COVID-19 Volumetric Pulmonary Lesion Estimation on CT Images using a U-NET and Probabilistic Active Contour Segmentation

Cendejas-Zaragoza, Leopoldo; Rodríguez-Obregón, D. E.; Mejía-Rodríguez, Aldo R.; Arce-Santana, Edgar R.; Santos‐Díaz, Alejandro

doi:10.1109/embc46164.2021.9629532

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These sUNet had evolved based on the applications of the individual studies. We have taken special care by categorizing the sUNet into eight distinct types, that integrates concepts such as (i) scales (sUNet.Scale) [57], (ii) parallel connection of convolutions (sUNet.Par) [57], (iii) cascading (or tandem connection) of convolutions (sUNet.Cascade) [60], (iv) integration of probability maps for boundary extraction (sUNet.Bndy) [65], (v) tailoring of fundamental cUNet by residual network (ResNet) models (sUNet.Res) [59,70,75,76], (vi) introducing feedback 5 system to improve cUNet performance (sUNet.Feed) [58] (vii) deriving the contextual encoder network information during the down sampling process (sUNet.Context) [74], (viii) change in dimensionality from 2-D to 3-D (sUNet.Dim) [59,60], and (ix) adjustment in the loss function upgrades while up sampling during the reconstruction process (sUNet.Loss) [76]. The components of UNet that were changed are encoder (E), decoder (D), skip connection (SC), bridge network (BgN), and the loss function (LF).…”

Section: Superior Unet Types -A Special Notementioning

confidence: 99%

“…We have identified 19 such modifications and categorized them as miscellaneous UNet. The modifications were namely, (M1) UNet combined with CNN for feature extraction and Random Forest for ML classification [63,124]; UNet-based lung segmentation + feature extraction using high resolution network (HRNet) + FCN (Softmax) [55,63]; (M2) changes after the last decoder with Conv [54,162]; (M3) cascade of two plain UNet for segmentation [53,72,73,93,148]; (M4) cascade of two 3D UNet [42,53,96,114,141]; (M5) patch input to the conventional CNN [98,105,121]; (M6) feedback system to improve the training [58]; (M7) fusion of parametric (active contour model) curves with UNet for COVID-19 lesion segmentation [60];…”

Section: E Miscellaneous Variations In Unet By External Additionsmentioning

confidence: 99%

See 1 more Smart Citation

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Suri¹,

Bhagawati

Agarwal³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Background & Motivation: Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. Methods: PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Findings and Conclusions: Vascular and non-vascular UNet systems dominated with sUNet classes with attention. The majority of the studies suffered from low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings. INDEX TERMS Image segmentation; vascular; non-vascular; UNet classes; UNet variations; UNetcomponents; explainable AI; pruning; bias.

show abstract

Section: Superior Unet Types -A Special Notementioning

confidence: 99%

Section: E Miscellaneous Variations In Unet By External Additionsmentioning

confidence: 99%

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Suri¹,

Bhagawati

Agarwal³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Deep learning solutions can be classified into three categories: First is deep neural networks with an attention mechanism trained by a primary information constraint [16] . For example, Inf-net obtained the low-level semantic features of contours in advance and then performed a network training to segment the GGO areas of chest CT [7] , [17] . It was also influential in connecting an attention-rejecting network with an interactive attention-thinning network to segment the infected regions of GGO [18] .…”

Section: Related Workmentioning

confidence: 99%