Acute ischemic stroke in tuberculous meningitis.

Background: The underlying mechanism for stroke in patients with tuberculous meningitis (TBM) remains unclear. This study aimed to investigate the predictors of acute ischemic stroke (AIS) in TBM and whether AIS mediates the relationship between inflammation markers and functional disability. Methods: TBM patients admitted to five hospitals between January 2011 and December 2021 were consecutively observed. Generalized linear mixed model and subgroup analyses were performed to investigate predictors of AIS in patients with and without vascular risk factors (VAFs). Mediation analyses were performed to explore the potential causal chain in which AIS may mediate the relationship between neuroimaging markers of inflammation and 90-day functional outcomes. Results: A total of 1,353 patients with TBM were included. The percentage rate of AIS within 30 days after admission was 20.4 (95% CI, 18.2-22.6). A multivariate analysis suggested that age ≥35 years (OR = 1.49; 95% CI, 1.06-2.09; P = 0.019), hypertension (OR = 3.56; 95% CI, 2.42-5.24; P < 0.001), diabetes (OR = 1.78; 95% CI, 1.11-2.86; P = 0.016), smoking (OR = 2.88; 95% CI, 1.68-4.95; P < 0.001), definite TBM (OR = 0.19; 95% CI, 0.06-0.42; P < 0.001), disease severity (OR = 2.11; 95% CI, 1.50-2.90; P = 0.056), meningeal enhancement (OR = 1.66; 95% CI, 1.19-2.31; P = 0.002), and hydrocephalus (OR = 2.98; 95% CI, 1.98-4.49; P < 0.001) were associated with AIS. Subgroup analyses indicated that disease severity (P for interaction = 0.003), tuberculoma (P for interaction = 0.008), and meningeal enhancement (P for interaction < 0.001) were significantly different in patients with and without VAFs. Mediation analyses revealed that the proportion of the association between neuroimaging markers of inflammation and functional disability mediated by AIS was 16.98% (95% CI, 7.82-35.12) for meningeal enhancement and 3.39% (95% CI, 1.22-6.91) for hydrocephalus. Conclusion: Neuroimaging markers of inflammation were predictors of AIS in TBM patients. AIS mediates < 20% of the association between inflammation and the functional outcome at 90 days. More attention should be paid to clinical therapies targeting inflammation and hydrocephalus to directly improve functional outcomes.

Multi-omics analysis reveals that linoleic acid metabolism is associated with variations of trained immunity induced by distinct BCG strains.

Trained immunity is one of the mechanisms by which BCG vaccination confers persistent nonspecific protection against diverse diseases. Genomic differences between the different BCG vaccine strains that are in global use could result in variable protection against tuberculosis and therapeutic effects on bladder cancer. In this study, we found that four representative BCG strains (BCG-Russia, BCG-Sweden, BCG-China, and BCG-Pasteur) covering all four genetic clusters differed in their ability to induce trained immunity and nonspecific protection. The trained immunity induced by BCG was associated with the Akt-mTOR-HIF1α axis, glycolysis, and NOD-like receptor signaling pathway. Multi-omics analysis (epigenomics, transcriptomics, and metabolomics) showed that linoleic acid metabolism was correlated with the trained immunity-inducing capacity of different BCG strains. Linoleic acid participated in the induction of trained immunity and could act as adjuvants to enhance BCG-induced trained immunity, revealing a trained immunity-inducing signaling pathway that could be used in the adjuvant development.

A nursing report on a corneal contact lens wearer receiving keratoplasty due to corneal ulcer and perforation caused by Pythium insidiosum infection: A case report.

BACKGROUND: To report the nursing experience of a case of corneal contact lens wearer receiving the 2nd keratoplasty due to corneal ulcer and perforation caused by Pythium insidiosum infection. METHODS: A 30-year-old female patient had blurred vision after deep anterior lamellar keratoplasty for a right corneal ulcer. At the 5th week, the right eye appeared the symptoms, such as redness and pain. The anterior segment photography was performed on the eye, and the result showed that the epithelium was missing in the right eye lesion area, and a large number of longitudinal and transversal streaks were visible from the epithelium to the stroma, with fungus filaments to be discharged. Upon macro-genome sequencing of the corneal secretion, a P. insidiosum infection was observed. Then, the patient underwent the keratoplasty, and 3 weeks later, the corneal implant showed a tendency to dissolve, the sutures were partially loosened, and the eye was almost blind. Subsequently, the patient was admitted to our hospital and subject to the 2nd penetrating keratoplasty of the right eye (allograft). After surgery, linezolid and azithromycin injections were given through intravenous drip and local drip of the eye for anti-inflammation, and tacrolimus eye drops for antirejection. RESULTS: Postoperatively, the patient showed signs of recovery with slight corneal edema and visible pupil, leading to discharge with improved vision. The corneal implant was normal 1 week after surgery and the vision of the right eye was hand move/before eye at the 6th month of follow-up. Continuous care and removal of sutures 3 months post-surgery contributed to a successful outcome, with the patient achieving hand motion vision 6 months after the procedure. CONCLUSION: Corneal ulcer caused by P. insidiosum infection not only needs timely and effective keratoplasty intervention, but also requires perfect nursing measures.

A Survey of Convolutional Neural Network in Breast Cancer.

Problems: For people all over the world, cancer is one of the most feared diseases. Cancer is one of the major obstacles to improving life expectancy in countries around the world and one of the biggest causes of death before the age of 70 in 112 countries. Among all kinds of cancers, breast cancer is the most common cancer for women. The data showed that female breast cancer had become one of the most common cancers. Aims: A large number of clinical trials have proved that if breast cancer is diagnosed at an early stage, it could give patients more treatment options and improve the treatment effect and survival ability. Based on this situation, there are many diagnostic methods for breast cancer, such as computer-aided diagnosis (CAD). Methods: We complete a comprehensive review of the diagnosis of breast cancer based on the convolutional neural network (CNN) after reviewing a sea of recent papers. Firstly, we introduce several different imaging modalities. The structure of CNN is given in the second part. After that, we introduce some public breast cancer data sets. Then, we divide the diagnosis of breast cancer into three different tasks: 1. classification; 2. detection; 3. segmentation. Conclusion: Although this diagnosis with CNN has achieved great success, there are still some limitations. (i) There are too few good data sets. A good public breast cancer dataset needs to involve many aspects, such as professional medical knowledge, privacy issues, financial issues, dataset size, and so on. (ii) When the data set is too large, the CNN-based model needs a sea of computation and time to complete the diagnosis. (iii) It is easy to cause overfitting when using small data sets.

GAM-SpCaNet: Gradient awareness minimization-based spinal convolution attention network for brain tumor classification.

Brain tumor is one of the common diseases of the central nervous system, with high morbidity and mortality. Due to the wide range of brain tumor types and pathological types, the same type is divided into different subgrades. The imaging manifestations are complex, making clinical diagnosis and treatment difficult. In this paper, we construct SpCaNet (Spinal Convolution Attention Network) to effectively utilize the pathological features of brain tumors, consisting of a Positional Attention (PA) convolution block, Relative self-attention transformer block, and Intermittent fully connected (IFC) layer. Our method is more lightweight and efficient in recognition of brain tumors. Compared with the SOTA model, the number of parameters is reduced by more than three times. In addition, we propose the gradient awareness minimization (GAM) algorithm to solve the problem of insufficient generalization ability of the traditional Stochastic Gradient Descent (SGD) method and use it to train the SpCaNet model. Compared with SGD, GAM achieves better classification performance. According to the experimental results, our method has achieved the highest accuracy of 99.28%, and the proposed method performs well in classifying brain tumors.

Multiple-level thresholding for breast mass detection.

Detection of breast mass plays a very important role in making the diagnosis of breast cancer. For faster detection of breast cancer caused by breast mass, we developed a novel and efficient patch-based breast mass detection system for mammography images. The proposed framework is comprised of three modules, including pre-processing, multiple-level breast tissue segmentation, and final breast mass detection. An improved Deeplabv3+ model for pectoral muscle removal is deployed in pre-processing. We then proposed a multiple-level thresholding segmentation method to segment breast mass and obtained the connected components (ConCs), where the corresponding image patch to each ConC is extracted for mass detection. In the final detection stage, each image patch is classified into breast mass and breast tissue background by trained deep learning models. The patches that are classified as breast mass are then taken as the candidates for breast mass. To reduce the false positive rate in the detection results, we applied the non-maximum suppression algorithm to combine the overlapped detection results. Once an image patch is considered a breast mass, the accurate detection result can then be retrieved from the corresponding ConC in the segmented images. Moreover, a coarse segmentation result can be simultaneously retrieved after detection. Compared to the state-of-the-art methods, the proposed method achieved comparable performance. On CBIS-DDSM, the proposed method achieved a detection sensitivity of 0.87 at 2.86 FPI (False Positive rate per Image), while the sensitivity reached 0.96 on INbreast with an FPI of only 1.29.

ReRNet: A Deep Learning Network for Classifying Blood Cells.

AIMS: Blood cell classification helps detect various diseases. However, the current classification model of blood cells cannot always get great results. A network that automatically classifies blood cells can provide doctors with data as one of the criteria for diagnosing patients' disease types and severity. If doctors diagnose blood cells, doctors could spend lots of time on the diagnosis. The diagnosis progress is very tedious. Doctors can make some mistakes when they feel tired. On the other hand, different doctors may have different points on the same patient. METHODS: We propose a ResNet50-based ensemble of randomized neural networks (ReRNet) for blood cell classification. ResNet50 is used as the backbone model for feature extraction. The extracted features are fed to 3 randomized neural networks (RNNs): Schmidt neural network, extreme learning machine, and dRVFL. The outputs of the ReRNet are the ensemble of these 3 RNNs based on the majority voting mechanism. The 5 × 5-fold cross-validation is applied to validate the proposed network. RESULTS: The average-accuracy, average-sensitivity, average-precision, and average-F1-score are 99.97%, 99.96%, 99.98%, and 99.97%, respectively. CONCLUSIONS: The ReRNet is compared with 4 state-of-the-art methods and achieves the best classification performance. The ReRNet is an effective method for blood cell classification based on these results.

Aculeaxanthones A-E, new xanthones from the marine-derived fungus Aspergillus aculeatinus WHUF0198.

Introduction: Dimeric natural products are widespread in plants and microorganisms, which usually have complex structures and exhibit greater bioactivities than their corresponding monomers. In this study, we report five new dimeric tetrahydroxanthones, aculeaxanthones A-E (4-8), along with the homodimeric tetrahydroxanthone secalonic acid D (1), chrysoxanthones B and C (2 and 3), and 4-4'-secalonic acid D (9), from different fermentation batches of the title fungus. Methods: A part of the culture was added to a total of 60 flasks containing 300 ml each of number II fungus liquid medium and culture 4 weeks in a static state at 28˚C. The liquid phase (18 L) and mycelia was separated from the fungal culture by filtering. A crude extract was obtained from the mycelia by ultrasound using acetone. To obtain a dry extract (18 g), the liquid phase combined with the crude extract were further extracted by EtOAc and concentrated in vacuo. The MIC of anaerobic bacteria was examined by a broth microdilution assay. To obtain MICs for aerobic bacteria, the agar dilution streak method recommended in Clinical and Laboratory Standards Institute document (CLSI) M07-A10 was used. Compounds 1-9 was tested against the Bel-7402, A-549 and HCT-116 cell lines according to MTT assay. Results and Discussion: The structures of these compounds were elucidated on the base of 1D and 2D NMR and HR-ESIMS data, and the absolute configurations of the new xanthones 4-8 were determined by conformational analysis and time-dependent density functional theory-electronic circular dichroism (TDDFT-ECD) calculations. Compounds 1-9 were tested for cytotoxicity against the Bel-7402, A549, and HCT-116 cancer cell lines. Of the dimeric tetrahydroxanthone derivatives, only compound 6 provided cytotoxicity effect against Bel-7402 cell line (IC50, 1.96 µM). Additionally, antimicrobial activity was evaluated for all dimeric tetrahydroxanthones, including four Gram-positive bacteria including Enterococcus faecium ATCC 19434, Bacillus subtilis 168, Staphylococcus aureus ATCC 25923 and MRSA USA300; four Gram-negative bacteria, including Helicobacter pylori 129, G27, as well as 26,695, and multi drug-resistant strain H. pylori 159, and one Mycobacterium M. smegmatis ATCC 607. However, only compound 1 performed activities against H. pylori G27, H. pylori 26695, H. pylori 129, H. pylori 159, S. aureus USA300, and B. subtilis 168 with MIC values of 4.0, 4.0, 2.0, 2.0, 2.0 and 1.0 µg/mL, respectively.

An integrated approach of network pharmacology, molecular docking, and experimental verification uncovers kaempferol as the effective modulator of HSD17B1 for treatment of endometrial cancer.

BACKGROUND: Endometrial cancer (EC) is one of the most common gynecological malignancies globally, and the development of innovative, effective drugs against EC remains a key issue. Phytoestrogen kaempferol exhibits anti-cancer effects, but the action mechanisms are still unclear. METHOD: MTT assays, colony-forming assays, flow cytometry, scratch healing, and transwell assays were used to evaluate the proliferation, apoptosis, cell cycle, migration, and invasion of both ER-subtype EC cells. Xenograft experiments were used to assess the effects of kaempferol inhibition on tumor growth. Next-generation RNA sequencing was used to compare the gene expression levels in vehicle-treated versus kaempferol-treated Ishikawa and HEC-1-A cells. A network pharmacology and molecular docking technique were applied to identify the anti-cancer mechanism of kaempferol, including the building of target-pathway network. GO analysis and KEGG pathway enrichment analysis were used to identify cancer-related targets. Finally, the study validated the mRNA and protein expression using real-time quantitative PCR, western blotting, and immunohistochemical analysis. RESULTS: Kaempferol was found to suppress the proliferation, promote apoptosis, and limit the tumor-forming, scratch healing, invasion, and migration capacities of EC cells. Kaempferol inhibited tumor growth and promotes apoptosis in a human endometrial cancer xenograft mouse model. No significant toxicity of kaempferol was found in human monocytes and normal cell lines at non-cytotoxic concentrations. No adverse effects or significant changes in body weight or organ coefficients were observed in 3-7 weeks' kaempferol-treated animals. The RNA sequencing, network pharmacology, and molecular docking approaches identified the overall survival-related differentially expressed gene HSD17B1. Interestingly, kaempferol upregulated HSD17B1 expression and sensitivity in ER-negative EC cells. Kaempferol differentially regulated PPARG expression in EC cells of different ER subtypes, independent of its effect on ESR1. HSD17B1 and HSD17B1-associated genes, such as ESR1, ESRRA, PPARG, AKT1, and AKR1C1\2\3, were involved in several estrogen metabolism pathways, such as steroid binding, 17-beta-hydroxysteroid dehydrogenase (NADP+) activity, steroid hormone biosynthesis, and regulation of hormone levels. The molecular basis of the effects of kaempferol treatment was evaluated. CONCLUSIONS: Kaempferol is a novel therapeutic candidate for EC via HSD17B1-related estrogen metabolism pathways. These results provide new insights into the efficiency of the medical translation of phytoestrogens.

COVID-19 classification using chest X-ray images: A framework of CNN-LSTM and improved max value moth flame optimization.

Coronavirus disease 2019 (COVID-19) is a highly contagious disease that has claimed the lives of millions of people worldwide in the last 2 years. Because of the disease's rapid spread, it is critical to diagnose it at an early stage in order to reduce the rate of spread. The images of the lungs are used to diagnose this infection. In the last 2 years, many studies have been introduced to help with the diagnosis of COVID-19 from chest X-Ray images. Because all researchers are looking for a quick method to diagnose this virus, deep learning-based computer controlled techniques are more suitable as a second opinion for radiologists. In this article, we look at the issue of multisource fusion and redundant features. We proposed a CNN-LSTM and improved max value features optimization framework for COVID-19 classification to address these issues. The original images are acquired and the contrast is increased using a combination of filtering algorithms in the proposed architecture. The dataset is then augmented to increase its size, which is then used to train two deep learning networks called Modified EfficientNet B0 and CNN-LSTM. Both networks are built from scratch and extract information from the deep layers. Following the extraction of features, the serial based maximum value fusion technique is proposed to combine the best information of both deep models. However, a few redundant information is also noted; therefore, an improved max value based moth flame optimization algorithm is proposed. Through this algorithm, the best features are selected and finally classified through machine learning classifiers. The experimental process was conducted on three publically available datasets and achieved improved accuracy than the existing techniques. Moreover, the classifiers based comparison is also conducted and the cubic support vector machine gives better accuracy.

Effect of Different Durations of Eye-Covering Pretreatment on Emergence Delirium after Ophthalmic Surgery in Preschool-Aged Children: A Randomized Controlled Study.

Background: Preoperative eye-covering training for 3 hours has been reported to effectively reduce the incidence of emergence delirium (ED) in preschool children. However, most children can only maintain the eye being covered for less than 60 min, and shortening eye-covering duration can also achieve similar clinical effects as long duration of eye-covering. This study was designed to compare the effects of 30-min and 60-min eye-covering pretreatment based on cartoon education only on preoperative anxiety, postoperative ED, and pain score after ophthalmic surgery with general anesthesia in preschool-aged children. Methods: Preschool-aged children (3-7 years) who were diagnosed with cataract, blepharoptosis, trichiasis, strabismus, eyelid tumor, and underwent ophthalmic surgery with general anesthesia from August 2021 to January 2022 were recruited. A total of 228 patients were randomly assigned at a 1 : 1:1 ratio to receive 30-min eye covering (30-min group), 60-min eye covering (60-min group) pretreatment, or programmed education only (C group). The preoperative anxiety, postoperative emergence delirium, and pain were compared between the groups. Results: The preoperative anxiety score, postoperative ED score, and incidence of ED in the 30-min group (n = 76) and 60-min group (n = 72) were significantly lower than those in the C group (n = 76), demonstrating a significant between-group difference (P < 0.001). However, the 30-min group and 60-min group had no significant difference in the abovementioned outcome measures (P > 0.05). Moreover, no significant difference was found in postoperative pain scores among the three groups (H = 0.274, P=0.872). Conclusion: Both 30-min and 60-min eye-covering pretreatments significantly reduce preoperative anxiety and postoperative ED after ophthalmic surgery with general anesthesia in preschool-aged children. The effects of the two groups show no intergroup difference, but the 30-min eye-covering pretreatment may be more convenient for practicing. Trial Registration. This study was registered with the No. NCT04973150.

Research Advances for Virus-vectored Tuberculosis Vaccines and Latest Findings on Tuberculosis Vaccine Development.

Tuberculosis (TB), caused by respiratory infection with Mycobacterium tuberculosis, remains a major global health threat. The only licensed TB vaccine, the one-hundred-year-old Bacille Calmette-Guérin has variable efficacy and often provides poor protection against adult pulmonary TB, the transmissible form of the disease. Thus, the lack of an optimal TB vaccine is one of the key barriers to TB control. Recently, the development of highly efficacious COVID-19 vaccines within one year accelerated the vaccine development process in human use, with the notable example of mRNA vaccines and adenovirus-vectored vaccines, and increased the public acceptance of the concept of the controlled human challenge model. In the TB vaccine field, recent progress also facilitated the deployment of an effective TB vaccine. In this review, we provide an update on the current virus-vectored TB vaccine pipeline and summarize the latest findings that might facilitate TB vaccine development. In detail, on the one hand, we provide a systematic literature review of the virus-vectored TB vaccines are in clinical trials, and other promising candidate vaccines at an earlier stage of development are being evaluated in preclinical animal models. These research sharply increase the likelihood of finding a more effective TB vaccine in the near future. On the other hand, we provide an update on the latest tools and concept that facilitating TB vaccine research development. We propose that a pre-requisite for successful development may be a better understanding of both the lung-resident memory T cell-mediated mucosal immunity and the trained immunity of phagocytic cells. Such knowledge could reveal novel targets and result in the innovative vaccine designs that may be needed for a quantum leap forward in vaccine efficacy. We also summarized the research on controlled human infection and ultra-low-dose aerosol infection murine models, which may provide more realistic assessments of vaccine utility at earlier stages. In addition, we believe that the success in the ongoing efforts to identify correlates of protection would be a game-changer for streamlining the triage of multiple next-generation TB vaccine candidates. Thus, with more advanced knowledge of TB vaccine research, we remain hopeful that a more effective TB vaccine will eventually be developed in the near future.

SAFNet: A deep spatial attention network with classifier fusion for breast cancer detection.

Breast cancer is a top dangerous killer for women. An accurate early diagnosis of breast cancer is the primary step for treatment. A novel breast cancer detection model called SAFNet is proposed based on ultrasound images and deep learning. We employ a pre-trained ResNet-18 embedded with the spatial attention mechanism as the backbone model. Three randomized network models are trained for prediction in the SAFNet, which are fused by majority voting to produce more accurate results. A public ultrasound image dataset is utilized to evaluate the generalization ability of our SAFNet using 5-fold cross-validation. The simulation experiments reveal that the SAFNet can produce higher classification results compared with four existing breast cancer classification methods. Therefore, our SAFNet is an accurate tool to detect breast cancer that can be applied in clinical diagnosis.

DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification.

Aims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer's disease (AD) as an example, the number of patients dramatically increases in developed countries. By 2025, the number of elderly patients with AD aged 65 and over will reach 7.1 million, an increase of nearly 29% over the 5.5 million patients of the same age in 2018. Unless medical breakthroughs are made, AD patients may increase from 5.5 million to 13.8 million by 2050, almost three times the original. Researchers have focused on developing complex machine learning (ML) algorithms, i.e., convolutional neural networks (CNNs), containing millions of parameters. However, CNN models need many training samples. A small number of training samples in CNN models may lead to overfitting problems. With the continuous research of CNN, other networks have been proposed, such as randomized neural networks (RNNs). Schmidt neural network (SNN), random vector functional link (RVFL), and extreme learning machine (ELM) are three types of RNNs. Methods: We propose three novel models to classify brain diseases to cope with these problems. The proposed models are DenseNet-based SNN (DSNN), DenseNet-based RVFL (DRVFL), and DenseNet-based ELM (DELM). The backbone of the three proposed models is the pre-trained "customize" DenseNet. The modified DenseNet is fine-tuned on the empirical dataset. Finally, the last five layers of the fine-tuned DenseNet are substituted by SNN, ELM, and RVFL, respectively. Results: Overall, the DSNN gets the best performance among the three proposed models in classification performance. We evaluate the proposed DSNN by five-fold cross-validation. The accuracy, sensitivity, specificity, precision, and F1-score of the proposed DSNN on the test set are 98.46% ± 2.05%, 100.00% ± 0.00%, 85.00% ± 20.00%, 98.36% ± 2.17%, and 99.16% ± 1.11%, respectively. The proposed DSNN is compared with restricted DenseNet, spiking neural network, and other state-of-the-art methods. Finally, our model obtains the best results among all models. Conclusions: DSNN is an effective model for classifying brain diseases.

Breast microscopic cancer segmentation and classification using unique 4-qubit-quantum model.

The visual inspection of histopathological samples is the benchmark for detecting breast cancer, but a strenuous and complicated process takes a long time of the pathologist practice. Deep learning models have shown excellent outcomes in clinical diagnosis and image processing and advances in various fields, including drug development, frequency simulation, and optimization techniques. However, the resemblance of histopathologic images of breast cancer and the inclusion of stable and infected tissues in different areas make detecting and classifying tumors on entire slide images more difficult. In breast cancer, a correct diagnosis is needed for complete care in a limited amount of time. An effective detection can relieve the pathologist's workload and mitigate diagnostic subjectivity. Therefore, this research work investigates improved the pre-trained xception and deeplabv3+ design semantic model. The model has been trained on input images with ground masks on the tuned parameters that significantly improve the segmentation of ultrasound breast images into respective classes, that is, benign/malignant. The segmentation model delivered an accuracy of greater than 99% to prove the model's effectiveness. The segmented images and histopathological breast images are transferred to the 4-qubit-quantum circuit with six-layered architecture to detect breast malignancy. The proposed framework achieved remarkable performance as contrasted to currently published methodologies. HIGHLIGHTS: This research proposed hybrid semantic model using pre-trained xception and deeplabv3 for breast microscopic cancer classification in to benign and malignant classes at accuracy of 95% accuracy, 99% accuracy for detection of breast malignancy.

PeMNet for Pectoral Muscle Segmentation.

As an important imaging modality, mammography is considered to be the global gold standard for early detection of breast cancer. Computer-Aided (CAD) systems have played a crucial role in facilitating quicker diagnostic procedures, which otherwise could take weeks if only radiologists were involved. In some of these CAD systems, breast pectoral segmentation is required for breast region partition from breast pectoral muscle for specific analysis tasks. Therefore, accurate and efficient breast pectoral muscle segmentation frameworks are in high demand. Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images. In the proposed PeMNet, we integrated a novel attention module called the Global Channel Attention Module (GCAM), which can effectively improve the segmentation performance of Deeplabv3+ using minimal parameter overheads. In GCAM, channel attention maps (CAMs) are first extracted by concatenating feature maps after paralleled global average pooling and global maximum pooling operation. CAMs are then refined and scaled up by multi-layer perceptron (MLP) for elementwise multiplication with CAMs in next feature level. By iteratively repeating this procedure, the global CAMs (GCAMs) are then formed and multiplied elementwise with final feature maps to lead to final segmentation. By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage. The experiments on a merged dataset derived from two datasets, INbreast and OPTIMAM, showed that PeMNet greatly outperformed state-of-the-art methods by achieving an IoU of 97.46%, global pixel accuracy of 99.48%, Dice similarity coefficient of 96.30%, and Jaccard of 93.33%, respectively.

PBTNet: A New Computer-Aided Diagnosis System for Detecting Primary Brain Tumors.

Brain tumors are among the leading human killers. There are over 120 different types of brain tumors, but they mainly fall into two groups: primary brain tumors and metastatic brain tumors. Primary brain tumors develop from normal brain cells. Early and accurate detection of primary brain tumors is vital for the treatment of this disease. Magnetic resonance imaging is the most common method to diagnose brain diseases, but the manual interpretation of the images suffers from high inter-observer variance. In this paper, we presented a new computer-aided diagnosis system named PBTNet for detecting primary brain tumors in magnetic resonance images. A pre-trained ResNet-18 was selected as the backbone model in our PBTNet, but it was fine-tuned only for feature extraction. Then, three randomized neural networks, Schmidt neural network, random vector functional-link, and extreme learning machine served as the classifiers in the PBTNet, which were trained with the features and their labels. The final predictions of the PBTNet were generated by the ensemble of the outputs from the three classifiers. 5-fold cross-validation was employed to evaluate the classification performance of the PBTNet, and experimental results demonstrated that the proposed PBTNet was an effective tool for the diagnosis of primary brain tumors.

A Survey of Computer-Aided Tumor Diagnosis Based on Convolutional Neural Network.

Tumors are new tissues that are harmful to human health. The malignant tumor is one of the main diseases that seriously affect human health and threaten human life. For cancer treatment, early detection of pathological features is essential to reduce cancer mortality effectively. Traditional diagnostic methods include routine laboratory tests of the patient's secretions, and serum, immune and genetic tests. At present, the commonly used clinical imaging examinations include X-ray, CT, MRI, SPECT scan, etc. With the emergence of new problems of radiation noise reduction, medical image noise reduction technology is more and more investigated by researchers. At the same time, doctors often need to rely on clinical experience and academic background knowledge in the follow-up diagnosis of lesions. However, it is challenging to promote clinical diagnosis technology. Therefore, due to the medical needs, research on medical imaging technology and computer-aided diagnosis appears. The advantages of a convolutional neural network in tumor diagnosis are increasingly obvious. The research on computer-aided diagnosis based on medical images of tumors has become a sharper focus in the industry. Neural networks have been commonly used to research intelligent methods to assist medical image diagnosis and have made significant progress. This paper introduces the traditional methods of computer-aided diagnosis of tumors. It introduces the segmentation and classification of tumor images as well as the diagnosis methods based on CNN to help doctors determine tumors. It provides a reference for developing a CNN computer-aided system based on tumor detection research in the future.

Improving ductal carcinoma in situ classification by convolutional neural network with exponential linear unit and rank-based weighted pooling.

Ductal carcinoma in situ (DCIS) is a pre-cancerous lesion in the ducts of the breast, and early diagnosis is crucial for optimal therapeutic intervention. Thermography imaging is a non-invasive imaging tool that can be utilized for detection of DCIS and although it has high accuracy (~ 88%), it is sensitivity can still be improved. Hence, we aimed to develop an automated artificial intelligence-based system for improved detection of DCIS in thermographs. This study proposed a novel artificial intelligence based system based on convolutional neural network (CNN) termed CNN-BDER on a multisource dataset containing 240 DCIS images and 240 healthy breast images. Based on CNN, batch normalization, dropout, exponential linear unit and rank-based weighted pooling were integrated, along with L-way data augmentation. Ten runs of tenfold cross validation were chosen to report the unbiased performances. Our proposed method achieved a sensitivity of 94.08 ± 1.22%, a specificity of 93.58 ± 1.49 and an accuracy of 93.83 ± 0.96. The proposed method gives superior performance than eight state-of-the-art approaches and manual diagnosis. The trained model could serve as a visual question answering system and improve diagnostic accuracy.