Dataset Information

Technical Note: More accurate and efficient segmentation of organs-at-risk in radiotherapy with convolutional neural networks cascades.

ABSTRACT: PURPOSE:Manual delineation of organs-at-risk (OARs) in radiotherapy is both time-consuming and subjective. Automated and more accurate segmentation is of the utmost importance in clinical application. The purpose of this study is to further improve the segmentation accuracy and efficiency with a novel network named convolutional neural networks (CNN) Cascades. METHODS:CNN Cascades was a two-step, coarse-to-fine approach that consisted of a simple region detector (SRD) and a fine segmentation unit (FSU). The SRD first used a relative shallow network to define the region of interest (ROI) where the organ was located, and then, the FSU took the smaller ROI as input and adopted a deep network for fine segmentation. The imaging data (14,651 slices) of 100 head-and-neck patients with segmentations were used for this study. The performance was compared with the state-of-the-art single CNN in terms of accuracy with metrics of Dice similarity coefficient (DSC) and Hausdorff distance (HD) values. RESULTS:The proposed CNN Cascades outperformed the single CNN on accuracy for each OAR. Similarly, for the average of all OARs, it was also the best with mean DSC of 0.90 (SRD: 0.86, FSU: 0.87, and U-Net: 0.85) and the mean HD of 3.0 mm (SRD: 4.0, FSU: 3.6, and U-Net: 4.4). Meanwhile, the CNN Cascades reduced the mean segmentation time per patient by 48% (FSU) and 5% (U-Net), respectively. CONCLUSIONS:The proposed two-step network demonstrated superior performance by reducing the input region. This potentially can be an effective segmentation method that provides accurate and consistent delineation with reduced clinician interventions for clinical applications as well as for quality assurance of a multicenter clinical trial.

SUBMITTER: Men K

PROVIDER: S-EPMC6322972 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Technical Note: More accurate and efficient segmentation of organs-at-risk in radiotherapy with convolutional neural networks cascades.

Men Kuo K Geng Huaizhi H Cheng Chingyun C Zhong Haoyu H Huang Mi M Fan Yong Y Plastaras John P JP Lin Alexander A Xiao Ying Y

Medical physics 20181207 1

<h4>Purpose</h4>Manual delineation of organs-at-risk (OARs) in radiotherapy is both time-consuming and subjective. Automated and more accurate segmentation is of the utmost importance in clinical application. The purpose of this study is to further improve the segmentation accuracy and efficiency with a novel network named convolutional neural networks (CNN) Cascades.<h4>Methods</h4>CNN Cascades was a two-step, coarse-to-fine approach that consisted of a simple region detector (SRD) and a fine s ...[more]

PMID: 30450825

Similar Datasets

Project description:BACKGROUND:Structure delineation is a necessary, yet time-consuming manual procedure in radiotherapy. Recently, convolutional neural networks have been proposed to speed-up and automatise this procedure, obtaining promising results. With the advent of magnetic resonance imaging (MRI)-guided radiotherapy, MR-based segmentation is becoming increasingly relevant. However, the majority of the studies investigated automatic contouring based on computed tomography (CT). PURPOSE:In this study, we investigate the feasibility of clinical use of deep learning-based automatic OARs delineation on MRI. MATERIALS AND METHODS:We included 150 patients diagnosed with prostate cancer who underwent MR-only radiotherapy. A three-dimensional (3D) T1-weighted dual spoiled gradient-recalled echo sequence was acquired with 3T MRI for the generation of the synthetic-CT. The first 48 patients were included in a feasibility study training two 3D convolutional networks called DeepMedic and dense V-net (dV-net) to segment bladder, rectum and femurs. A research version of an atlas-based software was considered for comparison. Dice similarity coefficient, 95% Hausdorff distances (HD95), and mean distances were calculated against clinical delineations. For eight patients, an expert RTT scored the quality of the contouring for all the three methods. A choice among the three approaches was made, and the chosen approach was retrained on 97 patients and implemented for automatic use in the clinical workflow. For the successive 53 patients, Dice, HD95 and mean distances were calculated against the clinically used delineations. RESULTS:DeepMedic, dV-net and the atlas-based software generated contours in 60 s, 4 s and 10-15 min, respectively. Performances were higher for both the networks compared to the atlas-based software. The qualitative analysis demonstrated that delineation from DeepMedic required fewer adaptations, followed by dV-net and the atlas-based software. DeepMedic was clinically implemented. After retraining DeepMedic and testing on the successive patients, the performances slightly improved. CONCLUSION:High conformality for OARs delineation was achieved with two in-house trained networks, obtaining a significant speed-up of the delineation procedure. Comparison of different approaches has been performed leading to the succesful adoption of one of the neural networks, DeepMedic, in the clinical workflow. DeepMedic maintained in a clinical setting the accuracy obtained in the feasibility study.

Project description:PURPOSE:This study demonstrated a magnetic resonance (MR) signal multitask learning method for three-dimensional (3D) simultaneous segmentation and relaxometry of human brain tissues. MATERIALS AND METHODS:A 3D inversion-prepared balanced steady-state free precession sequence was used for acquiring in vivo multicontrast brain images. The deep neural network contained three residual blocks, and each block had 8 fully connected layers with sigmoid activation, layer norm, and 256 neurons in each layer. Online-synthesized MR signal evolutions and labels were used to train the neural network batch-by-batch. Empirically defined ranges of T1 and T2 values for the normal gray matter, white matter, and cerebrospinal fluid (CSF) were used as the prior knowledge. MRI brain experiments were performed on three healthy volunteers. The mean and standard deviation for the T1 and T2 values in vivo were reported and compared to literature values. Additional animal (N = 6) and prostate patient (N = 1) experiments were performed to compare the estimated T1 and T2 values with those from gold standard methods and to demonstrate clinical applications of the proposed method. RESULTS:In animal validation experiment, the differences/errors (mean difference ± standard deviation of difference) between the T1 and T2 values estimated from the proposed method and the ground truth were 113 ± 486 and 154 ± 512 ms for T1, and 5 ± 33 and 7 ± 41 ms for T2, respectively. In healthy volunteer experiments (N = 3), whole brain segmentation and relaxometry were finished within ~ 5 s. The estimated apparent T1 and T2 maps were in accordance with known brain anatomy, and not affected by coil sensitivity variation. Gray matter, white matter, and CSF were successfully segmented. The deep neural network can also generate synthetic T1- and T2-weighted images. CONCLUSION:The proposed multitask learning method can directly generate brain apparent T1 and T2 maps, as well as synthetic T1- and T2-weighted images, in conjunction with segmentation of gray matter, white matter, and CSF.

Project description:Abstract End?to?end testing of a new breast radiotherapy technique preferably requires realistic phantom geometries, which is challenging to achieve using currently commercially available solutions. We have developed a series of three?dimensional (3D)?printed breast phantoms, with ionization chamber and radiochromic film inserts, which can be attached to a commercial anthropomorphic thorax phantom. A contoured left breast from a patient’s planning CT was mapped onto a CT of the CIRS E2E thorax phantom (CIRS Inc.) and cropped to fit the surface. Four versions of the breast were 3D printed, containing a cavity for an ionization chamber and slits for radiochromic film insertion in the three cardinal planes, respectively. The phantoms were fully compatible with surface scanning technology used for setup. The phantoms were validated using a whole?breast volumetric modulated arc therapy protocol with a simultaneous integrated boost to the tumor bed (VMAT?SIB). Six patient plans and one original plan on the breast phantom were verified with planar portal imaging, point dose, and film measurements in the MultiCube phantom and planar ??analysis using ArcCHECK diode array. Six patient plans were recalculated on the breast phantom (hybrid plans) and delivered with point dose and film measurements with 3% (local)/2 mm ??analysis. One complete end?to?end test on the breast phantom was performed. All plan quality verifications had point dose differences below 2.4% from the calculated dose and ??agreement scores (?AS) > 87.3% for film measurements in the MultiCube, portal dosimetry, and ArcCHECK. Point dose differences in the 3D?printed phantoms were below 2.6% (median ?1.4%, range ?2.6%; 0.3%). Median ?AS was 96.4% (range 80.1%–99.7%) for all film inserts. The proposed 3D?printed attachable breast dosimetry phantoms have been shown to be a valuable tool for end?to?end testing of a new radiotherapy protocol. The workflow described in this report can aid users to create their own phantom?specific breast 3D?printed phantoms.

Dataset Information

Technical Note: More accurate and efficient segmentation of organs-at-risk in radiotherapy with convolutional neural networks cascades.

Publications

Technical Note: More accurate and efficient segmentation of organs-at-risk in radiotherapy with convolutional neural networks cascades.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets