Current Medical Imaging - Volume 20, Issue 1, 2024

Although clinical assessment has historically been the primary method used for diagnosing and staging pediatric localized scleroderma (LS), high-frequency ultrasonography (HFUS) is being investigated as a more accurate method for evaluating lesions.

This study aimed to assess, compare dermal and subcutaneous tissue characteristics and enhance lesion staging in pediatric LS patients using HFUS.

Twenty two LS patients were cross-sectionally evaluated with B-mode ultrasonography. Lesions were clinically staged, and dermal and subcutaneous tissue characteristics were compared with healthy tissue using HFUS.

Among 55 lesions, 27 were active/new (49.1%), and 28 were atrophic/old (50.9%). Active lesions typically had increased dermal thickness in 66.6% of cases, while atrophic lesions often showed decreased dermal thickness (78.5%), with significant differences (p<0.05). Dermal echogenicity decreased in 40.7% of active lesions but remained largely unchanged in atrophic lesions (82.1%) (p<0.05). Subcutaneous tissue thickness significantly decreased in atrophic lesions (78.5%) and increased in 59.2% of active lesions, with a significant difference (p = 0.002). Subcutaneous tissue echogenicity increased in 44.4% of active lesions and remained mostly unchanged in atrophic lesions (67.8%). Importantly, a considerable proportion of lesions diagnosed as active through physical examination were actually inactive on HFUS evaluation (55.6%), while a significant portion of lesions categorized as atrophic on physical examination displayed areas of inactivity upon ultrasonographic assessment (35.7%). These findings highlight HFUS's potential as a valuable diagnostic tool and reveal discordances between clinical and HFUS staging.

Ultrasonography offers an objective LS lesion evaluation, especially in pediatrics.

Evidence of the association between obesity and renal cell carcinoma progression is contradictory. The effects of renal cell carcinoma on fat distribution are still unknown.

The goal of this study was to determine the ability of various forms of fat deposition to predict the Fuhrman nuclear grade of clear cell renal cell carcinoma [ccRCC].

This retrospective study included 320 patients with pathologically proven ccRCC [215 men and 105 women; 263 low-grade ccRCC and 57 high-grade ccRCC]. Based on computed tomography scans, adipose tissue in various body regions was classified into the perirenal fat area [PFA], visceral fat area [VFA], total fat area [TFA], subcutaneous fat area [SFA], and hepatic steatosis [HS]. Subsequently, the relative VFA [rVFA] was computed. Age, sex, body mass index, and maximal tumor diameter were also regarded as clinical factors. Univariate and multivariate logistic regression studies were conducted to evaluate whether there was an association between body fat composition and the Fuhrman classification and whether it was related to gender.

After correcting for age, males with low-grade ccRCC exhibited higher TFA [257.6 vs. 203.0, p = 0.002], VFA [151.6 vs.115.5, p = 0.007], SFA [106.0 vs. 87.5, p = 0.015], PFA [55.1 vs. 30.4, p < 0.001], and HS [18% vs. 0%, p = 0.031] than those with high-grade ccRCC. There was no significant difference among rVFA in males. In females, there was no significant difference in any of the parameters. VFA and PFA remained independent predictors for high-grade ccRCC in males in both the monovariate [VFA: odds ratio [OR] 0.992, 95% confidence interval [CI] 0.987–0.997, p = 0.004; PFA: OR 0.949, 95% CI 0.930–0.970, p < 0.001] and multivariate [VFA: OR 1.028, 95% CI 1.001–1.074, p < 0.001; PFA: OR 0.878, 95% CI 0.833–0.926, p < 0.001] models.

Gender-specific adipose tissue in different locations demonstrated varied values for predicting high-grade ccRCC and may be utilized as an independent predictor of high-grade ccRCC in male patients.

Angiomatoid fibrous histiocytoma (AFH) is a borderline tumor usually affecting the the children or young adults. ¹⁸F-Fluorodexoyglucose (FDG) positron emission tomography/computed tomography (PET/CT) investigations of pulmonary AFH are rare, and there are currently no reports of intense FDG uptake in AFH.

We report an AFH that occurred in the lung of a 57-year-old woman. She presented with paroxysmal cough and occasional bloodshot sputum. ¹⁸F-FDG PET/CT revealed a right parahilar nodule with intense FDG-avidity, middle lobe atelectasis, and several bilateral axillary lymph nodes with mild hypermetabolic activity. This patient underwent a right middle lobe lobectomy via video-assisted thoracoscopy. Histopathologically, the diagnosis was pulmonary AFH. She had an uneventful postoperative course, and the bilateral axillary lymph nodes regressed during postoperative follow-up.

The clinical presentation and image findings of patients with primary pulmonary AFH may be potential diagnosis pitfalls. The diagnosis of lymph nodes or distant metastases should be approached with caution. To avoid misdiagnosis, biopsy with histological examination and immunohistochemichal staining should be performed as early as possible.

Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning to expedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical image data to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatment of patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional Neural Network (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology.

In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal color fundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) the relative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model to serve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse disease manifestations.

We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted in significantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract, glaucoma, diabetic retinopathy.

The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.

The growing rate of breast cancer necessitates immediate global attention. Mammography images are used to determine the stage of malignancy. Breast cancer stages must be identified in order to save a person's life.

This article's main goal is to identify different techniques to obtain the difference between two breast cancer mammography images taken of the same individual at different times. This is the first effort to identify breast cancer in mammography images using change detection techniques. The Mammogram Image Change Detection (ICD) technique is also a recent advancement to prevent breast cancer in the early stage and precancerous level in medical images.

The main purpose of this work is to observe the changes between breast cancer images in different screening periods using different techniques. Mammogram Breast Cancer Image Change Detection (MBCICD) methods usually start with a Difference Image (DI) and classify the pixels in the DI into changed and unaffected classes using unsupervised fuzzy c means (FCM) clustering methods based on texture features taken from the log and mean ratio difference pictures. Two operators, mean ratio and log ratio, were used to check the changes in the images. The Gabor wavelet is utilized as a feature extraction technique among several standards. Using the Gabor wavelet ratio operators is a useful method for altering the detection of breast cancer in mammography images. Currently, it is challenging to obtain real malignant images of the same person for testing or training. In this study, two images are utilized. To clearly see the changes, one is an image from the MIAS breast cancer mammography images dataset, and the other is a self-generated change image.

The research aims to examine the image results and other quantitative analysis results of proposed change detection methods on cancer images. The Mean Ratio Accuracy result is 0.9738, and the Log ratio PCC is 0.9737. The classification results are the Log Ratio + Gabor Filter + FCM is 0.9737, and Mean Ratio +Gabor Filter + FCM is 0.9719. The mean Ratio Accuracy result is 0.9738, Log ratio is 0.9737. Log Ratio + Gabor Filter + FCM is 0.9737, Mean Ratio +Gabor Filter + FCM is 0.9719. Comparing the PCC of proposed change detection methods with the FDA-RMG method on the same dataset, the accuracy is 0.9481 only.

The study concludes that variations in mammography breast cancer images could be successfully identified using the ratio operators with Gabor wavelet features.

To investigate the magnetic resonance imaging (MRI) radiomics models in evaluating the human epidermal growth factor receptor 2(HER2) expression in breast cancer.

The MRI data of 161 patients with invasive ductal carcinoma (non-special type) of breast cancer were retrospectively collected, and the MRI radiomics models were established based on the MRI imaging features of the fat suppression T2 weighted image (T2WI) sequence, dynamic contrast-enhanced (DCE)-T1WIsequence and joint sequences. The T-test and the least absolute shrinkage and selection operator (LASSO) algorithm were used for feature dimensionality reduction and screening, respectively, and the random forest (RF) algorithm was used to construct the classification model.

The model established by the LASSO-RF algorithm was used in the ROC curve analysis. In predicting the low expression state of HER2 in breast cancer, the radiomics models of the fat suppression T2WI sequence, DCE-T1WI sequence, and the combination of the two sequences showed better predictive efficiency. In the receiver operating characteristic (ROC) curve analysis for the verification set of low, negative, and positive HER2 expression, the area under the ROC curve (AUC) value was 0.81, 0.72, and 0.62 for the DCE-T1WI sequence model, 0.79, 0.65 and 0.77 for the T2WI sequence model, and 0.84, 0.73 and 0.66 for the joint sequence model, respectively. The joint sequence model had the highest AUC value.

The MRI radiomics models can be used to effectively predict the HER2 expression in breast cancer and provide a non-invasive and early assistant method for clinicians to formulate individualized and accurate treatment plans.

Dermatofibrosarcoma Protuberans (DFSP) is a rare soft tissue sarcoma, accounting for approximately 1% of all tumors; however, DFSP of the breast is extremely rare. Moreover, DFSP generally has a low malignant potential and is characterized by a high rate of local recurrence along with a small but definite risk of metastasis. The risk of metastasis is higher in fibrosarcomatous transformation in DFSP than in ordinary DFSP.

We have, herein, reported a case of a 61-year-old male patient with fibrosarcomatous transformation in DFSP. Preoperative Dynamic Contrast-enhanced Magnetic Resonance Imaging (DCE-MRI) of the breast revealed an oval-shaped mass with heterogeneous internal enhancement, a large vessel embedded within, and a washout curve pattern on kinetic curve analysis. The mass exhibited a hyperintense signal on Diffusion-weighted Imaging (DWI), with a low apparent diffusion coefficient value. Histologically, the bland spindle tumor cells were arranged in a storiform pattern. Areas with the highest histological grade demonstrated increased cellularity, cytological atypia, and mitotic activity. Immunohistochemically, Ki-67 and p53 were highly expressed.

Recognizing the risk and accurately diagnosing fibrosarcomatous transformation in male breast DFSP are critical for improving prognosis and establishing appropriate treatment and follow-up plans. This emphasizes the significance of combining immunohistopathological features with DCE-MRI and DWI to assist clinicians in the early and accurate diagnosis of sarcomas arising from male breast DFSP.

To develop and evaluate machine learning models using tumor and nodal radiomics features for predicting the response to neoadjuvant chemotherapy (NAC) and recurrence risk in locally advanced gastric cancer (LAGC).

Early and accurate response prediction is vital to stratify LAGC patients and select proper candidates for NAC.

A total of 218 patients with LAGC undergoing NAC followed by gastrectomy were enrolled in our study and were randomly divided into a training cohort (n = 153) and a validation cohort (n = 65).

We extracted 1316 radiomics features from the volume of interest of the primary lesion and maximal lymph node on venous phase CT images. We built 3 radiomics signatures for distinguishing good responders and poor responders based on tumor radiomics (TR), nodal radiomics (NR), and a combination of the two (TNR), respectively. A nomogram was then developed by integrating the radiomics signature and clinical factors. Kaplan-Meier survival curves were used to evaluate the prognostic value of the nomogram.

The TNR signature achieved improved predictive value, with AUCs of 0.755 and 0.744 in the training and validation cohorts. Our proposed nomogram model (TNRN) showed a good performance for GR prediction in the prediction efficacy, calibration ability, and clinical benefit, with AUCs of 0.779 and 0.732 in the training and validation cohorts, superior to the clinical model. Moreover, the TNRN could accurately classify the patients into high-risk and low-risk groups in both training and validation cohorts with regard to postoperative recurrence and metastasis.

The TNRN performed well in identifying good responders and provided valuable information for predicting progression-free survival time (PFS) in patients with LAGC who underwent NAC.

To explore the potential of diffusion kurtosis imaging (DKI) for assessing the degree of liver injury in a paracetamol-induced rat model and to simultaneously investigate the effect of intravenous gadoxetate on DKI parameters.

Paracetamol was used to induce hepatoxicity in 39 rats. The rats were pathologically classified into 3 groups: normal (n=11), mild necrosis (n=18), and moderate necrosis (n=10). DKI was performed before and, 15 min, 25 min, and 45 min after gadoxetate administration. Repeated-measures ANOVA with Tukey’s multiple comparison test was used to investigate the effect of gadoxetate on mean diffusivity (MD) and mean diffusion kurtosis (MK) and to assess the differences in MD and MK among the three groups. A receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic accuracy of the MD values when discriminating between the necrotic groups.

Gadoxetate had no significant effect on either the MD or the MK, and the effect size was small. The MD in the moderate necrosis group was significantly lower than that in the other two groups (F = 13.502, p <0.001; η² = 0.428 [95% CI: 0.082-0.637]), while the MK did not significantly differ among the three groups (F = 2.702, p = 0.081; η² = 0.131 [95% CI: 0.001-0.4003]). The AUCs of MD for discriminating the moderate necrosis or normal group from the other groups were 0.921 (95% CI: 0.832-1.000) and 0.831 (95% CI: 0.701-0.961), respectively.

It would be better to measure the MD and MK before gadoxetate injection. MD showed potential for assessing the degree of liver necrosis in a paracetamol-induced liver injury rat model.

This study aims to develop an ultrasomics model for predicting lymph node metastasis in patients with gastric cancer (GC).

This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software. The Z-score algorithm was used for feature normalization, followed by the Wilcoxon test to identify the most informative features. Linear prediction models were constructed using the least absolute shrinkage and selection operator (LASSO). The performance of the ultrasomics model was evaluated using the area under curve (AUC), sensitivity, specificity, and the corresponding 95% confidence intervals (CIs).

A total of 464 GC patients (mean age: 60.4 years ±11.3 [SD]; 328 men [70.7%]) were analyzed, of whom 291 had lymph node metastasis. The patients were randomly assigned to either the training (n=324) or test (n=140) sets, using a 7:3 ratio. An ultrasomics model that consisted of 19 radiomics features was developed using Wilcoxon and LASSO algorithms in the training set. Our ultrasomics model showed moderate performance for lymph node metastasis prediction in both the training (AUC: 0.802, 95% CI: 0.752-0.851, P<0.001) and test sets (AUC: 0.802, 95% CI: 0.724-0.879, P<0.001). The calibration curve analysis indicated good agreement between the predicted probabilities of ultrasomics and actual lymph node metastasis status.

Our study highlights the potential of a machine learning-based ultrasomics model in predicting lymph node metastasis in GC patients, offering implications for personalized therapy approaches.

Idiopathic Sudden Sensorineural Hearing Loss (ISSNHL) is related to alterations in brain cortical and subcortical structures, and changes in brain functional activities involving multiple networks, which is often accompanied by tinnitus. There have been many in-depth research studies conducted concerning ISSNHL. Despite this, the neurophysiological mechanisms of ISSNHL with tinnitus are still under exploration.

The study aimed to investigate the neural mechanism in ISSNHL patients with tinnitus based on the alterations in intra- and inter-network Functional Connectivity (FC) of multiple networks.

Thirty ISSNHL subjects and 37 healthy subjects underwent resting-state functional Magnetic Resonance Imaging (rs-fMRI). Independent Component Analysis (ICA) was used to identify 8 Resting-state Networks (RSNs). Furthermore, the study used a two-sample t-test to calculate the intra-network FC differences, while calculating Functional Network Connectivity (FNC) to detect the inter-network FC differences.

By using the ICA approach, tinnitus patients with ISSNHL were found to have FC changes in the following RSNs: CN, VN, DMN, ECN, SMN, and AUN. In addition, the interconnections of VN-SMN, VN-ECN, and ECN-DAN were weakened.

The present study has demonstrated changes in FC within and between networks in ISSNHL with tinnitus, providing ideas for further study on the neuropathological mechanism of the disease.

In this study, a radiomics model was created based on High-Resolution Computed Tomography (HRCT) images to noninvasively predict whether the sub-centimeter pure Ground Glass Nodule (pGGN) is benign or malignant.

A total of 235 patients (251 sub-centimeter pGGNs) who underwent preoperative HRCT scans and had postoperative pathology results were retrospectively evaluated. The nodules were randomized in a 7:3 ratio to the training (n=175) and the validation cohort (n=76). The volume of interest was delineated in the thin-slice lung window, from which 1316 radiomics features were extracted. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to select the radiomics features. Univariate and multivariable logistic regression were used to evaluate the independent risk variables. The performance was assessed by obtaining Receiver Operating Characteristic (ROC) curves for the clinical, radiomics, and combined models, and then the Decision Curve Analysis (DCA) assessed the clinical applicability of each model.

Sex, volume, shape, and intensity mean were chosen by univariate analysis to establish the clinical model. Two radiomics features were retained by LASSO regression to build the radiomics model. In the training cohort, the Area Under the Curve (AUC) of the radiomics (AUC=0.844) and combined model (AUC=0.871) was higher than the clinical model (AUC=0.773). In evaluating whether or not the sub-centimeter pGGN is benign, the DCA demonstrated that the radiomics and combined model had a greater overall net benefit than the clinical model.

The radiomics model may be useful in predicting the benign and malignant sub-centimeter pGGN before surgery.

This study aimed to evaluate the diagnostic value of X-Map reconstruction based on Dual-Energy Computed Tomography (DECT) in acute ischemic stroke (AIS).

Sixty-six cases of suspected AIS patients hospitalized from November, 2021 to April, 2022 were retrospectively selected. DECT, Computed Tomography Perfusion imaging (CTP), Computed Tomography Angiography (CTA), and MRI were all performed within 24 hours after symptom onset. As the gold standard for diagnosing AIS, a total of 53 patients were diagnosed with AIS based on the diffusion-weighted imaging positive results in MRI. The Chi-square test was used to evaluate the diagnostic efficacy of AIS among X-Map, CTP, and CTA.

In the 53 patients with confirmed ASI, a total of 72 lesions were detected, including in the frontal lobes (n=33), parietal lobes (n=7), temporal lobes (n=12), basal ganglia regions (n=12), thalamus (n=3), and pons (n=5). The case detection rate of X-Map for AIS was similar to that of CTP (p=0.151) but was significantly higher than that of CTA (p<0.001). In terms of diagnostic efficacy, among the total 66 patients enrolled, X-Map achieved a higher diagnostic sensitivity (85%) than CTP and CTA. However, CTP achieved the best diagnostic specificity (84.6%) and diagnostic accuracy (77.4%) among the diagnostic tools used.

X-Map provides a better or equal clinical value for the diagnosis of AIS as compared to CTA and CTP, respectively, highlighting its potential in clinical applications.

Ultrasound-guided microwave ablation (MWA) is recommended as a first-line treatment for early liver cancer due to its minimally invasive, efficient, and cost-effective nature. It utilizes microwave radiation to heat and destroy tumor cells as a local thermal therapy and offers the benefits of being minimally invasive, repeatable, and applicable to tumors of various sizes and locations. However, despite the efficacy of MWA, early recurrence after treatment remains a challenge, particularly when it occurs within a year and has a significant impact on the prognosis of the patient.

This study aimed to identify the risk factors for early recurrence after MWA in patients with hepatocellular carcinoma (HCC) and establish a predictive model.

A total of 119 patients with hepatocellular carcinoma (HCC) treated in the Department of Ultrasound at the First Affiliated Hospital of the Air Force Medical University from January, 2020 to April, 2022 were included in this study. Patients were categorized into the early recurrence group and the non-early recurrence group based on whether recurrence occurred within 1 year. We conducted univariate analysis on 29 variables. A predictive model was developed using multiple-factor logistic regression analysis, and a risk column graph was created.

A total of 28 patients were included in the early recurrence group, with an early recurrence rate of 23%. Tumor size ≥ 3cm, multiple tumors, AST > 35 U/L, low pathological differentiation, CD34 positive, Ki67 level, quantitative parameters mean transit time (mTT), and rise time (RT) were confirmed as risk factors affecting early recurrence after ablation (P < 0.05). Furthermore, the model constructed based on these 5 predictive factors, including tumor size, tumor number, pathological differentiation, CD34, and quantitative analysis parameter mTT, demonstrated good predictive ability, with an AUC of 0.93 in the training set and 0.86 in the validation set.

Our research indicates that the risk column graph can be utilized to predict the risk of early postoperative recurrence in patients after MWA. This contributes to guiding personalized clinical treatment decisions and provides important references for improving the prognosis of patients.

Post COVID-19, everyone needs to be aware of health. The condition of the human body is judged based on various health reports like X-ray, CT scan and MRI scan. Due to misplacement or loss of medical reports, there lies a high chance of improper diagnosis.

In order to avoid improper diagnosis, a novel data-hiding technique is proposed in this work. In the proposed method, the patient’s health records are hidden using polynomial theory in the patient photograph. This is used by doctors in telemedicine for better treatment at the right time. Image steganography is useful for hiding secret images and also for generating secret keys. This enables only the authorized people (patient and corresponding doctor) to access the reports using secret keys.

Four secret images (medical reports of the patient) are successfully embedded onto a single cover image (patient photo) with good quality. After embedding, the stego images look like cover images so that unauthorized persons will not be able to access the data, and hence, safe transmission is being carried out.

A patient's medical report plays an important role in proper medical treatment. Particularly in telemedicine, the safe transmission of patient reports without any loss or damage is necessary. The proposed method embeds reports of a patient in his/her photo and transmits them to the destination safely with a quality of 45.5 dB. This hiding method is helpful to avoid cyber crimes, illegal transactions, malpractices etc.

Accurately predicting the hepatocellular carcinoma (HCC) grade may facilitate the rational selection of treatment strategies. The diagnostic efficacy of the combination of Gadolinium ethoxybenzy diethylenetriamine pentaacetic (Gd-EOB-DTPA) enhancement T1 mapping and apparent diffusion coefficient (ADC) values in predicting HCC grade needs further validation.

This study aimed to assess the capacity of Gd-EOB-DTPA-enhanced T1 mapping and ADC values, both individually and in combination, to discriminate between different grades of HCC.

From July 2017 to February 2020, 96 patients (male, 83; mean age, 53.67 years; age range, 29-71 years) clinically diagnosed with HCC were included in the present study. All patients underwent Gd-EOB-DTPA-enhanced magnetic resonance imaging (MRI, including T1 mapping sequence) before surgery or biopsy. All the patients were categorized into 3 groups according to the pathological results (including 24 cases of well-differentiated HCCs, 59 cases of moderately differentiated HCCs, 13 cases of and poorly differentiated HCCs). The mean Gd-EOB-DTPA enhanced T1 values (∆T1=[(T1pre-T1post)/T1pre]×100%) and ADC values between different grading groups of HCC were calculated and compared. The area under the characteristics curve (AUC), the diagnostic threshold, sensitivity, and specificity of ΔT1 and ADC for differential diagnosis were analyzed.

Mean ∆T1 was 58% for well-differentiated HCCs, 50% for moderately-differentiated HCCs, and 43% for poorly-differentiated HCCs. ∆T1 showed statistical differences between the groups (P<0.001). The mean ADC values of the 3 groups were 1.11×10−3 mm2/s, 0.91×10−3 mm2/s, and 0.80×10−3mm2/s, respectively. ADC showed statistical differences between the groups (P<0.001). In discriminating well- differentiated group from the moderately differentiated group, the AUC of ∆T1 was 0.751 (95% CI: 0.642, 0.859), the AUC of ADC was 0.782 (95% CI: 0.671, 0.894), the AUC of combined model was 0.811 (95% CI: 0.709, 0.914). In discriminating the poorly differentiated group from the moderately differentiated group, the AUC of ∆T1 was 0.768 (95% CI: 0.634, 0.902), the AUC of ADC was 0.754 (95% CI: 0.603, 0.904), and the AUC of the combined model was 0.841 (95% CI: 0.729, 0.953).

Gd-EOB-DTPA enhanced T1 mapping, and ADC values have complementary effects on the sensitivity and specificity for identifying different HCC grades. A combined model of Gd-EOB-DTPA-enhanced MRI T1 mapping and ADC values could improve diagnostic performance for predicting HCC grades.

The aim of the study was to develop deep-learning neural networks to guide treatment decisions and for the accurate evaluation of tumor response to neoadjuvant chemoradiotherapy (nCRT) in rectal cancer using magnetic resonance (MR) images.

Fifty-nine tumors with stage 2 or 3 rectal cancer that received nCRT were retrospectively evaluated. Pathological tumor regression grading was carried out using the Dworak (Dw-TRG) guidelines and served as the ground truth for response predictions. Imaging-based tumor regression grading was performed according to the MERCURY group guidelines from pre-treatment and post-treatment para-axial T2-weighted MR images (MR-TRG). Tumor signal intensity signatures were extracted by segmenting the tumors volumetrically on the images. Normalized histograms of the signatures were used as input to a deep neural network (DNN) housing long short-term memory (LSTM) units. The output of the network was the tumor regression grading prediction, DNN-TRG.

In predicting complete or good response, DNN-TRG demonstrated modest agreement with Dw-TRG (Cohen’s kappa= 0.79) and achieved 84.6% sensitivity, 93.9% specificity, and 89.8% accuracy. MR-TRG revealed 46.2% sensitivity, 100% specificity, and 76.3% accuracy. In predicting a complete response, DNN-TRG showed slight agreement with Dw-TRG (Cohen’s kappa= 0.75) with 71.4% sensitivity, 97.8% specificity, and 91.5% accuracy. MR-TRG provided 42.9% sensitivity, 100% specificity, and 86.4% accuracy. DNN-TRG benefited from higher sensitivity but lower specificity, leading to higher accuracy than MR-TRG in predicting tumor response.

The use of deep LSTM neural networks is a promising approach for evaluating the tumor response to nCRT in rectal cancer.

This study aimed to investigate the pancreatic morphology and clinical characteristics to predict risk factors of type 2 diabetes mellitus (T2DM) based on magnetic resonance imaging.

A total of 89 patients (T2DM group) and 68 healthy controls (HC group) were included. The T2DM group was divided into a long-term T2DM group and a short-term T2DM group according to whether the illness duration was more than 5 years. The clinical characteristics were collected, including sex, age, fasting plasma glucose, glycosylated hemoglobin, and lipoproteins. The pancreatic morphological characteristics, including the diameters of the pancreatic head, neck, body, and tail, the angle of the pancreaticobiliary junction (APJ), and the types of pancreaticobiliary junction were measured. The risk prediction model was established by logistic regression analysis.

In the long-term T2DM group, the pancreatic diameters were smaller than the other two groups. In the short-term T2DM group, the diameters of the pancreatic tail and body were smaller than the HC group. The APJ, very low-density lipoprotein, and triglyceride levels in the two T2DM groups were greater than the HC group, and the APJ of the short-term T2DM group was smaller than the long-term T2DM group. Pancreatic diameters showed a negative correlation with illness duration. Logistic regression analysis revealed pancreatic body diameter was a protective factor, and APJ was a risk factor for T2DM. Prediction model accuracy was 90.20%.

The morphology of the pancreas is helpful to predict the risk of the onset of T2DM. The risk of onset of T2DM increases with smaller pancreatic body diameter and higher APJ.

Congenital ileal atresia is a rare neonatal disease, the most common type of intestinal malformation in newborns, and one of the most common causes of congenital intestinal obstruction. It can cause various digestive system symptoms, including abdominal distension, vomiting, abnormal bowel movements, etc. In severe cases, it can be life-threatening. A prenatal ultrasound examination can assist clinical diagnosis of congenital ileal atresia, and those with a clear prenatal diagnosis should undergo surgical treatment after birth.

We have, herein, reported two cases of congenital ileal atresia, both of which showed fetal intestinal dilation (>7mm) and excessive amniotic fluid on prenatal ultrasound. Both newborns underwent surgical treatment after delivery and were confirmed to have congenital ileal atresia during surgery. Due to the different prenatal ultrasound manifestations of the two patients, they were divided into two different subtypes based on intraoperative manifestations. We observed significant differences in the prognosis of the two patients after surgery.

Accurately locating and classifying ileal atresia using prenatal ultrasound is challenging; however, it plays an effective role in disease progression, gestational assessment, and prognosis. Accurately identifying intestinal diseases and/or the location of lesion sites through direct and indirect ultrasound findings in the fetal abdominal cavity is an important research direction for prenatal ultrasound.

To investigate the optimal B1,rms value of renal amide proton transfer-weighted (APTw) images and the reproducibility of this value, and to explore the utility of APT imaging of renal masses and kidney tissues.

APTw images with different B1,rms values were repeatedly recorded in 15 healthy volunteers to determine the optimal value. Two 4-point Likert scales (poor [1] to excellent [4]) were used to evaluate contour clarity and artifacts in masses and normal tissues. The APTw values of masses and normal tissues were then compared in evaluable images (contour clarity score > 1, artifacts score > 1). The APTw of malignant masses, normal tissues, and benign masses were calculated and compared with the Mann-Whitney U test.

The optimal scanning parameter of B1,rms was 2 μT, and the APTw images had good agreement in the volunteers. Our study of APTw imaging examined 70 renal masses (13 benign, 57 malignant) and 49 normal kidneys (including those from 15 healthy volunteers). The mean APTw value for renal malignant masses (2.28(1.55)) was different from that for benign masses (0.91(1.30)) (P<0.001), renal cortex (1.30 (1.25)) (P<0.001), renal medulla (1.64 (1.33)) (P<0.05), and renal pelvis (5.49 (2.65)) (P<0.001).

These preliminary data demonstrate that APTw imaging of the kidneys has potential use as an imaging biomarker for the differentiation of normal tissues, malignant masses, and benign masses.