Choosing the right artificial intelligence solutions for your radiology department: key factors to consider.

The rapid evolution of artificial intelligence (AI), particularly in deep learning, has significantly impacted radiology, introducing an array of AI solutions for interpretative tasks. This paper provides radiology departments with a practical guide for selecting and integrating AI solutions, focusing on interpretative tasks that require the active involvement of radiologists. Our approach is not to list available applications or review scientific evidence, as this information is readily available in previous studies; instead, we concentrate on the essential factors radiology departments must consider when choosing AI solutions. These factors include clinical relevance, performance and validation, implementation and integration, clinical usability, costs and return on investment, and regulations, security, and privacy. We illustrate each factor with hypothetical scenarios to provide a clearer understanding and practical relevance. Through our experience and literature review, we provide insights and a practical roadmap for radiologists to navigate the complex landscape of AI in radiology. We aim to assist in making informed decisions that enhance diagnostic precision, improve patient outcomes, and streamline workflows, thus contributing to the advancement of radiological practices and patient care.

Quantitative evaluation of Saliency-Based Explainable artificial intelligence (XAI) methods in Deep Learning-Based mammogram analysis.

BACKGROUND: Explainable Artificial Intelligence (XAI) is prominent in the diagnostics of opaque deep learning (DL) models, especially in medical imaging. Saliency methods are commonly used, yet there's a lack of quantitative evidence regarding their performance. OBJECTIVES: To quantitatively evaluate the performance of widely utilized saliency XAI methods in the task of breast cancer detection on mammograms. METHODS: Three radiologists drew ground-truth boxes on a balanced mammogram dataset of women (n = 1496 cancer-positive and negative scans) from three centers. A modified, pre-trained DL model was employed for breast cancer detection, using MLO and CC images. Saliency XAI methods, including Gradient-weighted Class Activation Mapping (Grad-CAM), Grad-CAM++, and Eigen-CAM, were evaluated. We utilized the Pointing Game to assess these methods, determining if the maximum value of a saliency map aligned with the bounding boxes, representing the ratio of correctly identified lesions among all cancer patients, with a value ranging from 0 to 1. RESULTS: The development sample included 2,244 women (75%), with the remaining 748 women (25%) in the testing set for unbiased XAI evaluation. The model's recall, precision, accuracy, and F1-Score in identifying cancer in the testing set were 69%, 88%, 80%, and 0.77, respectively. The Pointing Game Scores for Grad-CAM, Grad-CAM++, and Eigen-CAM were 0.41, 0.30, and 0.35 in women with cancer and marginally increased to 0.41, 0.31, and 0.36 when considering only true-positive samples. CONCLUSIONS: While saliency-based methods provide some degree of explainability, they frequently fall short in delineating how DL models arrive at decisions in a considerable number of instances.

Anatomically guided self-adapting deep neural network for clinically significant prostate cancer detection on bi-parametric MRI: a multi-center study.

OBJECTIVE: To evaluate the effectiveness of a self-adapting deep network, trained on large-scale bi-parametric MRI data, in detecting clinically significant prostate cancer (csPCa) in external multi-center data from men of diverse demographics; to investigate the advantages of transfer learning. METHODS: We used two samples: (i) Publicly available multi-center and multi-vendor Prostate Imaging: Cancer AI (PI-CAI) training data, consisting of 1500 bi-parametric MRI scans, along with its unseen validation and testing samples; (ii) In-house multi-center testing and transfer learning data, comprising 1036 and 200 bi-parametric MRI scans. We trained a self-adapting 3D nnU-Net model using probabilistic prostate masks on the PI-CAI data and evaluated its performance on the hidden validation and testing samples and the in-house data with and without transfer learning. We used the area under the receiver operating characteristic (AUROC) curve to evaluate patient-level performance in detecting csPCa. RESULTS: The PI-CAI training data had 425 scans with csPCa, while the in-house testing and fine-tuning data had 288 and 50 scans with csPCa, respectively. The nnU-Net model achieved an AUROC of 0.888 and 0.889 on the hidden validation and testing data. The model performed with an AUROC of 0.886 on the in-house testing data, with a slight decrease in performance to 0.870 using transfer learning. CONCLUSIONS: The state-of-the-art deep learning method using prostate masks trained on large-scale bi-parametric MRI data provides high performance in detecting csPCa in internal and external testing data with different characteristics, demonstrating the robustness and generalizability of deep learning within and across datasets. CLINICAL RELEVANCE STATEMENT: A self-adapting deep network, utilizing prostate masks and trained on large-scale bi-parametric MRI data, is effective in accurately detecting clinically significant prostate cancer across diverse datasets, highlighting the potential of deep learning methods for improving prostate cancer detection in clinical practice.

Inter-reader agreement of the prostate imaging quality (PI-QUAL) score for basic readers in prostate MRI: A multi-center study.

BACKGROUND: The Prostate Imaging Quality (PI-QUAL) score is the first step toward image quality assessment in multi-parametric prostate MRI (mpMRI). Previous studies have demonstrated moderate to excellent inter-rater agreement among expert readers; however, there is a need for studies to assess the inter-reader agreement of PI-QUAL scoring in basic prostate readers. OBJECTIVES: To assess the inter-reader agreement of the PI-QUAL score amongst basic prostate readers on multi-center prostate mpMRI. METHODS: Five basic prostate readers from different centers assessed the PI-QUAL scores independently using T2-weighted images, diffusion-weighted imaging (DWI) including apparent diffusion coefficient (ADC) maps, and dynamic-contrast-enhanced (DCE) images on mpMRI data obtained from five different centers following Prostate Imaging-Reporting and Data System Version 2.1. The inter-reader agreements amongst radiologists for PI-QUAL were evaluated using weighted Cohen's kappa. Further, the absolute agreements in assessing the diagnostic adequacy of each mpMRI sequence were calculated. RESULTS: A total of 355 men with a median age of 71 years (IQR, 60-78) were enrolled in the study. The pair-wise kappa scores ranged from 0.656 to 0.786 for the PI-QUAL scores, indicating good inter-reader agreements between the readers. The pair-wise absolute agreements ranged from 0.75 to 0.88 for T2W imaging, from 0.74 to 0.83 for the ADC maps, and from 0.77 to 0.86 for DCE images. CONCLUSIONS: Basic prostate radiologists from different institutions provided good inter-reader agreements on multi-center data for the PI-QUAL scores.

Deep learning for assessing image quality in bi-parametric prostate MRI: A feasibility study.

BACKGROUND: Although systems such as Prostate Imaging Quality (PI-QUAL) have been proposed for quality assessment, visual evaluations by human readers remain somewhat inconsistent, particularly among less-experienced readers. OBJECTIVES: To assess the feasibility of deep learning (DL) for the automated assessment of image quality in bi-parametric MRI scans and compare its performance to that of less-experienced readers. METHODS: We used bi-parametric prostate MRI scans from the PI-CAI dataset in this study. A 3-point Likert scale, consisting of poor, moderate, and excellent, was utilized for assessing image quality. Three expert readers established the ground-truth labels for the development (500) and testing sets (100). We trained a 3D DL model on the development set using probabilistic prostate masks and an ordinal loss function. Four less-experienced readers scored the testing set for performance comparison. RESULTS: The kappa scores between the DL model and the expert consensus for T2W images and ADC maps were 0.42 and 0.61, representing moderate and good levels of agreement. The kappa scores between the less-experienced readers and the expert consensus for T2W images and ADC maps ranged from 0.39 to 0.56 (fair to moderate) and from 0.39 to 0.62 (fair to good). CONCLUSIONS: Deep learning (DL) can offer performance comparable to that of less-experienced readers when assessing image quality in bi-parametric prostate MRI, making it a viable option for an automated quality assessment tool. We suggest that DL models trained on more representative datasets, annotated by a larger group of experts, could yield reliable image quality assessment and potentially substitute or assist visual evaluations by human readers.

Automated LVO detection and collateral scoring on CTA using a 3D self-configuring object detection network: a multi-center study.

The use of deep learning (DL) techniques for automated diagnosis of large vessel occlusion (LVO) and collateral scoring on computed tomography angiography (CTA) is gaining attention. In this study, a state-of-the-art self-configuring object detection network called nnDetection was used to detect LVO and assess collateralization on CTA scans using a multi-task 3D object detection approach. The model was trained on single-phase CTA scans of 2425 patients at five centers, and its performance was evaluated on an external test set of 345 patients from another center. Ground-truth labels for the presence of LVO and collateral scores were provided by three radiologists. The nnDetection model achieved a diagnostic accuracy of 98.26% (95% CI 96.25-99.36%) in identifying LVO, correctly classifying 339 out of 345 CTA scans in the external test set. The DL-based collateral scores had a kappa of 0.80, indicating good agreement with the consensus of the radiologists. These results demonstrate that the self-configuring 3D nnDetection model can accurately detect LVO on single-phase CTA scans and provide semi-quantitative collateral scores, offering a comprehensive approach for automated stroke diagnostics in patients with LVO.

The Role of Whole-Body Magnetic Resonance Imaging in Assessing Extrapulmonary Metastases in Osteosarcoma Staging and Restaging: A Pilot Study.

OBJECTIVE: The aim of the study is to investigate the role of whole-body magnetic resonance imaging (MRI) in assessing extrapulmonary metastases in primary osteosarcoma staging. METHODS: We retrospectively reviewed medical data to identify primary osteosarcoma patients with available preoperative whole-body MRI obtained in the staging or restaging. Histopathology was the reference test for assessing the diagnostic performance, if available. Otherwise, oncology board decisions were used as the reference. In addition, the benefits of whole-body MRI to F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET-CT) and bone scintigraphy were investigated. RESULTS: In all, 36 patients with osteosarcoma (24 staging, 12 restaging) with a mean age of 16.36 ± 5.63 years (range, 9-29 years) were included in the study. The median follow-up duration was 26.61 months (interquartile range, 33.3 months). Of 36 patients, 8 had skeletal, 1 had a lymph node, and 1 had a subcutaneous metastasis. Whole-body MRI correctly identified all patients with metastatic disease but incorrectly classified a bone infarct in one patient as a skeletal metastasis, equating a scan-level sensitivity, specificity, accuracy, negative predictive value, and positive predictive value of 100%, 96.3%, 97.3%, 100%, and 90.91%. Whole-body MRI contributed to bone scintigraphy by identifying a skeletal metastasis in one patient and positron emission tomography-computed tomography by ruling out a skeletal metastasis in another. CONCLUSIONS: Whole-body MRI could accurately identify extrapulmonary metastases in primary osteosarcoma patients for staging or restaging. In addition, it might contribute to the standard whole-body imaging methods.

Does deep learning software improve the consistency and performance of radiologists with various levels of experience in assessing bi-parametric prostate MRI?

OBJECTIVE: To investigate whether commercially available deep learning (DL) software improves the Prostate Imaging-Reporting and Data System (PI-RADS) scoring consistency on bi-parametric MRI among radiologists with various levels of experience; to assess whether the DL software improves the performance of the radiologists in identifying clinically significant prostate cancer (csPCa). METHODS: We retrospectively enrolled consecutive men who underwent bi-parametric prostate MRI at a 3 T scanner due to suspicion of PCa. Four radiologists with 2, 3, 5, and > 20 years of experience evaluated the bi-parametric prostate MRI scans with and without the DL software. Whole-mount pathology or MRI/ultrasound fusion-guided biopsy was the reference. The area under the receiver operating curve (AUROC) was calculated for each radiologist with and without the DL software and compared using De Long's test. In addition, the inter-rater agreement was investigated using kappa statistics. RESULTS: In all, 153 men with a mean age of 63.59 ± 7.56 years (range 53-80) were enrolled in the study. In the study sample, 45 men (29.80%) had clinically significant PCa. During the reading with the DL software, the radiologists changed their initial scores in 1/153 (0.65%), 2/153 (1.3%), 0/153 (0%), and 3/153 (1.9%) of the patients, yielding no significant increase in the AUROC (p > 0.05). Fleiss' kappa scores among the radiologists were 0.39 and 0.40 with and without the DL software (p = 0.56). CONCLUSIONS: The commercially available DL software does not increase the consistency of the bi-parametric PI-RADS scoring or csPCa detection performance of radiologists with varying levels of experience.

Cribriform Pattern of The Prostate Adenocarcinoma: Sensitivity of Multiparametric MRI.

BACKGROUND: The aim of this study was to investigate the diagnostic performance of mpMRI for detecting cribriform pattern prostate cancer. MATERIALS AND METHODS: This study retrospectively enrolled 33 patients who were reported cribriform pattern prostate cancer at final pathology. The localization, grade and volumetric properties of the dominant tumors and areas with cribriform pattern at the final pathological specimens were recorded and the diagnostic value of mpMRI was evaluated on the basis of the cribriform morphology detection rate. It was analyzed using Wilcoxon test, the Chi-square test and Fisher's Exact test. The significance level (P-value) was set at .05 in all statistical analyses. RESULTS: A total of 58 prostate cancer foci were (38 cribriform, 20 non-cribriform foci) identified on the final pathology. mpMRI identified 36 of the 38 cribriform morphology harboring tumor foci with a sensitivity of 94.7% (95% confidence interval 82.7-98.5%). In 17 of the 33 patients mpMRI detected single lesion and for these lesions; mpMRI identified cribriform morphology positive areas precisely in 15 patients with significantly low ADCmean and ADCmin values compared to the non-cribriform cancer areas within the primary index lesion (P < .001). For the remaining 16 patients with multiple lesions; all of the tumor foci that harboring cribriform morphology were identified by mpMRI but in none of them any ADCmean and ADCmin value divergence were detected between the cribriform and non-cribriform pattern tumor foci within the primary index lesion. CONCLUSION: Cribiform pattern should be considered in single lesions with an area of lower ADC value on mpMRI.

Multiple Military Osteoma Cutis: Report of a Case and a Brief Review of the Literature.

A 39-year-old woman presented with a 4-year history of asymptomatic facial lesions that has progressively increased in number to become a cosmetic nuisance. These lesions have not responded to 6-months of topical 20% azelaic acid, 0.1% retinoic acid, and 20% vitamin C combination. She has had mild papulopustular acne. Her personal and family histories were unremarkable. On dermatologic examination, there were multiple flesh-colored to pigmented, firm ovoid to round papules, 2-5 mm in size, over the forehead and both cheeks (Figure 1). The dermatoscopic examination was nonspecific. Preliminary diagnoses were made of eccrine syringoma, steatocystoma multiplex, and papular elastorrhexis. A histopathologic examination from a punch biopsy displayed focal ossification within the dermis (Figure 2). Routine laboratory tests, including serum calcium, phosphorus, PTH, and vitamin D levels were within the normal ranges. A maxillofacial 3D CT scan, revealed multiple dermal and hypodermal ossifications, <3-5 mm in size-in the frontal, mandibular, and maxillary areas of the face (Figure 3). Scattered osteomas were also seen on the neck. A definitive diagnosis of multiple miliary osteoma cutis (MMOC) of the face and neck was firmly established based on clinical, histologic, and radiologic findings. Radiologically, the distribution and extent of the lesions were more pronounced than clinically anticipated. (SKINmed. 2022;20:469-471).

A Comparative Study of Multiparametric MRI Sequences in Measuring Prostate Cancer Index Lesion Volume.

Objectives: To compare the effectiveness of individual multiparametric prostate MRI (mpMRI) sequences-T2W, diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC), and dynamic contrast-enhanced (DCE)-in assessing prostate cancer (PCa) index lesion volume using whole-mount pathology as the ground-truth; to assess the impact of an endorectal coil (ERC) on the measurements. Materials and Methods: We retrospectively enrolled 72 PCa patients who underwent 3T mpMRI with (n = 39) or without (n = 33) an ERC. A pathologist drew the index lesion borders on whole-mount pathology using planimetry (whole-mountvol). A radiologist drew the borders of the index lesion on each mpMRI sequence-T2Wvol, DWIvol, ADCvol, and DCEvol. Additionally, we calculated the maximum index lesion volume for each patient (maxMRIvol). The correlation and differences between mpMRI and whole-mount pathology in measuring the index lesion volume and the impact of an ERC were investigated. Results: The median T2Wvol, DWIvol, ADCvol, DCEvol, and maxMRIvol were 0.68 cm3, 0.97 cm3, 0.98 cm3, 0.82 cm3, and 1.13 cm3. There were good positive correlations between whole-mountvol and mpMRI sequences. However, all mpMRI-derived volumes underestimated the median whole-mountvol volume of 1.97 cm3 (P ≤ 0.001), with T2Wvol having the largest volumetric underestimation while DWIvol and ADCvol having the smallest. The mean relative index lesion volume underestimations of maxMRIvol were 39.16% ± 32.58% and 7.65% ± 51.91% with and without an ERC (P = 0.002). Conclusion: T2Wvol, DWIvol, ADCvol, DCEvol, and maxMRIvol substantially underestimate PCa index lesion volume compared with whole-mount pathology, with T2Wvol having the largest volume underestimation. Additionally, using an ERC exacerbates the volume underestimation.

The analysis of 18 F-FDG PET/MRI, electroencephalography, and semiology in patients with gray matter heterotopia: A pilot study.

OBJECTIVES: To describe 18 F-fluorodeoxyglucose positron emission tomography/magnetic resonance imaging (18 F-FDG PET/MRI) along with semiology and electroencephalography (EEG) in patients with gray matter heterotopia (GMH); to evaluate the concordance between 18 F-FDG PET/MRI and clinical epileptogenic zone (EZ). MATERIALS & METHODS: GMH (subcortical heterotopia [SCH] and periventricular nodular heterotopia [PNH]) patients with epilepsy who underwent 18 F-FDG PET/MRI were retrospectively enrolled. Two radiologists evaluated brain MRI, while two nuclear medicine specialists assessed the 18 F-FDG PET. The SUVmax values of visually hypometabolic cortical areas were compared to the contralateral cortex using a SUVmax threshold value of 10%; the SUVmax values of GMH lesions were compared with that of the right precentral gyrus. The cortex or GMH with hypometabolism on 18 F-FDG PET/MRI was considered representative of the EZ. The clinical EZ was identified using EEG and semiology. RESULTS: Thirty patients (19 PNH; 11 SCH) with a mean age of 28.46 ± 9.52 years were enrolled. The heterotopic nodules were ametabolic in 3 patients (10%), hypometabolic in 16 (33.33%), isometabolic in 13 (26.66%), and hypermetabolic in 4 (10%). 18 F-FDG PET/MRI demonstrated hypometabolism in the cortex and GMH in 22/30 (73.33%) and 16/30 (53.33%). We could identify a clinical EZ in 18 patients, and 15 out of 18 (83.33%) had concordant 18 F-FDG PET/MRI findings. CONCLUSION: Heterotopic nodules in GMH patients show different metabolic patterns on 18 F-FDG PET/MRI, with nearly three-quarters of the patients having cortical hypometabolism. 18 F-FDG PET/ MRI findings are mostly concordant with the clinical EZ.

A Review on Cutaneous and Musculoskeletal Manifestations of CLOVES Syndrome.

CLOVES syndrome is a novel sporadic mosaic segmental overgrowth syndrome, currently categorized under the canopy of PROS (PIK3CA-related overgrowth spectrum) disorders. All PROS disorders harbor heterozygous postzygotic activating somatic mutations involving the PIK3CA gene. As an upstream regulator of the PI3K/AKT/mTOR signal transduction pathway, activating mutations of PIK3CA gene commence in uncontrolled growth of cutaneous, vascular (capillaries, veins, and lymphatics), adipose, neural, and musculoskeletal tissues. The excessive growth is segmental, patchy, asymmetric, and confined to body parts affected by the mutation. The term 'CLOVES' is an acronym denoting congenital lipomatous overgrowth, vascular malformations, epidermal nevi and spinal (scoliosis) and/ or skeletal anomalies. The syndrome is characterized by an admixture of overgrown tissues, derived mainly from mesoderm and neuroectoderm. Among PROS disorders, CLOVES syndrome represents the extreme end of the spectrum with massive affection of almost the entire body. The syndrome might judiciously be treated with medications hampering with the PI3K/AKT/mTOR signal transduction pathway. This article aims at reviewing the cutaneous and musculoskeletal manifestations of CLOVES syndrome, as the paradigm for PROS disorders. CLOVES syndrome and other PROS disorders are still misdiagnosed, underdiagnosed, underreported, and undertreated by the dermatology community.

Prevalence of benign bone lesions of the lower extremity in the pediatric spinal disorders: a whole-body imaging study.

There is a paucity of knowledge about benign bone lesions. The advances in imaging methods can screen bone lesions incidentally, and missing information can be provided. The aim of the study is to collect information about the prevalence and natural history of benign bone lesions with the use of whole-body biplanar slot-scanning imaging (EOS). EOS images acquired between 2015 and 2020 were retrospectively analyzed. Anatomical locations of lesions, number of lesions with polyostotic involvement and radiographic features of each were recorded. Fibrous lesions were further categorized according to the transition stages. The natural course was noted as remained in the same stage, progressed and disappeared during follow-up. A total of 1944 EOS images of 1378 (936 women and 442 men) patients were analyzed. The mean age was 12.3 (5-18) years. Bone lesions of the lower extremities were found in 278 scans (14.3%) of 196 (139 women and 57 men) patients (14.2%). Monostotic lesions were observed in 172 patients, and 24 had polyostotic lesions. The prevalence of lesions was 10.5%, 1.8%, 1.7%, 1.7% and 1.4‰ for fibrous cortical defect (FCD), nonossifying fibroma (NOF), osteochondroma, bone island and simple bone cyst, respectively. Among 145 FCDs, 55.2% of the lesions were stage A, 27.6% were stage B, 9.6% were stage C and 7.5% were stage D. EOS images acquired predominantly for spinal pathologies revealed a prevalence of 14% of benign bone tumors in the lower extremities. With the developments in imaging methods, the probability of encountering incidental lesion increases, and information about bone pathologies can be gathered.

A joint convolutional-recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CT.

To investigate the performance of a joint convolutional neural networks-recurrent neural networks (CNN-RNN) using an attention mechanism in identifying and classifying intracranial hemorrhage (ICH) on a large multi-center dataset; to test its performance in a prospective independent sample consisting of consecutive real-world patients. All consecutive patients who underwent emergency non-contrast-enhanced head CT in five different centers were retrospectively gathered. Five neuroradiologists created the ground-truth labels. The development dataset was divided into the training and validation set. After the development phase, we integrated the deep learning model into an independent center's PACS environment for over six months for assessing the performance in a real clinical setting. Three radiologists created the ground-truth labels of the testing set with a majority voting. A total of 55,179 head CT scans of 48,070 patients, 28,253 men (58.77%), with a mean age of 53.84 ± 17.64 years (range 18-89) were enrolled in the study. The validation sample comprised 5211 head CT scans, with 991 being annotated as ICH-positive. The model's binary accuracy, sensitivity, and specificity on the validation set were 99.41%, 99.70%, and 98.91, respectively. During the prospective implementation, the model yielded an accuracy of 96.02% on 452 head CT scans with an average prediction time of 45 ± 8 s. The joint CNN-RNN model with an attention mechanism yielded excellent diagnostic accuracy in assessing ICH and its subtypes on a large-scale sample. The model was seamlessly integrated into the radiology workflow. Though slightly decreased performance, it provided decisions on the sample of consecutive real-world patients within a minute.

Performance of apparent diffusion coefficient values and ratios for the prediction of prostate cancer aggressiveness across different MRI acquisition settings.

PURPOSE: In this study, we assessed the performance of apparent diffusion coefficient (ADC) and diffusion-weighted imaging (DWI) metrics and their ratios across different magnetic resonance imaging (MRI) acquisition settings, with or without an endorectal coil (ERC), for the evaluation of prostate cancer (PCa) aggressiveness using whole-mount specimens as a reference. METHODS: We retrospectively reviewed the data of prostate carcinoma patients with a Gleason score (GS) of 3+4 or higher who underwent prostate MRI using a 3T unit at our institution. They were divided into two groups based on the use of ERC for MRI acquisition, and patients who underwent prostate MRI with an ERC constituted the ERC (n = 55) data set, while the remaining patients accounted for the non-ERC data set (n = 41). DWI was performed with b-values of 50, 500, 1000, and 1,400 s/mm2, and ADC maps were automatically calculated. Additionally, computed DWI (cDWI) was performed with a b-value of 2000 s/mm2. Six ADC and two cDWI parameters were evaluated. In the ERC data set, receiver operating characteristic (ROC) curves were plotted for each metric to determine the best cutoff threshold values for differentiating GS 3+4 PCa from that with a higher GS. The performance of these cutoff values was assessed in non-ERC dataset. The diagnostic accuracies and area under the curves (AUCs) of the metrics were compared using Fisher's exact test and De Long's method, respectively. RESULTS: Among all metrics, the ADCmean-ratio yielded the highest AUC, 0.84, for differing GS 3+4 PCa from that with a higher GS. The best threshold cutoff values of ADCmean-ratio (£0.51) for discriminating GS 3+4 PCa from that with a higher GS classified 48 patients out of 55 with an accuracy of 87.27%. However, there was no significant difference between each metric in terms of accuracy and AUC (p = 0.163 and 0.214). Similarly, in the non-ERC data set, the ADCmean-ratio provided the highest diagnostic accuracy (82.92%) by classifying 34 patients out of 41. However, Fisher's exact test yielded no significant difference between DWI and ADC metrics in terms of diagnostic accuracy in non-ERC data (p = 0.561). CONCLUSION: The mean ADC ratio of the tumor to the normal prostate showed the highest accuracy and AUC in differentiating GS 3+4 PCa and PCa with a higher GS across different MRI acquisition settings; however, the performance of different ADC and DWI metrics did not differ significantly.

Third-Generation Dual-Source Computed Tomography for Coronary Angiography With Individually Tailored Scan Protocols Can Achieve a Low Radiation Dose With Good Image Quality in Unselected Patients.

OBJECTIVE: To explore the image quality and radiation exposure associated with coronary angiography obtained with a third-generation dual-source computed tomography, using body mass index (BMI)- and heart rate (HR)-adapted protocols in real-world patients. METHODS: Three scan protocols were implemented with regard to HR: prospective turbo high-pitch spiral, sequential, and retrospective spiral modes. We adapted the reference kilovoltage value according to BMI. Image quality was evaluated using a 4-point scale, and effective dose estimates were calculated using the dose-length product. RESULTS: Among the 896 patients, 417 (46.54%), 433 (48.32%), and 45 (5.02%) were imaged using prospective turbo high-pitch spiral, sequential, and retrospective spiral modes, respectively. The median BMI was 27.3 (25-30.4) kg/m2, and the effective dose was 0.65 mSv (interquartile range, 0.33-1.56 mSv). Only 32 of 896 examinations (3.5%) had poor image quality. CONCLUSIONS: Computed tomography angiography with BMI- and HR-tailored protocols offers good image quality with low radiation dose in unselected patients.

Comparing the Diagnostic Performance of Multiparametric Prostate MRI Versus 68Ga-PSMA PET-CT in the Evaluation Lymph Node Involvement and Extraprostatic Extension.

PURPOSE: Our research aims to compare the efficacy of PET and MRI for lymph node metastasis and extraprostatic extension in cases with newly diagnosed prostate cancer undergoing radical prostatectomy with extended pelvic lymph node dissection. METHODS: Thirty-nine cases who underwent radical prostatectomy with pelvic lymph node dissection between June 2015 and January 2020 were included in the study. Patients with gallium (ga-68 Prostate-specific membrane antigen (PSMA) PET) PSMA PET-CT and multiparametric (mp) prostate MRI performed according to PIRADS v2 criteria in our clinic were included. RESULTS: The extraprostatic extension was observed in 16 cases. The sensitivity of MR in detecting extracapsular invasion was calculated as 56.2%, specificity 82.6%, positive predictive value (PPV) 69.2%, negative predictive value (NPV) 73.0%. The sensitivity of PET was 62.5%, specificity 60.8%, PPV 52.6%, NPV 70%. Eleven lymph node metastases were observed in nine cases. The sensitivity, specificity, PPV and NPV of metastatic lymph node detection were; 36.3%, 99.6%, 57.1%, 99.0% for MRI and; 18.1%, 99.4%, 33.3%, 98.8% for PET CT, respectively. CONCLUSION: Mp prostate MRI showed low sensitivity and high specificity compared to PSMA PET CT in extracapsular invasion evaluation. The sensitivity of both modalities in the detection of metastatic lymph nodes was low.

Association between left ventricular strain and cardiac iron load in beta-thalassaemia major: a cardiac magnetic resonance study.

OBJECTIVE: To evaluate the utility of cardiac magnetic resonance feature tracking-derived left ventricular strain in assessing cardiac dysfunction and investigate the correlation between left ventricular strain and myocardial T2* in patients with beta-thalassaemia major. METHODS: Forty-two patients with beta-thalassaemia major, having a mean age of 22.49 ± 8.48 years, and age-matched healthy controls were enrolled in the study. The observer drew regions of interest on the interventricular septum, and T2* decay curves were calculated accordingly. The short-axis cine images were used to derive left ventricular circumferential and radial strains, and the long-axis four-chamber and two-chamber images were used to assess left ventricular longitudinal strain. RESULTS: The mean global left ventricular strains were lower in beta-thalassaemia major patients than the controls (p < 0.05). Left ventricular strains of beta-thalassaemia major patients with cardiac T2* values of > 20 ms were also significantly reduced compared with the controls (p < 0.05); there was no difference between the mean left ventricular ejection fractions of the two groups (p = 0.84). Cardiac T2* showed a weak correlation with left ventricular ejection fraction (r = 0.33, p = 0.03), while the left ventricular circumferential strain showed a good positive correlation with cardiac T2* (r = 0.6, p < 0.0001). CONCLUSION: Compared with healthy controls, patients with beta-thalassaemia major, including those with myocardial T2* values of >20 ms, showed reduced global left ventricular strains. Left ventricular circumferential strain was positively correlated with myocardial T2*. Left ventricular strain analysis using cardiac magnetic resonance feature tracking may have utility in beta-thalassaemia major assessment.Key FindingsPatients with beta-thalassaemia major, including those with myocardial T2* values of >20 ms, had reduced global left ventricular strains.Cardiac T2* showed a weak correlation with left ventricular ejection fraction, while the left ventricular circumferential strain showed a good positive correlation with cardiac T2*.ImportanceLeft ventricular strain using cardiac magnetic resonance feature tracking might be used as an adjunct in assessing cardiac functions in beta-thalassaemia major.

Risk of symptomatic radiation necrosis in patients treated with stereotactic radiosurgery for brain metastases.

INTRODUCTIO: Stereotactic radiosurgery (SRS) is a treatment option in the initial management of patients with brain metastases. While its efficacy has been demonstrated in several prior studies, treatment-related complications, particularly symptomatic radiation necrosis (RN), remains as an obstacle for wider implementation of this treatment modality. We thus examined risk factors associated with the development of symptomatic RN in patients treated with SRS for brain metastases. PATIENTS AND METHODS: We performed a retrospective review of our institutional database to identify patients with brain metastases treated with SRS. Diagnosis of symptomatic RN was determined by appearance on serial MRIs, MR spectroscopy, requirement of therapy, and the development of new neurological complaints without evidence of disease progression. RESULTS: We identified 323 brain metastases treated with SRS in 170 patients from 2009 to 2018. Thirteen patients (4%) experienced symptomatic RN after treatment of 23 (7%) lesions. After SRS, the median time to symptomatic RN was 8.3 months. Patients with symptomatic RN had a larger mean target volume (p<0.0001), and thus larger V100% (p<0.0001), V50% (p<0.0001), V12Gy (p<0.0001), and V10Gy (p=0.0002), compared to the rest of the cohort. Single-fraction treatment (p=0.0025) and diabetes (p=0.019) were also significantly associated with symptomatic RN. CONCLUSION: SRS is an effective treatment option for patients with brain metastases; however, a subset of patients may develop symptomatic RN. We found that patients with larger tumor size, larger plan V100%, V50%, V12Gy, or V10Gy, who received single-fraction SRS, or who had diabetes were all at higher risk of symptomatic RN.