Review of Semantic Segmentation of Medical Images Using Modified Architectures of UNET

AnbuDevi, M. Krithika alias; Suganthi, K.

doi:10.3390/diagnostics12123064

Cited by 45 publications

(24 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…To achieve this, we leverage the power of DL and use the UNet architecture, which has been widely adopted in various medical imaging tasks and has proven successful in segmenting complex structures. [14][15][16] Training the UNet model involves a comprehensive dataset of 1219 OCT images obtained from 300 patients, encompassing the different IOL models. By incorporating this diverse dataset, our system ensures robust analysis across various lens characteristics.…”

Section: Assessment Of Iol Glistening By Octmentioning

confidence: 99%

See 1 more Smart Citation

Comparative study of the glistening between four intraocular lens models assessed by optical coherence tomography and deep learning

Fernández-Vigo,

Macarro-Merino,

De Moura-Ramos

et al. 2023

J Cataract Refract Surg

View full text Add to dashboard Cite

Purpose: To evaluate the glistening in four different models of intraocular lenses (IOL) using optical coherence tomography (OCT) and deep learning (DL). Setting: XXXX Design: Cross-sectional study. Methods: 325 eyes were assessed for the presence and severity of glistening in four IOL models: ReSTOR+3 SN6AD1® (n=41), SN60WF® (n=110), PanOptix TFNT® (n=128) and Vivity DFT015® (n=46). The presence of glistening was analyzed using OCT, identifying the presence of hyperreflective foci (HRF) in the central area of the IOL. A manual and an original DL-based quantification algorithm designed for this purpose was applied. Results: Glistening was detected in 22 (53.7%) ReSTOR SN6AD1, 44 (40%) SN60WF, 49 (38.3%) PanOptix TFNT, and 4 (8.7%) Vivity DFT015 IOLs, when any grade was considered. In the comparison of the different types of IOLs, global glistening measured as total HRF was 17.3 ±25.9 for the ReSTOR+3; 9.3 ±15.7 for the SN60WF; 6.9 ±10.5 for the PanOptix; and 1.2 ±2.6 for the Vivity (p<0.05). There was excellent agreement between manual and DL-based quantification (≥0.829). Conclusions: It is possible to quantify, classify and compare the glistening severity in different IOL models using OCT images in a simple and objective manner with a DL algorithm. In the comparative study, the Vivity presented the lowest severity of glistening.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Assessment Of Iol Glistening By Octmentioning

confidence: 99%

Comparative study of the glistening between four intraocular lens models assessed by optical coherence tomography and deep learning

Fernández-Vigo,

Macarro-Merino,

De Moura-Ramos

et al. 2023

J Cataract Refract Surg

View full text Add to dashboard Cite

show abstract

“…UNet has become a widely recognized architecture in medical image segmentation, known for its ability to effectively capture both local and global contextual information [6]. Researchers have introduced various UNet variants, generally maintaining the U structure to ensure high accuracy [7]. One notable variant is UNet++, which incorporates nested skip connections (NSC) and deep supervision to capture intricate details and optimize the integration of feature maps [8].…”

Section: Existing Neural Networkmentioning

confidence: 99%

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

Krishnan,

Schmidt,

Onuoha

et al. 2024

Medical Imaging 2024: Clinical and Biomedical Imaging

View full text Add to dashboard Cite

Autosomal Dominant Polycystic Kidney Disease (ADPKD) presents a significant clinical challenge, demanding precise and efficient diagnostic tools. In this context, this research addresses the imperative need for accurate diagnosis of ADPKD through the refinement of deep learning models, specifically UNet++ and UNet3+, for precise segmentation of renal structures and cysts in T2W MRI images. By incorporating residual staging, switch normalization, and concatenated skip connections (CSC), our proposed models, rUNet++ and rUNet3+, aim to enhance feature fusion, extraction, and segmentation accuracy. Utilizing a dataset of 760 MRI images from 95 patients, we trained, validated, and tested the models, assigning images exclusively to each set to eliminate bias. The ground truth was established through a semi-automated technique. Evaluation metrics, including Dice Similarity Coefficient (DSC) and Mean Surface Distance (MSD), demonstrated improved performance for rUNet++ and rUNet3+, with the latter exhibiting the highest test minimum DSCs for kidneys and the former for the cysts. The proposed models achieved average DSC scores of 0.95±0.02 and 0.94±0.03 respectively for kidneys and 0.88±0.04 and 0.86±0.05 for cysts. The clinical significance of these findings lies in the enhanced precision of total kidney volume quantification, a vital biomarker for ADPKD diagnosis. This automated approach not only streamlines the diagnostic process but also reduces manual involvement, addressing a crucial aspect in the clinical workflow. By presenting a modified deep learning architecture, this research contributes to advancing the technological landscape in medical imaging, offering a promising avenue for improving the clinical management of ADPKD through accurate and efficient segmentation.

show abstract

“…[28] These multiscale feature fusion structures are also widely used in other image generation networks, thus becoming their basis. [37][38][39] Therefore, we propose a deep learning network for SSRNet for multitask prediction. We constructed an encoder-decoder FCN and incorporated a Unet-based feature fusion structure at the beginning and end of the network to improve the quality of the generated images.…”

Section: Ssrnetmentioning

confidence: 99%

SSRNet: A Deep Learning Network via Spatial‐Based Super‐resolution Reconstruction for Cell Counting and Segmentation

Deng

Zhou

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Cell counting and segmentation are critical tasks in biology and medicine. The traditional methods for cell counting are labor‐intensive, time‐consuming, and prone to human errors. Recently, deep learning‐based cell counting methods have become a trend, including point‐based counting methods, such as cell detection and cell density prediction, and non‐point‐based counting, such as cell number regression prediction. However, the point‐based counting method heavily relies on well‐annotated datasets, which are scarce and difficult to obtain. On the other hand, nonpoint‐based counting is less interpretable. The task of cell counting by dividing it into two subtasks is approached: cell number prediction and cell distribution prediction. To accomplish this, a deep learning network for spatial‐based super‐resolution reconstruction (SSRNet) is proposed that predicts the cell count and segments the cell distribution contour. To effectively train the model, an optimized multitask loss function (OM loss) is proposed that coordinates the training of multiple tasks. In SSRNet, a spatial‐based super‐resolution fast upsampling module (SSR‐upsampling) is proposed for feature map enhancement and one‐step upsampling, which can enlarge the deep feature map by 32 times without blurring and achieves fine‐grained detail and fast processing. SSRNet uses an optimized encoder network. Compared with the classic U‐Net, SSRNet's running memory read and write consumption is only 1/10 of that of U‐Net, and the total number of multiply and add calculations is 1/20 of that of U‐Net. Compared with the traditional sampling method, SSR‐upsampling can complete the upsampling of the entire decoder stage at one time, reducing the complexity of the network and achieving better performance. Experiments demonstrate that the method achieves state‐of‐the‐art performance in cell counting and segmentation tasks. The method achieves nonpoint‐based counting, eliminating the need for exact position annotation of each cell in the image during training. As a result, it has demonstrated excellent performance on cell counting and segmentation tasks. The code is public on GitHub (https://github.com/Roin626/SSRnet).

show abstract

Review of Semantic Segmentation of Medical Images Using Modified Architectures of UNET

Cited by 45 publications

References 78 publications

Comparative study of the glistening between four intraocular lens models assessed by optical coherence tomography and deep learning

Comparative study of the glistening between four intraocular lens models assessed by optical coherence tomography and deep learning

Enhancing the UNet3+ architecture for deep learning segmentation of kidneys and cysts in autosomal dominant polycystic kidney disease (ADPKD)

SSRNet: A Deep Learning Network via Spatial‐Based Super‐resolution Reconstruction for Cell Counting and Segmentation

Contact Info

Product

Resources

About