Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network
This work presents a deep-learning-based denoising technique to accelerate the acquisition of high <i>b</i>-value diffusion-weighted MRI for rectal cancer. A denoising convolutional neural network (DCNN) with a combined L1–L2 loss function was developed to denoise high <i>b</i&g...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/3/359 |
| _version_ | 1827751243473223680 |
|---|---|
| author | Mohaddese Mohammadi Elena A. Kaye Or Alus Youngwook Kee Jennifer S. Golia Pernicka Maria El Homsi Iva Petkovska Ricardo Otazo |
| author_facet | Mohaddese Mohammadi Elena A. Kaye Or Alus Youngwook Kee Jennifer S. Golia Pernicka Maria El Homsi Iva Petkovska Ricardo Otazo |
| author_sort | Mohaddese Mohammadi |
| collection | DOAJ |
| description | This work presents a deep-learning-based denoising technique to accelerate the acquisition of high <i>b</i>-value diffusion-weighted MRI for rectal cancer. A denoising convolutional neural network (DCNN) with a combined L1–L2 loss function was developed to denoise high <i>b</i>-value diffusion-weighted MRI data acquired with fewer repetitions (NEX: number of excitations) using the low <i>b</i>-value image as an anatomical guide. DCNN was trained using 85 datasets acquired on patients with rectal cancer and tested on 20 different datasets with NEX = 1, 2, and 4, corresponding to acceleration factors of 16, 8, and 4, respectively. Image quality was assessed qualitatively by expert body radiologists. Reader 1 scored similar overall image quality between denoised images with NEX = 1 and NEX = 2, which were slightly lower than the reference. Reader 2 scored similar quality between NEX = 1 and the reference, while better quality for NEX = 2. Denoised images with fourfold acceleration (NEX = 4) received even higher scores than the reference, which is due in part to the effect of gas-related motion in the rectum, which affects longer acquisitions. The proposed deep learning denoising technique can enable eightfold acceleration with similar image quality (average image quality = 2.8 ± 0.5) and fourfold acceleration with higher image quality (3.0 ± 0.6) than the clinical standard (2.5 ± 0.8) for improved diagnosis of rectal cancer. |
| first_indexed | 2024-03-11T06:55:31Z |
| format | Article |
| id | doaj.art-76e328cebada4ded8949d5dc84aba682 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-11T06:55:31Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-76e328cebada4ded8949d5dc84aba6822023-11-17T09:40:11ZengMDPI AGBioengineering2306-53542023-03-0110335910.3390/bioengineering10030359Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional NetworkMohaddese Mohammadi0Elena A. Kaye1Or Alus2Youngwook Kee3Jennifer S. Golia Pernicka4Maria El Homsi5Iva Petkovska6Ricardo Otazo7Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USADepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USAThis work presents a deep-learning-based denoising technique to accelerate the acquisition of high <i>b</i>-value diffusion-weighted MRI for rectal cancer. A denoising convolutional neural network (DCNN) with a combined L1–L2 loss function was developed to denoise high <i>b</i>-value diffusion-weighted MRI data acquired with fewer repetitions (NEX: number of excitations) using the low <i>b</i>-value image as an anatomical guide. DCNN was trained using 85 datasets acquired on patients with rectal cancer and tested on 20 different datasets with NEX = 1, 2, and 4, corresponding to acceleration factors of 16, 8, and 4, respectively. Image quality was assessed qualitatively by expert body radiologists. Reader 1 scored similar overall image quality between denoised images with NEX = 1 and NEX = 2, which were slightly lower than the reference. Reader 2 scored similar quality between NEX = 1 and the reference, while better quality for NEX = 2. Denoised images with fourfold acceleration (NEX = 4) received even higher scores than the reference, which is due in part to the effect of gas-related motion in the rectum, which affects longer acquisitions. The proposed deep learning denoising technique can enable eightfold acceleration with similar image quality (average image quality = 2.8 ± 0.5) and fourfold acceleration with higher image quality (3.0 ± 0.6) than the clinical standard (2.5 ± 0.8) for improved diagnosis of rectal cancer.https://www.mdpi.com/2306-5354/10/3/359diffusion-weighted MRIrectal cancerdeep learningdenoising |
| spellingShingle | Mohaddese Mohammadi Elena A. Kaye Or Alus Youngwook Kee Jennifer S. Golia Pernicka Maria El Homsi Iva Petkovska Ricardo Otazo Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network Bioengineering diffusion-weighted MRI rectal cancer deep learning denoising |
| title | Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network |
| title_full | Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network |
| title_fullStr | Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network |
| title_full_unstemmed | Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network |
| title_short | Accelerated Diffusion-Weighted MRI of Rectal Cancer Using a Residual Convolutional Network |
| title_sort | accelerated diffusion weighted mri of rectal cancer using a residual convolutional network |
| topic | diffusion-weighted MRI rectal cancer deep learning denoising |
| url | https://www.mdpi.com/2306-5354/10/3/359 |
| work_keys_str_mv | AT mohaddesemohammadi accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT elenaakaye accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT oralus accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT youngwookkee accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT jennifersgoliapernicka accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT mariaelhomsi accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT ivapetkovska accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork AT ricardootazo accelerateddiffusionweightedmriofrectalcancerusingaresidualconvolutionalnetwork |