Deep Learning for Head and Neck CT Angiography: Stenosis and Plaque Classification.

Background Studies have rarely investigated stenosis detection from head and neck CT angiography scans because accurate interpretation is time consuming and labor intensive. Purpose To develop an automated convolutional neural network-based method for accurate stenosis detection and plaque classification in head and neck CT angiography images and compare its performance with that of radiologists. Materials and Methods A deep learning (DL) algorithm was constructed and trained with use of head and neck CT angiography images that were collected retrospectively from four tertiary hospitals between March 2020 and July 2021. CT scans were partitioned into training, validation, and independent test sets at a ratio of 7:2:1. An independent test set of CT angiography scans was collected prospectively between October 2021 and December 2021 in one of the four tertiary centers. Stenosis grade categories were as follows: mild stenosis (<50%), moderate stenosis (50%-69%), severe stenosis (70%-99%), and occlusion (100%). The stenosis diagnosis and plaque classification of the algorithm were compared with the ground truth of consensus by two radiologists (with more than 10 years of experience). The performance of the models was analyzed in terms of accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve. Results There were 3266 patients (mean age ± SD, 62 years ± 12; 2096 men) evaluated. The consistency between radiologists and the DL-assisted algorithm on plaque classification was 85.6% (320 of 374 cases [95% CI: 83.2, 88.6]) on a per-vessel basis. Moreover, the artificial intelligence model assisted in visual assessment, such as increasing confidence in the degree of stenosis. This reduced the time needed for diagnosis and report writing of radiologists from 28.8 minutes ± 5.6 to 12.4 minutes ± 2.0 (P < .001). Conclusion A deep learning algorithm for head and neck CT angiography interpretation accurately determined vessel stenosis and plaque classification and had equivalent diagnostic performance when compared with experienced radiologists. © RSNA, 2023 Supplemental material is available for this article.

Brain Abnormalities in Pontine Infarction: A Longitudinal Diffusion Tensor Imaging and Functional Magnetic Resonance Imaging study.

OBJECTIVES: The aim of this study was to make a reasonable and accurate assessment of the prognosis of patients with pontine infarction. We assessed the changes in structure and function in the whole brain after pontine infarction from the acute to chronic phase using diffustion tensor imaging and functional magnetic resonance imaging. MATERIALS AND METHODS: Sixteen individuals with a recent pontine infarction and sixteen healthy controls were recruited and underwent 3.0T DTI, resting-state fMRI and upper extremity Fugl-Myer (UE-FM) functional evaluation at five time points: within one week (T1), half a month (T2), one month (T3), three months (T4), and six months (T5) after onset. Tract-based spatial statistics was used to conduct a voxelwise analysis. RESULTS: The fractional anisotropy (FA) values were significantly lower in the pontine infarction group than in the control group. Then, specific ROIs were analyzed. The FA values of 10 regions of interest were significantly increased at T2 compared with those at T1. The FA value of the corticospinal tract was significantly increased at T3 compared with that at T2. Regional brain activity results showed that the amplitude of low frequency fluctuations value of the frontal lobe decreased at T1, then increased. Finally, The UE-FM scores showed the same increased trend. CONCLUSION: These findings show that the microstructure changes most significantly within half a month after pontine infarction and stabilizes after one month. The recovery of motor function in the later period is mainly caused by changes in the cortex. This facilitates more treatment options.

Disrupted functional connectivity and activity in the white matter of the sensorimotor system in patients with pontine strokes.

BACKGROUND: White matter (WM) blood oxygenation level-dependent (BOLD) signals are reported to be related to neural activity. However, sensitivity of WM BOLD signals to disease remains unclear. PURPOSE: To investigate WM BOLD signal changes, directional variations of resting-state correlations in sensorimotor system in patients with pontine strokes, and to determine the relationship between WM BOLD signals and motor deficits. STUDY TYPE: Prospective. SUBJECTS: Ethical approval was obtained from the local Ethics Committee and each participant gave written informed consent. Sixteen patients with focal pontine lesions and 16 age-matched control subjects were included. FIELD STRENGTH/SEQUENCE: 3.0T T1 -weighted anatomic images using a 3D magnetization-prepared rapid gradient-echo sequence. Resting-state fMRI images using gradient-echo echo-planar imaging sequence. Diffusion-weighted images using single-shot spin-echo diffusion echo-planar imaging. ASSESSMENT: Relevant WM tracts in the sensorimotor system by region of interest-wise analysis were identified. Power spectra of BOLD signals and anisotropy of resting-state correlations were measured in sensorimotor system and compared between two groups. Their relationships with clinical scores were analyzed. STATISTICAL TESTS: Two-sample t-test; partial correlation analysis. RESULTS: Power spectra of BOLD signals in nerve tracts on the ipsilesional side were significantly decreased (P < 0.05). Compared with that in healthy subjects, the anisotropy of resting-state correlations along identified WM tracts was decreased in the thalamus-dorsolateral prefrontal cortex bundle on the contralesional side, and all nerve tracts on the ipsilesional side. Partial least squares regression analysis showed the predicted outcome scores correlated significantly with actual Fugl-Meyer scores (R2 = 0.944, P = 0.013). DATA CONCLUSION: Our findings suggest that disrupted activity and functional connectivity in WM areas of the sensorimotor system can be detected in pontine strokes, and may serve as a biomarker for motor function prediction. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:478-486.

Pontine infarction: diffusion-tensor imaging of motor pathways-a longitudinal study.

PURPOSE: To investigate the dynamic evolution of diffusion indexes in the corticospinal tract (CST) distal to a pontine infarct by using diffusion-tensor imaging, to determine the relationship of these indexes with clinical prognosis, and to explore the structural changes in the motor pathway during recovery. MATERIALS AND METHODS: This study was approved by the institutional ethics committee, and written informed consent was obtained from each participant. Seventeen patients with pontine infarct underwent five diffusion-tensor imaging examinations during a period of 6 months (within 7 days of onset, 14, 30, 90, and 180 after onset). Fractional anisotropic values were measured in the medulla, cerebral peduncle, internal capsule, and centrum semiovale. Fractional anisotropic values of the CST in the ipsilateral side of the infarct were compared with those in the contralateral sides and those in control subjects by using the Student t test and one-way analysis of variance, and their relationships with clinical scores were analyzed by using Pearson correlation analysis. Reconstructions of the CST were performed. Structural changes of the damaged CST were followed up. RESULTS: Fractional anisotropic ratios in the CST above the pons decreased significantly compared with those in the contralateral side and those in control subjects within 7 days, on day 14, and on day 30 after onset (P < .001). Fractional anisotropic ratios above the pons on day 14 correlated positively with Fugl-Meyer scores on day 90 (r = 0.771, P < .001) and day 180 (r = 0.730, P = .001). Follow-up diffusion-tensor tractographic images showed regeneration and reorganization of the motor pathways. CONCLUSION: Secondary degeneration of the CST can be detected at diffusion-tensor imaging in the early stages after pontine infarction, which could help predict the motor outcomes. Diffusion-tensor tractography can allow detection of regeneration and reorganization of the motor pathways during recovery.

[To evaluate the cervical spine curvature and growth rate for studying the pathogenesis of Hirayama disease in adolescents].

OBJECTIVE: To explore the pathogenesis of Hirayama disease from juvenile cervical curvature and growth rate. METHODS: Totally 60 patients diagnosed with Hirayama disease (HD) from 2009 to 2011 in our hospital were included in the present study. Patient's height and growth rate 1-2 years prior to the onset of disease were recalled by patients and family members. Lateral cervical X-ray was examined, and cervical curvature was measured by Borden's method. RESULTS: All the patients were adolescents with onset age at 12-25 (17.0 ± 2.4) years old and peak age of onset at 15-18 [45 cases (75.0%)]. Fifty-seven cases were male and 3 cases were female. Cervical MRI examination of the 60 cases showed that the spinal cord atrophy involving C4-C8 vertebral level. The C line values for cervical curvature by Borden's method of the patients was 2.6 (1.2, 4.2) mm. Among 60 patients, 57 of them were with abnormal cervical curvature. The average height growth rate 1 year prior to the onset was (7.1 ± 1.8) cm. CONCLUSIONS: The clinical manifestations that featured in overgrowth in the first two years and abnormal cervical vertebra curvature are possible related with pathogenesis of HD. HD is possibly a cervical spinal cord compression disease, which is associated with cervical spinal dysplasia during juvenile growth.

Diagnostic value of preoperative examination for evaluating margin status in breast cancer.

BACKGROUND: A positive resection margin is a major risk factor for local breast cancer recurrence after breast-conserving surgery (BCS). Preoperative imaging examinations are frequently employed to assess the surgical margin. AIM: To investigate the role and value of preoperative imaging examinations [magnetic resonance imaging (MRI), molybdenum target, and ultrasound] in evaluating margins for BCS. METHODS: A retrospective study was conducted on 323 breast cancer patients who met the criteria for BCS and consented to the procedure from January 2014 to July 2021. The study gathered preoperative imaging data (MRI, ultrasound, and molybdenum target examination) and intraoperative and postoperative pathological information. Based on their BCS outcomes, patients were categorized into positive and negative margin groups. Subsequently, the patients were randomly split into a training set (226 patients, approximately 70%) and a validation set (97 patients, approximately 30%). The imaging and pathological information was analyzed and summarized using R software. Non-conditional logistic regression and LASSO regression were conducted in the validation set to identify factors that might influence the failure of BCS. A column chart was generated and applied to the validation set to examine the relationship between pathological margin range and prognosis. This study aims to identify the risk factors associated with failure in BCS. RESULTS: The multivariate non-conditional logistic regression analysis demonstrated that various factors raise the risk of positive margins following BCS. These factors comprise non-mass enhancement (NME) on dynamic contrast-enhanced MRI, multiple focal vascular signs around the lesion on MRI, tumor size exceeding 2 cm, type III time-signal intensity curve, indistinct margins on molybdenum target examination, unclear margins on ultrasound examination, and estrogen receptor (ER) positivity in immunohistochemistry. LASSO regression was additionally employed in this study to identify four predictive factors for the model: ER, molybdenum target tumor type (MT Xmd Shape), maximum intensity projection imaging feature, and lesion type on MRI. The model constructed with these predictive factors exhibited strong consistency with the real-world scenario in both the training set and validation set. Particularly, the outcomes of the column chart model accurately predicted the likelihood of positive margins in BCS. CONCLUSION: The proposed column chart model effectively predicts the success of BCS for breast cancer. The model utilizes preoperative ultrasound, molybdenum target, MRI, and core needle biopsy pathology evaluation results, all of which align with the real-world scenario. Hence, our model can offer dependable guidance for clinical decision-making concerning BCS.

Focal pontine lesions provide evidence that intrinsic functional connectivity reflects polysynaptic anatomical pathways.

Intrinsic functional connectivity detected by functional MRI (fMRI) provides a useful but indirect approach to study the organization of human brain systems. An unresolved question is whether functional connectivity measured by resting-state fMRI reflects anatomical connections. In this study, we used the well-characterized anatomy of cerebrocerebellar circuits to directly test whether intrinsic functional connectivity is associated with an anatomic pathway. Eleven first-episode stroke patients were scanned five times during a period of 6 months, and 11 healthy control subjects were scanned three times within 1 month. In patients with right pontine strokes, the functional connectivity between the right motor cortex and the left cerebellum was selectively reduced. This connectivity pattern was reversed in patients with left pontine strokes. Although factors beyond anatomical connectivity contribute to fMRI measures of functional correlation, these results provide direct evidence that functional connectivity depends on intact connections within a specific polysynaptic pathway.

Short-term Changes on Follow-up Chest X-rays of Familial Cluster of COVID-19 Cases.

In this study, we report a familial cluster of cases which included five patients and two close contacts who were confirmed to have coronavirus disease 2019 (COVID-19). These participants had received real-time reverse transcription-polymerase chain reaction (RT-PCR) and chest X-rays (CXRs) before diagnosis. The follow-up CXRs of three patients in the family showed significant progression, with COVID-19 pneumonia, clinically worsening in a short period of time. Therefore, the results of follow-up CXRs in the short-term may be an adjunctive diagnostic method for COVID-19 disease diagnosis and its progression. Key Words: Chest X-ray, COVID-19, RT-PCR, Familial clustering.

Comparison of dry laser printer versus paper printer in full-field digital mammography.

BACKGROUND: Paper printers have been used to document radiological findings in some hospitals. It is critical to establish whether paper printers can achieve the same efficacy and quality as dry laser printers for full-field digital mammography (FFDM). PURPOSE: To compare the image quality and detection rate of dry laser printers and paper printers for FFDM. MATERIAL AND METHODS: Fifty-five cases (25 with single clustered microcalcifications and 30 controls) were selected by a radiologist not participating in the image review. All images were printed on film and paper by one experienced mammography technologist using the processing algorithm routinely used for our mammograms. Two radiologists evaluated hard copies from dry laser printers and paper printers for image quality and detectability of clustered microcalcifications. For the image quality comparisons, agreement between the reviewers was evaluated by means of kappa statistics. The significance of differences between both of the printers was determined using Wilcoxon's signed-rank test. The detection rate of two printing systems was evaluated using receiver operating characteristic (ROC) analysis. RESULTS: From 110 scores (55 patients, two readers) per printer system, the following quality results were achieved for dry laser printer images: 70 (63.6%) were rated as good and 40 (36.4%) as moderate. By contrast, for the paper printer images, 25 scores (22.7%) were rated as good and 85 (77.3%) as moderate. Therefore, the image quality of the dry laser printer was superior to that achieved by the paper printer (P=0.00). The average area-under-the-curve (Az) values for the dry laser printer and the paper printer were 0.991 and 0.805, respectively. The difference was 0.186. Results of ROC analysis showed significant difference in observer performance between the dry laser printer and paper printer (P=0.0015). CONCLUSION: The performance of dry laser printers is superior to that of paper printers. Paper printers should not be used in FFDM.

Dynamic Neural Network Changes Revealed by Voxel-Based Functional Connectivity Strength in Left Basal Ganglia Ischemic Stroke.

OBJECTIVE: This study intends to track whole-brain functional connectivity strength (FCS) changes and the lateralization index (LI) in left basal ganglia (BG) ischemic stroke patients. METHODS: Twenty-five patients (N = 25; aged 52.73 ± 10.51 years) with five visits at <7, 14, 30, 90, and 180 days and 26 healthy controls (HCs; N = 26; 51.84 ± 8.06 years) were examined with resting-state functional magnetic resonance imaging (rs-fMRI) and motor function testing. FCS and LI were calculated through constructing the voxel-based brain functional network. One-way analysis of covariance (ANOVA) was first performed to obtain longitudinal FCS and LI changes in patients among the five visits (Bonferroni corrected, P < 0.05). Then, pairwise comparisons of FCS and LI were obtained during the five visits, and the two-sample t test was used to examine between-group differences in FCS [family-wise error (FWE) corrected, P < 0.05] and LI. Correlations between connectivity metrics (FCS and LI) and motor function were further assessed. RESULTS: Compared to HCs, decreased FCS in the patients localized in the calcarine and inferior occipital gyrus (IOG), while increased FCS gathered in the middle prefrontal cortex (MPFC), middle frontal gyrus, and insula (P < 0.05). The LI and FCS of patients first decreased and then increased, which showed significant differences compared with HCs (P < 0.05) and demonstrated a transition at the 30-day visit. Additionally, LI at the third visit was significantly different from those at the other visits (P < 0.05). No significant longitudinal correlations were observed between motor function and FCS or LI (P > 0.05). CONCLUSION: Focal ischemic stroke in the left BG leads to extensive alterations in the FCS. Strong plasticity in the functional networks could be reorganized in different temporal dynamics to facilitate motor recovery after BG stroke, contribute to diagnosing the disease course, and estimate the intervention treatment.

Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network.

The computed tomography angiography (CTA) postprocessing manually recognized by technologists is extremely labor intensive and error prone. We propose an artificial intelligence reconstruction system supported by an optimized physiological anatomical-based 3D convolutional neural network that can automatically achieve CTA reconstruction in healthcare services. This system is trained and tested with 18,766 head and neck CTA scans from 5 tertiary hospitals in China collected between June 2017 and November 2018. The overall reconstruction accuracy of the independent testing dataset is 0.931. It is clinically applicable due to its consistency with manually processed images, which achieves a qualification rate of 92.1%. This system reduces the time consumed from 14.22 ± 3.64 min to 4.94 ± 0.36 min, the number of clicks from 115.87 ± 25.9 to 4 and the labor force from 3 to 1 technologist after five months application. Thus, the system facilitates clinical workflows and provides an opportunity for clinical technologists to improve humanistic patient care.

Patterns of motor recovery and structural neuroplasticity after basal ganglia infarcts.

OBJECTIVE: To elucidate the timeframe and spatial patterns of cortical reorganization after different stroke-induced basal ganglia lesions, we measured cortical thickness at 5 time points over a 6-month period. We hypothesized that cortical reorganization would occur very early and that, along with motor recovery, it would vary based on the stroke lesion site. METHODS: Thirty-three patients with unilateral basal ganglia stroke and 23 healthy control participants underwent MRI scanning and behavioral testing. To further decrease heterogeneity, we split patients into 2 groups according to whether or not the lesions mainly affect the striatal motor network as defined by resting-state functional connectivity. A priori measures included cortical thickness and motor outcome, as assessed with the Fugl-Meyer scale. RESULTS: Within 14 days poststroke, cortical thickness already increased in widespread brain areas (p = 0.001), mostly in the frontal and temporal cortices rather than in the motor cortex. Critically, the 2 groups differed in the severity of motor symptoms (p = 0.03) as well as in the cerebral reorganization they exhibited over a period of 6 months (Dice overlap index = 0.16). Specifically, the frontal and temporal regions demonstrating cortical thickening showed minimal overlap between these 2 groups, indicating different patterns of reorganization. CONCLUSIONS: Our findings underline the importance of assessing patients early and of considering individual differences, as patterns of cortical reorganization differ substantially depending on the precise location of damage and occur very soon after stroke. A better understanding of the macrostructural brain changes following stroke and their relationship with recovery may inform individualized treatment strategies.

Effects of different compression techniques on diagnostic accuracies of breast masses on digitized mammograms.

BACKGROUND: The JPEG 2000 compression technique has recently been introduced into the medical imaging field. It is critical to understand the effects of this technique on the detection of breast masses on digitized images by human observers. PURPOSE: To evaluate whether lossless and lossy techniques affect the diagnostic results of malignant and benign breast masses on digitized mammograms. MATERIAL AND METHODS: A total of 90 screen-film mammograms including craniocaudal and lateral views obtained from 45 patients were selected by two non-observing radiologists. Of these, 22 cases were benign lesions and 23 cases were malignant. The mammographic films were digitized by a laser film digitizer, and compressed to three levels (lossless and lossy 20:1 and 40:1) using the JPEG 2000 wavelet-based image compression algorithm. Four radiologists with 10-12 years' experience in mammography interpreted the original and compressed images. The time interval was 3 weeks for each reading session. A five-point malignancy scale was used, with a score of 1 corresponding to definitely not a malignant mass, a score of 2 referring to not a malignant mass, a score of 3 meaning possibly a malignant mass, a score of 4 being probably a malignant mass, and a score of 5 interpreted as definitely a malignant mass. The radiologists' performance was evaluated using receiver operating characteristic analysis. RESULTS: The average Az values for all radiologists decreased from 0.8933 for the original uncompressed images to 0.8299 for the images compressed at 40:1. This difference was not statistically significant. The detection accuracy of the original images was better than that of the compressed images, and the Az values decreased with increasing compression ratio. CONCLUSION: Digitized mammograms compressed at 40:1 could be used to substitute original images in the diagnosis of breast cancer.

Homotopic Connectivity in Early Pontine Infarction Predicts Late Motor Recovery.

Connectivity-based methods are essential to explore brain reorganization after a stroke and to provide meaningful predictors for late motor recovery. We aim to investigate the homotopic connectivity alterations during a 180-day follow-up of patients with pontine infarction to find an early biomarker for late motor recovery prediction. In our study, resting-state functional MRI was performed in 15 patients (11 males, 4 females, age: 57.87 ± 6.50) with unilateral pontine infarction and impaired motor function during a period of 6 months (7, 14, 30, 90, and 180 days after stroke onset). Clinical neurological assessments were performed using the Fugl-Meyer scale (FM).15 matched healthy volunteers were also recruited. Whole-brain functional homotopy in each individual scan was measured by voxel-mirrored homotopic connectivity (VMHC) values. Group-level analysis was performed between stroke patients and normal controls. A Pearson correlation was performed to evaluate correlations between early VMHC and the subsequent 4 visits for behavioral measures during day 14 to day 180. We found in early stroke (within 7 days after onset), decreased VMHC was detected in the bilateral precentral and postcentral gyrus and precuneus/posterior cingulate cortex (PCC), while increased VMHC was found in the hippocampus/amygdala and frontal pole (P < 0.01). During follow-up, VMHC in the precentral and postcentral gyrus increased to the normal level from day 90, while VMHC in the precuneus/PCC presented decreased intensity during all time points (P < 0.05). The hippocampus/amygdala and frontal pole presented a higher level of VMHC during all time points (P < 0.05). Negative correlation was found between early VMHC in the hippocampus/amygdala with FM on day 14 (r = -0.59, p = 0.021), day 30 (r = -0.643, p = 0.01), day 90 (r = -0.693, p = 0.004), and day 180 (r = -0.668, p = 0.007). Furthermore, early VMHC in the frontal pole was negatively correlated with FM scores on day 30 (r = -0.662, p = 0.013), day 90 (r = -0.606, p = 0.017), and day 180 (r = -0.552, p = 0.033). Our study demonstrated the potential utility of early homotopic connectivity for prediction of late motor recovery in pontine infarction.

Improvement of chronic hepatitis B by iron chelation therapy in a patient with iron overload: A case report.

RATIONALE: This report describes seroconversion of hepatitis B surface antigen (HBsAg) in a patient with marked iron overload caused by chronic hepatitis B (CHB) after receiving iron chelation therapy and discusses the role of iron chelation therapy in CHB. PATIENT CONCERNS: Increased serum ferritin level for 2 months. DIAGNOSIS: Secondary iron overload and CHB. INTERVENTION: To relieve iron load of the body, the patient underwent regular phlebotomy therapy and deferoxamine (DFO) therapy. During the therapy, serum ferritin and hepatitis B virus (HBV) were monitored and the iron concentration of the liver and heart were followed by T2* of magnetic resonance imaging (MRI) scan. OUTCOMES: Serum ferritin gradually decreased. Approximately 1 year after the therapy, HBsAg turned persistently negative. LESSONS: Iron chelation therapy may attenuate HBV infection.

Corticospinal tract change during motor recovery in patients with medulla infarct: a diffusion tensor imaging study.

Diffusion tensor imaging (DTI) and tractography (DTT) provide a powerful vehicle for investigating motor recovery mechanisms. However, little is known about these mechanisms in patients with medullary lesions. We used DTI and DTT to evaluate three patients presenting with motor deficits following unilateral medulla infarct. Patients were scanned three times during 1 month (within 7, 14, and 30 days after stroke onset). Fractional anisotropy (FA) values were measured in the medulla, cerebral peduncle, and internal capsule. The three-dimensional corticospinal tract (CST) was reconstructed using DTT. Patients 1 and 2 showed good motor recovery after 14 days, and the FA values of their affected CST were slightly decreased. DTTs demonstrated that the affected CST passed along periinfarct areas and that tract integrity was preserved in the medulla. Patient 3 had the most obvious decrease in FA values along the affected CST, with motor deficits of the right upper extremity after 30 days. The affected CST passed through the infarct and was disrupted in the medulla. In conclusion, DTI can detect the involvement and changes of the CST in patients with medulla infarct during motor recovery. The degree of degeneration and spared periinfarct CST compensation may be an important motor recovery mechanism.