Cascaded U-net for Kidney and Tumor Segmentation from CT volumes

2020 ◽  
Vol 2 (1) ◽  
pp. 004-008
Author(s):  
Asha K Kumaraswamy ◽  
Chandrashekar Patil
Keyword(s):  
Semantic Segmentation ◽  
Ct Images ◽  
Difficult Problem ◽  
Training Data ◽  
Tumor Segmentation ◽  
Computer Assisted ◽  
Kidney Tumors ◽  
Cross Sectional ◽  
Morphological Heterogeneity ◽  
Enhanced Computed Tomography

Contrast-enhanced Computed Tomography (CT) imaging is most useful tool in diagnosing and locating the kidney lesions. An automated kidney and tumor segmentation are very helpful because it can provide the precise information about the location and size of lesions which can be used in quantitative analysis of the tumor. Semantic segmentation of kidney is very challenging as it requires large dataset for training and its morphological heterogeneity makes it a difficult problem. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) has publicly released a 210 cross sectional CT images with kidney tumors along with corresponding semantic segmentation masks. In this work we proposed a novel two stage 2D segmentation method to automatically segment kidney and tumor using the combination of Unet++ and squeeze and excite approach. The proposed network is trained in keras framework. Our method achieves a dice score of 0.98 and 0.965 with kidney and tumor respectively on training data and the results demonstrates the accuracy of our proposed method. Proposed method was able to segment kidney and tumor from abdominal CT images which can provide the exact location and size of the tumor. This information can also be used to analyze treatment response.

An international challenge to use artificial intelligence to define the state-of-the-art in kidney and kidney tumor segmentation in CT imaging.

2020 ◽  
Vol 38 (6_suppl) ◽  
pp. 626-626
Author(s):  
Nicholas Heller ◽  
Sean McSweeney ◽  
Matthew Thomas Peterson ◽  
Sarah Peterson ◽  
Jack Rickman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Treatment Decision ◽  
Semantic Segmentation ◽  
Ct Images ◽  
Renal Tumors ◽  
Tumor Segmentation ◽  
Computer Assisted ◽  
Kidney Tumor ◽  
3D Segmentation ◽  
Kidney Tumors

626 Background: The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was an international competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) and sought to stimulate progress on this automatic segmentation frontier. Growing rates of kidney tumor incidence led to research into the use of artificial inteligence (AI) to radiographically differentiate and objectively characterize these tumors. Automated segmentation using AI objectively quantifies complexity and aggression of renal tumors to better differentiate and describe the tumors for improved treatment decision making. Methods: A training set of over 31,000 CT images from 210 patients with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated deep learning systems to predict the true segmentation masks on a test set of an additional 13,500 CT images in 90 patients for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between kidney and tumor across the 90 test cases. Results: The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the human inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an “open leaderboard” phase where it serves as a challenging benchmark in 3D semantic segmentation. Conclusions: Results of the KiTS19 challenge show deep learning methods are fully capable of reliable segmentation of kidneys and kidney tumors. The KiTS19 challenge attracted a high number of submissions and serves as an important and challenging benchmark in 3D segmentation. The publicly available data will further propel the use of automated 3D segmentation analysis. Fully segmented kidneys and tumors allow for automated calculation of all types of nephrometry, tumor textural variation and discovery of new predictive features important for personalized medicine and accurate prediction of patient relevant outcomes.

scholarly journals Automated Ventricular System Segmentation in Paediatric Patients Treated for Hydrocephalus Using Deep Learning Methods

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Michał Klimont ◽  
Mateusz Flieger ◽  
Jacek Rzeszutek ◽  
Joanna Stachera ◽  
Aleksandra Zakrzewska ◽  
...  
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Ct Images ◽  
Policy Transfer ◽  
Training Data ◽  
Intraobserver Variability ◽  
Practical Applications ◽  
Brain Scans ◽  
Rate Policy ◽  
Ct Brain

Hydrocephalus is a common neurological condition that can have traumatic ramifications and can be lethal without treatment. Nowadays, during therapy radiologists have to spend a vast amount of time assessing the volume of cerebrospinal fluid (CSF) by manual segmentation on Computed Tomography (CT) images. Further, some of the segmentations are prone to radiologist bias and high intraobserver variability. To improve this, researchers are exploring methods to automate the process, which would enable faster and more unbiased results. In this study, we propose the application of U-Net convolutional neural network in order to automatically segment CT brain scans for location of CSF. U-Net is a neural network that has proven to be successful for various interdisciplinary segmentation tasks. We optimised training using state of the art methods, including “1cycle” learning rate policy, transfer learning, generalized dice loss function, mixed float precision, self-attention, and data augmentation. Even though the study was performed using a limited amount of data (80 CT images), our experiment has shown near human-level performance. We managed to achieve a 0.917 mean dice score with 0.0352 standard deviation on cross validation across the training data and a 0.9506 mean dice score on a separate test set. To our knowledge, these results are better than any known method for CSF segmentation in hydrocephalic patients, and thus, it is promising for potential practical applications.

scholarly journals Aggregation-and-Attention Network for brain tumor segmentation

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Chih-Wei Lin ◽  
Yu Hong ◽  
Jinfu Liu
Keyword(s):  
Brain Tumor ◽  
Semantic Information ◽  
Spatial Relationship ◽  
Tumor Segmentation ◽  
Computer Assisted ◽  
Brain Tumor Segmentation ◽  
Attention Network ◽  
Multi Scale ◽  
Assisted Diagnosis ◽  
The Brain

Abstract Background Glioma is a malignant brain tumor; its location is complex and is difficult to remove surgically. To diagnosis the brain tumor, doctors can precisely diagnose and localize the disease using medical images. However, the computer-assisted diagnosis for the brain tumor diagnosis is still the problem because the rough segmentation of the brain tumor makes the internal grade of the tumor incorrect. Methods In this paper, we proposed an Aggregation-and-Attention Network for brain tumor segmentation. The proposed network takes the U-Net as the backbone, aggregates multi-scale semantic information, and focuses on crucial information to perform brain tumor segmentation. To this end, we proposed an enhanced down-sampling module and Up-Sampling Layer to compensate for the information loss. The multi-scale connection module is to construct the multi-receptive semantic fusion between encoder and decoder. Furthermore, we designed a dual-attention fusion module that can extract and enhance the spatial relationship of magnetic resonance imaging and applied the strategy of deep supervision in different parts of the proposed network. Results Experimental results show that the performance of the proposed framework is the best on the BraTS2020 dataset, compared with the-state-of-art networks. The performance of the proposed framework surpasses all the comparison networks, and its average accuracies of the four indexes are 0.860, 0.885, 0.932, and 1.2325, respectively. Conclusions The framework and modules of the proposed framework are scientific and practical, which can extract and aggregate useful semantic information and enhance the ability of glioma segmentation.

scholarly journals Correlation between lung infection severity and clinical laboratory indicators in patients with COVID-19: a cross-sectional study based on machine learning

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xingrui Wang ◽  
Qinglin Che ◽  
Xiaoxiao Ji ◽  
Xinyi Meng ◽  
Lang Zhang ◽  
...  
Keyword(s):  
Peripheral Blood Lymphocyte ◽  
Peripheral Blood ◽  
Blood Lymphocyte ◽  
Clinical Laboratory ◽  
Lung Infection ◽  
Cross Sectional Study ◽  
Ct Images ◽  
Sectional Study ◽  
Laboratory Examination ◽  
Cross Sectional

Abstract Background Coronavirus disease 2019 (COVID-19) has caused a global pandemic that has raised worldwide concern. This study aims to investigate the correlation between the extent of lung infection and relevant clinical laboratory testing indicators in COVID-19 and to analyse its underlying mechanism. Methods Chest high-resolution computer tomography (CT) images and laboratory examination data of 31 patients with COVID-19 were extracted, and the lesion areas in CT images were quantitatively segmented and calculated using a deep learning (DL) system. A cross-sectional study method was carried out to explore the differences among the proportions of lung lobe infection and to correlate the percentage of infection (POI) of the whole lung in all patients with clinical laboratory examination values. Results No significant difference in the proportion of infection was noted among various lung lobes (P > 0.05). The POI of total lung was negatively correlated with the peripheral blood lymphocyte percentage (L%) (r = − 0.633, P < 0.001) and lymphocyte (LY) count (r = − 0.555, P = 0.001) but positively correlated with the neutrophil percentage (N%) (r = 0.565, P = 0.001). Otherwise, the POI was not significantly correlated with the peripheral blood white blood cell (WBC) count, monocyte percentage (M%) or haemoglobin (HGB) content. In some patients, as the infection progressed, the L% and LY count decreased progressively accompanied by a continuous increase in the N%. Conclusions Lung lesions in COVID-19 patients are significantly correlated with the peripheral blood lymphocyte and neutrophil levels, both of which could serve as prognostic indicators that provide warning implications, and contribute to clinical interventions in patients.

scholarly journals Evaluating the relationship between citation set size, team size and screening methods used in systematic reviews: a cross-sectional study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Katie O’Hearn ◽  
Cameron MacDonald ◽  
Anne Tsampalieros ◽  
Leo Kadota ◽  
Ryan Sandarage ◽  
...  
Keyword(s):  
Systematic Reviews ◽  
Full Text ◽  
Gold Standard ◽  
Data Extraction ◽  
Statistical Testing ◽  
Computer Assisted ◽  
Screening Methods ◽  
Team Size ◽  
Cross Sectional ◽  
Set Size

Abstract Background Standard practice for conducting systematic reviews (SRs) is time consuming and involves the study team screening hundreds or thousands of citations. As the volume of medical literature grows, the citation set sizes and corresponding screening efforts increase. While larger team size and alternate screening methods have the potential to reduce workload and decrease SR completion times, it is unknown whether investigators adapt team size or methods in response to citation set sizes. Using a cross-sectional design, we sought to understand how citation set size impacts (1) the total number of authors or individuals contributing to screening and (2) screening methods. Methods MEDLINE was searched in April 2019 for SRs on any health topic. A total of 1880 unique publications were identified and sorted into five citation set size categories (after deduplication): < 1,000, 1,001–2,500, 2,501–5,000, 5,001–10,000, and > 10,000. A random sample of 259 SRs were selected (~ 50 per category) for data extraction and analysis. Results With the exception of the pairwise t test comparing the under 1000 and over 10,000 categories (median 5 vs. 6, p = 0.049) no statistically significant relationship was evident between author number and citation set size. While visual inspection was suggestive, statistical testing did not consistently identify a relationship between citation set size and number of screeners (title-abstract, full text) or data extractors. However, logistic regression identified investigators were significantly more likely to deviate from gold-standard screening methods (i.e. independent duplicate screening) with larger citation sets. For every doubling of citation size, the odds of using gold-standard screening decreased by 15 and 20% at title-abstract and full text review, respectively. Finally, few SRs reported using crowdsourcing (n = 2) or computer-assisted screening (n = 1). Conclusions Large citation set sizes present a challenge to SR teams, especially when faced with time-sensitive health policy questions. Our study suggests that with increasing citation set size, authors are less likely to adhere to gold-standard screening methods. It is possible that adjunct screening methods, such as crowdsourcing (large team) and computer-assisted technologies, may provide a viable solution for authors to complete their SRs in a timely manner.

scholarly journals Monitoring of dietary changes by telephone interviews: results from Denmark

2001 ◽  
Vol 4 (6) ◽  
pp. 1287-1295 ◽  
Author(s):  
Jóhanna Haraldsdóttir ◽  
Lotte Holm ◽  
Arne Vernon Astrup ◽  
Jytte Halkjær ◽  
Steen Stender
Keyword(s):  
Food Habits ◽  
Dietary Guidelines ◽  
Computer Assisted ◽  
Cross Sectional ◽  
Use Patterns ◽  
Telephone Interviews ◽  
Frequent Monitoring ◽  
Whole Milk ◽  
Consumption Frequency ◽  
Drinking Milk

AbstractObjectives:To monitor trends in Danish food habits with respect to selected key elements, from 1995 to 1998, and to evaluate the appropriateness of the method developed for that purpose.Design and method:Two cross-sectional population surveys, in 1995 and 1998. Data collection by computer-assisted telephone interviews including 10 food-frequency questions, questions on type of fat used on sandwiches and drinking milk, and check questions on the previous day. Reproducibility was tested in a subgroup (n=222) in the 1998 survey.Setting:The Danish Nutrition Council initiated the survey.Subjects:Men and women aged 15–90 years, 1007 in 1995 and 1024 in 1998. Samples of private telephone numbers were drawn from regional telephone registers, geographically stratified. Participation rates were 62%.Results:Significant differences were observed between 1995 and 1998, some of these in accordance with dietary guidelines (decreased use of whole milk and fat spread on bread, increased use of skimmed milk, salad vegetables, rice/pasta and fish). Other changes were opposite to dietary guidelines (increased use of soft butter, decreased use of soft margarine and low-fat spreads, potatoes, and fresh fruit). Differences in average consumption frequency amounted to 4–13%. Several results were confirmed by comparison with other data, and the reproducibility of the method was acceptable. Data were suitable for analysis of food use patterns, a relevant approach when assessing food habits in a lifestyle context.Conclusions:The changes observed illustrate the dynamics of food habits and the need for frequent monitoring. This simple telephone method may be a valuable tool for that purpose, as a supplement to national dietary surveys, also in a public health context.

scholarly journals Morphometrical Study of the Lumbar Segment of the Internal Vertebral Venous Plexus in Dogs: A Contrast CT-Based Study

Animals ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1502
Author(s):  
Valeria Ariete ◽  
Natalia Barnert ◽  
Marcelo Gómez ◽  
Marcelo Mieres ◽  
Bárbara Pérez ◽  
...  
Keyword(s):  
Epidural Space ◽  
Ct Images ◽  
Venous Plexus ◽  
Morphological Pattern ◽  
Vertebral Canal ◽  
Dural Sac ◽  
Internal Vertebral Venous Plexus ◽  
Adjacent Structures ◽  
Contrast Ct ◽  
Enhanced Computed Tomography

The internal vertebral venous plexus (IVVP) is a thin-walled, valveless venous network that is located inside the vertebral canal, communicating with the cerebral venous sinuses. The objective of this study was to perform a morphometric analysis of the IVVP, dural sac, epidural space and vertebral canal between the L1 and L7 vertebrae with contrast-enhanced computed tomography (CT). Six clinically healthy adult dogs weighing between 12 kg to 28 kg were used in the study. The CT venographic protocol consisted of a manual injection of 880 mgI/kg of contrast agent (587 mgI/kg in a bolus and 293 mgI/mL by continuous infusion). In all CT images, the dimensions of the IVVP, dural sac, and vertebral canal were collected. Dorsal reconstruction CT images showed a continuous rhomboidal morphological pattern for the IVVP. The dural sac was observed as a rounded isodense structure throughout the vertebral canal. The average area of the IVVP ranged from 0.61 to 0.74 mm2 between L1 and L7 vertebrae (6.3–8.9% of the vertebral canal), and the area of the dural sac was between 1.22 and 7.42 mm2 (13.8–72.2% of the vertebral canal). The area of the epidural space between L1 and L7 ranged from 2.85 to 7.78 mm2 (27.8–86.2% of the vertebral canal). This CT venography protocol is a safe method that allows adequate visualization and morphometric evaluation of the IVVP and adjacent structures.

Optimal Scale of Hierarchical Image Segmentation with Scribbles Guidance for Weakly Supervised Semantic Segmentation

2021 ◽  
pp. 2154026
Author(s):  
Zaid Al-Huda ◽  
Donghai Zhai ◽  
Yan Yang ◽  
Riyadh Nazar Ali Algburi
Keyword(s):  
Image Segmentation ◽  
Graphical Model ◽  
Semantic Segmentation ◽  
Saliency Map ◽  
Training Data ◽  
Deep Convolutional Neural Networks ◽  
High Quality ◽  
Optimal Scale ◽  
Supervised Segmentation ◽  
Weakly Supervised

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is [Formula: see text] mIoU.

scholarly journals Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3232 ◽  
Author(s):  
Yan Liu ◽  
Qirui Ren ◽  
Jiahui Geng ◽  
Meng Ding ◽  
Jiangyun Li
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Large Scale ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Training Data ◽  
Land Resources ◽  
Remote Sensing Images ◽  
Training Strategy ◽  
The Impact

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Sign in / Sign up

Export Citation Format

Share Document