The latest medical research on Nuclear Radiology

The research magnet gathers the latest research from around the web, based on your specialty area. Below you will find a sample of some of the most recent articles from reputable medical journals about nuclear radiology gathered by our medical AI research bot.

The selection below is filtered by medical specialty. Registered users get access to the Plexa Intelligent Filtering System that personalises your dashboard to display only content that is relevant to you.

Want more personalised results?

Request Access

Prognostic findings for ICU admission in patients with COVID-19 pneumonia: baseline and follow-up chest CT and the added value of artificial intelligence.

Emergency Radiology

Infection with SARS-CoV-2 has dominated discussion and caused global healthcare and economic crisis over the past 18 months. Coronavirus disease 19...

Prognosis of a second clinical event from baseline MRI in patients with a CIS: a multicenter study using a machine learning approach.


To predict the occurrence of a second clinical event in patients with a CIS suggestive of MS, from baseline magnetic resonance imaging (MRI), by means of a pattern recognition approach.

Two hundred sixty-six patients with a CIS were recruited from four participating centers. Over a follow-up of 3 years, 130 patients had a second clinical episode and 136 did not. Grey matter and white matter T1-hypointensities masks segmented from 3D T1-weighted images acquired on 3 T scanners were used as features for the classification approach. Differences between CIS that remained CIS and those that developed a second event were assessed at a global level and at a regional level, arranging the regions according to their contribution to the classification model.

All classification metrics were around or even below 50% for both global and regional approaches. Accuracies did not change when T1-hypointensity maps were added to the model; just the specificity was increased up to 80%. Among the 30 regions with the largest contribution, 26 were grey matter and 4 were white matter regions. For grey matter, regions contributing showed either a larger or a smaller volume in the group of patients that remained CIS, compared to those with a second event. The volume of T1-hypointensities was always larger for the group that presented a second event.

Prediction of a second clinical event in CIS patients from baseline MRI seems to present a highly heterogeneous pattern, leading to very low classification accuracies. Adding the T1-hypointensity maps does not seem to improve the accuracy of the classification model.

Identifying symptomatic trigeminal nerves from MRI in a cohort of trigeminal neuralgia patients using radiomics.


Trigeminal neuralgia (TN) is a devastating neuropathic condition. This work tests whether radiomics features derived from MRI of the trigeminal nerve can distinguish between TN-afflicted and pain-free nerves.

3D T1- and T2-weighted 1.5-Tesla MRI volumes were retrospectively acquired for patients undergoing stereotactic radiosurgery to treat TN. A convolutional U-net deep learning network was used to segment the trigeminal nerves from the pons to the ganglion. A total of 216 radiomics features consisting of image texture, shape, and intensity were extracted from each nerve. Within a cross-validation scheme, a random forest feature selection method was used, and a shallow neural network was trained using the selected variables to differentiate between TN-affected and non-affected nerves. Average performance over the validation sets was measured to estimate generalizability.

A total of 134 patients (i.e., 268 nerves) were included. The top 16 performing features extracted from the masks were selected for the predictive model. The average validation accuracy was 78%. The validation AUC of the model was 0.83, and sensitivity and specificity were 0.82 and 0.76, respectively.

Overall, this work suggests that radiomics features from MR imaging of the trigeminal nerves correlate with the presence of pain from TN.

Pediatric skull fractures: could suture contact be a sign of abuse?

Emergency Radiology

Skull fractures in infants and young children can occur as a result of both accidental trauma and abuse. 1/3 of children with abuse-related head trauma and 1/5 of children with abuse-related fractures were overlooked during the initial evaluation. In this study, we aim to investigate the prevalence of skull fractures that come into contact with the suture in head traumas caused by accidents and abuse, and also to see if contact of the fracture line with the suture could be used as a sign for abuse in the pediatric population.

Forry-four patients with head trauma were retrospectively assessed between January 2010 and June 2020 and were confirmed to have fractures on a brain CT. Patient age, gender, and head injury type were recorded. The fracture site, location and number, the contact of the fracture line with the suture, the name, and number of the suture it came into contact with were determined.

Twenty-eight skull fractures in 22 children with a diagnosis of child abuse and 25 skull fractures in 22 children due to accidental trauma were evaluated in the same age and gender range. Eighteen (64%) of 28 abuse-related skull fractures were in contact with two or more sutures. Two (8%) of 25 accident-related fractures were related to two or more sutures. Abuse-related fractures had a significantly higher suture contact rate than accident-related fractures (p = 0.007).

Contact with two or more sutures of a skull fracture is a finding related to abuse rather than accident.

Transfer patient imaging: discordances between community and subspecialist emergency radiologists.

Emergency Radiology

To determine the rate and nature of significant discordances between community and subspecialist emergency radiologists' interpretations of cross-sectional exams performed on patients transferred to our trauma center.

Outside hospital CT and MRI exams performed on transfer trauma patients are routinely overread by subspecialist emergency radiologists, specifying either concordance or discordance with the interpretation by the community radiologist. We evaluated the discordant reports for clinical significance, defined as an additional finding or difference in interpretation which was likely to affect patient management. The total rate of significant discordances, rate by modality, rate by body region, and rate per patient transferred were calculated. The most common errors were identified, and the distribution of errors among individual community radiologists was examined.

9175 exams were reviewed. Significant discordances were encountered in 4.1% of exams: 3.9% for CT and 6.7% for MRI; 5.1% for head and neck exams, 3.3% for spine, 3.8% for torso, and 2.9% for extremities. The discordance rate per patient transferred was 7.7%. The most common discordances involved missing injuries to the cranio-cervical junction, missing or misinterpreting vascular injuries in the neck, and incompletely characterizing facial fractures. Discordances were evenly spread among 220 community radiologists.

There is frequent discordance between community and emergency radiologists' interpretations of CT and MRI exams, leading to a change in transferred patient management. Thus, trauma center radiologists provide added value overreading these patients' exams. It is difficult to predict which patients or exams will contain discordances, justifying routine overreading of all such exams.

A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma.


This study aimed to investigate the clinical usefulness of the enhanced-T1WI-based deep learning radiomics model (DLRM) in differentiating low- and high-grade meningiomas.

A total of 132 patients with pathologically confirmed meningiomas were consecutively enrolled (105 in the training cohort and 27 in the test cohort). Radiomics features and deep learning features were extracted from T1 weighted images (T1WI) (both axial and sagittal) and the maximum slice of the axial tumor lesion, respectively. Then, the synthetic minority oversampling technique (SMOTE) was utilized to balance the sample numbers. The optimal discriminative features were selected for model building. LightGBM algorithm was used to develop DLRM by a combination of radiomics features and deep learning features. For comparison, a radiomics model (RM) and a deep learning model (DLM) were constructed using a similar method as well. Differentiating efficacy was determined by using the receiver operating characteristic (ROC) analysis.

A total of 15 features were selected to construct the DLRM with SMOTE, which showed good discrimination performance in both the training and test cohorts. The DLRM outperformed RM and DLM for differentiating low- and high-grade meningiomas (training AUC: 0.988 vs. 0.980 vs. 0.892; test AUC: 0.935 vs. 0.918 vs. 0.718). The accuracy, sensitivity, and specificity of the DLRM with SMOTE were 0.926, 0.900, and 0.924 in the test cohort, respectively.

The DLRM with SMOTE based on enhanced T1WI images has favorable performance for noninvasively individualized prediction of meningioma grades, which exhibited favorable clinical usefulness superior over the radiomics features.

Comparing two artificial intelligence software packages for normative brain volumetry in memory clinic imaging.


To compare two artificial intelligence software packages performing normative brain volumetry and explore whether they could differently impact dementia diagnostics in a clinical context.

Sixty patients (20 Alzheimer's disease, 20 frontotemporal dementia, 20 mild cognitive impairment) and 20 controls were included retrospectively. One MRI per subject was processed by software packages from two proprietary manufacturers, producing two quantitative reports per subject. Two neuroradiologists assigned forced-choice diagnoses using only the normative volumetry data in these reports. They classified the volumetric profile as "normal," or "abnormal", and if "abnormal," they specified the most likely dementia subtype. Differences between the packages' clinical impact were assessed by comparing (1) agreement between diagnoses based on software output; (2) diagnostic accuracy, sensitivity, and specificity; and (3) diagnostic confidence. Quantitative outputs were also compared to provide context to any diagnostic differences.

Diagnostic agreement between packages was moderate, for distinguishing normal and abnormal volumetry (K = .41-.43) and for specific diagnoses (K = .36-.38). However, each package yielded high inter-observer agreement when distinguishing normal and abnormal profiles (K = .73-.82). Accuracy, sensitivity, and specificity were not different between packages. Diagnostic confidence was different between packages for one rater. Whole brain intracranial volume output differed between software packages (10.73%, p < .001), and normative regional data interpreted for diagnosis correlated weakly to moderately (rs = .12-.80).

Different artificial intelligence software packages for quantitative normative assessment of brain MRI can produce distinct effects at the level of clinical interpretation. Clinics should not assume that different packages are interchangeable, thus recommending internal evaluation of packages before adoption.

Occult craniocervical dissociation on cervical CT: an under-appreciated presentation of craniocervical trauma requiring occipital cervical fusion.

Emergency Radiology

Craniocervical dissociation is a rare and life-threatening injury that results from a significant hyperflexion-hyperextension force. Occult craniocervical dissociation is defined as an unstable craniocervical injury in the absence of atlanto-occipital joint space widening or other skull base line abnormality. The early and accurate diagnosis of craniocervical dissociation is crucial since the early diagnosis and subsequent stabilization with occipital-cervical fusion has been shown to reduce neurologic morbidity and mortality. Several normative skull base lines have been developed to predict craniocervical dissociation. The purpose of our study was to measure the atlanto-occipital joint space and four other common skull base lines in patients who underwent occipital-cervical fusion for post-traumatic craniocervical instability.

Patients who underwent occipital-cervical fusion for craniocervical injury were identified retrospectively using a keyword search of radiology reports using Nuance mPower software. The cervical CT and MRI exams for these patients were reviewed and the atlanto-occipital joint space, Powers ratio, Wackenheim line, posterior axial line, and basion dens interval were measured. Detailed descriptions of craniocervical ligament injuries on MRI were recorded along with patient demographic information, clinical history, management, and outcome.

Nine adult patients who underwent occipital-cervical fusion for an acute craniocervical injury were identified. Six patients demonstrated an atlanto-occipital joint space measuring 2 mm or less on cervical spine CT with no additional abnormality in the Powers ratio, Wackenheim line, posterior axial line, or basion-dens interval. Three patients demonstrated widening of the atlanto-occipital joint space with two patients demonstrating an abnormality in at least two additional skull base lines. Clinical outcomes were variable with nearly half of the patients demonstrating persistent neurologic deficits, including one quadriplegic patient.

A normal atlanto-occipital joint space and skull base line measurements on cervical CT demonstrated a low predictive value for detecting unstable craniocervical injuries. Occult craniocervical dissociation was present in two-thirds of patients who underwent occipital cervical fusion for acute, craniocervical trauma. A high clinical and radiologic index of suspicion for craniocervical trauma with subsequent follow-up cervical MRI to directly evaluate ligamentous integrity is necessary to accurately diagnose and triage patients with high velocity trauma.

Accidental or intentional ingestion of toothbrushes: experience with 8 adult patients.

Emergency Radiology

Ingestion of a toothbrush is an unusual event but may occur either accident or by intent. Radiological examinations play a crucial role in determining the exact location of the object within the gastrointestinal tract and in planning for its removal by endoscopic or surgical intervention.

Medical and radiological records of 8 patients who had swallowed the broken heads or entire toothbrush were retrospectively reviewed. This series included 4 men and 4 women, ranging in age from 21 to 57 years (mean: 34 years).

Radiographs and computed tomography of the abdomen demonstrated the ingested toothbrushes within the stomach in 3, lodged in the duodenum in 1, and entrapped in various parts of the colon in 4 patients. They were removed by laparotomy in 3, laparoscopy in 2, colonoscopy in 2, and upper gastrointestinal endoscopy in 1 patient. There were no perforations or associated complications, and all patients had uneventful recoveries.

Ingested toothbrushes can be easily identified on radiological studies because of the radiopaque wires holding the nylon bristles. The plastic parts of it, however, are only visible on computed tomography. All cases would require endoscopic or surgical removal of the retained toothbrushes because spontaneous passage per rectum does not occur.

The utility of spectral Doppler evaluation of acute appendicitis.

Emergency Radiology

The use of spectral Doppler, peak systolic velocity (PSV), and resistive index (RI) imaging criteria to improve the accuracy of acute appendicitis diagnosis is hypothesized.

Graded compression ultrasound was performed for suspected patients. The spectral Doppler evaluation was conducted while observing the appendix. A total of 152 patients (82 males and 70 females, ages 4-63 years, mean age of 24.5 years) were examined using the spectral Doppler waveform between 2018 and 2019. RI and PSV values of patients with and without appendicitis were compared to histopathologic findings. SPSS 26 was used to analyze the data, including using descriptive statistics and measures of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Appendicitis was confirmed in 95 patients (62.5%) and rejected in 57 patients (37.5%). For the diagnosis of appendicitis, the area under the curve (AUC) of receiver operating characteristic (ROC) for RI (0.92 with 95% confidence interval (CI): 0.88, 0.97; P = 0.001) and PSV (0.96, with 95% CI: 0.93, 1.00; P = 0.001) was calculated. The discriminatory RI ≥ 0.49 demonstrated high sensitivity (90.5%) and low specificity (86%), and the discriminatory PSV ≥ 9.6 cm/s had high specificity (94.7%) and sensitivity (94.7%) for appendicitis.

By incorporating spectral Doppler criteria into routine graded compression ultrasound, the diagnostic accuracy of acute appendicitis was increased. In comparison, high PSV and RI values of the appendix with a cut-off point of 9.6 cm/s and 0.49 differ significantly between positive and negative appendectomy patients.

Alterations in the structural covariance network of the hypothalamus in patients with narcolepsy.


The hypothalamus plays a pivotal role in the pathogenesis of narcolepsy. This study aimed to evaluate the differences in the structural covariance network of thehypothalamus based on volume differences between patients with narcolepsy and healthy controls.

We retrospectively enrolled 15 patients with narcolepsy and 19 healthy controls.All subjects underwent three-dimensional T1-weighted imaging using a 3-T magnetic resonance imaging scanner. Hypothalamic subunits were segmented, and the volumes of individual hypothalamic subunits were obtained using the FreeSurfer program. Subsequently, we conducted a structural covariance network analysis of the subunit volumes with graph theory using the BRAPH program in patients with narcolepsy and in healthy controls.

There were no significant differences in the volumes of the entire right and left hypothalamus nor in the hypothalamic subunit between patients with narcolepsy and healthy controls. However, we found significant differences in the structural covariance network in the hypothalamus between these groups. The characteristic path length was significantly lower in patients with narcolepsy than in healthy controls (1.698 vs. 2.831, p = 0.001). However, other network measures did not differ between patients with narcolepsy and healthy controls.

We found that the structural covariance network of the hypothalamus, as assessed from the subunit volumes of hypothalamic regions using a graph theoretical analysis, is different in patients with narcolepsy compared to healthy controls. These findings may contribute to the understanding of the pathogenesis of narcolepsy.

Interventional radiology in renal emergencies: a pictorial essay.

Emergency Radiology

Renal emergencies necessitate prompt diagnosis and management to stop active bleeding and retain kidney function. Causes of renal emergencies can b...