Dataset Information

Deep learning-based automatic delineation of the hippocampus by MRI: geometric and dosimetric evaluation.

ABSTRACT:

Background

Whole brain radiotherapy (WBRT) can impair patients' cognitive function. Hippocampal avoidance during WBRT can potentially prevent this side effect. However, manually delineating the target area is time-consuming and difficult. Here, we proposed a credible approach of automatic hippocampal delineation based on convolutional neural networks.

Methods

Referring to the hippocampus contouring atlas proposed by RTOG 0933, we manually delineated (MD) the hippocampus on the MRI data sets (3-dimensional T1-weighted with slice thickness of 1 mm, n?=?175), which were used to construct a three-dimensional convolutional neural network aiming for the hippocampus automatic delineation (AD). The performance of this AD tool was tested on three cohorts: (a) 3D T1 MRI with 1-mm slice thickness (n?=?30); (b) non-3D T1-weighted MRI with 3-mm slice thickness (n?=?19); (c) non-3D T1-weighted MRI with 1-mm slice thickness (n?=?11). All MRIs confirmed with normal hippocampus has not been violated by any disease. Virtual radiation plans were created for AD and MD hippocampi in cohort c to evaluate the clinical feasibility of the artificial intelligence approach. Statistical analyses were performed using SPSS version 23. P?ResultsThe Dice similarity coefficient (DSC) and Average Hausdorff Distance (AVD) between the AD and MD hippocampi are 0.86?±?0.028 and 0.18?±?0.050 cm in cohort a, 0.76?±?0.035 and 0.31?±?0.064 cm in cohort b, 0.80?±?0.015 and 0.24?±?0.021 cm in cohort c, respectively. The DSC and AVD in cohort a were better than those in cohorts b and c (P?ConclusionThe AD of the hippocampus based on a deep learning algorithm showed satisfying results, which could have a positive impact on improving delineation accuracy and reducing work load.

SUBMITTER: Pan K

PROVIDER: S-EPMC7807715 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based automatic delineation of the hippocampus by MRI: geometric and dosimetric evaluation.

Pan Kaicheng K Zhao Lei L Gu Song S Tang Yi Y Wang Jiahao J Yu Wen W Zhu Lucheng L Feng Qi Q Su Ruipeng R Xu Zhiyong Z Li Xiadong X Ding Zhongxiang Z Fu Xiaolong X Ma Shenglin S Yan Jun J Kang Shigong S Zhou Tao T Xia Bing B

Radiation oncology (London, England) 20210114 1

<h4>Background</h4>Whole brain radiotherapy (WBRT) can impair patients' cognitive function. Hippocampal avoidance during WBRT can potentially prevent this side effect. However, manually delineating the target area is time-consuming and difficult. Here, we proposed a credible approach of automatic hippocampal delineation based on convolutional neural networks.<h4>Methods</h4>Referring to the hippocampus contouring atlas proposed by RTOG 0933, we manually delineated (MD) the hippocampus on the MRI ...[more]

PMID: 33446238

Similar Datasets

Project description:PurposeWe developed a deep learning model to achieve automatic multitarget delineation on planning CT (pCT) and synthetic CT (sCT) images generated from cone-beam CT (CBCT) images. The geometric and dosimetric impact of the model was evaluated for breast cancer adaptive radiation therapy.MethodsWe retrospectively analyzed 1,127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT images for patient setup acquired utilizing breath-hold guided by optical surface monitoring system were used to generate sCT with a generative adversarial network. Organs at risk (OARs), clinical target volume (CTV), and tumor bed (TB) were delineated automatically with a 3D U-Net model on pCT and sCT images. The geometric accuracy of the model was evaluated with metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Dosimetric evaluation was performed by quick dose recalculation on sCT images relying on gamma analysis and dose-volume histogram (DVH) parameters. The relationship between ΔD95, ΔV95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.ResultsThe ranges of DSC and HD95 were 0.73-0.97 and 2.22-9.36 mm for pCT, 0.63-0.95 and 2.30-19.57 mm for sCT from institution A, 0.70-0.97 and 2.10-11.43 mm for pCT from institution B, respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78 HU. The mean gamma pass rate (3%/3 mm criterion) was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3 Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2 Gy of D95. The mean ΔD90/ΔD95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer cases was larger than that in right breast cancer cases.ConclusionsThe accurate multitarget delineation is achievable on pCT and sCT via deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations during breast cancer radiotherapy.

Project description:BackgroundTraining deep learning (DL) models to automatically recognize diseases in nasopharyngeal MRI is a challenging task, and optimizing the performance of DL models is difficult.PurposeTo develop a method of training anatomical partition-based DL model which integrates knowledge of clinical anatomical regions in otorhinolaryngology to automatically recognize diseases in nasopharyngeal MRI.Study typeSingle-center retrospective study.PopulationA total of 2485 patients with nasopharyngeal diseases (age range 14-82 years, female, 779[31.3%]) and 600 people with normal nasopharynx (age range 18-78 years, female, 281[46.8%]) were included.Sequence3.0 T; T2WI fast spin-echo sequence.AssessmentFull images (512 × 512) of 3085 patients constituted 100% of the dataset, 50% and 25% of which were randomly retained as two new datasets. Two new series of images (seg112 image [112 × 112] and seg224 image [224 × 224]) were automatically generated by a segmentation model. Four pretrained neural networks for nasopharyngeal diseases classification were trained under the nine datasets (full image, seg112 image, and seg224 image, each with 100% dataset, 50% dataset, and 25% dataset).Statistical testsThe receiver operating characteristic curve was used to evaluate the performance of the models. Analysis of variance was used to compare the performance of the models built with different datasets. Statistical significance was set at P < 0.05.ResultsWhen the 100% dataset was used for training, the performances of the models trained with the seg112 images (average area under the curve [aAUC] 0.949 ± 0.052), seg224 images (aAUC 0.948 ± 0.053), and full images (aAUC 0.935 ± 0.053) were similar (P = 0.611). When the 25% dataset was used for training, the mean aAUC of the models that were trained with seg112 images (0.823 ± 0.116) and seg224 images (0.765 ± 0.155) was significantly higher than the models that were trained with full images (0.640 ± 0.154).Data conclusionThe proposed method can potentially improve the performance of the DL model for automatic recognition of diseases in nasopharyngeal MRI.Level of evidence4 TECHNICAL EFFICACY STAGE: 1.

Project description:BackgroundDeep learning-based head and neck lymph node level (HN_LNL) autodelineation is of high relevance to radiotherapy research and clinical treatment planning but still underinvestigated in academic literature. In particular, there is no publicly available open-source solution for large-scale autosegmentation of HN_LNL in the research setting.MethodsAn expert-delineated cohort of 35 planning CTs was used for training of an nnU-net 3D-fullres/2D-ensemble model for autosegmentation of 20 different HN_LNL. A second cohort acquired at the same institution later in time served as the test set (n = 20). In a completely blinded evaluation, 3 clinical experts rated the quality of deep learning autosegmentations in a head-to-head comparison with expert-created contours. For a subgroup of 10 cases, intraobserver variability was compared to the average deep learning autosegmentation accuracy on the original and recontoured set of expert segmentations. A postprocessing step to adjust craniocaudal boundaries of level autosegmentations to the CT slice plane was introduced and the effect of autocontour consistency with CT slice plane orientation on geometric accuracy and expert rating was investigated.ResultsBlinded expert ratings for deep learning segmentations and expert-created contours were not significantly different. Deep learning segmentations with slice plane adjustment were rated numerically higher (mean, 81.0 vs. 79.6, p = 0.185) and deep learning segmentations without slice plane adjustment were rated numerically lower (77.2 vs. 79.6, p = 0.167) than manually drawn contours. In a head-to-head comparison, deep learning segmentations with CT slice plane adjustment were rated significantly better than deep learning contours without slice plane adjustment (81.0 vs. 77.2, p = 0.004). Geometric accuracy of deep learning segmentations was not different from intraobserver variability (mean Dice per level, 0.76 vs. 0.77, p = 0.307). Clinical significance of contour consistency with CT slice plane orientation was not represented by geometric accuracy metrics (volumetric Dice, 0.78 vs. 0.78, p = 0.703).ConclusionsWe show that a nnU-net 3D-fullres/2D-ensemble model can be used for highly accurate autodelineation of HN_LNL using only a limited training dataset that is ideally suited for large-scale standardized autodelineation of HN_LNL in the research setting. Geometric accuracy metrics are only an imperfect surrogate for blinded expert rating.

Project description:ObjectivesTo simulate clinical deployment, evaluate performance, and establish quality assurance of a deep learning algorithm (U-Net) for detection, localization, and segmentation of clinically significant prostate cancer (sPC), ISUP grade group ≥ 2, using bi-parametric MRI.MethodsIn 2017, 284 consecutive men in active surveillance, biopsy-naïve or pre-biopsied, received targeted and extended systematic MRI/transrectal US-fusion biopsy, after examination on a single MRI scanner (3 T). A prospective adjustment scheme was evaluated comparing the performance of the Prostate Imaging Reporting and Data System (PI-RADS) and U-Net using sensitivity, specificity, predictive values, and the Dice coefficient.ResultsIn the 259 eligible men (median 64 [IQR 61-72] years), PI-RADS had a sensitivity of 98% [106/108]/84% [91/108] with a specificity of 17% [25/151]/58% [88/151], for thresholds at ≥ 3/≥ 4 respectively. U-Net using dynamic threshold adjustment had a sensitivity of 99% [107/108]/83% [90/108] (p > 0.99/> 0.99) with a specificity of 24% [36/151]/55% [83/151] (p > 0.99/> 0.99) for probability thresholds d3 and d4 emulating PI-RADS ≥ 3 and ≥ 4 decisions respectively, not statistically different from PI-RADS. Co-occurrence of a radiological PI-RADS ≥ 4 examination and U-Net ≥ d3 assessment significantly improved the positive predictive value from 59 to 63% (p = 0.03), on a per-patient basis.ConclusionsU-Net has similar performance to PI-RADS in simulated continued clinical use. Regular quality assurance should be implemented to ensure desired performance.Key points• U-Net maintained similar diagnostic performance compared to radiological assessment of PI-RADS ≥ 4 when applied in a simulated clinical deployment. • Application of our proposed prospective dynamic calibration method successfully adjusted U-Net performance within acceptable limits of the PI-RADS reference over time, while not being limited to PI-RADS as a reference. • Simultaneous detection by U-Net and radiological assessment significantly improved the positive predictive value on a per-patient and per-lesion basis, while the negative predictive value remained unchanged.

Dataset Information

Deep learning-based automatic delineation of the hippocampus by MRI: geometric and dosimetric evaluation.

Background

Methods

Publications

Deep learning-based automatic delineation of the hippocampus by MRI: geometric and dosimetric evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets