A Survey on Shape-Constraint Deep Learning for Medical Image Segmentation

Bohlender, Simon; Öksüz, İlkay; Mukhopadhyay, Anirban

doi:10.1109/rbme.2021.3136343

Cited by 20 publications

(4 citation statements)

References 117 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, box annotations [35] are required as coarse mask generation for pseudo mask labels in weakly supervised instance segmentation, then these labels are utilized as training samples for the self-training instance segmentation stage. As one-stage frameworks, PolarMask [31], [110] via polar coordinate and contour proposal networks [32]- [34] via contour modeling utilized the regressed shape representation for the simultaneous object detection and segmentation. Compared with the Encoder-Decoder segmentation architecture, detection-based segmentation under the guidance of region proposal and shape representation are more computationally efficient, suitable for instance segmentation, and beneficial for context relationship expression, while the Encoder-Decoder segmentation architecture has the advantage of fine segmentation.…”

Section: A Deep Learning Modelmentioning

confidence: 99%

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Liu,

Dong,

Qin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: A Deep Learning Modelmentioning

confidence: 99%

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Liu,

Dong,

Qin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Recent 2D-3D reconstruction studies have reconstructed full CT scans from a single or limited number of X-ray images using deep learning approaches [31][32][33], which would require an additional segmentation step to extract the final respiratory geometry. This approach is purely based on the pixel information, and does not have any constraint on the anatomical shape [34], allowing erroneous CT reconstructions to cause noise in the segmented geometry. A simpler approach would be to use a SSAM as a generator for possible shapes and evaluate their fit to the given X-ray, as done by Baka et al [20].…”

Section: Introductionmentioning

confidence: 99%

Validated respiratory drug deposition predictions from 2D and 3D medical images with statistical shape models and convolutional neural networks

Williams,

Ahlqvist,

Cunningham

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

For the one billion sufferers of respiratory disease, managing their disease with inhalers crucially influences their quality of life. Generic treatment plans could be improved with the aid of computational models that account for patient-specific features such as breathing pattern, lung pathology and morphology. Therefore, we aim to develop and validate an automated computational framework for patient-specific deposition modelling. To that end, an image processing approach is proposed that could produce 3D patient respiratory geometries from 2D chest X-rays and 3D CT images. We evaluated the airway and lung morphology produced by our image processing framework, and assessed deposition compared to in vivo data. The 2D-to-3D image processing reproduces airway diameter to 9% median error compared to ground truth segmentations, but is sensitive to outliers of up to 33% due to lung outline noise. Predicted regional deposition gave 5% median error compared to in vivo measurements. The proposed framework is capable of providing patient-specific deposition measurements for varying treatments, to determine which treatment would best satisfy the needs imposed by each patient (such as disease and lung/airway morphology). Integration of patient-specific modelling into clinical practice as an additional decision-making tool could optimise treatment plans and lower the burden of respiratory diseases.

show abstract

“…Furthermore, the training of radiologists in this specialized domain necessitates a substantial investment of time and financial resources. With the increasing volume of brain tumor image datasets, it becomes even more susceptible to subjective bias and human errors during the assessment [7,8].…”

Section: Introductionmentioning

confidence: 99%

MCE: Medical Cognition Embedded in 3D MRI feature extraction for advancing glioma staging

Xue,

Lu,

Wang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

In recent years, various data-driven algorithms have been applied to the classification and staging of brain glioma MRI detection. However, the restricted availability of brain glioma MRI data in purely data-driven deep learning algorithms has presented challenges in extracting high-quality features and capturing their complex patterns. Moreover, the analysis methods designed for 2D data necessitate the selection of ideal tumor image slices, which does not align with practical clinical scenarios. Our research proposes an novel brain glioma staging model, Medical Cognition Embedded (MCE) model for 3D data. This model embeds knowledge characteristics into data-driven approaches to enhance the quality of feature extraction. Approach includes the following key components: (1) Deep feature extraction, drawing upon the imaging technical characteristics of different MRI sequences, has led to the design of two methods at both the algorithmic and strategic levels to mimic the learning process of real image interpretation by medical professionals during film reading; (2) We conduct an extensive Radiomics feature extraction, capturing relevant features such as texture, morphology, and grayscale distribution; (3) By referencing key points in radiological diagnosis, Radiomics feature experimental results, and the imaging characteristics of various MRI sequences, we manually create diagnostic features (Diag-Features). The efficacy of proposed methodology is rigorously evaluated on the publicly available BraTS2018 and BraTS2020 datasets. Comparing it to most well-known purely data-driven models, our method achieved higher accuracy, recall, and precision, reaching 96.14%, 93.4%, 97.06%, and 97.57%, 92.80%, 95.96%, respectively.

show abstract

A Survey on Shape-Constraint Deep Learning for Medical Image Segmentation

Cited by 20 publications

References 117 publications

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Validated respiratory drug deposition predictions from 2D and 3D medical images with statistical shape models and convolutional neural networks

MCE: Medical Cognition Embedded in 3D MRI feature extraction for advancing glioma staging

Contact Info

Product

Resources

About