Towards a better understanding of annotation tools for medical imaging: a survey

Aljabri, Manar; AlAmir, Manal; Ghamdi, Manal Al; Abdel-Mottaleb, Mohamed; Collado-Mesa, Fernando

doi:10.1007/s11042-022-12100-1

Cited by 47 publications

(19 citation statements)

References 132 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, the region of interest was specified with a freehand-drawn mask and thus, the manual annotation would negatively affect the accuracy of the image analysis and segmentation. The deep learning-based automatic annotation workflow 30 can be used to enhance the accuracy and speed of the annotation process for further studies. In teeth with large interproximal contact areas, any uncertainty during the process of intersecting triangles for the connected component might affect the generation of STL data.…”

Section: Discussionmentioning

confidence: 99%

A digital workflow for pair matching of maxillary anterior teeth using a 3D segmentation technique for esthetic implant restorations

Choi

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

We investigated a state-of-the-art algorithm for 3D reconstruction with a pair-matching technique, which enabled the fabrication of individualized implant restorations in the esthetic zone. This method compared 3D mirror images of crowns and emergence profiles between symmetric tooth pairs in the anterior maxilla using digital slicewise DICOM segmentation and the superimposition of STL data. With the outline extraction of each segment provided by 100 patients, the Hausdorff distance (HD) between two point sets was calculated to identify the similarity of the sets. By using HD thresholds as a pair matching criterion, the true positive rates of crowns were 100, 98, and 98%, while the false negative rates were 0, 2, and 2% for central incisors, lateral incisors, and canines, respectively, indicating high pair matching accuracy (> 99%) and sensitivity (> 98%). The true positive rates of emergence profiles were 99, 100, and 98%, while the false negative rates were 1, 0, and 2% for central incisors, lateral incisors, and canines, respectively, indicating high pair matching accuracy (> 99%) and sensitivity (> 98%). Therefore, digitally flipped contours of crown and emergence profiles can be successfully transferred for implant reconstruction in the maxillary anterior region to optimize esthetics and function.

show abstract

Section: Discussionmentioning

confidence: 99%

A digital workflow for pair matching of maxillary anterior teeth using a 3D segmentation technique for esthetic implant restorations

Choi

Kim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The rest of the region is marked as 0, background portion. 28 Thus, the binary masked ground truth images are generated from the JSON files as shown in Fig. 6.…”

Section: Generating Ground Truth Mask Imagesmentioning

confidence: 99%

Optimized deep feature selective concatenation of recurrent encoder model and pretrained convolutional neural network model for leaf disease identification

Indu

Priyadharsini

2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Automated plant disease identification is one of the significant tasks in the agricultural sector. With the advent of deep-learning models, classification and segmentation have been completely automated using a convolutional neural network (CNN). This paper proposes the UV-Net model, with a recurrent encoder and an up-sampling decoder for multiclass image segmentation and generation of masks. The improvement of the segmentation model is the stacking of conv2D layers before the down convolution operation, concatenation of features extracted from the convolution process, up-sampling along with transpose convolution in the expansion path, and exponential linear unit (ELU) activation. This model is combined with an optimized, pretrained, and self-trained CNN for generating the classes of diseased leaves. The classification is further enhanced by concatenating the high-level features extracted from the pretrained CNN model along with the low-level features from the encoder part of the UV-Net model. The features are concatenated using the hybrid wind-driven particle swarm optimized (WDPSO) deep feature selective concatenation mechanism (DFSCM). The proposed model is trained and the performance is tested on multiclass diseases of tomato plants like bacterial spot, early blight, leaf mold, and target spot. The proposed architecture is also compared with some of the well-known CNN models such as FCN, FPN, U-Net, V-Net, and Mask R-CNN. The model proves to be a robust system for detecting diseases from images of varying sizes, shapes, and lighting. The proposed model achieved an average training accuracy of 98.20% with a dice coefficient of 0.8938 and an Intersection over union coefficient (IoU) of 0.7458. The model also generates accurate masks from which the intensity and pattern of diseases could be identified for earlier prevention and treatment of diseases.

show abstract

“…Dataset Annotation: The deep-learning-based image segmentation algorithms rely heavily on expert-annotated images with marked regions of interest (RoI) using contours for optimal performance. There exist several annotation methods to effectively draw the contours in the images [1]. However, the manual annotation of US images is a time-consuming, labour-intensive, and expensive procedure.…”

Section: Introductionmentioning

confidence: 99%

Slim U-Net: Efficient Anatomical Feature Preserving U-net Architecture for Ultrasound Image Segmentation

Raina

Verma

Chandrashekhara

et al. 2023

Preprint

View full text Add to dashboard Cite

We investigate the applicability of U-Net based models for segmenting Urinary Bladder (UB) in male pelvic view UltraSound (US) images. The segmentation of UB in the US image aids radiologists in diagnosing the UB. However, UB in US images has arbitrary shapes, indistinct boundaries and considerably large inter- and intra-subject variability, making segmentation a quite challenging task. Our study of the state-of-the-art (SOTA) segmentation network, U-Net, for the problem reveals that it often fails to capture the salient characteristics of UB due to the varying shape and scales of anatomy in the noisy US image. Also, U-net has an excessive number of trainable parameters, reporting poor computational efficiency during training. We propose a Slim U-Net to address the challenges of UB segmentation. Slim U-Net proposes to efficiently preserve the salient features of UB by reshaping the structure of U-Net using a less number of 2D convolution layers in the contracting path, in order to preserve and impose them on expanding path. To effectively distinguish the blurred boundaries, we propose a novel annotation methodology, which includes the background area of the image at the boundary of a marked region of interest (RoI), thereby steering the model's attention towards boundaries. In addition, we suggested a combination of loss functions for network training in the complex segmentation of UB. The experimental results demonstrate that Slim U-net is statistically superior to U-net for UB segmentation. The Slim U-net further decreases the number of trainable parameters and training time by 54% and 57.7%, respectively, compared to the standard U-Net, without compromising the segmentation accuracy.

show abstract

Towards a better understanding of annotation tools for medical imaging: a survey

Cited by 47 publications

References 132 publications

A digital workflow for pair matching of maxillary anterior teeth using a 3D segmentation technique for esthetic implant restorations

A digital workflow for pair matching of maxillary anterior teeth using a 3D segmentation technique for esthetic implant restorations

Optimized deep feature selective concatenation of recurrent encoder model and pretrained convolutional neural network model for leaf disease identification

Slim U-Net: Efficient Anatomical Feature Preserving U-net Architecture for Ultrasound Image Segmentation

Contact Info

Product

Resources

About