SDS-Net: A lightweight 3D convolutional neural network with multi-branch attention for multimodal brain tumor accurate segmentation

The accurate and fast segmentation method of tumor regions in brain Magnetic Resonance Imaging (MRI) is significant for clinical diagnosis, treatment and monitoring, given the aggressive and high mortality rate of brain tumors. However, due to the limitation of computational complexity, convolutional neural networks (CNNs) face challenges in being efficiently deployed on resource-limited devices, which restricts their popularity in practical medical applications. To address this issue, we propose a lightweight and efficient 3D convolutional neural network SDS-Net for multimodal brain tumor MRI image segmentation. SDS-Net combines depthwise separable convolution and traditional convolution to construct the 3D lightweight backbone blocks, lightweight feature extraction (LFE) and lightweight feature fusion (LFF) modules, which effectively utilizes the rich local features in multimodal images and enhances the segmentation performance of sub-tumor regions. In addition, 3D shuffle attention (SA) and 3D self-ensemble (SE) modules are incorporated into the encoder and decoder of the network. The SA helps to capture high-quality spatial and channel features from the modalities, and the SE acquires more refined edge features by gathering information from each layer. The proposed SDS-Net was validated on the BRATS datasets. The Dice coefficients were achieved 92.7, 80.0 and 88.9% for whole tumor (WT), enhancing tumor (ET) and tumor core (TC), respectively, on the BRTAS 2020 dataset. On the BRTAS 2021 dataset, the Dice coefficients were 91.8, 82.5 and 86.8% for WT, ET and TC, respectively. Compared with other state-of-the-art methods, SDS-Net achieved superior segmentation performance with fewer parameters and less computational cost, under the condition of 2.52 M counts and 68.18 G FLOPs.

EBV-ENCEPHALITIS IN CHILDREN: DIAGNOSTIC CRITERIA

OBJECTIVE

The aim: To investigate the clinical characteristics of EBV infection in the pediatric nervous system using laboratory methods and brain MRI data.

PATIENTS AND METHODS

Materials and methods: We observed 41 children with EBV encephalitis ranging from 8 months to 17 years old. The diagnosis of EBV-encephalitis was established on the basis of clinical and medical history, laboratory and instrumental (brain MRI) data. The main thing in the diagnosis was clinical symptoms, combining general infection, cerebral syndromes and focal neurological symptoms. The etiology of Epstein-Barr virus was determined using ELISA and PCR.

RESULTS

Results: EBV-encephalitis can be as a manifestation of reactivation of persistent EBV infection (85%), much less often - acute primary EBV infection (15%). By nature, the duration of EBV encephalitis has distinguished two forms of its course: acute (63%) and chronioc (37%). The criteria of differential diagnosis of acute and chronic forms of EBV-encephalitis are proposed, which include the most common anamnesis data, clinical manifestations and changes in brain MRI.

CONCLUSION

Conclusions: The proposed criteria specifically for acute and chronic forms of EBV-encephalitis can contribute to the timely and more accurate diagnosis of this disease in children.

Multi-modal brain MRI images enhancement based on framelet and local weights super-resolution

Magnetic resonance (MR) image enhancement technology can reconstruct high-resolution image from a low-resolution image, which is of great significance for clinical application and scientific research. T1 weighting and T2 weighting are the two common magnetic resonance imaging modes, each of which has its own advantages, but the imaging time of T2 is much longer than that of T1. Related studies have shown that they have very similar anatomical structures in brain images, which can be utilized to enhance the resolution of low-resolution T2 images by using the edge information of high-resolution T1 images that can be rapidly imaged, so as to shorten the imaging time needed for T2 images. In order to overcome the inflexibility of traditional methods using fixed weights for interpolation and the inaccuracy of using gradient threshold to determine edge regions, we propose a new model based on previous studies on multi-contrast MR image enhancement. Our model uses framelet decomposition to finely separate the edge structure of the T2 brain image, and uses the local regression weights calculated from T1 image to construct a global interpolation matrix, so that our model can not only guide the edge reconstruction more accurately where the weights are shared, but also carry out collaborative global optimization for the remaining pixels and their interpolated weights. Experimental results on a set of simulated MR data and two sets of real MR images show that the enhanced images obtained by the proposed method are superior to the compared methods in terms of visual sharpness or qualitative indicators.

PERSONIFICATION OF VISUAL DIAGNOSTIC METHODS IN WOMEN WITH SUBMUCOSAL UTERINE FIBROIDS: A RETROSPECTIVE CLINICAL ANALYSIS

OBJECTIVE

The aim: To determine the parameters of perioperative application of radiographic methods for visual diagnosis in women with submucous uterine fibroids.

PATIENTS AND METHODS

Materials and methods: We conducted a retrospective analysis of the data from 200 medical records of women with submucous uterine fibroids (SUF).

RESULTS

Results: Preoperatively, nodes were diagnosed by ultrasound as follows: solitary nodes - SM0 type - 65 (46%) near the fundus; SMІ - 41 (29%) on the anterior or posterior wall; SMІІ - 35 (25%) on the lateral walls of the uterus and in the cornual areas of the fallopian tubes; multiple in combinations: О3-4 / SMІ - 16 (27.0%) and О3-6 / SMІІ - 14 (24.0%); with localization: О3-4 / SM0 - mainly in the fundus - 49%, О3-4 / SMІ and О3-4 / SMІІ on the posterior and lateral - 25.0%, 28.0%; О5-6 / SM0 - posterior and fundus - 38.0%, 49.0%; О5-6 / SMІ and О5-6 / SMІІ - posterior and lateral - 45.0% and 37.5%. The maximum average diameter was 20-30 mm, with a quantity of ≤ 3 per individual. When comparing ultrasound and MRI data, discrepancies in the number and localization of nodes were observed in cases of isolated SMІ / SMІІ (on the lateral walls and in the cornual areas of the uterus) at 29.0%; as well as in cases involving combinations of nodes of types О 3-4 / SMІ at 39.0% and О 3-4 / SMІІ at 23.0% (p<0.05). During hysteroscopy, in the group without intraoperative sonography, there were 30% more conversions from hysteroscopic to laparoscopic myomectomy, and 25% more combinations of hysteroscopic myomectomy with laparoscopic monitoring.

CONCLUSION

Conclusions: Hysteroscopic myomectomy with intraoperative sonography is an effective method of treatment for isolated and multiple fibroids of types SMІ/ SMІІ and О3-4/SMІ as well as О3-4/SMІІ.

The effects of hyperbaric oxygen on MRI findings in rheumatoid arthritis: A pilot study

BACKGROUND

Rheumatoid arthritis is a debilitating and destructive disease for which limited therapeutic options exist.

OBJECTIVE

This report summarizes serial magnetic resonance imaging (MRI) findings from nine study participants treated with hyperbaric oxygen (HBO2) therapy and expands upon an earlier pilot study that showed improvement in disease activity and joint pain as determined by multiple, validated clinical measures.

METHODS

Rheumatoid arthritis patients received 30 hyperbaric oxygen treatments over six to 10 weeks. MRI with and without contrast was completed at baseline, and at three- and six-month intervals following initiation of HBO2 therapy. Ratings were based on Outcome Measures in Rheumatology Clinical Trials (OMERACT) Rheumatoid Arthritis Magnetic Resonance Imaging Score (RAMRIS) criteria, the standard method for quantification of inflammation and damage by MRI in RA trials.

RESULTS

Using RAMRIS criteria, nine of nine patients demonstrated no radiologic progression of erosions, synovitis, or bone marrow edema at three- and six-month scans.

CONCLUSION

Our findings suggest that HBO2 therapy may be useful as an adjunctive or alternative treatment to disease-modifying drugs for rheumatoid arthritis.

PHACE(S) SYNDROME - EARLY DIAGNOSTICS IN THE MAXILLOFACIAL AREA

OBJECTIVE

The aim: To determine the minimum criteria for early diagnosing PHACE(S) syndrome in neonates and infants with infantile hemangioma (IH) in the max¬illofacial area.

PATIENTS AND METHODS

Materials and methods: A total of 26 asymptomatic children from 20 days to six months of aged with IH of more than 5 cm² in the maxillofacial area were included in this study. A medical record of patients clinical examination, Holter monitoring, echocardiographic ultrasound and magnetic resonance imaging (MRI) were analysed. The IH treatment with β-blockers was carried out.

RESULTS

Results: IH localization was diagnosed: 62% with a lesion of a part facial segment, 23% in one segment, 15% in several segments (p=0.018), and 12% with other parts of the body lesion (p=1.000). The patent foramen ovale was diagnosed in 35% of children. Central nervous system disorders were observed in 12% over two years of age. The indices of Holter monitoring and blood glucose changed in age norm range during treatment. Cardiovascular (the aortic coarctation (p=0.003) and brain (the Dandy-Walker malformation) (p=0.031) abnormalities were determined in two cases (8%) according to the MRI only. We diagnosed PHACE(S) syndrome in both these cases of children, only aged 12 months and 2.5 years old.

CONCLUSION

Conclusions: Early diagnosis of PHACE(S) syndrome is possible on a contrast-enhanced MRI performed in asymptomatic neonates and infants with the facial several segmental IH with / without ulceration (p=0.018, p=0.046; p < 0.05) for recognition of presymptomatic cardiovascular and brain abnormalities.

A dual-path neural network fusing dual-sequence magnetic resonance image features for detection of placenta accrete spectrum (PAS) disorder

With the increase of various risk factors such as cesarean section and abortion, placenta accrete spectrum (PAS) disorder is happening more frequently year by year. Therefore, prenatal prediction of PAS is of crucial practical significance. Magnetic resonance imaging (MRI) quality will not be affected by fetal position, maternal size, amniotic fluid volume, etc., which has gradually become an important means for prenatal diagnosis of PAS. In clinical practice, T2-weighted imaging (T2WI) magnetic resonance (MR) images are used to reflect the placental signal and T1-weighted imaging (T1WI) MR images are used to reflect bleeding, both plays a key role in the diagnosis of PAS. However, it is difficult for traditional MR image analysis methods to extract multi-sequence MR image features simultaneously and assign corresponding weights to predict PAS according to their importance. To address this problem, we propose a dual-path neural network fused with a multi-head attention module to detect PAS. The model first uses a dual-path neural network to extract T2WI and T1WI MR image features separately, and then combines these features. The multi-head attention module learns multiple different attention weights to focus on different aspects of the placental image to generate highly discriminative final features. The experimental results on the dataset we constructed demonstrate a superior performance of the proposed method over state-of-the-art techniques in prenatal diagnosis of PAS. Specifically, the model we trained achieves 88.6% accuracy and 89.9% F1-score on the independent validation set, which shows a clear advantage over methods that only use a single sequence of MR images.

Tracking glioblastoma progression after initial resection with minimal reaction-diffusion models

We describe a preliminary effort to model the growth and progression of glioblastoma multiforme, an aggressive form of primary brain cancer, in patients undergoing treatment for recurrence of tumor following initial surgery and chemoradiation. Two reaction-diffusion models are used: the Fisher-Kolmogorov equation and a 2-population model, developed by the authors, that divides the tumor into actively proliferating and quiescent (or necrotic) cells. The models are simulated on 3-dimensional brain geometries derived from magnetic resonance imaging (MRI) scans provided by the Barrow Neurological Institute. The study consists of 17 clinical time intervals across 10 patients that have been followed in detail, each of whom shows significant progression of tumor over a period of 1 to 3 months on sequential follow up scans. A Taguchi sampling design is implemented to estimate the variability of the predicted tumors to using 144 different choices of model parameters. In 9 cases, model parameters can be identified such that the simulated tumor, using both models, contains at least 40 percent of the volume of the observed tumor. We discuss some potential improvements that can be made to the parameterizations of the models and their initialization.

Sequential shape similarity for active contour based left ventricle segmentation in cardiac cine MR image

Delineation of the boundaries of the Left Ventricle (LV) in cardiac Magnetic Resonance Images (MRI) is a hot topic due to its important diagnostic power. In this paper, an approach is proposed to extract the LV in a sequence of MR images. In the proposed paper, all images in the sequence are segmented simultaneously and the shape of the LV in each image is supposed to be similar to that of the LV in nearby images in the sequence. We coined the novel shape similarity constraint, and it is called sequential shape similarity (SSS in short). The proposed segmentation method takes the Active Contour Model as the base model and our previously proposed Gradient Vector Convolution (GVC) external force is also adopted. With the SSS constraint, the snake contour can accurately delineate the LV boundaries. We evaluate our method on two cardiac MRI datasets and the Mean Absolute Distance (MAD) metric and the Hausdorff Distance (HD) metric demonstrate that the proposed approach has good performance on segmenting the boundaries of the LV.

VESICAL IMAGING-REPORTING AND DATA SYSTEM - A NEW APPROACH TO BLADDER CANCER STAGING

OBJECTIVE

The aim: To present the assumptions and to show the usefulness of Vesical Imaging-Reporting and Data System (VI-RADS) based on multiparametric magnetic resonance imaging (mpMRI) in the diagnostic pathway management of patients with a bladder cancer.

PATIENTS AND METHODS

Materials and methods: The review is based on available literature from last 10 years from PubMed database and the Przegląd Urologiczny journal focusing on articles on VI-RADS. Overall, 18 articles were included. Presented magnetic resonance images come from the examinations of the patients who were diagnosed with bladder cancer from 2019 to 2021 at Department of Diagnostic Imaging in University Clinical Hospital in Opole, Poland.

CONCLUSION

Conclusions: The newly developed Vesical Imaging-Reporting and Data System has a potential to play a significant role in staging of the bladder cancer as a non-invasive, comprehensive, and effective diagnostic tool providing accurate information for differentiation non-muscle-invasive bladder cancer (NMIBC) from muscle-invasive bladder cancer (MIBC). However more prospective studies should be conducted to validate this system in clinical practice.

Deep learning and radiomics analysis for prediction of placenta invasion based on T2WI

The purpose of this study was to explore whether the Nomogram, which was constructed by combining the Deep learning and Radiomic features of T2-weighted MR images with Clinical factors (NDRC), could accurately predict placenta invasion. This retrospective study included 72 pregnant women with pathologically confirmed placenta invasion and 40 pregnant women with normal placenta. After 24 gestational weeks, all participants underwent magnetic resonance imaging. The uterus and placenta regions were segmented in magnetic resonance images on sagittal T2WI. Ninety-three radiomics features were extracted from the placenta region, and 128 deep features were extracted from the uterus region using a deep neural network. The least absolute shrinkage and selection operator (LASSO) algorithm was used to filter these 221 features and to form the combined signature. Then the combined signature (CS) and clinical factors were combined to construct a nomogram. The accuracy, sensitivity, specificity and AUC of the nomogram were compared with four machine learning methods. The model NDRC was trained on the dataset of 78 pregnant women in the training cohort. Finally, the model NDRC was compared with four machine learning methods on the independent validation cohort of 34 pregnant women. The results showed that the prediction accuracy, sensitivity, specificity and AUC of the NDRC model were 0.941, 0.952, 0.923 and 0.985 respectively, which outperforms the traditional machine learning methods which rely on radiomics features and deep learning features alone.

Two dimensional automatic active shape model of degenerative disc repaired by low-intensity laser

OBJECTIVE

Intervertebral disc degeneration is the main factor causing low back pain, and the related long-term treatment can improve the situation of degeneration. This study aimed to investigate the effect of low-intensity laser irradiation on the repair of degenerative intervertebral disc by two dimensional automatic active shape model (2D-AASM).

METHODS

Nine Bama miniature pigs were randomly divided into three groups: control group (Con), model group (Mod) and laser treatment group (Las). After one month, the discs were treated with low-energy laser for another month. MRI was performed for one month, and the statistical shape model and 2D-AASM of intervertebral disc were established based on the minimum description length method.

RESULTS

The model established by the proposed method is more accurate and the segmentation result is more accurate. From the segmented T2-weighted image, the signal intensity of the Mod group decreased significantly, and the signal intensity in the Las group was moderate and high compared with the Mod group. The HE staining display the structure of Con group was damaged, and the construction of Las group was restored compared with Mod group.

CONCLUSIONS

The 2D-AASM method effectively improves the accuracy of intervertebral disc segmentation. The low-intensity laser has a protective effect on the repair of the degenerative intervertebral disc.

A comparative study for glioma classification using deep convolutional neural networks

Gliomas are a type of central nervous system (CNS) tumor that accounts for the most of malignant brain tumors. The World Health Organization (WHO) divides gliomas into four grades based on the degree of malignancy. Gliomas of grades I-II are considered low-grade gliomas (LGGs), whereas gliomas of grades III-IV are termed high-grade gliomas (HGGs). Accurate classification of HGGs and LGGs prior to malignant transformation plays a crucial role in treatment planning. Magnetic resonance imaging (MRI) is the cornerstone for glioma diagnosis. However, examination of MRI data is a time-consuming process and error prone due to human intervention. In this study we introduced a custom convolutional neural network (CNN) based deep learning model trained from scratch and compared the performance with pretrained AlexNet, GoogLeNet and SqueezeNet through transfer learning for an effective glioma grade prediction. We trained and tested the models based on pathology-proven 104 clinical cases with glioma (50 LGGs, 54 HGGs). A combination of data augmentation techniques was used to expand the training data. Five-fold cross-validation was applied to evaluate the performance of each model. We compared the models in terms of averaged values of sensitivity, specificity, F1 score, accuracy, and area under the receiver operating characteristic curve (AUC). According to the experimental results, our custom-design deep CNN model achieved comparable or even better performance than the pretrained models. Sensitivity, specificity, F1 score, accuracy and AUC values of the custom model were 0.980, 0.963, 0.970, 0.971 and 0.989, respectively. GoogLeNet showed better performance than AlexNet and SqueezeNet in terms of accuracy and AUC with a sensitivity, specificity, F1 score, accuracy, and AUC values of 0.980, 0.889, 0.933, 0.933, and 0.987, respectively. AlexNet yielded a sensitivity, specificity, F1 score, accuracy, and AUC values of 0.940, 0.907, 0.922, 0.923 and 0.970, respectively. As for SqueezeNet, the sensitivity, specificity, F1 score, accuracy, and AUC values were 0.920, 0.870, 0.893, 0.894, and 0.975, respectively. The results have shown the effectiveness and robustness of the proposed custom model in classifying gliomas into LGG and HGG. The findings suggest that the deep CNNs and transfer learning approaches can be very useful to solve classification problems in the medical domain.

[Diagnostic problems in retroperinoneal fibrosis]

Retroperitoneal fibrosis (RPF) is a uncommon disease characterized by the presence of inflammatory and fibrous retroperitoneal tissue that often encircles the ureters or abdominal organs. The disease may be idiopathic or secondary to infections, malignancies, certain drugs or radiotherapy. Idiopathic form is an immune-mediated entity and a part of the broader spectrum of idiopathic diseases termed chronic periaortitis, characterized by a morphologically similar fibroinflammatory changes in aorta. In the article the most important diagnostic problems of RPF are reviewed.

[Patient with spine pain and magnetic resonance imaging result]

Degenerative spine disease is a serious social problem. In most cases, it causes pain and neurological symptoms. Most patients are therefore referred for magnetic resonance imaging (MRI). The article discusses the relationship between back pain and magnetic resonance changes. The signification of some of the radiological symptoms remains controversial. Some of them are markers of acute pain, others may be clinically insignificant, occurring with age. Authors presents some of the magnetic resonance alterations and based on the latest articles discusses their clinical significance. The issues of performing routine, control MRI examination due to chronic back pain and the incidence of new radiological findings were also discussed.