Evaluation of Tumor Fibrosis in Pancreatic Ductal Adenocarcinoma by 2-D Shear Wave Elastography: A Pilot Study.

OBJECTIVE: The aim of the work described here was to investigate the association of the stromal proportion with the elasticity obtained by 2-D shear wave elastography (SWE) and the diagnostic value of elasticity in evaluating tumor stromal fibrosis in pancreatic ductal adenocarcinoma (PDAC). METHODS: Patients who met inclusion criteria underwent pre-operative 2-D SWE examination and intra-operative determination of hardness by palpation from July 2021 to November 2022, and the post-operative specimens were used to evaluate pathological features including the tumor stromal proportion. A receiver operating characteristic curve was created to evaluate its diagnostic value in differentiating the degree of tumor stromal fibrosis. RESULTS: The 2-D SWE measurements in pancreatic lesions were successful in 62 of 69 patients (89.9%). A total of 52 eligible participants were enrolled for subsequent correlation analysis. Elasticity correlated well with tumor stromal proportion (rs = 0.646) and number of tumor cells (rs = -0.585) in PDAC. Moreover, pancreatic elasticity determined by 2-D SWE, palpation-determined hardness and tumor stromal proportion were well correlated with each other. Two-dimensional SWE could clearly distinguish mild and severe stromal fibrosis, and its diagnostic performance was better than that determined by palpation even though the difference was not statistically significant (p = 0.103). CONCLUSION: The elasticity of PDAC obtained using 2-D SWE was closely related to stromal proportion and tumor cellularity and could clearly be used to diagnose the degree of stromal fibrosis, which indicates that 2-D SWE can be a non-invasive predictive imaging biomarker in personalization of therapy and monitoring of treatment.

ResNet and its application to medical image processing: Research progress and challenges.

BACKGROUND AND OBJECTIVE: Deep learning, a novel approach and subset of machine learning, has drawn a growing amount of attention from computer vision researchers in recent years. This method has drawn a lot of interest because of its extraordinary ability to interpret medical pictures, especially when combined with residual neural networks, which have helped to progress the field. METHODS: In this paper, the following research is carried out on the residual network. First, the research status of ResNet in the medical field is introduced. The fundamental idea behind the residual neural network is then explained, along with the residual unit, its many structures, and the network architecture. Second, four aspects of the widespread use of residual neural networks in medical image processing are discussed: lung tumor, diagnosis of skin diseases, diagnosis of breast diseases, and diagnosis of diseases of the brain. Finally, the main issues and ResNet's future development in the area of processing medical images are discussed. RESULTS: In the area of medical graph processing, residual neural networks have made strides and have had success in the clinical auxiliary diagnosis of serious illnesses such as lung tumors, breast cancer, skin conditions, and cardiovascular and cerebrovascular diseases. CONCLUSION: We thoroughly sorted out the most recent developments in residual neural network research and their use in medical image processing, which serves as a crucial point of reference for this field of study. It offers a helpful reference for further promoting the application and research of the ResNet model in the field of medical image processing by summarising the application status and issues of the ResNet model in the field of medical image processing and putting forwards some future development directions.

Brain image segmentation of the corpus callosum by combining Bi-Directional Convolutional LSTM and U-Net using multi-slice CT and MRI.

BACKGROUND AND OBJECTIVE: Traditional disease diagnosis is usually performed by experienced physicians, but misdiagnosis or missed diagnosis still exists. Exploring the relationship between changes in the corpus callosum and multiple brain infarcts requires extracting corpus callosum features from brain image data, which requires addressing three key issues. (1) automation, (2) completeness, and (3) accuracy. Residual learning can facilitate network training, Bi-Directional Convolutional LSTM (BDC-LSTM) can exploit interlayer spatial dependencies, and HDC can expand the receptive domain without losing resolution. METHODS: In this paper, we propose a segmentation method by combining BDC-LSTM and U-Net to segment the corpus callosum from multiple angles of brain images based on computed tomography (CT) and magnetic resonance imaging (MRI) in which two types of sequence, namely T2-weighted imaging as well as the Fluid Attenuated Inversion Recovery (Flair), were utilized. The two-dimensional slice sequences are segmented in the cross-sectional plane, and the segmentation results are combined to obtain the final results. Encoding, BDC- LSTM, and decoding include convolutional neural networks. The coding part uses asymmetric convolutional layers of different sizes and dilated convolutions to get multi-slice information and extend the convolutional layers' perceptual field. RESULTS: This paper uses BDC-LSTM between the encoding and decoding parts of the algorithm. On the image segmentation of the brain in multiple cerebral infarcts dataset, accuracy rates of 0.876, 0.881, 0.887, and 0.912 were attained for the intersection of union (IOU), dice similarity coefficient (DS), sensitivity (SE), and predictive positivity value (PPV). The experimental findings demonstrate that the algorithm outperforms its rivals in accuracy. CONCLUSION: This paper obtained segmentation results for three images using three models, ConvLSTM, Pyramid-LSTM, and BDC-LSTM, and compared them to verify that BDC-LSTM is the best method to perform the segmentation task for faster and more accurate detection of 3D medical images. We improve the convolutional neural network segmentation method to obtain medical images with high segmentation accuracy by solving the over-segmentation problem.

Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart.

Background and Objective: Cardiovascular disease is a high-fatality health issue. Accurate measurement of cardiovascular function depends on precise segmentation of physiological structure and accurate evaluation of functional parameters. Structural segmentation of heart images and calculation of the volume of different ventricular activity cycles form the basis for quantitative analysis of physiological function and can provide the necessary support for clinical physiological diagnosis, as well as the analysis of various cardiac diseases. Therefore, it is important to develop an efficient heart segmentation algorithm. Methods: A total of 275 nuclear magnetic resonance imaging (MRI) heart scans were collected, analyzed, and preprocessed from Huaqiao University Affiliated Strait Hospital, and the data were used in our improved deep learning model, which was designed based on the U-net network. The training set included 80% of the images, and the remaining 20% was the test set. Based on five time phases from end-diastole (ED) to end-systole (ES), the segmentation findings showed that it is possible to achieve improved segmentation accuracy and computational complexity by segmenting the left ventricle (LV), right ventricle (RV), and myocardium (myo). Results: We improved the Dice index of the LV to 0.965 and 0.921, and the Hausdorff index decreased to 5.4 and 6.9 in the ED and ES phases, respectively; RV Dice increased to 0.938 and 0.860, and the Hausdorff index decreased to 11.7 and 12.6 in the ED and ES, respectively; myo Dice increased to 0.889 and 0.901, and the Hausdorff index decreased to 8.3 and 9.2 in the ED and ES, respectively. Conclusion: The model obtained in the final experiment provided more accurate segmentation of the left and right ventricles, as well as the myocardium, from cardiac MRI. The data from this model facilitate the prediction of cardiovascular disease in real-time, thereby providing potential clinical utility.

Medical image fusion using enhanced cross-visual cortex model based on artificial selection and impulse-coupled neural network.

OBJECTIVE: The traditional ICM is widely used in applications, such as image edge detection and image segmentation. However, several model parameters must be set, which tend to lead to reduced accuracy and increased cost. As medical images have more complex edges, contours and details, more suitable combinatorial algorithms are needed to handle the pathological diagnosis of multiple cerebral infarcts and acute strokes, resulting in the findings being more applicable, as well as having good clinical value. METHODS: To better solve the medical image fusion and diagnosis problems, this paper introduces the image fusion algorithm based on the combination of NSCT and improved ICM and proposes low-frequency, sub-band fusion rules and high-frequency sub-band fusion rules. The above method is applied to the fusion of CT/MRI images, subsequently, three other fusion algorithms, including NSCT-SF-PCNN, NSCT-SR-PCNN and Adaptive-PCNN are compared, and the simulation results of image fusion are analyzed and validated. RESULTS: According to the experimental findings, the suggested algorithm performs better than other fusion algorithms in terms of five objective evaluation metrics or subjective evaluation. The NSCT transform and the improved ICM were combined, and the outcomes were evaluated against those of other fusion algorithms. The CT/MRI medical images of healthy brain tissue, numerous cerebral infarcts and acute strokes were combined using this technique. CONCLUSION: Medical image fusion using Adaptive-PCNN produces satisfactory results, not only in relation to improved image clarity but also in terms of outstanding edge information, high contrast and brightness.

Investigation of the bio-stimulation of children's reading interest by chromatic pattern visual evoked potential.

PURPOSE: The characteristics of children's reading interest, stimulated by the visual evoked potentials of colour graphics in children's picture books, were tested to explore their normal reference value. The characteristics of chromatic pattern visual evoked potential (CP-VEP) can be harnessed by our methodology and may be applied to the visual screening of children in clinical ophthalmology. METHODS: The PR-650 spectral colour metre can strictly control factors, such as brightness and colour retention, based on colour contrast. This is performed in order to reduce the brightness contrast method. In our paper, we set up three kinds of visual stimulation conditions and performed CP-VEP inspections of the eye, based on 64 cases (128 eyes) of normal children (32 males and 32 females). Using CP-VEP detection, the latency and amplitude of the P100 wave were recorded and the waveforms of each group, under different spectral modes were compared. Art therapy combined with children's colour physiology and psychology will be more skilfully practiced in clinical practice. RESULTS: There was no significant difference in the amplitude and peak time of visual evoked potential (VEP) waveforms between the left and right eyes of the children using the three stimuli, indicating that the visual function and visual conduction pathway of children can vary. There was no significant difference in the latency and amplitude of the NPN complex wave. Note that the P1 wave of the right and left eyes of normal children is not statistically different (P > 0.05). We also found that there is insignificant difference in the visual impact of the colours for both male and female children in terms of reading interest, and red is a more stimulating colour for both sexes. CONCLUSION: Our study can provide normal reference value and methodological reference for clinical visual acuity detection in children. Combined with the visual characteristics of children, this paper selects the visual impact created by the colour of picture books and combines it with medical treatment. Make the whole test cover the scope of ophthalmology clinical more comprehensive.

Clear cell renal cell carcinoma: Machine learning-based computed tomography radiomics analysis for the prediction of WHO/ISUP grade.

PURPOSE: To evaluate the performance of machine learning (ML)-based computed tomography (CT) radiomics analysis for discriminating between low grade (WHO/ISUP I-II) and high grade (WHO/ISUP III-IV) clear cell renal cell carcinomas (ccRCCs). METHODS: A total of 164 low grade and 107 high grade ccRCCs were retrospectively analyzed in this study. Radiomic features were extracted from corticomedullary phase (CMP) and nephrographic phase (NP) CT images. Intraclass correlation coefficient (ICC) was calculated to quantify the feature's reproducibility. The training and validation cohort consisted of 163 and 108 cases. Least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were k-NearestNeighbor (KNN), Logistic Regression (LR), multilayer perceptron (MLP), Random Forest (RF), and support vector machine (SVM). The performance of classifiers was mainly evaluated and compared by certain metrics. RESULTS: Seven CMP features (ICC range, 0.990-0.999) and seven NP features (ICC range, 0.931-0.999) were selected. The accuracy of CMP, NP and the combination of CMP and NP ranged from 82.2%-85.9 %, 82.8%-94.5 % and 86.5%-90.8 % in the training cohort, and 90.7%-95.4%, 77.8%-79.6 % and 91.7%-93.5 % in the validation cohort. The AUC of CMP, NP and the combination of CMP and NP ranged from 0.901 to 0.938, 0.912 to 0.976, 0.948 to 0.968 in the training cohort, and 0.957 to 0.974, 0.856 to 0.875, 0.960 to 0.978 in the validation cohort. CONCLUSIONS: ML-based CT radiomics analysis can be used to predict the WHO/ISUP grade of ccRCCs preoperatively.

Mutational profiling of poorly differentiated and anaplastic thyroid carcinoma by the use of targeted next-generation sequencing.

AIMS: To characterise the mutational profiles of poorly differentiated thyroid carcinoma (PDTC) and anaplastic thyroid carcinoma (ATC) and to identify markers with potential diagnostic, prognostic and therapeutic significance. METHODS AND RESULTS: Targeted next-generation sequencing with a panel of 18 thyroid carcinoma-related genes was performed on tissue samples from 41 PDTC and 25 ATC patients. Genetic alterations and their correlations with clinicopathological factors, including survival outcomes, were also analysed. Our results showed that ATC had significantly higher mutation rates of BRAF, TP53, TERT and PIK3CA than PDTC (P = 0.005, P = 0.007, P = 0.005, and P = 0.033, respectively). Nine (69%) ATC cases with papillary thyroid carcinoma (PTC) components harboured BRAF mutations, all of which coexisted with a late mutation event (TP53, TERT, or PIK3CA). Nine cases with oncogenic fusion (six RET cases, one NTRK1 case, one ALK case, and one PPARG case) were identified in 41 PDTCs, whereas only one case with oncogenic fusion (NTRK1) was found among 25 ATCs. Moreover, all six cases of RET fusion were found in PDTC with PTC components, accounting for 33%. In PDTC/ATC patients, concurrent TERT and PIK3CA mutations were associated with poor overall survival after adjustment for TNM stage (P = 0.001). CONCLUSIONS: ATC with PTC components is typically characterised by a BRAF mutation with a late mutation event, whereas PDTC with PTC components is more closely correlated with RET fusion. TERT and concurrent PIK3CA mutations predict worse overall survival in PDTC/ATC patients.

Clear cell renal cell carcinoma: CT-based radiomics features for the prediction of Fuhrman grade.

OBJECTIVES: To discriminate low grade (Fuhrman I/II) and high grade (Fuhrman III/IV) clear cell renal cell carcinoma (CCRCC) by using CT-based radiomic features. METHODS: 161 and 99 patients diagnosed with low and high grade CCRCCs from January 2011 to May 2018 were enrolled in this study. 1029 radiomic features were extracted from corticomedullary (CMP), and nephrographic phase (NP) CT images of all patients. We used interclass correlation coefficient (ICC) and the least absolute shrinkage and selection operator (LASSO) regression method to select features, then the selected features were constructed three classification models (CMP, NP and with their combination) to discriminate high and low grades CCRCC. These three models were built by logistic regression method using 5-fold cross validation strategy, evaluated with receiver operating characteristics curve (ROC) and compared using DeLong test. RESULTS: We found 11 and 24 CMP and NP features were independently significantly associated with the Fuhrman grades. The model of CMP, NP and Combined model using radiomic feature set showed diagnostic accuracy of 0.719 (AUC [area under the curve], 0.766; 95% CI [confidence interval]: 0.709-0.816; sensitivity, 0.602; specificity, 0.838), 0.738 (AUC, 0.818; 95% CI:0.765-0.838; sensitivity, 0.693; specificity, 0.838), 0.777(AUC, 0.822; 95% CI: 0.769-0.866; sensitivity, 0.677; specificity, 0.839). There were significant differences in AUC between CMP model and Combined model (P = 0.0208), meanwhile, the differences between CMP model and NP model, NP model and Combined model reached no significant (P = 0.0844, 0.7915). CONCLUSIONS: Radiomic features could be used as biomarker for the preoperative evaluation of the CCRCC Fuhrman grades.

Induction chemotherapy followed by concurrent chemoradiotherapy is benefit for advanced stage nasopharyngeal carcinoma with different nonkeratinizing carcinoma subtypes.

Given the potentially distinctive histological variations in northwest of China, the aim of current study was to compare the efficacy of induction chemotherapy plus concurrent chemoradiotherapy (IC + CCRT) with concurrent chemoradiotherapy (CCRT) in nasopharyngeal carcinoma (NPC) patients with different histological types. A total of 301 patients were included in this study. Patients were classified in two cohorts according to the 2005 WHO World Health Organization histological classification: WHO type IIa group and WHO type IIb group. The Kaplan-Meier method was used to detect the efficacy between IC + CCRT and CCRT in two WHO types cohorts. Propensity score matching method was adopted to balance the baseline covariate and eliminate potential selection bias. On propensity matched analyses, IC + CCRT was found to produce better 3-year DMFS and OS than CCRT in WHO type IIa cohort (DMFS, 76.2% vs. 42.2%, p = 0.029; OS, 78.3% vs. 65.5%, p = 0.027). For WHO type IIb cohort, IC + CCRT was associated with a better 3-year OS (87.4% vs. 77.9%, p = 0.029) and a trend of better 3-year DMFS (85.9% vs. 76%, p = 0.162) compared with CCRT. IC + CCRT was benefit for advanced stage nasopharyngeal carcinoma with different nonkeratinizing carcinoma subtypes.