MRI-based automatic segmentation of rectal cancer using 2D U-Net on two independent cohorts

Knuth, Franziska; Adde, Ingvild Askim; Huynh, Bao Ngoc; Groendahl, Aurora Rosvoll; Winter, R.; Negård, Anne; Holmedal, Stein Harald; Meltzer, Sebastian; Ree, Anne Hansen; Flatmark, Kjersti; Dueland, Svein; Hole, Knut Håkon; Seierstad, Therese; Redalen, Kathrine Røe; Futsæther, Cecilia Marie

doi:10.1080/0284186x.2021.2013530

Cited by 24 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Discussionmentioning

confidence: 99%

“…The patient cohort analyzed in this study was also the basis for training a 2D U-Net for automatic segmentation [38] . In [38] , the use of T2w images alone resulted in a DICE of 0.77 [0.21] and T2w + DW images in a DICE of 0.76 [0.18] for patients in a holdout test set. Thus, adding DW images did not improve the U-Net segmentation which stands in contrast to the slight improvement in DICE observed in the present analysis for T2w relative to T2w + DW based models.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-automatic tumor segmentation of rectal cancer based on functional magnetic resonance imaging

Knuth

Groendahl

Winter

et al. 2022

Physics and Imaging in Radiation Oncology

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Semi-automatic tumor segmentation of rectal cancer based on functional magnetic resonance imaging

Knuth

Groendahl

Winter

et al. 2022

Physics and Imaging in Radiation Oncology

Self Cite

View full text Add to dashboard Cite

“…Utilising the U-Net approach, which were able to recognise the tumour from the functional and MRI images [6]…”

Section: Otsu Kmeans Methods Brats Datasetsmentioning

confidence: 99%

“…Utilising the u-net approach, Jian, et al [6] were able to recognise the tumour from the functional and MRI images (diffusion and perfusion MRI images). It utilises the 12CVB dataset from the U-Net network.…”

Section: Related Workmentioning

confidence: 99%

A Modified U-Net Based Architecture for Brain Tumour Segmentation on BRATS 2020

Kajal

Mittal

2022

Preprint

View full text Add to dashboard Cite

The segmentation of brain tumours plays a significant role in the analysis of medical imaging. For a precise diagnosis of the condition, radiologists employ medical imaging. In order to recognise brain tumours from medical imaging, the radiologist's work must be challenging and complex. There are various distinct steps that may be used to identify brain tumours using magnetic resonance imaging (MRI). In the field of medical imaging, segmentation is the key stage. Segmentation is carried out after classification and image analysis. The appropriate segmentation is crucial since a brain tumour's incorrect detection might have a number of negative effects Method: In this work, the multimodal Brain tumour segmentation challenge was employed (MICCAI BRATS). We removed the brain tumour from the MRI images using the BRATS 2020 dataset, which is openly accessible. In this collection, there are 371 NiFTI-format folders. Convolutional neural networks (CNNs), a kind of deep learning based on an encoder-decoder model, are used in the proposed method to separate the tumours. Results: Accuracy = 0.9759, loss = 0.8240, and IOU = 0.6413 indicate that the proposed model is successful. The proposed model performs better when compared to the state-of-art segmentation models used in this study.

show abstract

“…The DSC, JSC, HD, and ASD (mean AE SD) were 0.74 AE 0.14, 0.60 AE 0.16, 20.44 AE 13.35, and 3.25 AE 1.69 mm, respectively, for the validation dataset, and these indices were 0.71 AE 0.13, 0.57 AE 0.15, 14.91 AE 7.62, and 2.67 AE 1.46 mm, respectively, between the two human radiation oncologists. Knuth et al 68 collected two cohorts of RC patients (C1 and C2) from different hospitals and used a 2D U-Net network to realize RC tumor segmentation on T2WI and DWI. For cohort C1, the T2WI model resulted in a median DSC of 0.77 on the test set.…”

Section: Deep Learning In Segmentationmentioning

confidence: 99%

MRI‐Based Artificial Intelligence in Rectal Cancer

Wong

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Rectal cancer (RC) accounts for approximately one-third of colorectal cancer (CRC), with death rates increasing in patients younger than 50 years old. Magnetic resonance imaging (MRI) is routinely performed for tumor evaluation. However, the semantic features from images alone remain insufficient to guide treatment decisions. Functional MRIs are useful for revealing microstructural and functional abnormalities and nevertheless have low or modest repeatability and reproducibility. Therefore, during the preoperative evaluation and follow-up treatment of patients with RC, novel noninvasive imaging markers are needed to describe tumor characteristics to guide treatment strategies and achieve individualized diagnosis and treatment. In recent years, the development of artificial intelligence (AI) has created new tools for RC evaluation based on MRI. In this review, we summarize the research progress of AI in the evaluation of staging, prediction of high-risk factors, genotyping, response to therapy, recurrence, metastasis, prognosis, and segmentation with RC. We further discuss the challenges of clinical application, including improvement in imaging, model performance, and the biological meaning of features, which may also be major development directions in the future.

show abstract

MRI-based automatic segmentation of rectal cancer using 2D U-Net on two independent cohorts

Cited by 24 publications

References 25 publications

Semi-automatic tumor segmentation of rectal cancer based on functional magnetic resonance imaging

Semi-automatic tumor segmentation of rectal cancer based on functional magnetic resonance imaging

A Modified U-Net Based Architecture for Brain Tumour Segmentation on BRATS 2020

MRI‐Based Artificial Intelligence in Rectal Cancer

Contact Info

Product

Resources

About