Automatic Segmentation and Quantification of Thigh Tissues in CT Images

Felinto, Jonas de Carvalho; Poloni, Katia Maria; Freire, Paulo Guilherme de Lima; Aily, Jéssica Bianca; Almeida, Aline Castilho de; Pedroso, M.; Mattiello, Stela Márcia; Ferrari, Ricardo José

doi:10.1007/978-3-319-95162-1_18

Cited by 5 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Skeletal muscle and adipose tissue areas will be calculated by the attenuation value range for skeletal muscle tissue (0 to 100 Hounsfield) and adipose tissue (−190 to −30 Hounsfield) [ 46 , 47 ]. The mean muscle attenuation will be calculated by the average of the Hounsfield values obtained in the muscle fascia area.…”

Section: Methods: Participants Interventions and Outcomesmentioning

confidence: 99%

Effects of a periodized circuit training protocol delivered by telerehabilitation compared to face-to-face method for knee osteoarthritis: a protocol for a non-inferiority randomized controlled trial

Aily

Almeida

Noronha

et al. 2021

Trials

Self Cite

View full text Add to dashboard Cite

Background Regular exercise is an effective method for reducing pain and disability in patients with knee osteoarthritis (OA), as well as improving body composition. Thus, a combination of both resistance and aerobic training (circuit training) has shown to be promising for this population. However, access to physical therapy is limited by physical distance, social isolation, and/or treatment costs. Remote rehabilitation seems to be an effective way to minimize these barriers, but the benefits are dependent on the participants’ adherence to the interventions provided at a distance. The objectives of this protocol are to compare the effects of a periodized circuit training applied via telerehabilitation with the same protocol applied in the face-to-face model for individuals with knee OA. Methods This study presents a single-blinded protocol for a non-inferiority randomized controlled trial. One hundred participants diagnosed with knee OA (grades II and III Kellgren and Lawrence system), aged 40 years or more, and BMI < 30 kg/m2 will be randomly divided into two groups: telerehabilitation (TR) and face-to-face (FtF) circuit training. The FtF group will perform a 14-week periodized circuit training protocol supervised by a physical therapist, 3 times a week. The TR group will perform the same exercise protocol at home, at least 3 times a week. In addition, the TR group will be able to follow the execution and orientations of the exercises by DVD, a website, and online file sharing tools, and they will receive periodic phone calls in order to motivate, clarify, and inform some aspects of knee OA. The primary outcomes are changes in self-reported pain intensity (visual analog scale (VAS)) and physical function (Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC)), with a primary end-point of 14 weeks and a secondary end-point of 26 weeks. Secondary outcomes include changes in other clinical outcomes, in morphological characteristics, adherence, acceptability, and treatment perspective. Discussion A circuit training through telerehabilitation may contribute to developing early intervention in the causative and potentiating factors of the knee OA, verifying the effects of a low-cost, non-pharmacological and non-invasive treatment. Trial registration Brazilian Registry of Clinical Trials (ReBEC) ID: RBR-662hn2. Registered on 31 March 2019. Link: http://www.ensaiosclinicos.gov.br; Universal Trial Number (UTN) of World Health Organization: U1111-1230-9517.

show abstract

Section: Methods: Participants Interventions and Outcomesmentioning

confidence: 99%

Effects of a periodized circuit training protocol delivered by telerehabilitation compared to face-to-face method for knee osteoarthritis: a protocol for a non-inferiority randomized controlled trial

Aily

Almeida

Noronha

et al. 2021

Trials

Self Cite

View full text Add to dashboard Cite

show abstract

“…Tan et al 4 proposed using a variational Bayesian Gaussian mixture model to cluster fat, marrow, muscle bone, and air on three-dimensional (3D) CT scans. Felinto et al 5 proposed using a Gaussian mixture model and relative position to cluster similar tissues for intermuscular fat and muscles segmentation. With impressive performance of the deep neural network-based segmentation, Zhu et al 6 applied the H-DenseU-Net on MRI lower leg data of children with and without cerebral palsy.…”

Section: Introductionmentioning

confidence: 99%

“…proposed using a variational Bayesian Gaussian mixture model to cluster fat, marrow, muscle bone, and air on three-dimensional (3D) CT scans. Felinto et al 5 . proposed using a Gaussian mixture model and relative position to cluster similar tissues for intermuscular fat and muscles segmentation.…”

Section: Introductionmentioning

confidence: 99%

Label efficient segmentation of single slice thigh CT with two-stage pseudo labels

Yang

Lee

et al. 2022

J. Med. Imag.

View full text Add to dashboard Cite

. Purpose: Muscle, bone, and fat segmentation from thigh images is essential for quantifying body composition. Voxelwise image segmentation enables quantification of tissue properties including area, intensity, and texture. Deep learning approaches have had substantial success in medical image segmentation, but they typically require a significant amount of data. Due to the high cost of manual annotation, training deep learning models with limited human label data is desirable, but it is a challenging problem. Approach: Inspired by transfer learning, we proposed a two-stage deep learning pipeline to address the thigh and lower leg segmentation issue. We studied three datasets, 3022 thigh slices and 8939 lower leg slices from the BLSA dataset and 121 thigh slices from the GESTALT study. First, we generated pseudo labels for thigh based on approximate handcrafted approaches using CT intensity and anatomical morphology. Then, those pseudo labels were fed into deep neural networks to train models from scratch. Finally, the first stage model was loaded as the initialization and fine-tuned with a more limited set of expert human labels of the thigh. Results: We evaluated the performance of this framework on 73 thigh CT images and obtained an average Dice similarity coefficient (DSC) of 0.927 across muscle, internal bone, cortical bone, subcutaneous fat, and intermuscular fat. To test the generalizability of the proposed framework, we applied the model on lower leg images and obtained an average DSC of 0.823. Conclusions: Approximated handcrafted pseudo labels can build a good initialization for deep neural networks, which can help to reduce the need for, and make full use of, human expert labeled data.

show abstract

“…Usually, the differentiation between tissues requires an accurate segmentation of the fascia lata of the thigh. Especially in CT with relatively low soft tissue contrast, this can be a challenging task [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Segmentation of the fascia lata and reproducible quantification of intermuscular adipose tissue (IMAT) of the thigh

Chaudry

Friedberger

Grimm

et al. 2020

Magn Reson Mater Phy

View full text Add to dashboard Cite

Objective To develop a precise semi-automated segmentation of the fascia lata (FL) of the thigh to quantify IMAT volume in T1w MR images and fat fraction (FF) in Dixon MR images. Materials and methods A multi-step segmentation approach was developed to identify fibrous structures of the FL and combining them into a closed 3D surface. 23 healthy young men with low and 50 elderly sarcopenic men with moderate levels of IMAT were measured by T1w and 6pt Dixon MRI at 3T. 20 datasets were used to determine reanalysis precision errors. IMAT volume was compared using the new FL segmentation versus an easier to segment but less accurate, tightly fitting envelope of the thigh muscle ensemble. Results The segmentation was successfully applied to all 73 datasets and took about 7 min per 28 slices. In particular, in elderly subjects, it includes a large amount of adipose tissue below the FL typically not accounted for in other segmentation approaches. Inter- and intra-operator RMS-CVs were 0.33% and 0.14%, respectively, for IMAT volume and 0.04% and 0.02%, respectively, for FFMT. Discussion The FL segmentation is an important step to quantify IMAT with high precision and may be useful to investigate effects of aging and treatment on changes of IMAT and FF. ClinicalTrials.gov identifier NCT2857660, August 5, 2016. Trial registration ClinicalTrials.gov identifier NCT2857660, August 5, 2016.

show abstract

Automatic Segmentation and Quantification of Thigh Tissues in CT Images

Cited by 5 publications

References 29 publications

Effects of a periodized circuit training protocol delivered by telerehabilitation compared to face-to-face method for knee osteoarthritis: a protocol for a non-inferiority randomized controlled trial

Effects of a periodized circuit training protocol delivered by telerehabilitation compared to face-to-face method for knee osteoarthritis: a protocol for a non-inferiority randomized controlled trial

Label efficient segmentation of single slice thigh CT with two-stage pseudo labels

Segmentation of the fascia lata and reproducible quantification of intermuscular adipose tissue (IMAT) of the thigh

Contact Info

Product

Resources

About