Intracranial Hemorrhage Detection in CT Scans using Deep Learning

Lewick, Tomasz; Kumar, Meera; Hong, Raymond; Wu, Wencen

doi:10.1109/bigdataservice49289.2020.00033

Cited by 19 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results proved that the U-Net model has more advantages over the human diagnosis of hemorrhage. They achieve an accuracy of 0.9859 for detection of hemorrhage, 0.6919 intersections over union (IOU) for segmentation and 0.8033 dice coefficient value [25]. Like previous studies, Chen et al introduce a novel brain hemorrhage detection system, which is based on the Internet of Things (IoT).…”

Section: • Subdural Hemorrhagementioning

confidence: 96%

Automated Brain Hemorrhage Classification and Volume Analysis

Wardah¹,

Mateen²,

Malik³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Brain hemorrhage is a serious and life-threatening condition. It can cause permanent and lifelong disability even when it is not fatal. The word hemorrhage denotes leakage of blood within the brain and this leakage of blood from capillaries causes stroke and adequate supply of oxygen to the brain is hindered. Modern imaging methods such as computed tomography (CT) and magnetic resonance imaging (MRI) are employed to get an idea regarding the extent of the damage. An early diagnosis and treatment can save lives and limit the adverse effects of a brain hemorrhage. In this case, a deep neural network (DNN) is an effective choice for the early identification and classification of brain hemorrhage for the timely recovery and treatment of an affected person. In this paper, the proposed research work is divided into two novel approaches, where, one for the classification and the other for volume calculation of brain hemorrhage. Two different datasets are used for two different techniques classification and volume. A novel algorithm is proposed to calculate the volume of hemorrhage using CT scan images. In the first approach, the 'RSNA' dataset is used to classify the brain hemorrhage types using transfer learning and achieved an accuracy of 93.77%. Furthermore, in the second approach, a novel algorithm has been proposed to calculate the volume of brain hemorrhage and achieved tremendous results as 1035.91 mm 3 and 9.25 cm 3 , using the PhysioNet CT scan tomography dataset.

show abstract

Section: • Subdural Hemorrhagementioning

confidence: 96%

Automated Brain Hemorrhage Classification and Volume Analysis

Wardah¹,

Mateen²,

Malik³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Several studies were reported for disease of brain classification (Chin et al, 2017;Hsieh et al, 2019;Lewick, Kumar, Hong, & Wu, 2020;Livne et al, 2019;Talo, Yildirim, Baloglu, Aydin, & Acharya, 2019). China et al used the Otsu method for data pre-processing to extract cranium from CT images, and the affine transformations were used for data augmentation.…”

Section: Specialists Use Medical Imaging Techniques Such As Magneticmentioning

confidence: 99%

“…The model also segmented images to mark diseased parts (Livne et al, 2019). Lewick et al classified the types of bleeding in brain CT images as intraparenchymal, intraventricular, subarachnoid, subdural, and epidural with ResNet50 (Lewick et al, 2020).…”

Section: Specialists Use Medical Imaging Techniques Such As Magneticmentioning

confidence: 99%

“…The ResNet50 model predicted a training accuracy value of 0.9523 in (Talo et al, 2019) to classify multi-class brain disease. In (Lewick et al, 2020), the study was conducted to determine the hemorrhagic types, and the accuracy value was obtained as 0.98 per class. Unlike the others, the proposed system divides diagnostic mechanisms into CVD detection and ischemichemorrhagic classification.…”

Section: 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = 𝑇𝑃 + 𝑇𝑁 𝑇𝑃 + 𝑇𝑁 + 𝐹𝑃 + 𝐹𝑁mentioning

confidence: 99%

See 1 more Smart Citation

Beyin Bilgisayarlı Tomografi Görüntülerinde Yapay Zeka Tabanlı Beyin Damar Hastalıkları Tespiti

KARATAŞ

Doğan

Kılıç

2022

EJOSAT

View full text Add to dashboard Cite

Cerebrovascular disease (CVD) causes paralysis and even mortality in humans due to blockage or bleeding of brain vessels. The early diagnosis of the CVD type by the specialist can avoid these casualties with a correct course of treatment. However, it is not always possible to recruit enough specialists in hospitals or emergency services. Therefore, in this study, an artificial intelligence (AI)-based clinical decision support system for CVD detection from brain computed tomography (CT) images is proposed to improve the diagnostic results and relieve the burden of specialists. The deep learning model, a subset of AI, was implemented through a two-step process in which CVD is first detected and then classified as ischemic or hemorrhagic. Moreover, the developed system is integrated into our custom-designed desktop application that offers a user-friendly interface for CVD diagnosis. Experimental results prove that our system has great potential to improve early diagnosis and treatment for specialists, which contributes to the recovery rate of patients.

show abstract

“…Various reports on DL techniques for detecting ICH from CT brain images, including its subtypes [11][12][13][14][15][16], are based on large public data sets from the 2019-RSNA Brain CT Hemorrhage Challenge [17]. For example, Wang et al [14] obtained a higher classi cation performance of the RSNA data set by employing the 2D Convolution Neural Network (2D-CNN) and 3D Recurrent Neural Network (3D-RNN) for CT slice and scan level analysis, respectively, compared to using only 2D-CNN on CT slices [11,12,15].…”

Section: Introductionmentioning

confidence: 99%

Improvement in detecting and localizing intracranial hemorrhage lesions using the active learning concept and probabilistic CAM heatmap

Saiviroonporn

Chiewvit

Tritrakarn

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Intracranial hemorrhage (ICH) treatment requires a prompt diagnosis based on a CT scan evaluation by a radiologist. Manually analyzing the images is complex and time-consuming. Deep-learning techniques have been successfully applied to assist radiologists with this task. We further improved the detection and localization of ICH lesions without subtype classification using the active learning concept and the Probabilistic CAM (PCAM) heatmap. Methods The train set of the second stage 2019-RSNA ICH data set was randomly separated into the train (712,803 slices), validate (20,000), and test (20,000) data sets and interpolated from 512 into 256, 1024, and 2048 image resolutions. All resolutions were scaled to RGB channels according to their subdural, brain, and bone windows and used in a DenseNet-121 2D-CNN classifier with the PCAM technique for localization using ICH labels. The point closest-to-(0,1) corner approach was used to find a cutoff point of the training data set on each image resolution and applied the cutoff value to the validate and test data sets to calculate performance metrics. Two neuroradiologists reevaluated the mismatched data between the RSNA labels and prediction outcomes on the test data set and reassigned labels when the evaluations agreed with the prediction outcomes. Both radiologists also evaluated the usefulness of the PCAM heatmap to localize ICH lesions into three categories: not useful (Poor), functional (Acceptable), and valuable (Good) grades. The improvement in ICH detection after reassigned RSNA labels was measured by AUROC and AUPRC. McNemar’s test determined whether image resolution would have a similar detection outcome with a significant level at P < 0.05. Results The study found that detecting ICH at 512 and 1024 resolutions gave a comparable performance and was significantly higher than at 256 and 2048 resolutions. However, their AUROC and AUPRC were still in the same range of 0.98 and 0.93, respectively. After reevaluation, 55% (471 from 859 FP) and 51% (114 from 225 FN) of the test data set were relabeled. Furthermore, using the same cutoff value, the AUROC and AUPRC can be increased by 1.1% (0.984 vs. 0.995) and 5.3% (0.932 vs. 0.981), respectively. The PCAM heatmaps obtained a Good grade of around 86%, 37% and 0% at 2048, 1024, and 512 resolutions, respectively. Conclusion Image resolution has a minor effect on altering the ICH detection performance, while reassessing the RSNA labels can significantly improve the performance. PCAM heatmaps can better localize the boundary regions of the ICH lesion at higher resolutions, with the best result in 2048.

show abstract

Intracranial Hemorrhage Detection in CT Scans using Deep Learning

Cited by 19 publications

References 7 publications

Automated Brain Hemorrhage Classification and Volume Analysis

Automated Brain Hemorrhage Classification and Volume Analysis

Beyin Bilgisayarlı Tomografi Görüntülerinde Yapay Zeka Tabanlı Beyin Damar Hastalıkları Tespiti

Improvement in detecting and localizing intracranial hemorrhage lesions using the active learning concept and probabilistic CAM heatmap

Contact Info

Product

Resources

About