scholarly journals Segmentação de imagens de ultrassonografia da carcaça em pequenos ruminantes utilizando Deep Learning

2021 ◽  
Author(s):  
Tiago M. Oliveira ◽  
José L. R. Sarmento ◽  
Luiz A. S. Figueiredo Filho ◽  
Romuere R. V. Silva
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Small Ruminants ◽  
Final Evaluation ◽  
Longissimus Dorsi ◽  
Muscle Area ◽  
Longissimus Dorsi Muscle ◽  
Dorsi Muscle ◽  
Goat Farming

Brazil is one of the main countries operating in the agribusiness sector. Sheep and goat farming is one of the segments of Brazilian agribusiness. The evaluation of each carcass of goats and sheep is carried out by a specialist who evaluates them based on visual aspects, being susceptible to errors in the final evaluation. In this context, the purpose of this work is to use Convolutional Neural Networks to segment the Longissimus dorsi muscle area in ultrasonographic images of small ruminants. Our experiments showed that the PSPNet CNN architecture achieved the results with an Intersect over Union (IoU) rate of 0.89. It was possible to obtain a precise segmentation of the images, which will allow the producer to correctly diagnose the measurements of the animals with greater practicality and saving time.

TheCOL9A1gene is associated with longissimus dorsi muscle area in the pig

2009 ◽  
Vol 40 (5) ◽  
pp. 788-788 ◽  
Author(s):  
B. Fan ◽  
S. K. Onteru ◽  
M. T. Nikkilä ◽  
K. J. Stalder ◽  
M. F. Rothschild
Keyword(s):  
Longissimus Dorsi ◽  
Muscle Area ◽  
Longissimus Dorsi Muscle ◽  
Dorsi Muscle

scholarly journals PROTEÍNA PROTEGIDA DE SOJA E O DESEMPENHO DE CORDEIROS EM CONFINAMENTO

2002 ◽  
Vol 7 (1) ◽  
Author(s):  
J. L. ANDRIGUETTO ◽  
E. CAVASSIN
Keyword(s):  
Plasma Glucose ◽  
Glucose Concentration ◽  
Plasma Glucose Concentration ◽  
Carcass Weight ◽  
Longissimus Dorsi ◽  
Muscle Area ◽  
Plasma Urea ◽  
Longissimus Dorsi Muscle ◽  
Dorsi Muscle ◽  
Perirenal Fat

O presente trabalho compara a eficiência de três formas de proteína de soja na alimentação de cordeiros confinados. Utilizaram-se 21 cordeiros machos, distribuídos em blocos ao acaso em três grupos de tratamento: farelo de soja (FS) (n=7); soja integral tostado (SIT) (n=7); proteína protegida de soja (PPS) (n=7). As três rações foram balanceadas de acordo com o NRC (1985) e continham os mesmos teores de proteína bruta (18%), energia metabolizável (2370 kcal/kg) e fibra em detergente neutro (38%), diferindo quanto à fonte principal de proteína. Os resultados médios obtidos para ganho de peso, consumo de ração e conversão alimentar não diferiram significativamente (P>0,05). Quanto às características de carcaça, não foram observadas diferenças significativas (P>0,05) para o peso de carcaça quente e para a área de olho de lombo. A taxa de rendimento de carcaça foi significativamente menor (P=0,05) com PPS. A porcentagem de gordura perirenal em relação ao peso de carcaça foi menor (P=0,07) com PPS do que com FS e SIT, que não diferiram entre si. Não foram observadas diferenças significativas nos níveis de glucose plasmática, porém os níveis plasmáticos de uréia aumentaram consideravelmente entre a segunda e a terceira semana após o início dos tratamentos, sendo que a elevação da concentração de uréia plasmática foi significativamente menor (P0.05). There were also no effects (P>0.05) on carcass weight and Longissimus dorsi muscle area. The carcass yield of lambs receiving PSP was significantly lower (P=0.05) than that observed with other sources of protein. The percentage of perirenal fat was also lower (P=0.07) for animals fed with PSP. There was no effect on plasma glucose concentration. Plasma urea levels, however, were increased after the second week of the beginning of the experiment, and that increase was significantly lower (P

A Technique for Measuring the Cross-Sectional Axes of the Longissimus Dorsi Muscle and Fat Depth in Lambs1,2

1960 ◽  
Vol 19 (3) ◽  
pp. 803-809
Author(s):  
D. J. Matthews ◽  
R. A. Merkel ◽  
J. D. Wheat ◽  
R. F. Cox
Keyword(s):  
Longissimus Dorsi ◽  
Cross Sectional ◽  
Longissimus Dorsi Muscle ◽  
Dorsi Muscle ◽  
The Cross

Intrauterine Growth Restriction Alters the Genome-Wide DNA Methylation Profiles in Small Intestine, Liver and Longissimus Dorsi Muscle of Newborn Piglets

2019 ◽  
Vol 20 (7) ◽  
pp. 713-726 ◽  
Author(s):  
Shiyu Tao ◽  
Tianjiao Zhou ◽  
Perot Saelao ◽  
Ying Wang ◽  
Yuhua Zhu ◽  
...  
Keyword(s):  
Small Intestine ◽  
Birth Weight ◽  
Intrauterine Growth Restriction ◽  
Longissimus Dorsi ◽  
Intrauterine Growth ◽  
Longissimus Dorsi Muscle ◽  
Newborn Piglets ◽  
Dorsi Muscle ◽  
Genome Wide ◽  
Differentially Methylated Genes

Intrauterine growth restriction (IUGR) remains a major problem in swine production since the associated low birth weight leads to high rates of pre-weaning morbidity and mortality, and permanent retardation of growth and development. The underlying regulatory mechanisms from the aspects of epigenetic modification has received widespread attention. Studies explore the changes in genome wide methylation in small intestine (SI), liver and longissimus dorsi muscle (LDM) between IUGR and normal birth weight (NBW) newborn piglets using a methylated DNA immunoprecipitation-sequencing (MeDIP-Seq) approach. The data demonstrated that methylated peaks were prominently distributed in distal intergenic regions and the quantities of peaks in IUGR piglets were more than that of NBW piglets. IUGR piglets had relatively high methylated level in promoters, introns and coding exons in all the three tissues. Through KEGG pathway analysis of differentially methylated genes found that 33, 54 and 5 differentially methylated genes in small intestine, liver and longissimus dorsi muscle between NBW and IUGR piglets, respectively, which are related to development and differentiation, carbohydrate and energy metabolism, lipid metabolism, protein turnover, immune response, detoxification, oxidative stress and apoptosis pathway. The objective of this review is to assess the impact of differentially methylation status on developmental delay, metabolic disorders and immune deficiency of IUGR piglets.

scholarly journals PSII-22 Comparison of the meat quality traits of crossbred pigs and the Large Black pigs

2019 ◽  
Vol 97 (Supplement_3) ◽  
pp. 241-242
Author(s):  
Yongjie Wang ◽  
Keshari Thakali ◽  
Sarah Shelby ◽  
Jason Apple ◽  
Yan Huang
Keyword(s):  
Meat Quality ◽  
Genomic Diversity ◽  
Longissimus Dorsi ◽  
Rna Seq ◽  
Longissimus Dorsi Muscle ◽  
A Value ◽  
Dorsi Muscle ◽  
Body Weights ◽  
C Value ◽  
Crossbred Pigs

Abstract The purpose of this study was to compare the meat quality and genomic differences between cross-bred commercial pig (CP) and domestic Large Black pig (BP). Seven cross-bred commercial pigs and eight British Large Black pigs were assigned to CP group and BP group, with initial mean body weights of 18.82±1.412 kg for CP group and 23.31±1.935 kg for BP group, P = 0.061, and fed ad libitum. The final BW of the CP at d101 was similar to the BP (130.0±8.16 kg vs. 121.1±2.80 kg, P = 0.132). However, the BP group took 108 days to reach the final BW. The ADG in the CP was higher than BP (1.102±0.0599 kg vs. 0.905±0.0138 kg, P = 0.003). The hot carcass weight of CP was higher (P < 0.01) than BP, but the backfat of BP was higher (P < 0.01) than CP. The a* value of CP was higher (P < 0.05) than BP, and the c* value of CP was tended to be higher (P < 0.10) than BP. However, the h value of BP was higher (P < 0.05) than CP. The longissimus dorsi muscle fat content of BP was higher (P < 0.05) than CP. For the fatty acid composition, the SFA and MUFA of BP were higher (P < 0.05) than CP, but the PUFA of CP was higher (P < 0.05) than BP. The metmyoglobin content of CP was tended to be higher (P < 0.10) than BP. For the meat metabolism, the oxygen consumption of longissimus dorsi muscle of BP was higher (P < 0.01) than CP. The RNA-Seq data showed that the expression of the genes related to lipid metabolism is higher in BP (fold change > 3, P < 0.05). To conclude, BP has higher meat quality, while CP has its advantages in growth performance. And the differences between these two breeds may due to the genomic diversity.

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

Sign in / Sign up

Export Citation Format

Share Document