Automatic detection of vessel structure by deep learning using intravascular ultrasound images of the coronary arteries

Shinohara, Hiroki; Kodera, Satoshi; Ninomiya, Kota; Nakamoto, Mitsuhiko; Katsushika, Susumu; Saito, Akihito; Minatsuki, Shun; Kikuchi, Hiromi; Kiyosue, Arihiro; Higashikuni, Yasutomi; Takeda, Norifumi; Fujiu, Katsuhito; Ando, Jiro; Akazawa, Hiroshi; Morita, Hiroyuki; Komuro, Issei

doi:10.1371/journal.pone.0255577

Cited by 14 publications

(24 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To begin with, the encoder is the most adapted and most changeable component of the UNet architecture. Since it is practically not possible to study each of the architectural variations in the encoder, we have therefore listed here the 23 variations (E1 to E23, representing encoder changes) along with their references in a tabular format and it is as follows: (E1) conventional system (Ronneberger) [43][44][45][46][47][48][49][50][51][52]90]; (E2) cascade of convolutions [77,91,99,116,117]; (E3) parallel convolutions (multiple convolution network) [57]; (E4) convolution with dropout [70,76,86,95,101,102,134,138]; (E5) Residual network [76,78,105,129,135,138,[149][150][151]; (E6) Xception encoder [56,88,112]; (E7) encoder layers with independent inputs [104,140]; (E8) squeeze excitation (SE) network [92,103,138]; (E9) pooling types (max pooling, global average pooling) [95]; (E10) input image dimension change with changing filter (channe...…”

Section: A Encoder Variationsmentioning

confidence: 99%

“…Note that the decoder receives input in many different ways, such as encoder, skip connection or data after data transmission via bridge network (or bottle neck). Using these fundamental changes, the decoder variations can be categorized into 16 different type listed as follows: (D1) convolution with dropout [70,76,86,95,101,102,134,138]; (D2) UNet++ type of change [130,144,154]; (D3) UNet+++ (UNet 3+) Full scale deep supervision [157]; (D4) Output from decoders to make a loss function [104,140]; (D5) fusion of the decoder outputs for scale adjustment [59,107]; (D6) recurrent residual [118,129,138]; (D7) residual block [75,84,88,105,138,150]; (D8) channel attention and scale attention block [65,113]; (D9) transpose convolution [66,88,94,95,139]; (D10) squeeze excitation (SE) Network [103,125]; (D11) cascade convolution [99]; (D12) addition of original image to each layer [100]; (D13) batch normalization [95,106,155]; (D14) inception block [97]; (D15) dense layer [87,91,…”

Section: B Decoder Variationsmentioning

confidence: 99%

“…The different fundamental blocks which were adapted for UNet modification were (Table 4): (1) residual block [75,76,78,84,88,105,129,135,138]; (2) classifier in encoder [145]; (3) Xception block [56,88]; (4) dense layer block [68,100,102,122,142]; (5) recurrent residual block ; (6) attention block [65, 66, 71, 75, 113, 125, 128, 129, 131-135, 139, 161]; (7) dropout layer [70,76,86,95,101,102,134,138]; (8) dilated convolution [67,76]; (9) transpose convolution [66,88,95,137,139]; (10) SE network [92,103,125,133,138], and (11) squeeze and excitation block [92,103,125,133,138].…”

Section: G Understanding Major Blocks Affecting For Unet Modificationmentioning

confidence: 99%

See 2 more Smart Citations

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: A Encoder Variationsmentioning

confidence: 99%

Section: B Decoder Variationsmentioning

confidence: 99%

Section: G Understanding Major Blocks Affecting For Unet Modificationmentioning

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

show abstract

“…Further, the extraction of arterial borders is done using deep learning architectures with promising results. [12][13][14][15][16][17] Dense calcium is regarded as the most typical type of plaque tissue, due to its' high echo-reflectivity. The amount of calcium present inside the artery is thought of as an important parameter by cardiologists in determining the accurate treatment plan.…”

Section: Introductionmentioning

confidence: 99%

“…Further, the extraction of arterial borders is done using deep learning architectures with promising results. 12-17…”

Section: Introductionmentioning

confidence: 99%

Calcification Detection in Intravascular Ultrasound (IVUS) Images Using Transfer Learning Based MultiSVM model

et al. 2023

View full text Add to dashboard Cite

Cardiovascular disease serves as the leading cause of death worldwide. Calcification detection is considered an important factor in cardiovascular diseases. Currently, medical practitioners visually inspect the presence of calcification using intravascular ultrasound (IVUS) images. The study aims to detect the extent of calcification as belonging to class I, II as mild calcification, and class III, IV as dense calcification from IVUS images acquired at 40 MHz. To detect calcification, the features were extracted using improved AlexNet architecture and then were fed into machine learning classifiers. The experiments were carried out using 14 real IVUS pullbacks of 10 patients. Experimental results show that the combination of traditional machine learning with deep learning approaches significantly improves accuracy. The results show that support vector machines outperform all other classifiers. The proposed model is compared with two other pre-trained models GoogLeNet (98.8%), SqueezeNet (99.2%), and exhibits considerable improvement in classification accuracy (99.8%). In the future other models such as Vision Transformers could be explored with additional feature selection methods such as ReliefF, PSO, ACO, etc. to improve the overall accuracy of diagnosis.

show abstract

Supervised segmentation for guiding peripheral revascularization with forward‐viewing, robotically steered ultrasound guidewire

et al. 2023

View full text Add to dashboard Cite

Background Approximately 500 000 patients present with critical limb ischemia (CLI) each year in the U.S., requiring revascularization to avoid amputation. While peripheral arteries can be revascularized via minimally invasive procedures, 25% of cases with chronic total occlusions are unsuccessful due to inability to route the guidewire beyond the proximal occlusion. Improvements to guidewire navigation would lead to limb salvage in a greater number of patients. Purpose Integrating ultrasound imaging into the guidewire could enable direct visualization of routes for guidewire advancement. In order to navigate a robotically‐steerable guidewire with integrated imaging beyond a chronic occlusion proximal to the symptomatic lesion for revascularization, acquired ultrasound images must be segmented to visualize the path for guidewire advancement. Methods The first approach for automated segmentation of viable paths through occlusions in peripheral arteries is demonstrated in simulations and experimentally‐acquired data with a forward‐viewing, robotically‐steered guidewire imaging system. B‐mode ultrasound images formed via synthetic aperture focusing (SAF) were segmented using a supervised approach (U‐net architecture). A total of 2500 simulated images were used to train the classifier to distinguish the vessel wall and occlusion from viable paths for guidewire advancement. First, the size of the synthetic aperture resulting in the highest classification performance was determined in simulations (90 test images) and compared with traditional classifiers (global thresholding, local adaptive thresholding, and hierarchical classification). Next, classification performance as a function of the diameter of the remaining lumen (0.5 to 1.5 mm) in the partially‐occluded artery was tested using both simulated (60 test images at each of 7 diameters) and experimental data sets. Experimental test data sets were acquired in four 3D‐printed phantoms from human anatomy and six ex vivo porcine arteries. Accuracy of classifying the path through the artery was evaluated using microcomputed tomography of phantoms and ex vivo arteries as a ground truth for comparison. Results An aperture size of 3.8 mm resulted in the best‐performing classification based on sensitivity and Jaccard index, with a significant increase in Jaccard index (p < 0.05) as aperture diameter increased. In comparing the performance of the supervised classifier and traditional classification strategies with simulated test data, sensitivity and F1 score for U‐net were 0.95 ± 0.02 and 0.96 ± 0.01, respectively, compared to 0.83 ± 0.03 and 0.41 ± 0.13 for the best‐performing conventional approach, hierarchical classification. In simulated test images, sensitivity (p < 0.05) and Jaccard index both increased with increasing artery diameter (p < 0.05). Classification of images acquired in artery phantoms with remaining lumen diameters ≥ 0.75 mm resulted in accuracies > 90%, while mean accuracy decreased to 82% when artery diameter decreased to 0.5 mm. For testing i...

show abstract

Automatic detection of vessel structure by deep learning using intravascular ultrasound images of the coronary arteries

Cited by 14 publications

References 28 publications

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

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

Calcification Detection in Intravascular Ultrasound (IVUS) Images Using Transfer Learning Based MultiSVM model

Supervised segmentation for guiding peripheral revascularization with forward‐viewing, robotically steered ultrasound guidewire

Contact Info

Product

Resources

About