Lesion Shape Research Articles

CAM-QUS guided self-tuning modular CNNs with multi-loss functions for fully automated breast lesion classification in ultrasound images

Objective. Breast cancer is the major cause of cancer death among women worldwide. Deep learning-based computer-aided diagnosis (CAD) systems for classifying lesions in breast ultrasound images can help materialise the early detection of breast cancer and enhance survival chances. Approach. This paper presents a completely automated BUS diagnosis system with modular convolutional neural networks tuned with novel loss functions. The proposed network comprises a dynamic channel input enhancement network, an attention-guided InceptionV3-based feature extraction network, a classification network, and a parallel feature transformation network to map deep features into quantitative ultrasound (QUS) feature space. These networks function together to improve classification accuracy by increasing the separation of benign and malignant class-specific features and enriching them simultaneously. Unlike the categorical crossentropy (CCE) loss-based traditional approaches, our method uses two additional novel losses: class activation mapping (CAM)-based and QUS feature-based losses, to capacitate the overall network learn the extraction of clinically valued lesion shape and texture-related properties focusing primarily the lesion area for explainable AI (XAI). Main results. Experiments on four public, one private, and a combined breast ultrasound dataset are used to validate our strategy. The suggested technique obtains an accuracy of 97.28%, sensitivity of 93.87%, F1-score of 95.42% on dataset 1 (BUSI), and an accuracy of 91.50%, sensitivity of 89.38%, and F1-score of 89.31% on the combined dataset, consisting of 1494 images collected from hospitals in five demographic locations using four ultrasound systems of different manufacturers. These results outperform techniques reported in the literature by a considerable margin. Significance. The proposed CAD system provides diagnosis from the auto-focused lesion area of B-mode BUS images, avoiding the explicit requirement of any segmentation or region of interest extraction, and thus can be a handy tool for making accurate and reliable diagnoses even in unspecialized healthcare centers.

A System for Identifying Deficiency Elements in Apple Leaf Disease Based on Deep Learning

Background: Plant diseases and pests were natural disasters that seriously threaten agricultural production. Leaf diseases posed a significant threat to the overall productivity and quality of apple orchards. Currently, the diagnosis of plant diseases in apple orchards mainly relied on manual labor, which was both time-consuming and costly. It took a considerable amount of time to train an expert capable of accurately identifying apple diseases and pests, and different crop diseases vary. However, with the use of AI technology, training could be completed in just a few hours to a day, transforming computers into experts in disease and pest identification. Although China became a major apple cultivation nation, the development data from 2021 revealed that traditional advantageous production areas were undergoing dynamic adjustments due to optimization of industrial structure, leading to a decrease in cultivated land. Conversely, the demand for apples in the Chinese market continued to rise, even as the country's population structure gradually trended towards an aging population. This situation underscored the urgent need to replace the laborious and high-cost task of identifying apple foliar diseases in the cultivation process with intelligent agricultural technological solutions. Taking into account the aforementioned factors of the natural environment and socio-cultural considerations and addressing the issue of reduced apple yields due to the high impact of foliar diseases, we initiated study on disease prevention and control during the cultivation process. Methods: To overcome the objective impact of environmental factors, the system extracted images and performed operations such as enhancement and segmentation. Subsequently, a convolutional neural network was employed to process the enhanced images, extracting features such as color, shape, and texture of apple foliar lesions, which were then summarized into histograms using mathematical methods. These histograms served as the primary reference for distinguishing various diseases. Python was chosen as the programming language for the system, and the recognition system was operated by integrating frontend technologies, backend database design, and other relevant techniques. Results: Based on a substantial number of experimental results, the apple leaf disease and nutrient deficiency recognition system could accurately and with extremely high precision identifying major diseases commonly occurring in apple plants, including apple scab, leaf spot disease, rust disease, gray mold disease, and brown spot disease. Moreover, the system was capable of proposing remedies tailored to the specific pain points of each disease. It not only detected apple leaf diseases but also performs nutrient deficiency detection. This holds significant importance in enhancing both the yield and quality of apples. Conclusion: For the commonly occurring foliar diseases in cultivation, the system exhibited the capability to autonomously recognize and provide decision feedback. In contrast to the less efficient and more costly traditional approach of consulting experts, the more accessible apple foliar disease recognition system was poised to replace it as a primary tool for prevention and control assistance. This system will serve as a guiding companion, safeguarding the robust growth of apple plants.

Predictivity of Human Telomerase Reverse Transcriptase (h-TERT) in Oral Squamous Cell Carcinoma: Immunohistochemical Study

Aims: Determine the potential role of h-TERT as a prognostic marker for oral squamous cell carcinoma by evaluating its immunohistochemical expression in different OSCC histologic grades in comparison with normal oral mucosa.
 Study Design: A retrospective study.
 Place and Duration: Oncology Center, Mansoura University, and Oral Pathology Department, Faculty of Dentistry, Mansoura University. The worked sample selected from the years (2015-2019).
 Methodology: Our study was accomplished on 30 OSCC cases and a control group of normal oral mucosa. Histopathologic grading of OSCCs was made using the WHO grade and Anneroth`s grading systems. Immunohistochemical expression of h-TERT was assessed in relation to different clinicopathological parameters. The data was analyzed using Pearson`s chi-square test to compare the differences between groups. Spearman's correlation co-efficiency test was used to test the association between different variables. A P value ≤ 0.05 was considered to be statistically significant.
 Results: A significant increased h-TERT expression was recorded from normal to OSCC groups (P=0.000). Additionally, elevated h-TERT expression was significantly correlated with the higher carcinoma histologic grade (P =0.025). There were high statistically significant differences in h-TERT expression concerning the parameters; Anneroth pattern of invasion (P= 0.049), depth of invasion (DOI, P=0.024), and lymphoplasmacytic infiltration (LPI, P=0.009). There were no statistically significant differences in h-TERT immunoexpression considering the clinical parameters; patient age, gender, anatomical sites, clinical shape of lesion, T, N, M, and TNM stages (Chi-square test, P values were > 0.05).
 Conclusions: Increased h-TERT immunoexpression from normal to OSCC groups suggests its involvement in malignant transformation. Additionally, the significant differential expression of h-TERT among different OSCC histologic grades signaling its valuable use as a biomarker for assessing the cellular malignant progression of oral carcinomas, but unreliable as a clinical tumor progression marker. Moreover, the significant correlation of h-TERT expression with LPI, DOI and pattern of invasion indicating its possible reliable role in tumor host relation during multistage carcinogenesis.

ETU-Net: edge enhancement-guided U-Net with transformer for skin lesion segmentation

Objective. Convolutional neural network (CNN)-based deep learning algorithms have been widely used in recent years for automatic skin lesion segmentation. However, the limited receptive fields of convolutional architectures hinder their ability to effectively model dependencies between different image ranges. The transformer is often employed in conjunction with CNN to extract both global and local information from images, as it excels at capturing long-range dependencies. However, this method cannot accurately segment skin lesions with blurred boundaries. To overcome this difficulty, we proposed ETU-Net. Approach. ETU-Net, a novel multi-scale architecture, combines edge enhancement, CNN, and transformer. We introduce the concept of edge detection operators into difference convolution, resulting in the design of the edge enhanced convolution block (EC block) and the local transformer block (LT block), which emphasize edge features. To capture the semantic information contained in local features, we propose the multi-scale local attention block (MLA block), which utilizes convolutions with different kernel sizes. Furthermore, to address the boundary uncertainty caused by patch division in the transformer, we introduce a novel global transformer block (GT block), which allows each patch to gather full-size feature information. Main results. Extensive experimental results on three publicly available skin datasets (PH2, ISIC-2017, and ISIC-2018) demonstrate that ETU-Net outperforms state-of-the-art hybrid methods based on CNN and Transformer in terms of segmentation performance. Moreover, ETU-Net exhibits excellent generalization ability in practical segmentation applications on dermatoscopy images contributed by the Wuxi No.2 People’s Hospital. Significance. We propose ETU-Net, a novel multi-scale U-Net model guided by edge enhancement, which can address the challenges posed by complex lesion shapes and ambiguous boundaries in skin lesion segmentation tasks.

Sonographic Findings of Cervical Chondrocutaneous Branchial Remnants-A Comparison With Dermal Lesions/Cysts and a Literature Review: A Pilot Study.

Cervical chondrocutaneous branchial remnants (CCBRs) and dermal lesions, such as epidermoid cysts or brachial anomalies, including lateral cervical cysts/sinuses or dermal sinuses of anterior chest lesions, are usually located at the lower neck at the anterior or posterior border of the sternocleidomastoid muscle (SCM). We aimed to demonstrate the usefulness of ultrasonography in the differential diagnosis and evaluation of CCBRs. We evaluated 22 lesions of 20 pediatric patients, classified into CCBR and dermal lesion groups. We used Fisher's exact test to evaluate differences between these groups in terms of lesion shape (low-echoic mass- or tubular-like), whether the lesion was adjacent to/in contact with the SCM or not, and the presence or absence of a concave SCM caused by the lesion. Of the 22 lesions, 8 were CCBRs, and 14 were dermal lesions. We found a significant difference in the presence/absence of adjacency to or contact with the SCM (presence/absence of adjacency to or contact with the SCM in CCBRs vs that in dermal lesions: 6/2 vs 1/13, P = .002) and presence/absence of lesion-induced concavity of the SCM (presence/absence of lesion-induced concavity of the SCM in CCBRs vs that in dermal lesions: 3/5 vs 0/14, P = .036). The lesion shape (low-echoic mass-like/tubular-like lesions) did not significantly differ between the two study groups (low-echoic mass-like/tubular-like lesions in CCBRs vs that in dermal lesions: 5/3 vs 11/6, P = .624). CCBRs have a strong association with the SCM. These sonographic findings may be useful in the differential diagnosis of dermal cervical lesions.

Possibility of Using Conventional Computed Tomography Features and Histogram Texture Analysis Parameters as Imaging Biomarkers for Preoperative Prediction of High-Risk Gastrointestinal Stromal Tumors of the Stomach.

The objective of this study is to determine the morphological computed tomography features of the tumor and texture analysis parameters, which may be a useful diagnostic tool for the preoperative prediction of high-risk gastrointestinal stromal tumors (HR GISTs). This is a prospective cohort study that was carried out in the period from 2019 to 2022. The study included 79 patients who underwent CT examination, texture analysis, surgical resection of a lesion that was suspicious for GIST as well as pathohistological and immunohistochemical analysis. Textural analysis pointed out min norm (p = 0.032) as a histogram parameter that significantly differed between HR and LR GISTs, while min norm (p = 0.007), skewness (p = 0.035) and kurtosis (p = 0.003) showed significant differences between high-grade and low-grade tumors. Univariate regression analysis identified tumor diameter, margin appearance, growth pattern, lesion shape, structure, mucosal continuity, enlarged peri- and intra-tumoral feeding or draining vessel (EFDV) and max norm as significant predictive factors for HR GISTs. Interrupted mucosa (p < 0.001) and presence of EFDV (p < 0.001) were obtained by multivariate regression analysis as independent predictive factors of high-risk GISTs with an AUC of 0.878 (CI: 0.797-0.959), sensitivity of 94%, specificity of 77% and accuracy of 88%. This result shows that morphological CT features of GIST are of great importance in the prediction of non-invasive preoperative metastatic risk. The incorporation of texture analysis into basic imaging protocols may further improve the preoperative assessment of risk stratification.

Relationship between white matter lesion coalescence and plasma cystatin C in an ethnically diverse population

AbstractBackgroundBrain and kidney share anatomical similarities in terms of the small vessels serving their irrigation. Previous work have shown associations between markers of cerebral small vessel disease (CSVD) e.g. white matter hyperintensities (WMH) and markers of renal function e.g. cystatin C. Few studies have however investigated the relationship between renal function and more detailed descriptions of lesion shape and distributionMethod768 individuals from the tri‐ethnic SABRE cohort underwent brain MRI including T1w and FLAIR sequences. WMH were automatically segmented and an overall measure of coalescence was derived from the lesion map ranging from 0 (only punctuate lesions) to 4 (high level of coalescence). Regional coalescence measures according to distance from the ventricles were further derived in 4 equidistant layers. Clinic blood samples were available for 731 individuals (45% female, mean age 71.3 (SD 6.4) years) including from 311 European; 172 African Caribbean; and 248 South Asian ethnicity. Blood measures include plasma cystatin C, a marker of glomerular filtration rate, white blood cell count (WBC) and HbA1c. Associations between cystatin C and coalescence score or lesion volume expressed as percentage of total intracranial volume were investigated using robust linear regression adjusting for age, ethnicity, sex, HbA1c and WBC; all factors known to be associated with cystatin C levels and WMH.ResultCystatin C was positively associated with male sex, WBC and HbA1c, and differed across ethnicities being highest in South Asians and lowest in African Caribbeans. After adjusting for potential confounders, cystatin C was positively associated with overall coalescence score (b = 0.026 [0.004;0.047], p = 0.018) despite unconvincing evidence of an association with overall lesion volume (b = 0.003 [‐0.0003; 0.007], p = 0.066). Associations between cystatin C and coalescence score were stronger in the South Asian group (b = 0.066 [0.027;0.105], p interaction = 0.001). Associations between cystatin C and coalescence score were similar across different layers.ConclusionShape patterns of WMH, rather than overall WMH volume, may provide a more sensitive measure to assess the relationship with markers of small vessel disease in the kidneys.

Relationship between white matter lesion coalescence and plasma cystatin C in an ethnically diverse population.

AbstractBackground: Brain and kidney share anatomical similarities in terms of the small vessels serving their irrigation. Previous work have shown associations between markers of cerebral small vessel disease (CSVD) e.g. white matter hyperintensities (WMH) and markers of renal function e.g. cystatin C. Few studies have however investigated the relationship between renal function and more detailed descriptions of lesion shape and distributionMethod768 individuals from the tri‐ethnic SABRE cohort underwent brain MRI including T1w and FLAIR sequences. WMH were automatically segmented and an overall measure of coalescence was derived from the lesion map ranging from 0 (only punctuate lesions) to 4 (high level of coalescence). Regional coalescence measures according to distance from the ventricles were further derived in 4 equidistant layers. Clinic blood samples were available for 731 individuals (45% female, mean age 71.3 (SD 6.4) years) including from 311 European; 172 African Caribbean; and 248 South Asian ethnicity. Blood measures include plasma cystatin C, a marker of glomerular filtration rate, white blood cell count (WBC) and HbA1c. Associations between cystatin C and coalescence score or lesion volume expressed as percentage of total intracranial volume were investigated using robust linear regression adjusting for age, ethnicity, sex, HbA1c and WBC; all factors known to be associated with cystatin C levels and WMH.ResultCystatin C was positively associated with male sex, WBC and HbA1c, and differed across ethnicities being highest in South Asians and lowest in African Caribbeans. After adjusting for potential confounders, cystatin C was positively associated with overall coalescence score (b = 0.026 [0.004;0.047], p = 0.018) despite unconvincing evidence of an association with overall lesion volume (b = 0.003 [‐0.0003; 0.007], p = 0.066). Associations between cystatin C and coalescence score were stronger in the South Asian group (b = 0.066 [0.027;0.105], p interaction = 0.001). Associations between cystatin C and coalescence score were similar across different layers.ConclusionShape patterns of WMH, rather than overall WMH volume, may provide a more sensitive measure to assess the relationship with markers of small vessel disease in the kidneys.

Investigation of an efficient multi-modal convolutional neural network for multiple sclerosis lesion detection

In this study, an automated 2D machine learning approach for fast and precise segmentation of MS lesions from multi-modal magnetic resonance images (mmMRI) is presented. The method is based on an U-Net like convolutional neural network (CNN) for automated 2D slice-based-segmentation of brain MRI volumes. The individual modalities are encoded in separate downsampling branches without weight sharing, to leverage the specific features. Skip connections input feature maps to multi-scale feature fusion (MSFF) blocks at every decoder stage of the network. Those are followed by multi-scale feature upsampling (MSFU) blocks which use the information about lesion shape and location. The CNN is evaluated on two publicly available datasets: The ISBI 2015 longitudinal MS lesion segmentation challenge dataset containing 19 subjects and the MICCAI 2016 MSSEG challenge dataset containing 15 subjects from various scanners. The proposed multi-input 2D architecture is among the top performing approaches in the ISBI challenge, to which open-access papers are available, is able to outperform state-of-the-art 3D approaches without additional post-processing, can be adapted to other scanners quickly, is robust against scanner variability and can be deployed for inference even on a standard laptop without a dedicated GPU.

Reverse time migration and genetic algorithms Combined for Reconstruction in Transluminal Shear Wave Elastography: An In Silico Case Study

A new reconstruction approach that combines Reverse Time Migration (RTM) and Genetic Algorithms (GAs) is proposed for solving the inverse problem associated with transluminal shear wave elastography. The transurethral identification of the first thermal lesion generated by transrectal High Intensity Focused Ultrasound (HIFU) for the treatment of prostate cancer, was used to preliminarily test in silico the combined reconstruction method. The RTM method was optimised by comparing reconstruction images from several cross-correlation techniques, including a new proposed one, and different device configurations in terms of the number and arrangement of emitters and receivers of the conceptual transurethral probe. The best results were obtained for the new proposed cross-correlation method and a device configuration with 3 emitters and 32 receivers. The RTM reconstructions did not completely contour the shape of the HIFU lesion, however, as planned for the combined approach, the areas in the RTM images with high level of correlation were used to narrow down the search space in the GA-based technique. The GA-based technique was set to find the location of the HIFU lesion and the increment in stiffness and viscosity due to thermal damage. Overall, the combined approach achieves lower level of error in the reconstructed values, and in a shorter computational time, compared to the GA-based technique alone. The lowest errors were accomplished for the location of HIFU lesion, followed by the contrast ratio of stiffness between thermally treated tissue and non-treated normal tissue. The homologous ratio of viscosity obtained higher level of error. Further investigation considering diverse scenarios to be reconstructed and with experimental data is required to fully evaluate the feasibility of the combined approach.

How intramyocardial fat can alter the electric field distribution during Pulsed Field Ablation (PFA): Qualitative findings from computer modeling.

Even though the preliminary experimental data suggests that cardiac Pulsed Field Ablation (PFA) could be superior to radiofrequency ablation (RFA) in terms of being able to ablate the viable myocardium separated from the catheter by collagen and fat, as yet there is no formal physical-based analysis that describes the process by which fat can affect the electric field distribution. Our objective was thus to determine the electrical impact of intramyocardial fat during PFA by means of computer modeling. Computer models were built considering a PFA 3.5-mm blunt-tip catheter in contact with a 7-mm ventricular wall (with and without a scar) and a 2-mm epicardial fat layer. High voltage was set to obtain delivered currents of 19, 22 and 25 A. An electric field value of 1000 V/cm was considered as the lethal threshold. We found that the presence of fibrotic tissue in the scar seems to have a similar impact on the electric field distribution and lesion size to that of healthy myocardium only. However, intramyocardial fat considerably alters the electrical field distribution and the resulting lesion shape. The electric field tends to peak in zones with fat, even away from the ablation electrode, so that 'cold points' (i.e. low electric fields) appear around the fat at the current entry and exit points, while 'hot points' (high electric fields) occur in the lateral areas of the fat zones. The results show that intramyocardial fat can alter the electric field distribution and lesion size during PFA due to its much lower electrical conductivity than that of myocardium and fibrotic tissue.

Skin lesion recognition via global-local attention and dual-branch input network

Owing to the deficiency of training data, the variety of skin lesion shapes for different patients, inter-class similarity, and intra-class variation, the recognition accuracy and speed in skin lesion recognition based on deep learning remain challenging. To solve the above issues, we propose a Dual-Branch and Global-Local Attention network based on ResNet50 (DGLA-ResNet50) to reduce model parameters and improve identification accuracy. For inter-class and intra-class problems, a global-local attention mechanism is designed to obtain the dependency information of query points in horizontal and vertical directions in turn for obtaining the global information indirectly. And we choose to obtain the local information through multiple convolutions simultaneously. Aiming at insufficient samples, the attention mechanism is lightened from the perspectives of reducing query points and the points associated with them, so as to reduce parameter redundancy. In addition, we present a dual-branch input network to deal with the problem of image variety, in which two branches are used to extract image features with different resolutions for fusion, so as to expand the network receptive field. We evaluated DGLA-ResNet50 on ISIC2018 and ISIC2019. The experimental results on ISIC2018 demonstrate that DGLA-ResNet50 has a recognition accuracy of 90.71%, while the parameters of the model are only 104.2M and the FLOPs value is 15.6G. Compared with the common models, our model obtains significantly better performance. The results indicate that DGLA-ResNet50 can improve the accuracy well while ensuring the lightweight of the model, and can prospectively assist doctors in the rapid diagnosis of skin lesions.

Artificial Intelligence Decision Support for Triple-Negative Breast Cancers on Ultrasound.

To assess performance of an artificial intelligence (AI) decision support software in assessing and recommending biopsy of triple-negative breast cancers (TNBCs) on US. Retrospective institutional review board-approved review identified patients diagnosed with TNBC after US-guided biopsy between 2009 and 2019. Artificial intelligence output for TNBCs on diagnostic US included lesion features (shape, orientation) and likelihood of malignancy category (benign, probably benign, suspicious, and probably malignant). Artificial intelligence true positive was defined as suspicious or probably malignant and AI false negative (FN) as benign or probably benign. Artificial intelligence and radiologist lesion feature agreement, AI and radiologist sensitivity and FN rate (FNR), and features associated with AI FNs were determined using Wilcoxon rank-sum test, Fisher's exact test, chi-square test of independence, and kappa statistics. The study included 332 patients with 345 TNBCs. Artificial intelligence and radiologists demonstrated moderate agreement for lesion shape and orientation (k = 0.48 and k = 0.47, each P <.001). On the set of examinations using 6 earlier diagnostic US, radiologists recommended biopsy of 339/345 lesions (sensitivity 98.3%, FNR 1.7%), and AI recommended biopsy of 333/345 lesions (sensitivity 96.5%, FNR 3.5%), including 6/6 radiologist FNs. On the set of examinations using immediate prebiopsy diagnostic US, AI recommended biopsy of 331/345 lesions (sensitivity 95.9%, FNR 4.1%). Artificial intelligence FNs were more frequently oval (q < 0.001), parallel (q < 0.001), circumscribed (q = 0.04), and complex cystic and solid (q = 0.006). Artificial intelligence accurately recommended biopsies for 96% to 97% of TNBCs on US and may assist radiologists in classifying these lesions, which often demonstrate benign sonographic features.

Evaluation of deep learning for detecting intraosseous jaw lesions in cone beam computed tomography volumes

The study aim was to develop and assess the performance of a deep learning (DL) algorithm in the detection of radiolucent intraosseous jaw lesions in cone beam computed tomography (CBCT) volumes. A total of 290 CBCT volumes from more than 12 different scanners were acquired. Fields of view ranged from 6 × 6 × 6 cm to 18 × 18 × 16 cm. CBCT volumes contained either zero or at least one biopsy-confirmed intraosseous lesion. 80 volumes with no intraosseous lesions were included as controls and were not annotated. 210 volumes with intraosseous lesions were manually annotated using ITK-Snap 3.8.0. 150 volumes (10 control, 140 positive) were presented to the DL software for training. Validation was performed using 60 volumes (30 control, 30 positive). Testing was performed using the remaining 80 volumes (40 control, 40 positive). The DL algorithm obtained an adjusted sensitivity by case, specificity by case, positive predictive value by case, and negative predictive value by case of 0.975, 0.825, 0.848, and 0.971, respectively. A DL algorithm showed moderate success at lesion detection in their correct locations, as well as recognition of lesion shape and extent. This study demonstrated the potential of DL methods for intraosseous lesion detection in CBCT volumes.

Ayurveda Perspective on Visarpa Vyadhi and its Management

Skin is the largest organ of the body which acts as a first line of defense in providing resistance to the body. The aggravation of various Dhatus and Doshas result in skin diseases. More than one-fifty skin related diseases are mentioned in various Ayurvedic texts. They are categorized as Visarpa, Kustha, Shotha, Upadansh etc. Visarpa is a very common disease mentioned in Ayurvedic texts which spreads in body in various directions. It is said to be caused by Varicella zoster virus as per modern concept. It manifests as Daha, Jwara, Anunnatashopha and Vedana. Around 20-30% sufferers of various skin ailments are demonstrated through large community prevalence study. A 40-year-male presented along with the vesicular lesions on his neck region associated with mild fever, itching, and pain on the local lesion. He was administered with 250mg of Kamadudha rasa (plain) twice a day before meals with milk, Chandrakala rasa 250mg twice a day, Paripathadi kwatha 2 tsp twice a day and Shatadhauta ghrita for local application on the lesions. The patient reported on the 5th day with significant relief in the size and shape of the facial lesions and other symptoms. The scars limited to minimal without any inflammatory signs by the 7th day of follow-up. Above medications are two readily available and cost-effective compound Ayurvedic formulations, which can be used in the management of herpes zoster infection, especially in low-resource settings.

The Role of CT-Based Radiomics Nomogram in Differential Diagnosis of Immune Checkpoint Inhibitor-Related Pneumonitis from Radiation Pneumonitis for Patients with ESCC

The combination of immunotherapy and chemoradiotherapy has widely used for patients with esophageal squamous cell carcinoma (ESCC) and induced treatment-related adverse effects, particularly immune checkpoint inhibitor-related pneumonitis (CIP) and radiation pneumonitis (RP). The aim of this study is to differentiate between CIP and RP by the CT radiomics and clinical or radiological parameters. A total of 76 ESCC patients with pneumonitis were enrolled in this retrospective study and divided into training dataset (n = 53) and validation dataset (n = 23). A total of 837 radiomics features were extracted from regions of interest (ROIs) based on the lung parenchyma window of CT images. A radiomics signature was constructed on the basis of the predictive features by the least absolute shrinkage and selection operator (LASSO). A logistic regression was applied to develop radiomics nomogram. Receiver operating characteristics (ROC) curve and area under the curve (AUC) were applied to evaluate the performance of pneumonitis etiology identification. No significant difference was detected between training dataset and validation dataset. The radiomics signature which was made up of four radiomics features shown a favorable performance on differentiating between CIP and RP with the α-binormal-based and empirical AUC = 0.831 and 0.843. Patients with RP had a close relationship with location (p = 0.003) and shape of lesions (p = 0.002). The nomogram that combined with radiomics signature and clinical factors improved the classifying performance on discrimination in the training dataset (AUCαbin = 0.963 and AUCemp = 0.964). The results were verified in the validation dataset with AUC = 0.967 and 0.964. CT-based radiomics features have potential values for differentiating between patients with CIP and RP. Addition of bilateral changes and sharp border produced superior model performance on classifying, which could be a useful method to improve related clinical decision-making.

ARM-Net: Attention-guided residual multiscale CNN for multiclass brain tumor classification using MR images

Brain tumor is the deadliest type of cancer and has the lowest survival rate when compared with other cancers. Hence, timely detection of brain tumor is indispensable for patients to make better treatment plans, leading to improved life expectancy. However, accurate classification of different brain tumor types from MR images is challenging due to high inter-class similarities. Though deep learning architectures, mainly CNNs, have shown promising performance compared to traditional approaches, such models often demand huge parameters and lead to overfitting while dealing with limited training samples. Further, the state-of-the-art CNN models cannot capture the subtle lesion size and shape variations among different classes. To cope with these issues, in this paper, we propose an attention-based residual multiscale CNN called ARM-Net for multiclass brain tumor classification. In particular, we propose a lightweight residual multiscale CNN dubbed RM-Net to capture high-level feature representations at different receptive fields. Further, a lightweight global attention module (LGAM) is proposed to selectively learn more discriminative features. The LGAM is placed on the top of RM-Net and is introduced to capture wide-range feature dependencies. Experimental results on two benchmark datasets indicate the superiority of our ARM-Net over the state-of-the-art CNN architectures and existing methods. The ARM-Net achieves an accuracy of 96.64% and 97.11% on MBTD and BraTS 2020 dataset, respectively. The ablation studies, Grad-CAM, and Grad-CAM++ visualization results confirm the effectiveness of our proposed LGAM. In addition, our ARM-Net is lightweight, end-to-end learnable, and hence more suitable for real-time brain tumor classification.

MSRNet: Multiclass Skin Lesion Recognition Using Additional Residual Block Based Fine-Tuned Deep Models Information Fusion and Best Feature Selection.

Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin cancer, particularly melanoma, is becoming a severe health problem due to its rising prevalence. The considerable death rate linked with melanoma requires early detection to receive immediate and successful treatment. Lesion detection and classification are more challenging due to many forms of artifacts such as hairs, noise, and irregularity of lesion shape, color, irrelevant features, and textures. In this work, we proposed a deep-learning architecture for classifying multiclass skin cancer and melanoma detection. The proposed architecture consists of four core steps: image preprocessing, feature extraction and fusion, feature selection, and classification. A novel contrast enhancement technique is proposed based on the image luminance information. After that, two pre-trained deep models, DarkNet-53 and DensNet-201, are modified in terms of a residual block at the end and trained through transfer learning. In the learning process, the Genetic algorithm is applied to select hyperparameters. The resultant features are fused using a two-step approach named serial-harmonic mean. This step increases the accuracy of the correct classification, but some irrelevant information is also observed. Therefore, an algorithm is developed to select the best features called marine predator optimization (MPA) controlled Reyni Entropy. The selected features are finally classified using machine learning classifiers for the final classification. Two datasets, ISIC2018 and ISIC2019, have been selected for the experimental process. On these datasets, the obtained maximum accuracy of 85.4% and 98.80%, respectively. To prove the effectiveness of the proposed methods, a detailed comparison is conducted with several recent techniques and shows the proposed framework outperforms.

Deep learning-based multiscale CNN-based U network model for leaf disease diagnosis and segmentation of lesions in tomato

BackgroundThe advent of deep learning technologies has expanded the utilization of convolutional neural networks in diagnosing and segmenting plant leaf diseases. However, the segmentation of lesions, especially those with diverse sizes and shapes, often requires extensive pixel-level annotations. ObjectiveThis study aims to introduce a multiscale U-network for effective concurrent segmentation and diagnosis of tomato leaf lesions. MethodsOur model employs multi-scale residual modules to adapt dynamically to diseases that alter lesion size and shape. The Classifier and Bridge (CB) module is introduced to connect the disease feature extraction stage with the disease spot segmentation stage, providing crucial information about a specific lesion type. During the segmentation stage, the activation map of a specific class is deconvoluted using a combination of up-sampling and convolution. This deconvolution feature is fused with the low-level feature through a skip connection strategy. A limited number of pixel-level labels are used, and the binary cross-entropy loss function is applied for supervised training at each pixel point, directing the feature extraction network to focus on the lesion location. ResultsThe model was evaluated using an original test set and an interference test set simulating noise and light intensity changes. The multiscale U-network demonstrated an average pixel accuracy of approximately 99.2%, a resilience to brightness reduction by about 92.4%, and an ability to handle up to 0.98 salt and pepper noise at a rate of about 99.2%, showcasing its robustness against various image alterations. The GFLOPs for the proposed method was found to be approximately 3.13e+06, indicating its computational efficiency. ConclusionThe experimental results highlight the potential of the proposed multiscale U-network in effectively segmenting and identifying lesions in tomato leaf tissue. These findings suggest promising opportunities for applying this model in the broader field of agricultural disease management.

Ultrasonography characteristics of cystic components in primary salivary gland tumors

ObjectivesThe present study aimed to characterize the ultrasonography (US) features of cystic components in salivary gland tumors (SGTs).Materials and methodsA total of 207 patients (218 lesions) with pathologically confirmed primary SGTs were analyzed. Preoperative US revealed the presence of cystic components in lesions. Lesion size, shape, margin, and US findings of the cystic components, including number, distribution, margin, occupying rate, and internal characteristics, were evaluated.ResultsSimilarities were observed between the US performance of benign SGTs (B-SGTs) and malignant SGTs (M-SGTs) with cystic components. Differences in sex and age of patients, number, distribution, and internal characteristics of cystic components were statistically significant. For SGTs with cystic components, the proportions of M-SGTs to ill-defined margins (P = 0.002), eccentric distribution (P = 0.019), and none of the internal characteristics (P = 0.019) were significantly higher than those of B-SGTs. Younger age (P = 0.001), eccentric distribution (P = 0.034) and ill-defined margin (P < 0.001) were risk factors for diagnosing M-SGTs. Cystic component features needed to be combined with lesion indicators (border and shape) to improve diagnostic sensitivity.ConclusionsUS features of the B-SGTs and M-SGTs were significantly different. Cystic component is of interest in the US-related differential diagnosis of B-SGT and M-SGT.Clinical relevanceCystic components are potentially valuable in the differential diagnosis of B-SGTs and M-SGTs on US.