MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

Müller, Dominik

doi:10.24926/548719.074

Cited by 24 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To segment the COVID-19 infection from lung CT images, LungINFseg is compared with the state-of-the-art segmentation models, such as FCN [ 15 ], UNet [ 16 ], SegNet [ 17 ], FSSNet [ 18 ], SQNet [ 19 ], ContextNet [ 20 ], EDANet [ 21 ], CGNet [ 22 ], ERFNet [ 23 ], ESNet [ 24 ], DABNet [ 25 ], Inf-Net [ 12 ], and MIScnn [ 26 ] models. All these models are assessed both quantitatively and qualitatively.…”

Section: Resultsmentioning

confidence: 99%

“…Additionally, we have trained MIScnn [ 26 ] from scratch and then compared it with LungINFseg, finding that our model outperforms the results of MIScnn in terms of all evaluation metrics. Unlike the models mentioned-above, LungINFseg has a great generalization ability to segment the infection areas from lung CT images, thanks to RFA and DWT modules that can enlarge the receptive field of the segmentation models and increase the learning ability of the model without information loss.…”

Section: Resultsmentioning

confidence: 99%

“… We propose the RFA module that can enlarge the receptive field of the segmentation models and increase the learning ability of the model without information loss. We present a comprehensive comparison with 13 state-of-the-art segmentation models, namely, FCN [ 15 ], UNet [ 16 ], SegNet [ 17 ], FSSNet [ 18 ], SQNet [ 19 ], ContextNet [ 20 ], EDANet [ 21 ], CGNet [ 22 ], ERFNet [ 23 ], ESNet [ 24 ], DABNet [ 25 ], Inf-Net [ 12 ], and MIScnn [ 26 ]. Extensive experiments were performed to provide ablation studies that add a thorough analysis of the proposed LungINFSeg (e.g., the effect of resolution size and variation of the loss function).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LungINFseg: Segmenting COVID-19 Infected Regions in Lung CT Images Based on a Receptive-Field-Aware Deep Learning Framework

et al. 2021

View full text Add to dashboard Cite

COVID-19 is a fast-growing disease all over the world, but facilities in the hospitals are restricted. Due to unavailability of an appropriate vaccine or medicine, early identification of patients suspected to have COVID-19 plays an important role in limiting the extent of disease. Lung computed tomography (CT) imaging is an alternative to the RT-PCR test for diagnosing COVID-19. Manual segmentation of lung CT images is time consuming and has several challenges, such as the high disparities in texture, size, and location of infections. Patchy ground-glass and consolidations, along with pathological changes, limit the accuracy of the existing deep learning-based CT slices segmentation methods. To cope with these issues, in this paper we propose a fully automated and efficient deep learning-based method, called LungINFseg, to segment the COVID-19 infections in lung CT images. Specifically, we propose the receptive-field-aware (RFA) module that can enlarge the receptive field of the segmentation models and increase the learning ability of the model without information loss. RFA includes convolution layers to extract COVID-19 features, dilated convolution consolidated with learnable parallel-group convolution to enlarge the receptive field, frequency domain features obtained by discrete wavelet transform, which also enlarges the receptive field, and an attention mechanism to promote COVID-19-related features. Large receptive fields could help deep learning models to learn contextual information and COVID-19 infection-related features that yield accurate segmentation results. In our experiments, we used a total of 1800+ annotated CT slices to build and test LungINFseg. We also compared LungINFseg with 13 state-of-the-art deep learning-based segmentation methods to demonstrate its effectiveness. LungINFseg achieved a dice score of 80.34% and an intersection-over-union (IoU) score of 68.77%—higher than the ones of the other 13 segmentation methods. Specifically, the dice and IoU scores of LungINFseg were 10% better than those of the popular biomedical segmentation method U-Net.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LungINFseg: Segmenting COVID-19 Infected Regions in Lung CT Images Based on a Receptive-Field-Aware Deep Learning Framework

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For our experiments, we use the Medical Imaging Segmentation with Convolutional Neural Networks (MIScnn) open-source Python library [ 68 ]. For all datasets, images and associated ground truth masks are provided in the png file format.…”

Section: Materials and Evaluation Methodsmentioning

confidence: 99%

Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy

Yeung

Sala

Schönlieb

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

Background Colonoscopy remains the gold-standard screening for colorectal cancer. However, significant miss rates for polyps have been reported, particularly when there are multiple small adenomas. This presents an opportunity to leverage computer-aided systems to support clinicians and reduce the number of polyps missed. Method In this work we introduce the Focus U-Net, a novel dual attention-gated deep neural network, which combines efficient spatial and channel-based attention into a single Focus Gate module to encourage selective learning of polyp features. The Focus U-Net incorporates several further architectural modifications, including the addition of short-range skip connections and deep supervision. Furthermore, we introduce the Hybrid Focal loss, a new compound loss function based on the Focal loss and Focal Tversky loss, designed to handle class-imbalanced image segmentation. For our experiments, we selected five public datasets containing images of polyps obtained during optical colonoscopy: CVC-ClinicDB, Kvasir-SEG, CVC-ColonDB, ETIS-Larib PolypDB and EndoScene test set. We first perform a series of ablation studies and then evaluate the Focus U-Net on the CVC-ClinicDB and Kvasir-SEG datasets separately, and on a combined dataset of all five public datasets. To evaluate model performance, we use the Dice similarity coefficient (DSC) and Intersection over Union (IoU) metrics. Results Our model achieves state-of-the-art results for both CVC-ClinicDB and Kvasir-SEG, with a mean DSC of 0.941 and 0.910, respectively. When evaluated on a combination of five public polyp datasets, our model similarly achieves state-of-the-art results with a mean DSC of 0.878 and mean IoU of 0.809, a 14 % and 15 % improvement over the previous state-of-the-art results of 0.768 and 0.702, respectively. Conclusions This study shows the potential for deep learning to provide fast and accurate polyp segmentation results for use during colonoscopy. The Focus U-Net may be adapted for future use in newer non-invasive colorectal cancer screening and more broadly to other biomedical image segmentation tasks similarly involving class imbalance and requiring efficiency.

show abstract

“…The pipeline was based on our in-house developed framework MIScnn [2]. We utilized the COVID-19 Lung CT Lesion Segmentation Challenge 2020 dataset containing 245 CT scans into a pre-defined training and testing dataset consisting of 199 and 46 samples, respectively 2 .…”

Section: Methodsmentioning

confidence: 99%

COVID-19 Image Segmentation Based on Deep Learning and Ensemble Learning

Meyer

Müller

Soto-Rey

2021

Studies in Health Technology and Informatics

Self Cite

View full text Add to dashboard Cite

Medical imaging offers great potential for COVID-19 diagnosis and monitoring. Our work introduces an automated pipeline to segment areas of COVID-19 infection in CT scans using deep convolutional neural networks. Furthermore, we evaluate the performance impact of ensemble learning techniques (Bagging and Augmenting). Our models showed highly accurate segmentation results, in which Bagging achieved the highest dice similarity coefficient.

show abstract

MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

Cited by 24 publications

References 22 publications

LungINFseg: Segmenting COVID-19 Infected Regions in Lung CT Images Based on a Receptive-Field-Aware Deep Learning Framework

LungINFseg: Segmenting COVID-19 Infected Regions in Lung CT Images Based on a Receptive-Field-Aware Deep Learning Framework

Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy

COVID-19 Image Segmentation Based on Deep Learning and Ensemble Learning

Contact Info

Product

Resources

About