Search

Purpose: Machine learning algorithms are best trained with large quantities of accurately annotated samples. While natural scene images can often be labeled relatively cheaply and at large scale, obtaining accurate annotations for medical images is both time consuming and expensive. In this study, we propose a cooperative labeling method that allows us to make use of weakly annotated medical imaging data for the training of a machine learning algorithm. As most clinically produced data are weakly‐annotated – produced for use by humans rather than machines and lacking information machine learning depends upon – this approach allows us to incorporate a wider range of clinical data and thereby increase the training set size. Methods: Our pseudo‐labeling method consists of multiple stages. In the first stage, a previously established network is trained using a limited number of samples with high‐quality expert‐produced annotations. This network is used to generate annotations for a separate larger dataset that contains only weakly annotated scans. In the second stage, by cross‐checking the two types of annotations against each other, we obtain higher‐fidelity annotations. In the third stage, we extract training data from the weakly annotated scans, and combine it with the fully annotated data, producing a larger training dataset. We use this larger dataset to develop a computer‐aided detection (CADe) system for nodule detection in chest CT. Results: We evaluated the proposed approach by presenting the network with different numbers of expert‐annotated scans in training and then testing the CADe using an independent expert‐annotated dataset. We demonstrate that when availability of expert annotations is severely limited, the inclusion of weakly‐labeled data leads to a 5% improvement in the competitive performance metric (CPM), defined as the average of sensitivities at different false‐positive rates. Conclusions: Our proposed approach can effectively merge a weakly‐annotated dataset with a small, well‐annotated dataset for algorithm training. This approach can help enlarge limited training data by leveraging the large amount of weakly labeled data typically generated in clinical image interpretation. [ABSTRACT FROM AUTHOR]

Purpose: Most state‐of‐the‐art automated medical image analysis methods for volumetric data rely on adaptations of two‐dimensional (2D) and three‐dimensional (3D) convolutional neural networks (CNNs). In this paper, we develop a novel unified CNN‐based model that combines the benefits of 2D and 3D networks for analyzing volumetric medical images. Methods: In our proposed framework, multiscale contextual information is first extracted from 2D slices inside a volume of interest (VOI). This is followed by dilated 1D convolutions across slices to aggregate in‐plane features in a slice‐wise manner and encode the information in the entire volume. Moreover, we formalize a curriculum learning strategy for a two‐stage system (i.e., a system that consists of screening and false positive reduction), where the training samples are presented to the network in a meaningful order to further improve the performance. Results: We evaluated the proposed approach by developing a computer‐aided detection (CADe) system for lung nodules. Our results on 888 CT exams demonstrate that the proposed approach can effectively analyze volumetric data by achieving a sensitivity of > 0.99 in the screening stage and a sensitivity of > 0.96 at eight false positives per case in the false positive reduction stage. Conclusion: Our experimental results show that the proposed method provides competitive results compared to state‐of‐the‐art 3D frameworks. In addition, we illustrate the benefits of curriculum learning strategies in two‐stage systems that are of common use in medical imaging applications. [ABSTRACT FROM AUTHOR]

Purpose: Multiview two‐dimensional (2D) convolutional neural networks (CNNs) and three‐dimensional (3D) CNNs have been successfully used for analyzing volumetric data in many state‐of‐the‐art medical imaging applications. We propose an alternative modular framework that analyzes volumetric data with an approach that is analogous to radiologists' interpretation, and apply the framework to reduce false positives that are generated in computer‐aided detection (CADe) systems for pulmonary nodules in thoracic computed tomography (CT) scans. Methods: In our approach, a deep network consisting of 2D CNNs first processes slices individually. The features extracted in this stage are then passed to a recurrent neural network (RNN), thereby modeling consecutive slices as a sequence of temporal data and capturing the contextual information across all three dimensions in the volume of interest. Outputs of the RNN layer are weighed before the final fully connected layer, enabling the network to scale the importance of different slices within a volume of interest in an end‐to‐end training framework. Results: We validated the proposed architecture on the false positive reduction track of the lung nodule analysis (LUNA) challenge for pulmonary nodule detection in chest CT scans, and obtained competitive results compared to 3D CNNs. Our results show that the proposed approach can encode the 3D information in volumetric data effectively by achieving a sensitivity >0.8 with just 1/8 false positives per scan. Conclusions: Our experimental results demonstrate the effectiveness of temporal analysis of volumetric images for the application of false positive reduction in chest CT scans and show that state‐of‐the‐art 2D architectures from the literature can be directly applied to analyzing volumetric medical data. As newer and better 2D architectures are being developed at a much faster rate compared to 3D architectures, our approach makes it easy to obtain state‐of‐the‐art performance on volumetric data using new 2D architectures. [ABSTRACT FROM AUTHOR]

A 56-d feeding trial was conducted to investigate the effect of dietary mannan-oligosaccharides ( MOS) and fructo-oligosaccharide ( FOS) on growth indices, body composition, intestinal bacterial community and digestive enzymes activity of regal peacock. A total of 240 fish were randomly distributed to 15 experimental units (40-L aquariums) of 16 fish each. These replicates were randomly assigned to one of five treatments in a 2 × 2 + 1 factorial arrangement. The treatments were control diet (no MOS and FOS), diet A (2 gkg−1 MOS + 1.5 g kg−1 FOS), diet B (2 g kg−1 MOS + 3 g kg−1 FOS), diet C (4 g kg−1 MOS + 1.5 g kg−1 FOS) or diet D (4 g kg−1 MOS + 3 g kg−1 FOS). The results showed that feeding diet C increased specific growth rate and protein efficiency ratio and decreased feed conversion ratio compared with control diet. Higher intestinal trypsin activity and increased Lactobacillus counts were observed in fish fed diets B and C. All diets significantly elevated body protein deposition and intestinal amylase activity compared to the control diet. In conclusion, the diet supplemented with 4 g kg−1 MOS + 1.5 g kg−1 FOS was advantageous over other MOS + FOS-supplemented diets, with respect to growth performance and health benefits of regal peacock. [ABSTRACT FROM AUTHOR]

The study of digestive enzymes activity at Salmo caspius fry showed that enzymes were available at the moment of mouth opening on the first day post hatching (dph) and the activity of enzymes showed no significant difference from the hatching day 28 dph. An increased activity was seen between 32 and 43 dph and this activity was significantly higher than the activity during the first 28 days. In the primary stages after yolk sac resorption (43–58 dph), enzymes activity showed an increased profile, however none of them showed a significant difference between 43 and 58 dph. [ABSTRACT FROM AUTHOR]

The utilization of dehulled lupin as a partial replacement for fish meal was studied in diets of rainbow trout. Fish were fed diets with 0%, 10%, 20%, 30%, 40% and 50% of dehulled lupin, at a daily feeding rate of 2% body weight for 8 weeks at 15 ± 0.5 °C. Growth performance generally decreased with increasing dehulled lupin in the diet (R[SUP2] = 0.81, P < 0.0001). However, there was no significant difference between 0%, 10%, 20%, 30% and 40% dehulled lupin fed groups. Feed conversion ratio generally increased at higher inclusion levels of dehulled lupin (R[SUP2] = 0.74, P < 0.002). The protein efficiency ratio, protein productive value, lipid efficiency ratio and lipid productive value were similar in all groups but the energy efficiency ratio was significantly lower (P < 0.01) in the 50% dehulled lupin fed group. Different treatments showed similar digestive enzyme activity, villus height, pyloric caeca and hepato somatic indexes. None of the nonspecific immune responses, with the exception of total plasma protein and neutrophils, was affected by different inclusion level of lupin. Results show that dehulled lupin can be included at up to 40% of a rainbow trout diet without a significant effect on growth performance or nutrient utilization. Rainbow trout utilize dehulled lupin protein as efficiently as fish meal protein but have a lower ability to utilize the energy content of dehulled lupin at higher inclusion levels. [ABSTRACT FROM AUTHOR]

A functional factor X deficiency is described which caused pronounced reduction in the in vitro activation of the extrinsic system while marginally affecting the in vitro activation of the intrinsic pathway. All studies were normal with the exception of a prolonged PT, an elevated factor X antigen, and low factor X activity. Western blot analysis revealed the presence of two factor X species. The abnormal molecule was of higher molecular weight. Interestingly, there was no bleeding associated with this deficiency. The biochemical basis of this defect is currently under investigation.

Amyloidosis primarily involving bone is described in a 59-year-old male pateint. Well circumscribed lytic lesions of the skeleton raised the possibility of myelomatosis. The prolonged insidious course of the disease was uncomplicated by hypercalcemia, pathological fracture, or hematologic abnormalities. The clinical course, together with histological findings and strongly positive bone scan, were the distinguishing features. The osseous manifestations without plasma cell tumor appears to be a rare occurrence in amyloidosis.