Lesion Shape Research Articles

A deep supervised cross-attention strategy for ischemic stroke segmentation in MRI studies

The key component of stroke diagnosis is the localization and delineation of brain lesions, especially from MRI studies. Nonetheless, this manual delineation is time-consuming and biased by expert opinion. The main purpose of this study is to introduce an autoencoder architecture that effectively integrates cross-attention mechanisms, together with hierarchical deep supervision to delineate lesions under scenarios of remarked unbalance tissue classes, challenging geometry of the shape, and a variable textural representation. This work introduces a cross-attention deep autoencoder that focuses on the lesion shape through a set of convolutional saliency maps, forcing skip connections to preserve the morphology of affected tissue. Moreover, a deep supervision training scheme was herein adapted to induce the learning of hierarchical lesion details. Besides, a special weighted loss function remarks lesion tissue, alleviating the negative impact of class imbalance. The proposed approach was validated on the public ISLES2017 dataset outperforming state-of-the-art results, achieving a dice score of 0.36 and a precision of 0.42. Deeply supervised cross-attention autoencoders, trained to pay more attention to lesion tissue, are better at estimating ischemic lesions in MRI studies. The best architectural configuration was achieved by integrating ADC, TTP and Tmax sequences. The contribution of deeply supervised cross-attention autoencoders allows better support the discrimination between healthy and lesion regions, which in consequence results in favorable prognosis and follow-up of patients.

PD22-03 IMPROVING PROSTATE CANCER DETECTION ON MRI WITH DEEP LEARNING, CLINICAL VARIABLES, AND RADIOMICS

You have accessJournal of UrologyCME1 Apr 2023PD22-03 IMPROVING PROSTATE CANCER DETECTION ON MRI WITH DEEP LEARNING, CLINICAL VARIABLES, AND RADIOMICS Sara Saunders, Xinran Li, Sulaiman Vesal, Indrani Bhattacharya, Simon J. C. Soerensen, Richard E. Fan, Mirabela Rusu, and Geoffrey A. Sonn Sara SaundersSara Saunders More articles by this author , Xinran LiXinran Li More articles by this author , Sulaiman VesalSulaiman Vesal More articles by this author , Indrani BhattacharyaIndrani Bhattacharya More articles by this author , Simon J. C. SoerensenSimon J. C. Soerensen More articles by this author , Richard E. FanRichard E. Fan More articles by this author , Mirabela RusuMirabela Rusu More articles by this author , and Geoffrey A. SonnGeoffrey A. Sonn More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003295.03AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Radiologists often struggle to differentiate prostate cancer from benign confounders on MRI (i.e. BPH nodules, focal atrophy, prostatitis), but deep learning models may assist clinicians. These models demonstrate high sensitivity in cancer detection but are often limited by high false positive rates. Accurately identifying cancers while minimizing false positives is critical to preventing unnecessary biopsies. We trained classification models on clinical variables and radiomic features to improve differentiation between prostate cancer and benign confounders. METHODS: We trained two state-of-the-art deep learning prostate cancer detection models (SPCNet and U-Net) to identify lesions on MRI in the publicly available PI-CAI dataset consisting of 1500 cases. The SPCNet and U-Net predicted prostate cancer lesions from T2WI, Apparent Diffusion Coefficient (ADC), and Diffusion Weighted Images (DWI). We compared these predictions to pathology confirmed annotations. To identify falsely detected lesions, we trained a Random Forest Classifier on clinical variables (age, PSA, and prostate volume) and radiomic features (i.e. lesion shape, intensity). Once trained on 90% of these cases, it was evaluated on 10%. RESULTS: The U-Net and SPCNet predicted cancerous lesions with positive predictive values of 0.12 and 0.07. Our approach removed 40% of lesions falsely detected by the U-Net and 56% of those falsely detected by the SPCNet while maintaining high sensitivities of 1.0 and 0.97, respectively, compared to all lesions predicted by the cancer detection models. Even more false positive lesions can be removed (71% for U-Net, 74% for SPCNet) at a sensitivity of 0.91. At the patient level, this Random Forest Classifier eliminated 55% of non-cancerous cases but also 15% of true cancer cases predicted by the U-Net. Similar trends were seen for SPCNet. CONCLUSIONS: While clinical variables are routinely used in prostate cancer diagnosis, most deep learning prostate cancer detection models do not utilize them. A classification algorithm trained on clinical variables and radiomic features improves accuracy of cancer detection models by discarding false positive lesions. Source of Funding: Stanford Cancer Imaging Training Program, Departments of Radiology and Urology, Stanford University, National Cancer Institute of the National Institutes of Health (R37CA260346 to M.R, and U01CA196387 to J.D.B.), and the generous philanthropic support of our patients (G.S.) The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e665 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Sara Saunders More articles by this author Xinran Li More articles by this author Sulaiman Vesal More articles by this author Indrani Bhattacharya More articles by this author Simon J. C. Soerensen More articles by this author Richard E. Fan More articles by this author Mirabela Rusu More articles by this author Geoffrey A. Sonn More articles by this author Expand All Advertisement PDF downloadLoading ...

Automated quantification of the pulmonary vasculature in pulmonary embolism and chronic thromboembolic pulmonary hypertension.

The shape and distribution of vascular lesions in pulmonary embolism (PE) and chronic thromboembolic pulmonary hypertension (CTEPH) are different. We investigated whether automated quantification of pulmonary vascular morphology and densitometry in arteries and veins imaged by computed tomographic pulmonary angiography (CTPA) could distinguish PE from CTEPH. We analyzed CTPA images from a cohort of 16 PE patients, 6 CTEPH patients, and 15 controls. Pulmonary vessels were extracted with a graph-cut method, and separated into arteries and veins using deep-learning classification. Vascular morphology was quantified by the slope (α) and intercept (β) of the vessel radii distribution. To quantify lung perfusion defects, the median pulmonary vascular density was calculated. By combining these measurements with densities measured in parenchymal areas, pulmonary trunk, and descending aorta, a static perfusion curve was constructed. All separate quantifications were compared between the three groups. No vascular morphology differences were detected in contrast to vascular density values. The median vascular density (interquartile range) was -567 (113), -452 (95), and -470 (323) HU, for the control, PE, and CTEPH group. The static perfusion curves showed different patterns between groups, with a statistically significant difference in aorta-pulmonary trunk gradient between the PE and CTEPH groups (p = 0.008). In this proof of concept study, not vasculature morphology but densities differentiated between patients of three groups. Further technical improvements are needed to allow for accurate differentiation between PE and CTEPH, which in this study was only possible statistically by measuring the density gradient between aorta and pulmonary trunk.

Hemolysis of red blood cells in blood vessels modeled via computational fluid dynamics.

The research aims to verify the universal relationship between vessel shape and the risk of hemolysis using a rheological model of blood reflecting the physiological processes related to blood for any blood vessel. Blood is a multi-component fluid, the rheology of which depends on many factors, such as the concentration of red blood cells and local shear stress, which significantly affect the process of hemolysis. Blood rheology models used so far cannot be used for all flows and geometries. Therefore, a new rheology model has been introduced suitable for modeling hemolytic flows observed in arteries with atherosclerotic lesions in the in vivo environment. The previously presented model also has advantages in modeling local viscosity in stenosis. Geometries of the blood vessels from computed tomography scans and simplified models of the actual arteries observed during medical procedures were used in the calculations. Population Balance Based Rheology model predicts the concentration of single, deagglomerated red blood cells and the concentration and size of red blood cell agglomerates, which affect blood rheology and hemolysis. Based on the simulations carried out, a correlation was found between the shape of the vessel cavity and the risk of hemolysis. Presented results can be used in the future to create a correlation between the shape of the atherosclerotic lesions and the risk of hemolysis in the blood to make an initial risk assessment for a given patient.

The epifascial cap: A typical imaging sign for subcutaneous granuloma annulare in children.

Subcutaneous granuloma annulare (SGA) is a rare, self-limiting granulomatous disease in children, commonly diagnosed by histopathology following biopsy or surgical excision. This study aimed to identify imaging clues for SGA that could expedite accurate diagnosis and avoid the need for biopsy in children. We retrospectively analyzed complete hospital records of all children diagnosed with SGA at our institution from January 2001 to December 2020. Detailed disease history, imaging findings, management, and outcome were evaluated. We identified 28 patients (20 girls) at a median age of 3.75 (range 1-12.5 years). Ten patients presented with multiple lesions. Most lesions were located on the lower extremities (n = 26/41). Ultrasound examinations were performed on all patients, and 12 (43%) patients also received an MRI. Surgical intervention was conducted in 18 (64%) patients either by incisional biopsy (n = 6) or total excision of the lump (n = 12). In all patients who did not undergo surgery, SGA resolved spontaneously. A careful review of the MRIs led to the discovery of a characteristic imaging shape of SGA lesions: the epifascial cap with a typical broad circular base laying on the fascia, extending towards the subdermal/dermal tissue. This distinctive shape was evident in every patient in our cohort. The "Epifascial Cap Sign" is a specific imaging sign for SGA, which to the best of our knowledge, helps distinguish this disease from other subcutaneous lesions. Recognition of this novel diagnostic sign combined with the historical and physical findings should enable clinicians to establish SGA diagnosis easily and diminish the need for further invasive diagnostic procedures.

Combining physics-based models with deep learning image synthesis and uncertainty in intraoperative cone-beam CT of the brain.

Image-guided neurosurgery requires high localization and registration accuracy to enable effective treatment and avoid complications. However, accurate neuronavigation based on preoperative magnetic resonance (MR) or computed tomography (CT) images is challenged by brain deformation occurring during the surgical intervention. To facilitate intraoperative visualization of brain tissues and deformable registration with preoperative images, a 3D deep learning (DL) reconstruction framework (termed DL-Recon) was proposed for improved intraoperative cone-beam CT (CBCT) image quality. The DL-Recon framework combines physics-based models with deep learning CT synthesis and leverages uncertainty information to promote robustness to unseen features. A 3D generative adversarial network (GAN) with a conditional loss function modulated by aleatoric uncertainty was developed for CBCT-to-CT synthesis. Epistemic uncertainty of the synthesis model was estimated via Monte Carlo (MC) dropout. Using spatially varying weights derived from epistemic uncertainty, the DL-Recon image combines the synthetic CT with an artifact-corrected filtered back-projection (FBP) reconstruction. In regions of high epistemic uncertainty, DL-Recon includes greater contribution from the FBP image. Twenty paired real CT and simulated CBCT images of the head were used for network training and validation, and experiments evaluated the performance of DL-Recon on CBCT images containing simulated and real brain lesions not present in the training data. Performance among learning- and physics-based methods was quantified in terms of structural similarity (SSIM) of the resulting image to diagnostic CT and Dice similarity metric (DSC) in lesion segmentation compared to ground truth. A pilot study was conducted involving seven subjects with CBCT images acquired during neurosurgery to assess the feasibility of DL-Recon in clinical data. CBCT images reconstructed via FBP with physics-based corrections exhibited the usual challenges to soft-tissue contrast resolution due to image non-uniformity, noise, and residual artifacts. GAN synthesis improved image uniformity and soft-tissue visibility but was subject to error in the shape and contrast of simulated lesions that were unseen in training. Incorporation of aleatoric uncertainty in synthesis loss improved estimation of epistemic uncertainty, with variable brain structures and unseen lesions exhibiting higher epistemic uncertainty. The DL-Recon approach mitigated synthesis errors while maintaining improvement in image quality, yielding 15%-22% increase in SSIM (image appearance compared to diagnostic CT) and up to 25% increase in DSC in lesion segmentation compared to FBP. Clear gains in visual image quality were also observed in real brain lesions and in clinical CBCT images. DL-Recon leveraged uncertainty estimation to combine the strengths of DL and physics-based reconstruction and demonstrated substantial improvements in the accuracy and quality of intraoperative CBCT. The improved soft-tissue contrast resolution could facilitate visualization of brain structures and support deformable registration with preoperative images, further extending the utility of intraoperative CBCT in image-guided neurosurgery.

COVID-ResNet: COVID-19 Recognition Based on Improved Attention ResNet

COVID-19 is the most widespread infectious disease in the world. There is an incubation period in the early stage of infection. At present, there are some difficulties in the diagnosis of COVID-19. Medical image analysis based on computed tomography (CT) images is an important tool for clinical diagnosis. However, the lesion size of COVID-19 is smaller, and the lesion shape of COVID-19 is more complex. The effect of the aided diagnosis model is not good. To solve this problem, an aided diagnostic model of COVID-ResNet was proposed based on CT images. Firstly, an improved attention ResNet model was designed based on CT images to focus on the focal lesion area. Secondly, the SE-Res block was constructed. The squeeze excitation mechanism with the residual connection was introduced into the ResNet. The SE-Res block can enhance the correlation degree among different channels and improve the overall accuracy of the model. Thirdly, MFCA (multi-layer feature converge attention) blocks were proposed, which extract multi-layer features. In this model, coordinated attention was used to focus on the direction information of the lesion area. Different layer features were concatenated so that the shallow layer and deep layer features were fused. The experimental results showed that the model could significantly improve the recognition accuracy of COVID-19. Compared with similar models, COVID-ResNet has better performance. On the COVID-19 CT dataset, the accuracy, recall rate, F1 score, and AUC value could reach 96.89%, 98.15%,96.96%, and 99.04%, respectively. Compared with the ResNet model, the accuracy, recall rate, F1 score, and AUC value were higher by 3.1%, 2.46%, 3.0%, and 1.16%, respectively. In ablation experiments, the experimental results showed that the SE-Res block and MFCA model proposed by us were effective. COVID-ResNet transfers the shallow features to the deep, gathers the features, and makes the information complementary. COVID-ResNet can improve the work efficiency of doctors and reduce the misdiagnosis rate. It has a positive significance for the computer-aided diagnosis of COVID-19.

Contour extraction of medical images using an attention-based network

A comprehensive analysis of medical images is important, as it assists in early screening and clinical treatment as well as subsequent rehabilitation. In general, the contour information can elaborately describe the shape and size of lesions in a medical image, which accurately reflects specific and valuable properties that facilitate the identification of abnormalities, so contour extraction is meaningful. However, the traditional method usually depends on the output of image segmentation, which causes blurred edges and loss of details. To address these issues, an effective attention-based network for contour extraction is proposed, where a model mixed with U-Net and an attention network is utilized to extract image features, and a multilayer perceptron (MLP) is employed to classify those features to obtain a clear contour. Compared with the existing methods, the experimental results on three datasets (Herlev, Drosophila, and ISIC-2017) show that the accuracy reaches approximately 93–98 % by using the proposed network, and the number of parameters is 46.4 % less than the deep active contour network (DACN). Such performances are impressive when considering accuracy and the number of parameters as the key concerns. Therefore, this study reduces the model computation with almost no loss of accuracy, which can satisfy clinical requirements for medical image analysis.

On Selecting, Ranking, and Quantifying Features for Building a Liver CT Diagnosis Aiding Computational Intelligence Method

The liver is one of the most common locations for incidental findings during abdominal CT scans. There are multiple types of disease that can arise within the liver and many of them are nodular. The ultimate goal of our research is to develop an expert knowledge-based system using fuzzy signatures, to support decisions during diagnosis of the most frequent of these nodular lesions. Since the literature contains limited information about the graphical properties of CT images that must be taken into consideration and their relationship to one another, in this paper we focused on selecting and ranking the input parameters using expert knowledge and determining their importance. Six visual attributes of lesions (size, shape, density, homogeneity contour, and other features) were selected based on textbooks of radiology and expert opinion. The importance of these attributes was ranked by radiologist experts using questionnaires and a pairwise comparison technique. The most important feature was found to be the density of the lesion on the various CT phases, and the least important was the size, the order of the other attributes was other features, contour, homogeneity, and shape, with a Kendall concordance coefficient of 0.612. Weights for the attributes, to be used in the future fuzzy signatures, were also determined. As a last step, several statistical parameter-based quantities were generated to represent the above abstract attributes and evaluated by comparing them to expert opinions.

Residual attention based uncertainty-guided mean teacher model for semi-supervised breast masses segmentation in 2D ultrasonography.

Breast tumor is the second deadliest disease among women around the world. Earlier tumor diagnosis is extremely important for improving the survival rate. Recent deep-learning techniques proved helpful in the timely diagnosis of various tumors. However, in the case of breast tumors, the characteristics of the tumors, i.e., low visual contrast, unclear boundary, and diversity in shape and size of breast lesions, make it more challenging to design a highly efficient detection system. Additionally, the scarcity of publicly available labeled data is also a major hurdle in the development of highly accurate and robust deep-learning models for breast tumor detection. To overcome these issues, we propose residual-attention-based uncertainty-guided mean teacher framework which incorporates the residual and attention blocks. The residual for optimizing the deep network by enabling the flow of high-level features and attention modules improves the focus of the model by optimizing its weights during the learning process. We further explore the potential of utilizing unlabeled data during the training process by employing the semi-supervised learning (SSL) method. Particularly, the uncertainty-guided mean-teacher student architecture is exploited to demonstrate the potential of incorporating the unlabeled samples during the training of residual attention U-Net model. The proposed SSL framework has been rigorously evaluated on two publicly available labeled datasets, i.e., BUSI and UDIAT datasets. The quantitative as well as qualitative results demonstrate that the proposed framework achieved competitive performance with respect to the previous state-of-the-art techniques and outperform the existing breast ultrasound masses segmentation techniques. Most importantly, the study demonstrates the potential of incorporating the additional unlabeled data for improving the performance of breast tumor segmentation.

SAN-Net: Learning generalization to unseen sites for stroke lesion segmentation with self-adaptive normalization

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular disease. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large inter-site discrepancy among different scanners, imaging protocols, and populations, but also the variations in stroke lesion shape, size, and location. To tackle this issue, we introduce a self-adaptive normalization network, termed SAN-Net, to achieve adaptive generalization on unseen sites for stroke lesion segmentation. Motivated by traditional z-score normalization and dynamic network, we devise a masked adaptive instance normalization (MAIN) to minimize inter-site discrepancies, which standardizes input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input; i.e., MAIN can affinely transform the intensity values. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation with a site classifier, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the “pseudosymmetry” of the human brain, we introduce a simple yet effective data augmentation technique, termed symmetry-inspired data augmentation (SIDA), that can be embedded within SAN-Net to double the sample size while halving memory consumption. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) v1.2 dataset, which includes MR images from 9 different sites, demonstrate that under the “leave-one-site-out” setting, the proposed SAN-Net outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

A partial convolution generative adversarial network for lesion synthesis and enhanced liver tumor segmentation.

Lesion segmentation is critical for clinicians to accurately stage the disease and determine treatment strategy. Deep learning based automatic segmentation can improve both the segmentation efficiency and accuracy. However, training a robust deep learning segmentation model requires sufficient training examples with sufficient diversity in lesion location and lesion size. This study is to develop a deep learning framework for generation of synthetic lesions with various locations and sizes that can be included in the training dataset to enhance the lesion segmentation performance. The lesion synthesis network is a modified generative adversarial network (GAN). Specifically, we innovated a partial convolution strategy to construct a U-Net-like generator. The discriminator is designed using Wasserstein GAN with gradient penalty and spectral normalization. A mask generation method based on principal component analysis (PCA) was developed to model various lesion shapes. The generated masks are then converted into liver lesions through a lesion synthesis network. The lesion synthesis framework was evaluated for lesion textures, and the synthetic lesions were used to train a lesion segmentation network to further validate the effectiveness of the lesion synthesis framework. All the networks are trained and tested on the LITS public dataset. Our experiments demonstrate that the synthetic lesions generated by our approach have very similar distributions for the two parameters, GLCM-energy and GLCM-correlation. Including the synthetic lesions in the segmentation network improved the segmentation dice performance from 67.3% to 71.4%. Meanwhile, the precision and sensitivity for lesion segmentation were improved from 74.6% to 76.0% and 66.1% to 70.9%, respectively. The proposed lesion synthesis approach outperforms the other two existing approaches. Including the synthetic lesion data into the training dataset significantly improves the segmentation performance.

MCA-UNet: multi-scale cross co-attentional U-Net for automatic medical image segmentation.

Medical image segmentation is a challenging task due to the high variation in shape, size and position of infections or lesions in medical images. It is necessary to construct multi-scale representations to capture image contents from different scales. However, it is still challenging for U-Net with a simple skip connection to model the global multi-scale context. To overcome it, we proposed a dense skip-connection with cross co-attention in U-Net to solve the semantic gaps for an accurate automatic medical image segmentation. We name our method MCA-UNet, which enjoys two benefits: (1) it has a strong ability to model the multi-scale features, and (2) it jointly explores the spatial and channel attentions. The experimental results on the COVID-19 and IDRiD datasets suggest that our MCA-UNet produces more precise segmentation performance for the consolidation, ground-glass opacity (GGO), microaneurysms (MA) and hard exudates (EX). The source code of this work will be released via https://github.com/McGregorWwww/MCA-UNet/.

The detection rate of granulomas differs between intestinal segments and lesions in Chinese patients with Crohn's disease

BackgroundCrohn's disease (CD) is characterized by non-caseating intestinal granulomas. However, the reported detection rate of granulomas on endoscopy is low. This study aimed to analyze the differences in the detection rate of granulomas in different intestinal segments and lesions in Chinese patients with CD to improve the detection rate of granulomas in clinical practice. Patients and methods113 patients with CD were analyzed retrospectively. Patients were divided into two groups: those with (n = 51) and without granulomas (n = 62) on endoscopic biopsies. Clinical information was collected from the medical records, including age; erythrocyte sedimentation rate (ESR); C-reactive protein (CRP), albumin, and hemoglobin (Hb) levels; platelet count; disease course; sex; smoking history; related operation history; Montreal classification; and lesion location, size, and shape. ResultsThe detection rates of granulomas in different lesion shapes were significantly different (P < 0.001), with those of longitudinal ulcers and circular ulcers being higher than those of erosion and irregular ulcers. We also found that the detection rates of granulomas in ascending colon and sigmoid colon were relatively higher than other segments of the intestine, however, the difference was not statistically significant (P = 0.716). Additionally, age, sex, smoking history, Montreal classification, related surgical history, disease course, and serum biochemical indicators (ESR; platelet count; and CRP, albumin, and Hb levels) were not significantly different between the two groups. ConclusionsThe detection rate of granulomas in patients with CD is related to the morphology of the intestinal lesions. Meanwhile, lesion location may be correlated with the detection rate of granulomas.

Prediction of high-grade patterns of stage IA lung invasive adenocarcinoma based on high-resolution CT features: a bicentric study.

This study aims to predict the high-grade pattern (HGP) of stage IA lung invasive adenocarcinoma (IAC) based on the high-resolution CT (HRCT) features. The clinical, pathological, and HRCT imaging data of 457 patients (from bicentric) with pathologically confirmed stage IA IAC (459 lesions in total) were retrospectively analyzed. The 459 lesions were classified into high-grade pattern (HGP) (n = 101) and non-high-grade pattern (n-HGP) (n = 358) groups depending on the presence of HGP (micropapillary and solid) in pathological results. The clinical and pathological data contained age, gender, smoking history, tumor stage, pathological type, and presence or absence of tumor spread through air spaces (STAS). CT features consisted of lesion location, size, density, shape, spiculation, lobulation, vacuole, air bronchogram, and pleural indentation. The independent predictors for HGP were screened by univariable and multivariable logistic regression analyses. The clinical, CT, and clinical-CT models were constructed according to the multivariable analysis results. The multivariate analysis suggested the independent predictors of HGP, encompassing tumor size (p = 0.001; OR = 1.090, 95% CI 1.035-1.148), density (p < 0.001; OR = 9.454, 95% CI 4.911-18.199), and lobulation (p = 0.002; OR = 2.722, 95% CI 1.438-5.154). The AUC values of clinical, CT, and clinical-CT models for predicting HGP were 0.641 (95% CI 0.583-0.699) (sensitivity = 69.3%, specificity = 79.2%), 0.851 (95% CI 0.806-0.896) (sensitivity = 79.2%, specificity = 79.6%), and 0.852 (95% CI 0.808-0.896) (sensitivity = 74.3%, specificity = 85.8%). The logistic regression model based on HRCT features has a good diagnostic performance for the high-grade pattern of stage IA IAC. • The AUC values of clinical, CT, and clinical-CT models for predicting high-grade patterns were 0.641 (95% CI 0.583-0.699), 0.851 (95% CI 0.806-0.896), and 0.852 (95% CI 0.808-0.896). • Tumor size, density, and lobulation were independent predictive markers for high-grade patterns. • The logistic regression model based on HRCT features has a good diagnostic performance for the high-grade patterns of invasive adenocarcinoma.

MCA-Unet: A multiscale context aggregation U-Net for the segmentation of COVID-19 lesions from CT images

The pandemic of coronavirus disease (COVID-19) caused the world to face an existential health crisis. COVID-19 lesions segmentation from CT images is nowadays an essential step to assess the severity of the disease and the amount of damage to the lungs. Deep learning has brought about a breakthrough in medical image segmentation where U-Net is the most prominent deep network. However, in this study, we argue that its architecture still lacks in certain aspects. First, there is an incompatibility in the U-Net skip connection between the encoder and decoder features which adversely affects the final prediction. Second, it lacks capturing multiscale context information and ignores the contribution of all semantic information through the segmentation process. Therefore, we propose a model named MCA-Unet, a novel multiscale deep learning segmentation model, which proposes some modifications to improve upon the U-Net model. MCA-Unet is integrated with a multiscale context aggregation module which is constituted of two blocks; a context embedding block (CEB) and a cascaded dilated convolution block (CDCB). The CEB aims at reducing the semantic gap between the concatenated features along the U-Net skip connections, it enriches the low-level encoder features with rich semantics inherited from the subsequent higher-level features, to reduce the semantic gap between the low-processed encoder features and the highly-processed decoder features, thus ensuring effectual concatenation. The CDCB is integrated to address the variability in shape and size of the COVID-19 lesions, it captures global context information by gradually expanding the receptive field, then operates reversely to capture the small fine details that might be scattered by enlarging the receptive field. To validate the robustness of our model, we tested it on a publicly available dataset of 1705 axial CT images with different types of COVID-19 infection. Experimental results show that MCA-Unet has attained a remarkable gain in performance in comparison with the basic U-Net and its variant. It achieved high performance using different evaluation metrics showing 88.6% Dice similarity coefficient, 85.4% Jaccard index, and 93.5% F-score measure. This outperformance shows great potential to help physicians during their examination and improve the clinical workflow.

MR findings of the inflammatory demyelinating diseases of the central nervous system

When demyelinating disease of the central nervous system is suspected, MR examination has mainly three roles: diagnosis, imaging biomarkers, and early detection of adverse effects from therapeutic agents. Because the location, size, shape, distribution, signal intensity, and contrast pattern of the brain lesions on MRI vary depending on the demyelinating diseases, careful attentions are required to assess the differential diagnosis and activity. It is necessary to be familiar with not only typical imaging findings but also atypical findings of demyelinating disease since minor neurological findings and nonspecific brain lesions may lead to misdiagnosis of demyelinating disease. This article reviewed the characteristics of MRI findings and showed recent topics of the demyelinating diseases.

The Effect of Varying Irrigation Flow Rate During Irrigated Radiofrequency Ablation on Optimizing Lesion Shape

The Effect of Varying Irrigation Flow Rate During Irrigated Radiofrequency Ablation on Optimizing Lesion Shape

A Multiscale Nonlocal Feature Extraction Network for Breast Lesion Segmentation in Ultrasound Images

Breast lesion segmentation in ultrasound images is of great importance since it can help us to characterize and localize lesion regions. However, low-quality imaging, blurred boundary, and variable lesion shapes bring challenges to accurate segmentation. In recent years, many U-Net variants have been proposed and successfully applied to breast lesion segmentation. However, these methods suffer from two limitations: (1) Ignoring the ability to capture rich global context information, and (2) Introducing extra complex operations. To alleviate these challenges, we propose a multiscale nonlocal feature extraction network (MNFE-Net) for accurately segmenting breast lesions. The core idea includes three points: (1) Parallel Encoder models long-range dependencies, (2) Multiscale Feature Module refines local features without introducing extra complex operations, and (3) Global Feature Guidance Module extracts global semantic information. MNFE-Net mainly has the following advantages: (1) The method has excellent performance for segmentation of malignant breast lesions, (2) The Parallel Encoder increases network parameters without significantly decreasing inference speed, and (3) The method is easy to understand and execute. Extensive experiment results with six state-of-the-art (SOTA) methods on three public breast ultrasound datasets demonstrate the superior segmentation performance of our proposed MNFE-Net.

Variability in Alternaria lini causing leaf blight disease of linseed (Linum usitatissimum L.)

Alternaria blight is an important disease of linseed that hampers its productivity and oil content. The pathogen is geneticallydiverse showing variability in respect of cultural, morphological and pathogenic characters. Variability in seventeen isolates of Alternaria lini was carried out. Studies on cultural variability showed considerable variation among the isolates. The colony diameter varied from 46.67- 71.67 mm after 96 hrs. of incubation and most of the isolates recorded medium growth rate (50-64mm). The isolates Alt-6,Alt-7 Alt-12 showed fast growth habit (&gt;65mm). The colony colour varied from grayish white, grey, dark olive green to grayish black. Sporulation in most of the isolates were late and concentric ring was present only in four isolates (Alt 3, Alt 8, Alt 13, Alt 14) while zonation was completely absent in other isolates. Morphologically different isolates of A. lini revealed variation with respect to mycelium width, size, shape, colour and septation of conidia. Mycelial width of most of the isolates having moderate to long width. Conidial length ranged from 24.87-33.68 mm similarly breadth of conidia ranged from7.54-10.67 mm. Transverse septation were more than longitudinal septation. Variation in beak size ranged from 3.5-6.4 mm while colour of conidia varied from brown to dark brown colour and most of the isolates exhibited obclavate, oval to obclavate shaped conidia while one isolate appeared as oval shaped. Studies on pathogenic variations revealed that the variation observed in accordance with the latent period, lesion size, lesion shape and plant disease index. The latent period of A. lini isolates varied from4.75 to 6.25 days with shortest (4.75 days) latent period recorded by isolates Alt-3 and Alt-11 and longest latent period of 6.25 days was observed in isolates Alt-6, Alt-14, Alt-16. The size of lesion varied from 2.25 to 4.75 mm and maximum lesions size (4.75 mm) was observed in isolate Alt-4 whereas minimum lesion size (2.25 mm) was observed in isolate Alt-5. The lesion produced after inoculation were elongated, oval and irregular in shape. The average number of lesions ranged from 2.75 to 4.00 with maximum number (4.00) of lesion recorded in isolate Alt-13. Plant disease index revealed that Meera and Nagarkot were more severe/virulent compare to Divya and Priyam in all the isolates.