The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

Sunoqrot, Mohammed R. S.; Selnæs, Kirsten Margrete; Sandsmark, Elise; Langørgen, Sverre; Bertilsson, Helena; Bathen, Tone Frost; Elschot, Mattijs

doi:10.3390/diagnostics11091690

Cited by 16 publications

(8 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using these values as a benchmark, the nnU-Net models in the study performed better than the manually derived label-sets, except for HD95 score of TZ in model 1, which was slightly higher, but comparable to that of the manual label-sets. The performance of the nnU-Net models was also comparable to other similar models trained with different training and/or testing sets [ 21 , 22 ].…”

Section: Discussionmentioning

confidence: 72%

Label-set impact on deep learning-based prostate segmentation on MRI

Meglič,

Sunoqrot,

Bathen

et al. 2023

Insights Imaging

Self Cite

View full text Add to dashboard Cite

Background Prostate segmentation is an essential step in computer-aided detection and diagnosis systems for prostate cancer. Deep learning (DL)-based methods provide good performance for prostate gland and zones segmentation, but little is known about the impact of manual segmentation (that is, label) selection on their performance. In this work, we investigated these effects by obtaining two different expert label-sets for the PROSTATEx I challenge training dataset (n = 198) and using them, in addition to an in-house dataset (n = 233), to assess the effect on segmentation performance. The automatic segmentation method we used was nnU-Net. Results The selection of training/testing label-set had a significant (p < 0.001) impact on model performance. Furthermore, it was found that model performance was significantly (p < 0.001) higher when the model was trained and tested with the same label-set. Moreover, the results showed that agreement between automatic segmentations was significantly (p < 0.0001) higher than agreement between manual segmentations and that the models were able to outperform the human label-sets used to train them. Conclusions We investigated the impact of label-set selection on the performance of a DL-based prostate segmentation model. We found that the use of different sets of manual prostate gland and zone segmentations has a measurable impact on model performance. Nevertheless, DL-based segmentation appeared to have a greater inter-reader agreement than manual segmentation. More thought should be given to the label-set, with a focus on multicenter manual segmentation and agreement on common procedures. Critical relevance statement Label-set selection significantly impacts the performance of a deep learning-based prostate segmentation model. Models using different label-set showed higher agreement than manual segmentations. Key points • Label-set selection has a significant impact on the performance of automatic segmentation models. • Deep learning-based models demonstrated true learning rather than simply mimicking the label-set. • Automatic segmentation appears to have a greater inter-reader agreement than manual segmentation. Graphical Abstract

show abstract

Section: Discussionmentioning

confidence: 72%

Label-set impact on deep learning-based prostate segmentation on MRI

Meglič,

Sunoqrot,

Bathen

et al. 2023

Insights Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…U-Net combines low-resolution information (the basis for identifying object categories) with high-resolution information (the basis for accurate segmentation and localization), which is suitable for medical image recognition and segmentation. The U-Net can accurately detect and segment prostate glands and lesions on MR images [ [15] , [16] , [17] ]. The U-Net trained with T2 and diffusion-weighted images performed similarly to that evaluated by clinical prostate imaging reports and data systems [ 18 ].…”

Section: Discussionmentioning

confidence: 99%

“…A U-shaped fully convolutional neural network (U-Net) has been proposed to compensate for the shortcomings of CNNs. U-Net currently has better results in the segmentation of prostate glands and lesions in magnetic resonance imaging (MRI) images [ [15] , [16] , [17] , [18] ], but its algorithm still needs to be optimized to improve its recognition and segmentation.…”

Section: Introductionmentioning

confidence: 99%

A modified U-Net convolutional neural network for segmenting periprostatic adipose tissue based on contour feature learning

Wang,

Hu,

Zhang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…However, developing effective DL models with high precision is complex, as it requires the availability of significant medical data and clinical labels. Among various imaging modalities, multiparametric magnetic resonance imaging (mpMRI) is widely utilized due to its high sensitivity in detecting PCa and its ability to offer superior anatomical imaging of the prostate gland [8,9]. This superiority stems from the advanced spatial and contrast resolution of mpMRI, surpassing that of other imaging techniques.…”

Section: Introductionmentioning

confidence: 99%

Automated Diagnosis of Prostate Cancer Using mpMRI Images: A Deep Learning Approach for Clinical Decision Support

Gavade¹,

Nerli²,

Kanwal

et al. 2023

Computers

View full text Add to dashboard Cite

Prostate cancer (PCa) is a significant health concern for men worldwide, where early detection and effective diagnosis can be crucial for successful treatment. Multiparametric magnetic resonance imaging (mpMRI) has evolved into a significant imaging modality in this regard, which provides detailed images of the anatomy and tissue characteristics of the prostate gland. However, interpreting mpMRI images can be challenging for humans due to the wide range of appearances and features of PCa, which can be subtle and difficult to distinguish from normal prostate tissue. Deep learning (DL) approaches can be beneficial in this regard by automatically differentiating relevant features and providing an automated diagnosis of PCa. DL models can assist the existing clinical decision support system by saving a physician’s time in localizing regions of interest (ROIs) and help in providing better patient care. In this paper, contemporary DL models are used to create a pipeline for the segmentation and classification of mpMRI images. Our DL approach follows two steps: a U-Net architecture for segmenting ROI in the first stage and a long short-term memory (LSTM) network for classifying the ROI as either cancerous or non-cancerous. We trained our DL models on the I2CVB (Initiative for Collaborative Computer Vision Benchmarking) dataset and conducted a thorough comparison with our experimental setup. Our proposed DL approach, with simpler architectures and training strategy using a single dataset, outperforms existing techniques in the literature. Results demonstrate that the proposed approach can detect PCa disease with high precision and also has a high potential to improve clinical assessment.

show abstract

The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

Cited by 16 publications

References 46 publications

Label-set impact on deep learning-based prostate segmentation on MRI

Label-set impact on deep learning-based prostate segmentation on MRI

A modified U-Net convolutional neural network for segmenting periprostatic adipose tissue based on contour feature learning

Automated Diagnosis of Prostate Cancer Using mpMRI Images: A Deep Learning Approach for Clinical Decision Support

Contact Info

Product

Resources

About