Metadata-independent classification of MRI sequences using convolutional neural networks: Successful application to prostate MRI

Baumgärtner, Georg L; Hamm, Charlie Alexander; Schulze-Weddige, Sophia; Ruppel, Richard; Beetz, Nick Lasse; Rudolph, Madhuri; Dräger, Franziska; Froböse, Konrad; Posch, Helena; Lenk, Julian; Bießmann, Felix; Penzkofer, Tobias

doi:10.1016/j.ejrad.2023.110964

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A 3D ResNet18 network, which is widely used in medical image analysis and has good performance, was used to construct the classification model [ 14 , 15 ]. The process employed for the deep-learning model was a two-stage task: first, detecting PCas in the internal datasets, and second, predicting the Gleason grade in all PCas including the internal, external, and public challenge datasets.…”

Section: Methodsmentioning

confidence: 99%

T2-weighted imaging-based deep-learning method for noninvasive prostate cancer detection and Gleason grade prediction: a multicenter study

Jin,

Yu,

Gao

et al. 2024

Insights Imaging

View full text Add to dashboard Cite

Objectives To noninvasively detect prostate cancer and predict the Gleason grade using single-modality T2-weighted imaging with a deep-learning approach. Methods Patients with prostate cancer, confirmed by histopathology, who underwent magnetic resonance imaging examinations at our hospital during September 2015–June 2022 were retrospectively included in an internal dataset. An external dataset from another medical center and a public challenge dataset were used for external validation. A deep-learning approach was designed for prostate cancer detection and Gleason grade prediction. The area under the curve (AUC) was calculated to compare the model performance. Results For prostate cancer detection, the internal datasets comprised data from 195 healthy individuals (age: 57.27 ± 14.45 years) and 302 patients (age: 72.20 ± 8.34 years) diagnosed with prostate cancer. The AUC of our model for prostate cancer detection in the validation set (n = 96, 19.7%) was 0.918. For Gleason grade prediction, datasets comprising data from 283 of 302 patients with prostate cancer were used, with 227 (age: 72.06 ± 7.98 years) and 56 (age: 72.78 ± 9.49 years) patients being used for training and testing, respectively. The external and public challenge datasets comprised data from 48 (age: 72.19 ± 7.81 years) and 91 patients (unavailable information on age), respectively. The AUC of our model for Gleason grade prediction in the training set (n = 227) was 0.902, whereas those of the validation (n = 56), external validation (n = 48), and public challenge validation sets (n = 91) were 0.854, 0.776, and 0.838, respectively. Conclusion Through multicenter dataset validation, our proposed deep-learning method could detect prostate cancer and predict the Gleason grade better than human experts. Critical relevance statement Precise prostate cancer detection and Gleason grade prediction have great significance for clinical treatment and decision making. Key Points Prostate segmentation is easier to annotate than prostate cancer lesions for radiologists. Our deep-learning method detected prostate cancer and predicted the Gleason grade, outperforming human experts. Non-invasive Gleason grade prediction can reduce the number of unnecessary biopsies. Graphical Abstract

show abstract

Section: Methodsmentioning

confidence: 99%

T2-weighted imaging-based deep-learning method for noninvasive prostate cancer detection and Gleason grade prediction: a multicenter study

Jin,

Yu,

Gao

et al. 2024

Insights Imaging

View full text Add to dashboard Cite

show abstract

“…Their system claims to achieve an F1 score of 99.5% at classifying 5 MRI types obtained from three Siemens scanners. Another study ( Baumgärtner et al, 2023 ) employs 3D ResNet18 to classify 10 MRI sequence types using prostate MRI volumes from 1,243 patients. The accuracy achieved by this system is 99.88% ± 0.13%.…”

Section: Prior Artmentioning

confidence: 99%

“…According to literature, approximately 16% of the information present in such headers is found to be inaccurate. In addition, to ensure anonymity in research settings, the DICOM tags are removed, rendering important information for data management unavailable ( Baumgärtner et al, 2023 ). Other MRI data types commonly available in online sources include Neuroimaging Informatics Technology Initiative (NIfTI) volumetric data, and Jpeg/Png, etc., which do not contain such metadata.…”

Section: Introductionmentioning

confidence: 99%

“…Other MRI data types commonly available in online sources include Neuroimaging Informatics Technology Initiative (NIfTI) volumetric data, and Jpeg/Png, etc., which do not contain such metadata. The only possible way to avoid such misclassifications from inaccurate DICOM headers information or absence of metadata, is the “Gold Standard” manual examination by radiologist, which can be a very tedious and time-consuming process given the massive data available online ( Baumgärtner et al, 2023 ). In such scenarios, automatic identification of the MRI sequence and slice view plane from raw MRI data can prove to be of immense significance in sorting these massive datasets out for training DL models ( Pizarro et al, 2019 ; Liang et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Brain MRI sequence and view plane identification using deep learning

Ali

2024

Front. Neuroinform.

View full text Add to dashboard Cite

Brain magnetic resonance imaging (MRI) scans are available in a wide variety of sequences, view planes, and magnet strengths. A necessary preprocessing step for any automated diagnosis is to identify the MRI sequence, view plane, and magnet strength of the acquired image. Automatic identification of the MRI sequence can be useful in labeling massive online datasets used by data scientists in the design and development of computer aided diagnosis (CAD) tools. This paper presents a deep learning (DL) approach for brain MRI sequence and view plane identification using scans of different data types as input. A 12-class classification system is presented for commonly used MRI scans, including T1, T2-weighted, proton density (PD), fluid attenuated inversion recovery (FLAIR) sequences in axial, coronal and sagittal view planes. Multiple online publicly available datasets have been used to train the system, with multiple infrastructures. MobileNet-v2 offers an adequate performance accuracy of 99.76% with unprocessed MRI scans and a comparable accuracy with skull-stripped scans and has been deployed in a tool for public use. The tool has been tested on unseen data from online and hospital sources with a satisfactory performance accuracy of 99.84 and 86.49%, respectively.

show abstract

ECMS-NET:A multi-task model for early endometrial cancer MRI sequences classification and segmentation of key tumor structures

Feng,

Chen,

Wang

et al. 2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Metadata-independent classification of MRI sequences using convolutional neural networks: Successful application to prostate MRI

Cited by 8 publications

References 14 publications

T2-weighted imaging-based deep-learning method for noninvasive prostate cancer detection and Gleason grade prediction: a multicenter study

T2-weighted imaging-based deep-learning method for noninvasive prostate cancer detection and Gleason grade prediction: a multicenter study

Brain MRI sequence and view plane identification using deep learning

ECMS-NET:A multi-task model for early endometrial cancer MRI sequences classification and segmentation of key tumor structures

Contact Info

Product

Resources

About