Research on automatic recognition radiomics algorithm for early sacroiliac arthritis based on sacroiliac MRI imaging.

OBJECTIVE: To create an automated machine learning model using sacroiliac joint MRI imaging for early sacroiliac arthritis detection, aiming to enhance diagnostic accuracy. METHODS: We conducted a retrospective analysis involving 71 patients with early sacroiliac arthritis and 85 patients with normal sacroiliac joint MRI scans. Transverse T1WI and T2WI sequences were collected and subjected to radiomics analysis by two physicians. Patients were randomly divided into training and test groups at a 7:3 ratio. Initially, we extracted the region of interest on the sacroiliac joint surface using ITK-SNAP 3.6.0 software and extracted radiomic features. We retained features with an Intraclass Correlation Coefficient > 0.80, followed by filtering using max-relevance and min-redundancy (mRMR) and LASSO algorithms to establish an automatic identification model for sacroiliac joint surface injury. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was calculated. Model performance was assessed by accuracy, sensitivity, and specificity. RESULTS: We evaluated model performance, achieving an AUC of 0.943 for the SVM-T1WI training group, with accuracy, sensitivity, and specificity values of 0.878, 0.836, and 0.943, respectively. The SVM-T1WI test group exhibited an AUC of 0.875, with corresponding accuracy, sensitivity, and specificity values of 0.909, 0.929, and 0.875, respectively. For the SVM-T2WI training group, the AUC was 0.975, with accuracy, sensitivity, and specificity values of 0.933, 0.889, and 0.750. The SVM-T2WI test group produced an AUC of 0.902, with accuracy, sensitivity, and specificity values of 0.864, 0.889, and 0.800. In the SVM-bimodal training group, we achieved an AUC of 0.974, with accuracy, sensitivity, and specificity values of 0.921, 0.889, and 0.971, respectively. The SVM-bimodal test group exhibited an AUC of 0.964, with accuracy, sensitivity, and specificity values of 0.955, 1.000, and 0.875, respectively. CONCLUSION: The radiomics-based detection model demonstrates excellent automatic identification performance for early sacroiliitis.

Nomogram model for predicting invasive placenta in patients with placenta previa: integrating MRI findings and clinical characteristics.

This study aims to validate a nomogram model that predicts invasive placenta in patients with placenta previa, utilizing MRI findings and clinical characteristics. A retrospective analysis was conducted on a training cohort of 269 patients from the Second Affiliated Hospital of Fujian Medical University and a validation cohort of 41 patients from Quanzhou Children's Hospital. Patients were classified into noninvasive and invasive placenta groups based on pathological reports and intraoperative findings. Three clinical characteristics and eight MRI signs were collected and analyzed to identify risk factors and develop the nomogram model. The mode's performance was evaluated in terms of its discrimination, calibration, and clinical utility. Independent risk factors incorporated into the nomogram included the number of previous cesarean sections ≥ 2 (odds ratio [OR] 3.32; 95% confidence interval [CI] 1.28-8.59), type-II placental bulge (OR 17.54; 95% CI 3.53-87.17), placenta covering the scar (OR 2.92; CI 1.23-6.96), and placental protrusion sign (OR 4.01; CI 1.06-15.18). The area under the curve (AUC) was 0.908 for the training cohort and 0.803 for external validation. The study successfully developed a highly accurate nomogram model for predicting invasive placenta in placenta previa cases, based on MRI signs and clinical characteristics.

RSU-Net: U-net based on residual and self-attention mechanism in the segmentation of cardiac magnetic resonance images.

BACKGROUND: Automated segmentation techniques for cardiac magnetic resonance imaging (MRI) are beneficial for evaluating cardiac functional parameters in clinical diagnosis. However, due to the characteristics of unclear image boundaries and anisotropic resolution anisotropy produced by cardiac magnetic resonance imaging technology, most of the existing methods still have the problems of intra-class uncertainty and inter-class uncertainty. However, due to the irregularity of the anatomical shape of the heart and the inhomogeneity of tissue density, the boundaries of its anatomical structures become uncertain and discontinuous. Therefore, fast and accurate segmentation of cardiac tissue remains a challenging problem in medical image processing. METHODOLOGY: We collected cardiac MRI data from 195 patients as training set and 35patients from different medical centers as external validation set. Our research proposed a U-net network architecture with residual connections and a self-attentive mechanism (Residual Self-Attention U-net, RSU-Net). The network relies on the classic U-net network, adopts the U-shaped symmetric architecture of the encoding and decoding mode, improves the convolution module in the network, introduces skip connections, and improves the network's capacity for feature extraction. Then for solving locality defects of ordinary convolutional networks. To achieve a global receptive field, a self-attention mechanism is introduced at the bottom of the model. The loss function employs a combination of Cross Entropy Loss and Dice Loss to jointly guide network training, resulting in more stable network training. RESULTS: In our study, we employ the Hausdorff distance (HD) and the Dice similarity coefficient (DSC) as metrics for assessing segmentation outcomes. Comparsion was made with the segmentation frameworks of other papers, and the comparison results prove that our RSU-Net network performs better and can make accurate segmentation of the heart. New ideas for scientific research. CONCLUSION: Our proposed RSU-Net network combines the advantages of residual connections and self-attention. This paper uses the residual links to facilitate the training of the network. In this paper, a self-attention mechanism is introduced, and a bottom self-attention block (BSA Block) is used to aggregate global information. Self-attention aggregates global information, and has achieved good segmentation results on the cardiac segmentation dataset. It facilitates the diagnosis of cardiovascular patients in the future.

Cardiac MRI segmentation of the atria based on UU-NET.

Background and objective: In today's society, people's work pressure, coupled with irregular diet, lack of exercise and other bad lifestyle, resulting in frequent cardiovascular diseases. Medical imaging has made great progress in modern society, among which the role of MRI in cardiovascular field is self-evident. Based on this research background, how to process cardiac MRI quickly and accurately by computer has been extensively discussed. By comparing and analyzing several traditional image segmentation and deep learning image segmentation, this paper proposes the left and right atria segmentation algorithm of cardiac MRI based on UU-NET network. Methods: In this paper, an atrial segmentation algorithm for cardiac MRI images in UU-NET network is proposed. Firstly, U-shaped upper and lower sampling modules are constructed by using residual theory, which are used as encoders and decoders of the model. Then, the modules are interconnected to form multiple paths from input to output to increase the information transmission capacity of the model. Results: The segmentation method based on UU-NET network has achieved good results proposed in this paper, compared with the current mainstream image segmentation algorithm results have been improved to a certain extent. Through the analysis of the experimental results, the image segmentation algorithm based on UU-NET network on the data set, its performance in the verification set and online set is higher than other grid models. The DSC in the verification set is 96.7%, and the DSC in the online set is 96.7%, which is nearly one percentage point higher than the deconvolution neural network model. The hausdorff distance (HD) is 1.2 mm. Compared with other deep learning models, it is significantly improved (about 3 mm error is reduced), and the time is 0.4 min. Conclusion: The segmentation algorithm based on UU-NET improves the segmentation accuracy obviously compared with other segmentation models. Our technique will be able to help diagnose and treat cardiac complications.

RU-Net: An improved U-Net placenta segmentation network based on ResNet.

BACKGROUND: In recent years, with the increase of late puerperium, cesarean section and induced abortion, the incidence of placenta accreta has been on the rise. It has become one of the common clinical diseases in obstetrics and gynecology. In clinical practice, accurate segmentation of placental tissue is the basis for identifying placental accreta and assessing the degree of accreta. By analyzing the placenta and its surrounding tissues and organs, it is expected to realize automatic computer segmentation of placental adhesion, implantation, and penetration and help clinicians in prenatal planning and preparation. METHODOLOGY: We propose an improved U-Net framework: RU-Net. The direct mapping structure of ResNet was added to the original contraction path and expansion path of U-Net. The feature information of the image was restored to a greater extent through the residual structure to improve the segmentation accuracy of the image. RESULTS: Through testing on the collected placenta dataset, it is found that our proposed RU-Net network achieves 0.9547 and 1.32% on the Dice coefficient and RVD index, respectively. We also compared with the segmentation frameworks of other papers, and the comparison results show that our RU-Net network has better performance and can accurately segment the placenta. CONCLUSION: Our proposed RU-Net network addresses issues such as network degradation of the original U-Net network. Good segmentation results have been achieved on the placenta dataset, which will be of great significance for pregnant women's prenatal planning and preparation in the future.

Automated meniscus segmentation and tear detection of knee MRI with a 3D mask-RCNN.

BACKGROUND: The diagnostic results of magnetic resonance imaging (MRI) are essential references for arthroscopy as an invasive procedure. A deviation between medical imaging diagnosis and arthroscopy results may cause irreversible damage to patients and lead to excessive medical treatment. To improve the accurate diagnosis of meniscus injury, it is urgent to develop auxiliary diagnosis algorithms to improve the accuracy of radiological diagnosis. PURPOSE: This study aims to present a fully automatic 3D deep convolutional neural network (DCNN) for meniscus segmentation and detects arthroscopically proven meniscus tears. MATERIALS AND METHODS: Our institution retrospectively included 533 patients with 546 knees who underwent knee magnetic resonance imaging (MRI) and knee arthroscopy. Sagittal proton density-weighted (PDW) images in MRI of 382 knees were regarded as a training set to train our 3D-Mask RCNN. The remaining data from 164 knees were used to validate the trained network as a test set. The masks were hand-drawn by an experienced radiologist, and the reference standard is arthroscopic surgical reports. The performance statistics included Dice accuracy, sensitivity, specificity, FROC, receiver operating characteristic (ROC) curve analysis, and bootstrap test statistics. The segmentation performance was compared with a 3D-Unet, and the detection performance was compared with radiological evaluation by two experienced musculoskeletal radiologists without knowledge of the arthroscopic surgical diagnosis. RESULTS: Our model produced strong Dice coefficients for sagittal PDW of 0.924, 0.95 sensitivity with 0.823 FPs/knee. 3D-Unet produced a Dice coefficient for sagittal PDW of 0.891, 0.95 sensitivity with 1.355 FPs/knee. The difference in the areas under 3D-Mask-RCNN FROC and 3D-Unet FROC was statistically significant (p = 0.0011) by bootstrap test. Our model detection performance achieved an area under the curve (AUC) value, accuracy, and sensitivity of 0.907, 0.924, 0.941, and 0.785, respectively. Based on the radiological evaluations, the AUC value, accuracy, sensitivity, and specificity were 0.834, 0.835, 0.889, and 0.754, respectively. The difference in the areas between 3D-Mask-RCNN ROC and radiological evaluation ROC was statistically significant (p = 0.0009) by bootstrap test. 3D Mask RCNN significantly outperformed the 3D-Unet and radiological evaluation demonstrated by these results. CONCLUSIONS: 3D-Mask RCNN has demonstrated efficacy and precision for meniscus segmentation and tear detection in knee MRI, which can assist radiologists in improving the accuracy and efficiency of diagnosis. It can also provide effective diagnostic indicators for orthopedic surgeons before arthroscopic surgery and further promote precise treatment.

Breast MRI Segmentation and Ki-67 High- and Low-Expression Prediction Algorithm Based on Deep Learning.

Results: The DSC, PPV, and sensitivity of our combined model are 0.94, 0.93, and 0.94, respectively, with better segmentation performance. And we compare with the segmentation frameworks of other papers and find that our combined model can make accurate segmentation of breast tumors. Conclusion: Our method can adapt to the variability of breast tumors and segment breast tumors accurately and efficiently. In the future, it can be widely used in clinical practice, so as to help the clinic better formulate a reasonable diagnosis and treatment plan for breast cancer patients.

Breast MRI Tumor Automatic Segmentation and Triple-Negative Breast Cancer Discrimination Algorithm Based on Deep Learning.

Background: Breast cancer is a kind of cancer that starts in the epithelial tissue of the breast. Breast cancer has been on the rise in recent years, with a younger generation developing the disease. Magnetic resonance imaging (MRI) plays an important role in breast tumor detection and treatment planning in today's clinical practice. As manual segmentation grows more time-consuming and the observed topic becomes more diversified, automated segmentation becomes more appealing. Methodology. For MRI breast tumor segmentation, we propose a CNN-SVM network. The labels from the trained convolutional neural network are output using a support vector machine in this technique. During the testing phase, the convolutional neural network's labeled output, as well as the test grayscale picture, is passed to the SVM classifier for accurate segmentation. Results: We tested on the collected breast tumor dataset and found that our proposed combined CNN-SVM network achieved 0.93, 0.95, and 0.92 on DSC coefficient, PPV, and sensitivity index, respectively. We also compare with the segmentation frameworks of other papers, and the comparison results prove that our CNN-SVM network performs better and can accurately segment breast tumors. Conclusion: Our proposed CNN-SVM combined network achieves good segmentation results on the breast tumor dataset. The method can adapt to the differences in breast tumors and segment breast tumors accurately and efficiently. It is of great significance for identifying triple-negative breast cancer in the future.

Application value of preoperative dual-source computed tomography in assessing the rupture site of thoracic aortic dissection.

OBJECTIVE: To investigate the application value of dual-source computed tomography (DSCT) in preoperative assessment the rupture site of an thoracic aortic dissection (TAD). METHODS: A retrospective analysis of preoperative DSCT, multislice computed tomography (MSCT), and transthoracic echocardiography (TTE) results of 150 patients with suspected TAD in our hospital was conducted, and the intraoperative findings or interventional treatment results were used as the diagnostic gold standard. RESULTS: Of all 150 suspected TAD patients, 123 patients were confirmed to have TAD. The rupture site of TAD was in the ascending aorta in 46 patients, in the aortic arch in 13 patients, and in the descending aorta in 64 patients. The sensitivity of DSCT, MSCT, and TTE for locating the rupture site of the TAD was 100%, 93.5%, and 89.5%, respectively, and the specificity was 100%, 88.9%, and 81.5%. The differences were statistically significant. The distance between the actual rupture site and the one diagnosed by DSCT, MSCT, and TTE was 1.9 ± 1.2 mm, 5.1 ± 2.7 mm, and 7.8 ± 3.5 mm, respectively; the latter two were significantly worse than DSCT. The size of the rupture site diagnosed by DSCT, MSCT, and TTE was 1.5 ± 0.8 cm, 1.7 ± 0.9 cm, and 1.9 ± 1.0 cm, respectively. The size of the rupture site diagnosed by DSCT was not significantly different from the actual size of 1.4 ± 0.7 cm, while those by MSCT and TTE were. CONCLUSION: DSCT has high sensitivity and specificity in diagnosing the rupture site of TAD and can clearly locate the rupture site. It can be a preferred imaging method for TAD.

A Left Pulmonary Artery Sling in an Asymptomatic Adult Patient, A Case Report and Review of Literature.

Pulmonary artery sling (PAS) is a rare congenital vascular anomaly. Ninety percent of patients with PAS have respiratory distress and need surgical correction. Asymptomatic adult presentation of PAS is rare. We report the case of a 56-year-old female with an asymptomatic left pulmonary artery sling.

Myxofibrosarcoma of the scalp with difficult preoperative diagnosis: A case report and review of the literature.

BACKGROUND: A myxofibrosarcoma (MFS) is a malignant fibroblastic tumor that tends to occur in the lower and upper extremities. The reported incidence of head and neck MFSs is extremely rare. We report a 46-year-old male with "a neoplasm in the scalp" who was hospitalized and diagnosed with an MFS (highly malignant with massive necrotic lesions) based on histologic and immunohistochemistry evaluations. The magnetic resonance imaging manifestations did not demonstrate the "tail sign" mentioned in several studies, which resulted in a great challenge to establish an imaging diagnosis. The treatment plan is closely associated with the anatomic location and histologic grade, and more importantly, aggressive surgery and adjuvant radiotherapy may be helpful. Hence, we report the case and share some valuable information about the disease. CASE SUMMARY: A 46-year-old male with "a neoplasm in the scalp for 6 mo" was hospitalized. Initially, the tumor was about the size of a soybean, without algesia or ulceration. The patient ignored the growth, did not seek treatment, and thus, did not receive treatment. Recently, the tumor increased to the size of an egg; there was no bleeding or algesia. His family history was unremarkable. No abnormalities were found upon laboratory testing, including routine hematologic, biochemistry, and tumor markers. Computed tomography showed an ovoid mass (6.25 cm × 3.29 cm × 3.09 cm in size) in the left frontal scalp with low density intermingled with equidense strips in adjacent areas of the scalp. Magnetic resonance imaging revealed a lesion with an irregular surface and an approximate size of 3.55 cm × 6.34 cm in the left frontal region, with clear boundaries and visible separation. Adjacent areas of the skull were damaged and the dura mater was involved. Contrast enhancement showed an uneven enhancement pattern. Surgery was performed and postoperative adjuvant radiotherapy was administered to avoid recurrence or metastasis. The post-operative pathologic diagnosis confirmed an MFS. A repeat computed tomography scan showed no local recurrence or distant metastasis 19 mo post-operatively. CONCLUSION: The case reported herein of MFS was demonstrated in an extremely rare location on the scalp and had atypical magnetic resonance imaging findings, which serves as a reminder to radiologists of the possibility of this diagnosis to assist in clinical treatment. Given the special anatomic location and the high malignant potential of this rare tumor, combined surgical and adjuvant radiotherapy should be considered to avoid local recurrence and distant metastasis. The significance of regular follow-up is strongly recommended to improve the long-term survival rate.

Application of Indirect Signs of Magnetic Resonance Imaging (MRI) in Prenatal Diagnosis of Abnormally Invasive Placenta.

BACKGROUND The aim of this study was to assess the value of indirect MRI signs in the prenatal diagnosis of abnormally invasive placenta (AIP). MATERIAL AND METHODS This study involved the retrospective analysis of indirect signs of 109 patients with AIP and 59 patients without AIP. The numbers of cases of placenta increta, accreta, and percreta confirmed by surgical and pathological results were 54, 19, and 36, respectively. The indirect signs included the following: dark intraplacental bands in T2WI sequence, focal outward bulging of the placenta, abnormal placental vascularity, and heterogeneous placental signal intensity. RESULTS There were significant differences in dark intraplacental bands in T2WI sequence, focal outward bulging of the placenta, and abnormal placental vascularity between the AIP and the non-AIP groups. There was no significant difference in dark intraplacental bands in T2WI sequence between the placenta percreta and increta groups, but there was a significant difference between the other 2 AIP groups and the placenta accreta group. Focal outward bulging of the placenta was significantly different between the percreta group and the placenta accreta group, but there was no significant difference between the other 2 AIP groups and the placenta increta group. There were no significant differences in abnormal placental vascularity among the3 subtypes of AIP. CONCLUSIONS The indirect signs of dark intraplacental bands in T2WI sequence, focal outward bulging of the placenta, and abnormal placental vascularity are reliable signs of AIP. The indirect sign of dark intraplacental bands in T2WI sequence may be used to distinguish placental accreta from the other 2 subtypes of AIP.

The Role of Dual-Source Computed Tomography Angiography in Evaluating the Aortic Arch Vessels in Acute Type A Aortic Dissection: A Retrospective Study of 42 Patients.

BACKGROUND This study aimed to investigate the role of dual-source computed tomography angiography (DSCTA) to evaluate the anatomy of the aortic arch vessels in patients with acute Type A aortic dissection (AD). MATERIAL AND METHODS A retrospective clinical study included 42 patients with acute Type A AD who underwent DSCTA and were treated in our hospital between January 2018 and December 2018. The findings were compared with a control group of 45 healthy individuals with hypertension and without aortic arch lesions. RESULTS The diagnostic accuracy of DSCTA in patients with acute Type A AD was almost 100%. The innominate artery was most frequently affected. The mean DSCTA imaging measurements for the root of the innominate artery, the left common carotid artery, and the left subclavian artery, in the coronal plane of the aortic arch, were 17.7±3.7 mm, 17.7±3.7 mm, and 12.9±3.1 mm, respectively. The angles formed by the origin of the three aortic arch branches vessels and the aortic arch were 70.5±10.2°, 58.5±15.5°, and 90.2±22.7°, respectively. In the transverse plane of the aortic arch, the mean angles were 110.5±22.3°, 100.3±15.2°, and 95.4±10.6°, respectively. These DSCTA imaging findings were significantly different in the patient group compared with the control group. CONCLUSIONS DCTA demonstrated that patients with Type A AD showed anatomic differences in the aortic arch vessels. These findings may help surgeons to develop treatment strategies and select the most appropriate vascular grafts and stents.

Diagnosis of Congenital Coarctation of the Aorta and Accompany Malformations in Infants by Multi-Detector Computed Tomography Angiography and Transthoracic Echocardiography: A Chinese Clinical Study.

BACKGROUND The purpose of this study was to evaluate the utility of multi-detector computed tomography (MDCT) angiography and transthoracic echocardiography (TTE) in the diagnosis of congenital coarctation of the aorta (CoA) and accompanying malformations in infants. MATERIAL AND METHODS From January 2012 and December 2015, we enrolled 68 infants with clinically suspected CoA who underwent MDCT angiography and TTE in our hospital. Surgical correction was conducted to confirm the diagnostic accuracy of both examinations in all patients. RESULTS In this study, the diagnosis of CoA was confirmed infants by surgical results in 55 of 68 infants. The diagnostic accuracy, sensitivity, and specificity of MDCT angiography were 95.6%, 96.4%, and 92.3%, respectively. The diagnostic accuracy, sensitivity, and specificity of TTE were 88.2%, 90.9%, and 76.9%, respectively. There was no significant difference in diagnostic accuracy, sensitivity, and specificity between MDCT angiography and TTE (χ²=2.473, p>0.05, χ²=1.373, p>0.05 and χ²=1.182, p>0.05, respectively). In the diagnosis of concomitant cardiac abnormalities with CoA, the 2 methods also play different roles. CONCLUSIONS MDCT angiography and TTE play different roles in the diagnosis of CoA and accompany malformations. MDCT angiography in the diagnosis of the extra-cardiac vascular malformations is better than TTE, and TTE is superior to MDCT angiography in diagnosing intracardiac malformation. Combined MDCT angiography and TTE is a relatively valuable, reliable, and noninvasive method in the diagnosis of CoA and accompany malformations in infants.

Preoperative evaluation value of aortic arch lesions by multidetector computed tomography angiography in type A aortic dissection.

The purpose of this study was to preoperatively evaluate the value of aortic arch lesions by multidetector computed tomography (MDCT) angiography in type A aortic dissection (AD).From January 2013 to December 2015, we enrolled 42 patients with type A AD who underwent MDCT angiography in our hospital. The institutional database of patients was retrospectively reviewed to identify MDCT angiography examinations for type A AD. Surgical corrections were conducted in all patients to confirm diagnostic accuracy.In this study, the diagnostic accuracy of MDCT angiography was 100% in all 42 patients. The intimal tear site locations that were identified in patients included the ascending aorta (n = 25), aortic arch (n = 12), and all other sites (n = 5). Compared with the control group, there were significant differences in the aortic arch anatomy among the cases. Regarding the distance between the left common carotid and left subclavian arteries, compared with the control group, most cases with type A AD had a significant variation.MDCT angiography plays an important role in detecting aortic arch lesions of type A AD, especially in determining the location of the intimal entry site and change of branch blood vessels. Surgeons can formulate an appropriate operating plan, according to the preoperative MDCT diagnosis information.

[MRI image analysis of 1,2-dichloroethane chronic toxic encephalopath].

OBJECTIVE: To study the MRI features of 1,2-dichloroethane Chronic Toxic Encephalopathy of 10 cases. METHOD: 10 cases were examined by MRI, slice thickness 8 mm, layer from 2 mm, axial and coronal line scan, T1WI, T2WI, FLAIR imaging. RESULTS: 10 cases show varying degrees of abnormal signal of white matters, low signal intensity on T1WI, high signal intensity on T2WI and FLAIR. MRI could also show extensive abnormal signal in cerebral white matter although the toxic manifestation is mild to moderate. Therefore the symptoms and the shows of MRI could be inconsistent. CONCLUSION: Combined with a history of exposure, the show of varying degrees of abnormal signal of white matter in 1,2-dichloroethane Chronic Toxic Encephalopathy cases are characteristic.