CSNet: A new DeepNet framework for ischemic stroke lesion segmentation

Kumar, Amish; Upadhyay, Neha; Ghosal, Palash; Chowdhury, Tamal; Das, Dipayan; Mukherjee, Amritendu; Nandi, Debashis

doi:10.1016/j.cmpb.2020.105524

Cited by 46 publications

(31 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most commonly used metrics to evaluate the automatic segmentation accuracy, quality, and strength of the model are [179]  Precision: Is the measure of over-segmentation between 0 and 1, and it means the proportion of the computed segmentation that overlaps with the reference segmentation [179,180]. This also is called the positive predictive value (PPV), with a high PPV indicating that a patient identified with a lesion does actually have the lesion [182].…”

Section: Image Segmentationmentioning

confidence: 99%

“… Recall, also known as sensitivity: Gives a metric between 0 and 1. It is a sign of oversegmentation, and it is a measure of the amount of the reference segmentation that overlaps with the computed segmentation [179,180].…”

Section: Image Segmentationmentioning

confidence: 99%

“…It is clear that currently, DL algorithms, especially those that use a combination of CNNs and machine learning classifiers, produce a marked transformation [197] in the featurization and segmentation in medical image processing [16,124]. CNNs have high utility in tasks like identification of compositional hierarchy features and low-level features (e.g., edges), specific pattern forms, and development of intrinsic structures (e.g., shapes, textures) [5], as well as spatial feature generation from an n-dimensional array of basically any arbitrary size [43,144], e.g., the U-Net model proposed by Ronneberger et al [141], which employs parameter sharing between encoder-decoder paths for incorporating spatial and semantic data that allow better segmentation performance [179]. Based on the U-Net model, currently there are novel variants of U-Net designs.…”

Section: Feature Extractionmentioning

confidence: 99%

“…Even though there are a large number of publications related to ischemic stroke (27 documents) and most deal with the classification of stroke patients versus normal controls, or the prediction of post-stroke functional impairment or treatment outcome [21,25,26,28,33,38,42,66,67,72,74,75,77,78,80,167,168,179,[184][185][186][187][188][189][190][193][194][195], there is a paucity of results related to demyelinating diseases alone. However, there are some publications dealing with multiple sclerosis (MS), which is the most common demyelinating disease (2) [191,192].…”

Section: And DL Classifiers Applied To Diagnosis Of Ischemia and Dmentioning

confidence: 99%

See 3 more Smart Citations

MR Images, Brain Lesions, and Deep Learning

2021

View full text Add to dashboard Cite

Medical brain image analysis is a necessary step in computer-assisted/computer-aided diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of white matter hyperintensities (WMHs) of brain magnetic resonance (MR) images, specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used bibliometric networks. Of a total of 140 documents, we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and development of new deep learning models to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with good performance metrics (e.g., Dice similarity coefficient, DSC: 0.99) were found; however, there is little practical application due to the use of small datasets and a lack of reproducibility. Therefore, the main conclusion is that there should be multidisciplinary research groups to overcome the gap between CAD developments and their deployment in the clinical environment.

show abstract

Section: Image Segmentationmentioning

confidence: 99%

Section: Image Segmentationmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: And DL Classifiers Applied To Diagnosis Of Ischemia and Dmentioning

confidence: 99%

See 2 more Smart Citations

MR Images, Brain Lesions, and Deep Learning

2021

View full text Add to dashboard Cite

show abstract

“…Recent studies have demonstrated that DL, particularly convolutional neural networks (CNNs), is a robust tool for analyzing medical images for a variety of tasks, including classi cation, segmentation, and object detection [12]. Several studies published within the last 3 years have demonstrated the yield of deep learning in estimating the ischemic core on DWI and that DL-based methods surpassed the predecessor methods mentioned above [13][14][15][16][17][18][19]. However, most of the earlier efforts that utilized DL used samples obtained at a single institution and lacked independent external validation and performance comparison with a radiologist [13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Inter-Vendor Performance of Deep Learning in Segmenting Acute Ischemic Lesions on Diffusion-Weighted Imaging: A Multicenter Study

Aliş

Yergin

Alış

et al. 2020

Preprint

View full text Add to dashboard Cite

There is little evidence on the applicability of deep learning (DL) in segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n=2986) and B (n=3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets and six neuroradiologist created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B and also fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist’s performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.

show abstract

HeCapsNet: An enhanced capsule network for automated heel disease diagnosis using lateral foot X‐Ray images

Taher,

Özacar

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Foot pain, particularly caused by heel spurs and Sever's disease, significantly impacts mobility and daily activities for many people. These diseases are traditionally diagnosed by orthopedic specialists using X‐ray images of the lateral foot. In certain situations, the absence of specialists requires the adoption of AI‐based methods; however, the lack of a dataset hinders the use of AI for the preliminary diagnosis of these diseases. Therefore, this study first presents a novel dataset consisting of 3956 annotated lateral foot X‐ray images and uses the original capsule network (CapsNet) to automatically detect and classify heel bone diseases. The low accuracy of 73.99% of CapsNet due to the low extraction feature layers led us to search for a new model. For this reason, this paper also proposes a new enhanced capsule network (HeCapsNet) by adjusting the features extraction layers, adding extra convolutional layers, using “he normal” kernel initializer instead of “normal” and utilizing the “same” padding scheme to perform better with medical images. Evaluating the performance of the proposed model, higher accuracy rates are achieved, including 97.29% for balanced data, 94.19% for imbalanced data, area under the curve (AUC) of 98.69%, and a fivefold cross‐validation accuracy of 95.77%. We then compared our proposed model with state‐of‐the‐art modified CapsNet models using various datasets (MNIST, Fashion‐MNIST, CIFAR10, and brain tumor). HeCapsNet performed similarly to modified CapsNets on relatively simple non‐medical datasets such as MNIST and Fashion‐MNIST, but performed better on more complex medical datasets.

show abstract

CSNet: A new DeepNet framework for ischemic stroke lesion segmentation

Cited by 46 publications

References 11 publications

MR Images, Brain Lesions, and Deep Learning

MR Images, Brain Lesions, and Deep Learning

Inter-Vendor Performance of Deep Learning in Segmenting Acute Ischemic Lesions on Diffusion-Weighted Imaging: A Multicenter Study

HeCapsNet: An enhanced capsule network for automated heel disease diagnosis using lateral foot X‐Ray images

Contact Info

Product

Resources

About