. Radiomic features were therefore extracted and selected using multistep feature selection process. A logistic regression ML classifier was then employed for the prediction of ODXRS. RESULTS: 248 patients were included, of which 87 with positive ODXRS. 166 (66%) patients were grouped in the training set, while 82 (33%) in the test set. A total of 1288 features was extracted. Of these, 1244 were excluded as 771, 82 and 391 were excluded as not stable (n = 771), not variant (n = 82), and highly intercorrelated (n = 391), respectively. After the use of recursive feature elimination with logistic regression estimator and polynomial transformation, 92 features were finally selected. In the training set, the logistic regression classifier obtained an overall mean accuracy of 60%. In the test set, the accuracy of the ML classifier was 63%, with a sensitivity of 80%, specificity of 43%, and AUC of 66%. CONCLUSIONS: Radiomics and ML applied to pre-operative DCE-MRI in patients with IBC showed promises for the non-invasive prediction of ODXRS, aiding in selecting patients who will benefit from NAC.

Role of advanced imaging techniques in the evaluation of oncological therapies in patients with colorectal liver metastases.

In patients with colorectal liver metastasis (CRLMs) unsuitable for surgery, oncological treatments, such as chemotherapy and targeted agents, can be performed. Cross-sectional imaging [computed tomography (CT), magnetic resonance imaging (MRI), 18-fluorodexoyglucose positron emission tomography with CT/MRI] evaluates the response of CRLMs to therapy, using post-treatment lesion shrinkage as a qualitative imaging parameter. This point is critical because the risk of toxicity induced by oncological treatments is not always balanced by an effective response to them. Consequently, there is a pressing need to define biomarkers that can predict treatment responses and estimate the likelihood of drug resistance in individual patients. Advanced quantitative imaging (diffusion-weighted imaging, perfusion imaging, molecular imaging) allows the in vivo evaluation of specific biological tissue features described as quantitative parameters. Furthermore, radiomics can represent large amounts of numerical and statistical information buried inside cross-sectional images as quantitative parameters. As a result, parametric analysis (PA) translates the numerical data contained in the voxels of each image into quantitative parameters representative of peculiar neoplastic features such as perfusion, structural heterogeneity, cellularity, oxygenation, and glucose consumption. PA could be a potentially useful imaging marker for predicting CRLMs treatment response. This review describes the role of PA applied to cross-sectional imaging in predicting the response to oncological therapies in patients with CRLMs.

The True Value of Quantitative Imaging for Adrenal Mass Characterization: Reality or Possibility?

The widespread use of cross-sectional imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), in the evaluation of abdominal disorders has significantly increased the number of incidentally detected adrenal abnormalities, particularly adrenal masses [...].

David Against Goliath: Direct Comparison of Handheld Bowel Sonography and Magnetic Resonance Enterography for Diagnosis of Crohn's Disease.

BACKGROUND: Diagnosis of Crohn's disease (CD) requires ileo-colonoscopy (IC) and cross-sectional evaluation. Recently, "echoscopy" has been used effectively in several settings, although data about its use for CD diagnosis are still limited. Our aim was to evaluate the diagnostic accuracy of handheld bowel sonography (HHBS) in comparison with magnetic resonance enterography (MRE) for CD diagnosis. METHODS: From September 2019 to June 2021, we prospectively recruited consecutive subjects attending our third level IBD Unit for suspected CD. Patients underwent IC, HHBS, and MRE in random order with operators blinded about the result of the other procedures. Bivariate correlation between MRE and HHBS was calculated by Spearman coefficient (r). To test the consistency between MRE and HHBS for CD location and complications, the Cohen's k measure was applied. RESULTS: Crohn's disease diagnosis was made in 48 out of 85 subjects (56%). Sensitivity, specificity, positive predictive values, and negative predictive values for CD diagnosis were 87.50%, 91.89%, 93.33%, and 85% for HHBS; and 91.67%, 94.59%, 95.65%, and 89.74% for MRE, without significant differences in terms of diagnostic accuracy (89.41% for HHBS vs 92.94% for MRE, P = NS). Magnetic resonance enterography was superior to HHBS in defining CD extension (r = 0.67; P < .01) with a better diagnostic performance than HHBS for detecting location (k = 0.81; P < .01), strictures (k = 0.75; P < .01), abscesses (k = 0.68; P < .01), and fistulas (k = 0.65; P < .01). CONCLUSION: Handheld bowel sonography and MRE are 2 accurate and noninvasive procedures for diagnosis of CD, although MRE is more sensitive in defining extension, location, and complications. Handheld bowel sonography could be used as effective ambulatory (or out-of-office) screening tool for identifying patients to refer for MRE examination due to high probability of CD diagnosis.

Artificial Intelligence and Radiomics for Endometrial Cancer MRI: Exploring the Whats, Whys and Hows.

Endometrial cancer (EC) is intricately linked to obesity and diabetes, which are widespread risk factors. Medical imaging, especially magnetic resonance imaging (MRI), plays a major role in EC assessment, particularly for disease staging. However, the diagnostic performance of MRI exhibits variability in the detection of clinically relevant prognostic factors (e.g., deep myometrial invasion and metastatic lymph nodes assessment). To address these challenges and enhance the value of MRI, radiomics and artificial intelligence (AI) algorithms emerge as promising tools with a potential to impact EC risk assessment, treatment planning, and prognosis prediction. These advanced post-processing techniques allow us to quantitatively analyse medical images, providing novel insights into cancer characteristics beyond conventional qualitative image evaluation. However, despite the growing interest and research efforts, the integration of radiomics and AI to EC management is still far from clinical practice and represents a possible perspective rather than an actual reality. This review focuses on the state of radiomics and AI in EC MRI, emphasizing risk stratification and prognostic factor prediction, aiming to illuminate potential advancements and address existing challenges in the field.

Oncologic Imaging and Radiomics: A Walkthrough Review of Methodological Challenges.

Imaging plays a crucial role in the management of oncologic patients, from the initial diagnosis to staging and treatment response monitoring. Recently, it has been suggested that its importance could be further increased by accessing a new layer of previously hidden quantitative data at the pixel level. Using a multi-step process, radiomics extracts potential biomarkers from medical images that could power decision support tools. Despite the growing interest and rising number of research articles being published, radiomics is still far from fulfilling its promise of guiding oncologic imaging toward personalized medicine. This is, at least partly, due to the heterogeneous methodological quality in radiomic research, caused by the complexity of the analysis pipelines. In this review, we aim to disentangle this complexity with a stepwise approach. Specifically, we focus on challenges to face during image preprocessing and segmentation, how to handle imbalanced classes and avoid information leaks, as well as strategies for the proper validation of findings.

Placenta Accreta Spectrum Disorders and Radiomics: Systematic review and quality appraisal.

PURPOSE: Ultrasound and magnetic resonance imaging are the imaging modalities of choice for placenta accrete spectrum (PAS) disorders assessment. Radiomics could further increase the value of medical images and allow to overcome the limitations linked to their visual assessment. Aim of this systematic review was to identify and appraise the methodological quality of radiomics studies focused PAS disorders applications. METHOD: Three online databases (PubMed, Scopus and Web of Science) were searched to identify original research articles on human subjects published in English. For the qualitative synthesis of results, data regarding study design (e.g., retrospective or prospective), purpose, patient population (e.g., sample size), imaging modalities and radiomics pipelines (e.g., segmentation and feature extraction strategy) were collected. The appraisal of methodological quality was performed using the Radiomics Quality Score (RQS). RESULTS: 10 articles were finally included and analyzed. All were retrospective and MRI-powered. The majority included more than 100 patients (6/10). Four were prognostic (focused on either the prediction of bleeding volume or the prediction of needed management) while six diagnostic (PAS vs not PAS classification) studies. The median RQS was 8, with maximum and minimum respectively equal to 17/36 and - 6/36. Major methodological concerns were the lack of feature stability to multiple segmentation testing and poor data openness. CONCLUSIONS: Radiomics studies focused on PAS disorders showed a heterogeneous methodological quality, overall lower than desirable. Furthermore, many relevant research questions remain unexplored. More robust investigations are needed to foster advancements in the field and possibly clinical translation.

COVID-19 vaccine-induced lymphadenopathies: incidence, course and imaging features from an ultrasound prospective study.

AIMS: lymphadenopathy can occur after COVID-19 vaccination and when encountered at ultrasound examinations performed for other reasons might pose a diagnostic challenge. Purpose of the study was to evaluate the incidence, course and ultrasound imaging features of vaccine-induced lymphadenopathy. METHODS: 89 healthy volunteers (median age 30, 76 females) were prospectively enrolled. Vaccine-related clinical side effects (e.g., fever, fatigue, palpable or painful lymphadenopathy) were recorded. Participants underwent bilateral axillary, supraclavicular and cervical lymph node stations ultrasound 1-4 weeks after the second dose and then again after 4-12 weeks in those who showed lymphadenopathy at the first ultrasound. B-mode, color-Doppler assessment, and shear-wave elastography (SWE) evaluation were performed. The correlation between lymphadenopathy and vaccine-related side effects was assessed using the Fisher's exact test. RESULTS: Post-vaccine lymphadenopathy were found in 69/89 (78%) participants (37 single and 32 multiple lymphadenopathy). Among them, 60 presented vaccine-related side effects, but no statistically significant difference was observed between post-vaccine side effect and lymphadenopathy. Ultrasound features of vaccine-related lymphadenopathy consisted of absence of fatty hilum, round shape and diffuse or asymmetric cortical thickness (median cortical thickness of 5 mm). Vascular signal was mainly found to be increased, localized in both central and peripheral regions. SWE showed a soft cortical consistence in all cases (median value 11 Kpa). At follow-up, lymph-node morphology was completely restored in most cases (54/69, 78%) and in no case lymphadenopathy had worsened. CONCLUSION: A high incidence of vaccine-induced lymphadenopathy was found in a population of healthy subjects, with nearly complete regression within 4-12 weeks.

MRI radiomics: A machine learning approach for the risk stratification of endometrial cancer patients.

PURPOSE: To investigate radiomics and machine learning (ML) as possible tools to enhance MRI-based risk stratification in patients with endometrial cancer (EC). METHOD: From two institutions, 133 patients (Institution1 = 104 and Institution2 = 29) with EC and pre-operative MRI were retrospectively enrolled and divided in two a low-risk and a high-risk group according to EC stage and grade. T2-weighted (T2w) images were three-dimensionally annotated to obtain volumes of interest of the entire tumor. A PyRadiomics based and previously validated pipeline was used to extract radiomics features and perform feature selection. In particular, feature stability, variance and pairwise correlation were analyzed. Then, the least absolute shrinkage and selection operator technique and recursive feature elimination were used to obtain the final feature set. The performance of a Support Vector Machine (SVM) algorithm was assessed on the dataset from Institution 1 via 2-fold cross-validation. Then, the model was trained on the entire Institution 1 dataset and tested on the external test set from Institution 2. RESULTS: In total, 1197 radiomics features were extracted. After the exclusion of unstable, low variance and intercorrelated features least absolute shrinkage and selection operator and recursive feature elimination identified 4 features that were used to build the predictive ML model. It obtained an accuracy of 0.71 and 0.72 in the train and test sets respectively. CONCLUSIONS: Whole-lesion T2w-derived radiomics showed encouraging results and good generalizability for the identification of low-risk EC patients.

Radiomics in Cross-Sectional Adrenal Imaging: A Systematic Review and Quality Assessment Study.

In this study, we aimed to systematically review the current literature on radiomics applied to cross-sectional adrenal imaging and assess its methodological quality. Scopus, PubMed and Web of Science were searched to identify original research articles investigating radiomics applications on cross-sectional adrenal imaging (search end date February 2021). For qualitative synthesis, details regarding study design, aim, sample size and imaging modality were recorded as well as those regarding the radiomics pipeline (e.g., segmentation and feature extraction strategy). The methodological quality of each study was evaluated using the radiomics quality score (RQS). After duplicate removal and selection criteria application, 25 full-text articles were included and evaluated. All were retrospective studies, mostly based on CT images (17/25, 68%), with manual (19/25, 76%) and two-dimensional segmentation (13/25, 52%) being preferred. Machine learning was paired to radiomics in about half of the studies (12/25, 48%). The median total and percentage RQS scores were 2 (interquartile range, IQR = -5-8) and 6% (IQR = 0-22%), respectively. The highest and lowest scores registered were 12/36 (33%) and -5/36 (0%). The most critical issues were the absence of proper feature selection, the lack of appropriate model validation and poor data openness. The methodological quality of radiomics studies on adrenal cross-sectional imaging is heterogeneous and lower than desirable. Efforts toward building higher quality evidence are essential to facilitate the future translation into clinical practice.