Current Medical Imaging - Volume 20, Issue 1, 2024

The objective of this study was to evaluate the feasibility of weight-based tube voltage and iodine delivery rate (IDR) for coronary artery CT angiography (CCTA).

A total of 193 patients (mean age: 58 ± 12 years) with suspected coronary heart disease indicated for CCTA between May and October 2022 were prospectively enrolled. The subjects were divided into five groups according to body weight: < 60 kg, 60 – 69 kg, 70 – 79 kg, 80 – 89 kg, and ≥ 90 kg. The tube voltage and IDR settings of each group were as follows: 70 kVp/0.8 gI/s, 80 kVp/1.0 gI/s, 80 kVp/1.1 gI/s, 100 kVp/1.5 gI/s, and 100 kVp/1.5 gI/s, respectively. Objective image quality data included the CT value and standard deviation (noise) of the aortic root (AR), the proximal left anterior descending branch (LAD), and the distal right coronary artery (RCA), as well as the signal-to-noise ratio and contrast-to-noise ratio of the LAD and RCA. Subjective image quality assessment was performed based on the 18-segment model. Contrast and radiation doses, as well as effective dose (ED), were recorded. All continuous variables were compared using either the one-way ANOVA or the Kruskal-Wallis rank sum test.

No significant differences were observed in all objective and subjective parameters of image quality between the groups (P > 0.05). However, significant differences in contrast and radiation doses were observed (P < 0.05). The contrast doses across the weight groups were 27 mL, 35 mL, 38 mL, 53 mL, and 53 mL, respectively, while the ED were 1.567 (1.30, 2.197) mSv, 1.53 (1.373, 1.78) mSv, 2.113 (1.963, 2.256) mSv, 4.22 (3.771, 4.483) mSv, and 4.786 (4.339, 5.536) mSv, respectively.

Weight-based tube voltage and IDR yielded consistently high image quality, and allowed for further reduction in contrast and radiation exposure during CCTA for coronary artery diseases.

To develop and validate a radiomics-clinical nomogram for the detection of the acquired T790M mutation in patients with advanced non-small cell lung cancer (NSCLC) with resistance after the duration of first-line epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitor (TKI) treatment.

Thoracic CT was collected from 120 advanced NSCLC patients who suffered progression on first- or second-generation TKIs. Radiomics signatures were retrieved from the entire tumor. Pearson correlation and the least absolute shrinkage and selection operator (LASSO) regression method were adopted to choose the most suitable radiomics features. Clinical and radiological factors were assessed using univariate and multivariate analysis. Three Machine Learning (ML) models were constructed according to three classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), and RandomForest (RF), combining clinical and radiomic features. A nomogram combining clinical features and the rad score signature was built. The predictive ability of the nomogram was assessed by the ROC curve, calibration curve, and decision curve analysis (DCA).

Multivariate regression analysis showed that two clinicopathological characteristics and two radiological features were highly correlated with the acquired T790M mutation, including the progression-free survival (PFS) of first-line EGFR TKIs (P = 0.029), the initial EGFR profile (P = 0.01), vascular convergence (P = 0.043), and air bronchogram (P = 0.030). The AUCs of clinical, radiomics, and combined models using RF classifiers for T790M mutation detection were 0.951 (95% confidence interval [CI] 0.911,0.991), 0.917 (95%CI 0.856,0.978), and 0.961 (95%CI 0.927,0.995) in the training cohort, respectively, higher than those of other classifier models.The calibration curve and Hosmer-Lemeshow Test showed good calibration power, and the DCA demonstrated a significant net benefit.

A radiomics-clinical nomogram based on CT radiomics proved valuable in non-invasively and efficiently predicting the acquired T790M mutation in patients who suffered progression on first-line TKIs.

Magnetic Resonance Imaging (MRI) plays a role in demonstrating substantial utility in lung lesion imaging, detection, diagnosis, and evaluation. Previous studies have found that free-breathing star VIBE sequences not only have high image quality but also have a high ability to detect and display nodules. However, in our routine clinical practice, we have encountered suboptimal image quality in the free-breathing sequences of certain patients.

This study aims to assess the impact of breath training on the quality of chest magnetic resonance imaging obtained during free-breathing sequences.

A total of 68 patients with lung lesions, such as nodules or masses detected via Computed Tomography (CT) examination, were prospectively gathered. They were then randomly divided into two groups: an observation group and a control group. Standard preparation was performed for all patients in both groups before the examination. The observation group underwent 30 minutes of breath training prior to the MRI examination additionally, followed by the acquisition of MRI free-breathing sequence images. The signal intensity (SI) and standard deviation (SD) of the lesion and adjacent normal lung tissue were measured, and the image signal-to-noise ratio (SNR) and contrast signal-to-noise ratio (CNR) of the lesion were calculated for objective image quality evaluation. The subjective image quality of the two groups of images was also evaluated using a 5-point method.

MRI examinations were completed in both groups. Significantly better subjective image quality (edge and internal structure clarity, vascular clarity, breathing and cardiac artifacts, and overall image quality) was achieved in the observation group compared to the control group (P<0.05). In addition, higher SNR and CNR values for disease lesions were observed in the observation group compared to the control group (t=4.35, P<0.05; t=5.35, P<0.05).

It is concluded that the image quality of free-breathing sequences MRI can be improved through breath training before examination.

The visualization and understanding of the details of the root configurations and root canal structure are essential prior to root canal treatment. This study aimed to identify key indicators of pronounced root divergence between the distobuccal and distolingual roots in mandibular first molars by highlighting common features observed in panoramic radiographs. These indicators can help predict the likelihood of encountering significant root divergence before initiating endodontic treatment.

We present three cases in which panoramic radiographs displayed imaging features characteristic of root resorption in the distal root of the mandibular first molars. However, subsequent periapical radiographs in case 1 and cone-beam computed tomography images in cases 2 and 3 revealed that the mandibular first molars were in normal condition, with pronounced root divergence but no evidence of root resorption.

Panoramic radiographs depicting mandibular molar roots with a resorptive and unclear appearance may indicate the presence of severe root divergence. In such cases, we strongly recommend additional cone-beam computed tomographic imaging to ensure precise diagnosis and facilitate optimal treatment planning for endodontic procedures.

In recent years, automated grading of knee osteoarthritis (KOA) has focused on determining disease progression. Clinical examinations and radiographic image review are necessary for diagnosis. Timely and accurate diagnosis, along with medical care, can slow down KOA progression. X-rays and MRI are crucial diagnostic tools. KOA diagnosis traditionally relies on radiologists' and clinicians' experience. However, the rapid development of deep learning technology (AI) offers promising solutions for medical applications.

The objective of this study was to review and summarize various methods proposed by researchers for the automated grading of KOA. Additionally, this study aimed to evaluate the performance of the AlexNet model in classifying the severity of KOA. The performance of the AlexNet model has been compared to that of other models, and the results have been assessed.

A comprehensive review of existing research on automated grading of KOA has been conducted. Various methods proposed by different researchers have been examined and summarized. The AlexNet model has been employed for classifying the severity of KOA, and its performance has been evaluated. A comparative analysis has been carried out to compare the performance of the AlexNet model with that of other models. The results obtained from the evaluation have been assessed to determine the effectiveness of the AlexNet model in the automated grading of KOA.

The results of the study indicate that the AlexNet model demonstrates promising performance in classifying the severity of KOA. Comparative analysis reveals that the AlexNet model outperforms other models in terms of accuracy and efficiency. The evaluation of the model's performance provides valuable insights into the effectiveness of deep learning techniques for automated grading of KOA.

This study highlights the significance of automated grading in the diagnosis and management of knee osteoarthritis. The utilization of deep learning technology, particularly the AlexNet model, shows promise in accurately classifying the severity of KOA. The findings suggest that automated grading methods can serve as valuable tools for healthcare professionals in assessing the progression of KOA and providing appropriate medical care. Further research and development in this area can contribute to enhancing the efficiency and accuracy of automated grading systems for KOA.

The diagnosis and characterization of vertebral compression fractures are very important for clinical management. In this evaluation, which is usually performed with diagnostic (conventional) imaging, the findings are not always typical or diagnostic. Therefore, it is important to have new information to support imaging findings. Texture analysis is a method that can evaluate information contained in diagnostic images and is not visually noticeable. This study aimed to evaluate the magnetic resonance images of cases diagnosed with vertebral compression fractures by the texture analysis method, compare them with histopathological data, and investigate the effectiveness of this method in the differentiation of benign and malignant vertebral compression fractures.

Fifty-five patients with a total of 56 vertebral compression fractures were included in the study. Magnetic resonance images were examined and segmented using Local Image Feature Extraction (LIFEx) software, which is an open-source program for texture analysis. The results were compared with the histopathological diagnosis.

The application of the Decision Tree algorithm to the dataset yielded impressively accurate predictions (≈95% in accuracy, precision, and recall).

Interpreting tissue analysis parameters together with conventional magnetic resonance imaging findings can improve the abilities of radiologists, lead to accurate diagnoses, and prevent unnecessary invasive procedures. Further prospective trials in larger populations are needed to verify the role and performance of texture analysis in patients with vertebral compression fractures.

Whole-body bone scanning is a nuclear medicine technique with high sensitivity used for the diagnosis of bone-related diseases [e.g., bone metastases] that can be obtained by positron emission tomography (PET) or single-photon emission computed tomography[SPECT] imaging, depending on the different radiopharmaceuticals used. In contrast to the high sensitivity of the bone scan, it has low specificity, which leads to misinterpretation, causing adverse effects of unwarranted intervention or interruption to timely treatment.

To address this problem, this paper proposes a joint model called mSegResRF-SPECT, which accomplishes for the first time the task of classifying whole-body bone scan images on a public SPECT dataset [BS-80K] for the diagnosis of bone metastases.

The mSegResRF-SPECT adopts a multi-bone region segmentation algorithm to segment the whole body image into 13 regions, ResNet34 as an extractor to extract the regional features, and a random forest algorithm as a classifier.

The experimental results of the proposed model show that the average accuracy, sensitivity, and F1 score of the model on the BS-80K dataset reached SOTA.

The proposed method presents a promising solution for better bone scan classification methods.

This study explored whether breast MRI manifestations could be used to predict the stroma distribution of breast cancer (BC) and the role of tumor stroma-based MRI manifestations in molecular subtype prediction.

57 patients with pathologically confirmed invasive BC (non-special type) who had lumpy BC on MRI within one week before surgery were retrospectively collected in the study. Stroma distributions were classified according to their characteristics in the pathological sections. The stromal distribution patterns among molecular subtypes were compared with the MRI manifestations of BC with different stroma distribution types (SDTs).

SDTs were significantly different and depended on the BC hormone receptor (HR) (P<0.001). There were also significant differences among five SDTs on T2WI, ADC map, internal delayed enhanced features (IDEF), marginal delayed enhanced features (MDEF), and time signal intensity (TSI) curves. Spiculated margin and the absence of type-I TSI were independent predictors for BC with star grid type stroma. The appearance frequency of hypo-intensity on T2WI in HR- BCs was significantly lower (P=0.043) than in HR+ BCs. Star grid stroma and spiculated margin were key factors in predicting HR+ BCs, and the AUC was 0.927 (95% CI: 0.867-0.987).

Breast MRI can be used to predict BC's stromal distribution and molecular subtypes.

Interstitial lung abnormalities (ILA) are associated with further disease progression, increased mortality risk, and decline in lung function in the elderly, which deserves enough attention.

The objective of this study was to quantify the extent of interstitial lung abnormalities (ILA) in a non-smoking asymptomatic urban cohort in China using low-dose CT (LDCT) and to analyze the age-related pathological changes.

We retrospectively analyzed clinical data and chest LDCT images from a cohort of 733 subjects who were categorized into 3 groups: 18–39, 40-59, and ≥60 years old according to age. Furthermore, we selected 40 cases of wax-embedded lung tissue blocks archived after pulmonary bullectomy and the same age groups were categorized. Four representative CT signs of ILA, including interlobular septal thickening (ILST), intralobular interstitial thickening (ILIT), ground-glass opacity (GGO), and reticular shadow (RS), were semi-quantified based on the percentage of the affected area. The scores and distribution of four CT signs of ILA were compared between different sex and age groups. The age-related pathological changes were analyzed.

The ILA findings were found predominantly in the lower lobes and the subpleural region. The semi-quantitative scores of four CT signs in all subjects under 40 were 0. However, in subjects over 40 years old, the scores gradually increased with age, although most of them remained low. The size of the alveoli increased, the number of alveoli decreased, the alveolar septum became thinner, and the number of ATII cells increased with age. A statistically significant difference was observed among the different age groups (χ2=50.624, P=0.033; χ2=80.000, P=0.043; χ2=33.833, P=0.000; χ2=13.525, P=0.031). The macrophage population and the percentage of collagen fibers in the alveolar septum increased, while the percentage of elastic fibers decreased with age. There was no significant difference among the different age groups (χ2=19.817, P=0.506; χ2=52.419, P=0. 682; χ2=54.868, P=0.518).

When the four CT signs mentioned above are in the upper central area, and the score has a medium or high score, it is crucial to determine the underlying pathological causes. ILA may be the result of chronic lung injury.

Hepatic portal venous gas (HPVG) is very rare; it is associated with multiple gastrointestinal etiologies, with pathophysiology not yet fully understood. It is characteristically fast-progressing and has a high mortality rate. Treatment choice depends on the etiology, including conservative and surgical management.

We report an adult patient (less than 25 years old) of HPVG combined with acute upper gastrointestinal hemorrhage, in which massive gas in the hepatic portal vein system by computed tomography of the abdomen was rapidly dissipated by nasogastric decompression conservative management.

Nasogastric decompression can be an effective treatment approach for HPVG when timely surgical treatment is not required.

Fat-suppressed (FS) T2-weighed turbo spin-echo (TSE) sequence was used to detect the signal of the thymus and the characteristics of the thymus location, measure the two-dimensional diameter at specific levels, and analyze the association with gestational weeks.

This study involved 51 fetal specimens. Post-mortem MRI scanning was implemented with a 3.0-T MRI system. T2-weighted imaging (T2WI) features of the thymus in fetuses were quantitatively investigated with DICOM images. Statistical analysis was done with the Chi-Square test, one-way ANOVA, and Student’s t-test.

There was heterogeneity in the morphology of the fetal thymus. FS T2-weighted TSE sequence clearly exhibited the microstructure of the fetal thymus. The thymus extensively showed a lobulated appearance. The central signal is much higher than the peripheral signal in each lobule. In addition, FS-T2WI images can clearly show the interlobular septum, which is filled with fluid and presents a linear high signal. The signal intensity of fetal thymus increased with gestational weeks. The diameter measured in a particular plane was highly correlated with gestational week.

FS T2-weighted TSE sequence provides high-resolution images of the fetal thymus. The change in signal intensity, location, and two-dimensional diameter in a specific plane can be used as a research direction for the fetal thymus.

Mesenchymal tumours of the bladder are benign but rare occurrences and represent approximately 1% of all bladder tumours.

We report a case of a large bladder leiomyoma in an asymptomatic patient. A large pelvic mass was discovered incidentally on the bedside ultrasound scan during a review at the gynecology clinic. Intra-operatively, no mass was seen in the pelvis, and cystoscopy demonstrated an intravesical mass. It was further evaluated with cystoscopy. MR imaging demonstrated typical features of a bladder leiomyoma. Subsequently, the patient underwent partial cystectomy, and the mass was removed, which was histologically proven leiomyoma.

Awareness of this rare clinical entity and identification of its typical radiological features on MR imaging can aid with accurate diagnosis and preclude unnecessary radical surgery.

The aim of this study was to develop an algorithm model to predict the heat sink effect during thermal ablation of lung tumors and to assist doctors in the formulation and adjustment of surgical protocols.

The heat sink effect is an important factor affecting the therapeutic effect of tumor thermal ablation. At present, there is no algorithm model to predict the intraoperative heat sink effect automatically, which needs to be measured manually, which lacks accuracy and consumes time.

To construct a segmentation model based on a convolutional neural network that can automatically identify and segment pulmonary nodules and vascular structure and measure the distance between the nodule and vascular.

First, the classical Faster RCNN model was used as the nodule detection network. After obtaining the bounding box of pulmonary nodules, the VSPP-NET model was used to segment nodules in the bounding box. The distance from the nodule to the vasculature was measured after the surrounding vasculature was segmented by the VSPP-NET model. The lung CT images of 392 patients with pulmonary nodules were used as the training data for the algorithm. 68 cases were used as algorithm validation data, 29 as nodule algorithm test data, and 80 as vascular algorithm test data. We compared the heat sink effect of 29 cases of data with the results of the algorithm model and expert segmentation and compared the difference between the two results.

In pulmonary CT image vasculature segmentation, the recall and precision of the algorithm model reached >0.88 and >0.78, respectively. The average time for automatic segmentation of each image model is 29 seconds, and the average time for manual segmentation is 158 seconds. The output image of the model shows that the results of nodule segmentation and nodule distance measurement are satisfactory. In terms of heat sink effect prediction, the positive rate of the algorithm group was 28.3%, and that of the expert group was 32.1%, with no significant difference between the two groups (p=0.687).

The algorithm model developed in this study shows good performance in predicting the heat sink effect during pulmonary thermal ablation. It can improve the speed and accuracy of nodule and vessel segmentation, save ablation planning time, reduce the interference of human factors, and provide more reference information for surgeons to make ablation plans to improve the ablation effect.

Currently, coronavirus disease 2019 (COVID-19) continues to remain in the pandemic stage, leading to severe challenges in the global public healthcare system. Magnetic resonance imaging (MRI) methods have played an important role in the diagnosis of COVID-19 and the structural evaluation of the affected organs. Reviewing and summarizing the application of MRI has significant clinical implications for COVID-19. Objective: The study aimed to analyze literature related to the application of MRI in COVID-19 using bibliometric tools, to explore the research status, hotspots, and developmental trends in this field, and to provide a reference for the application of MRI in the clinical diagnosis and evaluation of COVID-19.

We used the Web of Science Core Collection database to search and collect relevant literature on the use of MRI in COVID-19. The authors, institutes, countries, journals, and keyword modules of the bibliometric analysis software CiteSpace and VOSviewer were used to analyze and plot the network map.

A total of 1506 relevant articles were shortlisted through the search; the earliest study was published in 2019, showing an overall upward trend every year. The research was mainly presented as published articles. Clinical neurology was found to be the primary discipline. The United States had the highest publication volume and influence in this field. Countries around the world cooperated more closely. The Cureus Journal of Medical Science was the main periodical to publish articles. Institutes, such as Harvard Medical School, Mayo Clinic, and Massachusetts General Hospital, have published a large number of papers. Some of the high-frequency keywords were “COVID-19”, “SARS-CoV-2”, “magnetic resonance”, “myocarditis”, and “cardiac magnetic resonance imaging”. The keyword clustering study showed that the current research mainly focuses on five “hot” directions.

There is a need to strengthen cross-teamwork and multidisciplinary collaboration in the future to completely explore the positive role of MRI in COVID-19 and to discover breakthroughs for the challenges in the clinical diagnosis and treatment of COVID-19.

Interstitial lung diseases (ILD) encompass various disorders characterized by inflammation and/or fibrosis in the lung interstitium. These conditions produce distinct patterns in High-Resolution Computed Tomography (HRCT).

We employ a deep learning method to diagnose the most commonly encountered patterns in ILD differentially.

Patients were categorized into usual interstitial pneumonia (UIP), nonspecific interstitial pneumonia (NSIP), and normal lung parenchyma groups. VGG16 and VGG19 deep learning architectures were utilized. 85% of each pattern was used as training data for the artificial intelligence model. The models were then tasked with diagnosing the patterns in the test dataset without human intervention. Accuracy rates were calculated for both models.

1 The success of the VGG16 model in the test phase was 95.02% accuracy. 2 Using the same data, 98.05% accuracy results were obtained in the test phase of the VGG19 model.

Deep Learning models showed high accuracy in distinguishing the two most common patterns of ILD.

At present, there are some problems in multimodal medical image fusion, such as texture detail loss, leading to edge contour blurring and image energy loss, leading to contrast reduction.

To solve these problems and obtain higher-quality fusion images, this study proposes an image fusion method based on local saliency energy and multi-scale fractal dimension.

First, by using a non-subsampled contourlet transform, the medical image was divided into 4 layers of high-pass subbands and 1 layer of low-pass subband. Second, in order to fuse the high-pass subbands of layers 2 to 4, the fusion rules based on a multi-scale morphological gradient and an activity measure were used as external stimuli in pulse coupled neural network. Third, a fusion rule based on the improved multi-scale fractal dimension and new local saliency energy was proposed, respectively, for the low-pass subband and the 1^st closest to the low-pass subband. Layer-high pass sub-bands were fused. Lastly, the fused image was created by performing the inverse non-subsampled contourlet transform on the fused sub-bands.

On three multimodal medical image datasets, the proposed method was compared with 7 other fusion methods using 5 common objective evaluation metrics.

Experiments showed that this method can protect the contrast and edge of fusion image well and has strong competitiveness in both subjective and objective evaluation.

Secondary cardiac tumors are a rare disease that is hard to detect when the tumor is small and asymptomatic. This case report focuses on a massive pulmonary metastasis filling almost the entire left atrium. Multimodal enhancement imaging, cardiac contrast-enhanced ultrasound (CEUS), enhanced electron computed tomography, and positron emission tomography imaging were applied to detect the malignant origin of this case. The aim of this project was to provide an important basis for clinical treatment and decision-making with multimodal imaging.

The patient was hospitalized with suspected to be a lumbar spine fracture. According to the multimodal imaging, pathologically confirmed to suffer a cardiac metastasis from small cell lung cancer. EP-regimen (Etoposide 0.1gd 1-5+Nedaplatin 30mgd 1-4) was selected for the systemic chemotherapy of the patient. During three years of follow-up, the left intra-atrial occupancy was significantly reduced.

Multimodality imaging can cover up the deficiencies of single imaging examinations and further clarify and enrich the understanding of the relationship between the location and the surrounding structure of the mass, thus providing a good reference for clinical treatment and decision-making.

Nowadays, High Intensity Focused Ultrasound (HIFU) is a common surgery option for the treatment of uterine fibroids in China, the immediate response of which is clinically evaluated using Contrast Enhanced (CE) imaging. However, the injection of gadolinium with its potential adverse effect is of concern in CE and therefore, it deserves efforts to find a better imaging method without the need for contrast agent injection for this task.

To assess the role of Diffusion-weighted Imaging (DWI) in evaluating the immediate therapeutic response of HIFU treatment for uterine fibroids in comparison with CE.

68 patients with 74 uterine fibroids receiving HIFU treatment were enrolled, and immediate treatment response was assessed using post-surgical DWI images. Semi-quantitative ordinal ablation quality grading and quantitative nonperfusion volume (NPV) measurement based on DWI and CE imaging were determined by two experienced radiologists. Agreement of ablation quality grading between DWI and CE was assessed using the weighted kappa coefficient, while intraobserver, interobserver and interprotocol agreements of NPV measurements within and between DWI and CE were evaluated using the intraclass correlation (ICC) and Bland-Altman analysis.

Grading of immediate HIFU treatment response showed a moderate agreement between DWI and CE (weighted kappa = 0.446, p < 0.001). NPV measured in 65 fibroids with DWI of Grade 3~5 showed very high ICCs for the intraobserver and interobserver agreement within DWI and CE (all ICC > 0.980, p < 0.001) and also for the interprotocol agreement between DWI and CE (ICC = 0.976, p < 0.001).

DWI could provide satisfactory ablation quality grading, and reliable NPV quantification results to assess immediate therapeutic responses of HIFU treatment for uterine fibroids in most cases, which suggests that non-contrast enhanced DWI might be potentially used as a more cost-effective and convenient method in a large proportion of patients for this task replacing CE imaging.