Regression of Instance Boundary by Aggregated CNN and GCN

Meng, Yanda; Meng, Wei; Gao, Dongxu; Zhao, Yitian; Yang, Xiaoyun; Huang, Xiaowei; Zheng, Yalin

doi:10.1007/978-3-030-58598-3_12

Cited by 27 publications

(24 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optic disc/cup and fetal head: The size of the optic disc and optic cup in color fundus images is also of great importance for the diagnosis of glaucoma, an irreversible eye disease. Meng et al [ 164 ] developed a multi-level aggregation network to regress the coordinates of the boundary of instances instead of using a pixel-wise dense prediction. This model combines a CNN with an attention refine module and a GCN.…”

Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning

confidence: 99%

“…Compared to a previous work from the same authors [ 165 ], this model also extracts feature correlations among different layers in the GCN. Meng et al [ 164 ] also demonstrated the effectiveness of the network in the segmentation of the fetal head in ultrasound images. Fetal head circumference in ultrasound images is a critical indicator for prenatal diagnosis and can be used to estimate the gestational age and to monitor the growth of the fetus [ 171 ].…”

Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Ahmedt-Aristizabal

Armin

Denman

et al. 2021

Sensors

136

View full text Add to dashboard Cite

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered, which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be determined by either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.

show abstract

Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning

confidence: 99%

Section: Case Studies Of Gnn For Medical Diagnosis and Analysismentioning

confidence: 99%

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Ahmedt-Aristizabal

Armin

Denman

et al. 2021

Sensors

136

View full text Add to dashboard Cite

show abstract

“…Deep Learning based works has achieved superior performance in many computer vision tasks, such as classification [4,61], segmentation [29,30,6,66], and registration [5]. In this section, we will discuss and compare with deeplearning based crowd counting methods in different supervision manners.…”

Section: Related Workmentioning

confidence: 99%

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

Meng

Zhang

Zhao

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Self Cite

View full text Add to dashboard Cite

Semi-supervised approaches for crowd counting attract attention, as the fully supervised paradigm is expensive and laborious due to its request for a large number of images of dense crowd scenarios and their annotations. This paper proposes a spatial uncertainty-aware semi-supervised approach via regularized surrogate task (binary segmentation) for crowd counting problems. Different from existing semisupervised learning-based crowd counting methods, to exploit the unlabeled data, our proposed spatial uncertaintyaware teacher-student framework focuses on high confident regions' information while addressing the noisy supervision from the unlabeled data in an end-to-end manner. Specifically, we estimate the spatial uncertainty maps from the teacher model's surrogate task to guide the feature learning of the main task (density regression) and the surrogate task of the student model at the same time. Besides, we introduce a simple yet effective differential transformation layer to enforce the inherent spatial consistency regularization between the main task and the surrogate task in the student model, which helps the surrogate task to yield more reliable predictions and generates high-quality uncertainty maps. Thus, our model can also address the task-level perturbation problems that occur spatial inconsistency between the primary and surrogate tasks in the student model. Experimental results on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised methods. Code is available at : https://github.com/ smallmax00/SUA_crowd_counting

show abstract

“…As a result, multiple HC segmentation hypotheses are provided to the clinicians, which can choose the best one. Segmentation CNNs with attention mechanism are investigated in [10,11], showing interesting preliminary results.…”

Section: State Of the Artmentioning

confidence: 99%

“…We decided to compare the performance of Mask-R 2 CNN against [4], which is the most similar to this work, and against [6,8,10,14,17] which follow the deeplearning paradigm and use the HC18 Grand Challenge dataset only. We excluded the work in [11] because it uses a portion of the training set of the HC18 Grand Challenge for evaluation purposes. We decided to include also the work in [1], even if it relies on handcrafted features, because it introduced the HC18 Grand Challenge dataset.…”

Section: Ablation Study and Comparison With The Literaturementioning

confidence: 99%

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

2021

View full text Add to dashboard Cite

Background and objectives Fetal head-circumference (HC) measurement from ultrasound (US) images provides useful hints for assessing fetal growth. Such measurement is performed manually during the actual clinical practice, posing issues relevant to intra- and inter-clinician variability. This work presents a fully automatic, deep-learning-based approach to HC delineation, which we named Mask-R$$^{2}$$ 2 CNN. It advances our previous work in the field and performs HC distance-field regression in an end-to-end fashion, without requiring a priori HC localization nor any postprocessing for outlier removal. Methods Mask-R$$^{2}$$ 2 CNN follows the Mask-RCNN architecture, with a backbone inspired by feature-pyramid networks, a region-proposal network and the ROI align. The Mask-RCNN segmentation head is here modified to regress the HC distance field. Results Mask-R$$^{2}$$ 2 CNN was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. With a comprehensive ablation study, we showed that Mask-R$$^{2}$$ 2 CNN achieved a mean absolute difference of 1.95 mm (standard deviation $$=\pm 1.92$$ = ± 1.92 mm), outperforming other approaches in the literature. Conclusions With this work, we proposed an end-to-end model for HC distance-field regression. With our experimental results, we showed that Mask-R$$^{2}$$ 2 CNN may be an effective support for clinicians for assessing fetal growth.

show abstract

Regression of Instance Boundary by Aggregated CNN and GCN

Cited by 27 publications

References 40 publications

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

Contact Info

Product

Resources

About