Search

Purpose: Ultrahigh-dose-rate (FLASH) irradiation has been reported to reduce normal tissue damage compared with conventional dose rate (CONV) irradiation without compromising tumor control. This proof-of-concept study aims to develop a deep learning (DL) approach to quantify the FLASH isoeffective dose (dose of CONV that would be required to produce the same effect as the given physical FLASH dose) with postirradiation mouse intestinal histology images., Methods and Materials: Eighty-four healthy C57BL/6J female mice underwent 16 MeV electron CONV (0.12 Gy/s; n = 41) or FLASH (200 Gy/s; n = 43) single fraction whole abdominal irradiation. Physical dose ranged from 12 to 16 Gy for FLASH and 11 to 15 Gy for CONV in 1 Gy increments. Four days after irradiation, 9 jejunum cross-sections from each mouse were hematoxylin and eosin stained and digitized for histological analysis. CONV data set was randomly split into training (n = 33) and testing (n = 8) data sets. ResNet101-based DL models were retrained using the CONV training data set to estimate the dose based on histological features. The classical manual crypt counting (CC) approach was implemented for model comparison. Cross-section-wise mean squared error was computed to evaluate the dose estimation accuracy of both approaches. The validated DL model was applied to the FLASH data set to map the physical FLASH dose into the isoeffective dose., Results: The DL model achieved a cross-section-wise mean squared error of 0.20 Gy 2 on the CONV testing data set compared with 0.40 Gy 2 of the CC approach. Isoeffective doses estimated by the DL model for FLASH doses of 12, 13, 14, 15, and 16 Gy were 12.19 ± 0.46, 12.54 ± 0.37, 12.69 ± 0.26, 12.84 ± 0.26, and 13.03 ± 0.28 Gy, respectively., Conclusions: Our proposed DL model achieved accurate CONV dose estimation. The DL model results indicate that in the physical dose range of 13 to 16 Gy, the biologic dose response of small intestinal tissue to FLASH irradiation is represented by a lower isoeffective dose compared with the physical dose. Our DL approach can be a tool for studying isoeffective doses of other radiation dose modifying interventions., (Copyright © 2023 Elsevier Inc. All rights reserved.)

Accurate and efficient delineation of the clinical target volume (CTV) is of utmost significance in post-operative breast cancer radiotherapy. However, CTV delineation is challenging as the exact extent of microscopic disease encompassed by CTV is not visualizable in radiological images and remains uncertain. We proposed to mimic physicians' contouring practice for CTV segmentation in stereotactic partial breast irradiation (S-PBI) where CTV is derived from tumor bed volume (TBV) via a margin expansion followed by correcting the extensions for anatomical barriers of tumor invasion (e.g. skin, chest wall). We proposed a deep-learning model, where CT images and the corresponding TBV masks formed a multi-channel input for a 3D U-Net based architecture. The design guided the model to encode the location-related image features and directed the network to focus on TBV to initiate CTV segmentation. Gradient weighted class activation map (Grad-CAM) visualizations of the model predictions revealed that the extension rules and geometric/anatomical boundaries were learnt during model training to assist the network to limit the expansion to a certain distance from the chest wall and the skin. We retrospectively collected 175 prone CT images from 35 post-operative breast cancer patients who received 5-fraction partial breast irradiation regimen on GammaPod. The 35 patients were randomly split into training (25), validation (5) and test (5) sets. Our model achieved mean (standard deviation) of 0.94 (±0.02), 2.46 (±0.5) mm, and 0.53 (±0.14) mm for Dice similarity coefficient, 95th percentile Hausdorff distance, and average symmetric surface distance respectively on the test set. The results are promising for improving the efficiency and accuracy of CTV delineation during on-line treatment planning procedure., (© 2023 Institute of Physics and Engineering in Medicine.)

Purpose: Adaptive radiotherapy (ART), especially online ART, effectively accounts for positioning errors and anatomical changes. One key component of online ART process is accurately and efficiently delineating organs at risk (OARs) and targets on online images, such as cone beam computed tomography (CBCT). Direct application of deep learning (DL)-based segmentation to CBCT images suffered from issues such as low image quality and limited available contour labels for training. To overcome these obstacles to online CBCT segmentation, we propose a registration-guided DL (RgDL) segmentation framework that integrates image registration algorithms and DL segmentation models., Methods: The RgDL framework is composed of two components: image registration and RgDL segmentation. The image registration algorithm transforms/deforms planning contours that were subsequently used as guidance by the DL model to obtain accurate final segmentations. We had two implementations of the proposed framework-Rig-RgDL (Rig for rigid body) and Def-RgDL (Def for deformable)-with rigid body (RB) registration or deformable image registration (DIR) as the registration algorithm, respectively, and U-Net as the DL model architecture. The two implementations of RgDL framework were trained and evaluated on seven OARs in an institutional clinical head-and-neck dataset., Results: Compared to the baseline approaches using the registration or the DL alone, RgDLs achieved more accurate segmentation, as measured by higher mean Dice similarity coefficients (DSCs) and other distance-based metrics. Rig-RgDL achieved a DSC of 84.5% on seven OARs on average, higher than RB or DL alone by 4.5% and 4.7%. The average DSC of Def-RgDL was 86.5%, higher than DIR or DL alone by 2.4% and 6.7%. The inference time required by the DL model component to generate final segmentations of seven OARs was less than 1 s in RgDL. By examining the contours from RgDLs and DL case by case, we found that RgDL was less susceptible to image artifacts. We also studied how the performances of RgDL and DL vary with the size of the training dataset. The DSC of DL dropped by 12.1% as the number of training data decreased from 22 to 5, whereas RgDL only dropped by 3.4%., Conclusion: By incorporating the patient-specific registration guidance to a population-based DL segmentation model, RgDL framework overcame the obstacles associated with online CBCT segmentation, including low image quality and insufficient training data, and achieved better segmentation accuracy than baseline methods. The resulting segmentation accuracy and efficiency show promise for applying this RgDL framework for online ART., (© 2022 American Association of Physicists in Medicine.)

Stereotactic radiosurgery (SRS) is now the standard of care for brain metastases (BMs) patients. The SRS treatment planning process requires precise target delineation, which in clinical workflow for patients with multiple (>4) BMs (mBMs) could become a pronounced time bottleneck. Our group has developed an automated BMs segmentation platform to assist in this process. The accuracy of the auto-segmentation, however, is influenced by the presence of false-positive segmentations, mainly caused by the injected contrast during MRI acquisition. To address this problem and further improve the segmentation performance, a deep-learning and radiomics ensemble classifier was developed to reduce the false-positive rate in segmentations. The proposed model consists of a Siamese network and a radiomic-based support vector machine (SVM) classifier. The 2D-based Siamese network contains a pair of parallel feature extractors with shared weights followed by a single classifier. This architecture is designed to identify the inter-class difference. On the other hand, the SVM model takes the radiomic features extracted from 3D segmentation volumes as the input for twofold classification, either a false-positive segmentation or a true BM. Lastly, the outputs from both models create an ensemble to generate the final label. The performance of the proposed model in the segmented mBMs testing dataset reached the accuracy (ACC), sensitivity (SEN), specificity (SPE) and area under the curve of 0.91, 0.96, 0.90 and 0.93, respectively. After integrating the proposed model into the original segmentation platform, the average segmentation false negative rate (FNR) and the false positive over the union (FPoU) were 0.13 and 0.09, respectively, which preserved the initial FNR (0.07) and significantly improved the FPoU (0.55). The proposed method effectively reduced the false-positive rate in the BMs raw segmentations indicating that the integration of the proposed ensemble classifier into the BMs segmentation platform provides a beneficial tool for mBMs SRS management., (© 2022 Institute of Physics and Engineering in Medicine.)

Efficient, reliable and reproducible target volume delineation is a key step in the effective planning of breast radiotherapy. However, post-operative breast target delineation is challenging as the contrast between the tumor bed volume (TBV) and normal breast tissue is relatively low in CT images. In this study, we propose to mimic the marker-guidance procedure in manual target delineation. We developed a saliency-based deep learning segmentation (SDL-Seg) algorithm for accurate TBV segmentation in post-operative breast irradiation. The SDL-Seg algorithm incorporates saliency information in the form of markers' location cues into a U-Net model. The design forces the model to encode the location-related features, which underscores regions with high saliency levels and suppresses low saliency regions. The saliency maps were generated by identifying markers on CT images. Markers' location were then converted to probability maps using a distance transformation coupled with a Gaussian filter. Subsequently, the CT images and the corresponding saliency maps formed a multi-channel input for the SDL-Seg network. Our in-house dataset was comprised of 145 prone CT images from 29 post-operative breast cancer patients, who received 5-fraction partial breast irradiation (PBI) regimen on GammaPod. The 29 patients were randomly split into training (19), validation (5) and test (5) sets. The performance of the proposed method was compared against basic U-Net. Our model achieved mean (standard deviation) of 76.4(±2.7) %, 6.76(±1.83) mm, and 1.9(±0.66) mm for Dice similarity coefficient, 95 percentile Hausdorff distance, and average symmetric surface distance respectively on the test set with computation time of below 11 seconds per one CT volume. SDL-Seg showed superior performance relative to basic U-Net for all the evaluation metrics while preserving low computation cost. The findings demonstrate that SDL-Seg is a promising approach for improving the efficiency and accuracy of the on-line treatment planning procedure of PBI, such as GammaPod based PBI., (© 2021 Institute of Physics and Engineering in Medicine.)

We developed a fluence map prediction method that directly generates fluence maps for a given desired dose distribution without optimization for volumetric modulated arc therapy (VMAT) planning. The prediction consists of two steps. First, projections of the desired dose are calculated and then inversely mapped to fluence maps in the phantom geometry by a deep neural network. Second, a plan scaling technique is applied to scale fluence maps from phantom to patient geometry. We evaluated the performance of the proposed fluence map prediction method for 102 head and neck (H&N) and 14 prostate cancer VMAT plans by comparing the patient doses calculated from the predicted fluence maps with the given desired dose distributions. The mean dose differences were 1.42% ± 0.37%, 1.53% ± 0.44% and 1.25% ± 0.44% for the planning target volume (PTV), the region from the PTV boundary to the 50% isodose line, and the region from the 50% to the 20% isodose line, respectively. The gamma passing rate was 98.06% ± 2.64% with the 3 mm/3% criterion. The prediction time for a single VMAT plan was less than one second. In conclusion, we developed an inverse mapping-based method that predicts fluence maps for desired dose distributions with high accuracy. Our method is effectively an optimization-free inverse planning approach, which was orders of magnitude faster than fluence map optimization. Combining the proposed method with leaf sequencing has the potential to dramatically speed up VMAT treatment planning., (© 2020 Institute of Physics and Engineering in Medicine.)

Deep learning (DL)-based auto-segmentation has the potential for accurate organ delineation in radiotherapy applications but requires large amounts of clean labeled data to train a robust model. However, annotating medical images is extremely time-consuming and requires clinical expertise, especially for segmentation that demands voxel-wise labels. On the other hand, medical images without annotations are abundant and highly accessible. To alleviate the influence of the limited number of clean labels, we propose a weakly supervised DL training approach using deformable image registration (DIR)-based annotations, leveraging the abundance of unlabeled data. We generate pseudo-contours by utilizing DIR to propagate atlas contours onto abundant unlabeled images and train a robust DL-based segmentation model. With 10 labeled TCIA dataset and 50 unlabeled CT scans from our institution, our model achieved Dice similarity coefficient of 87.9%, 73.4%, 73.4%, 63.2% and 61.0% on mandible, left & right parotid glands and left & right submandibular glands of TCIA test set and competitive performance on our institutional clinical dataset and a third party (PDDCA) dataset. Experimental results demonstrated the proposed method outperformed traditional multi-atlas DIR methods and fully supervised limited data training and is promising for DL-based medical image segmentation application with limited annotated data., (© 2020 Institute of Physics and Engineering in Medicine.)

Partly due to the use of exhaustive-annotated data, deep networks have achieved impressive performance on medical image segmentation. Medical imaging data paired with noisy annotation are, however, ubiquitous, but little is known about the effect of noisy annotation on deep learning based medical image segmentation. We studied the effect of noisy annotation in the context of mandible segmentation from CT images. First, 202 images of head and neck cancer patients were collected from our clinical database, where the organs-at-risk were annotated by one of twelve planning dosimetrists. The mandibles were roughly annotated as the planning avoiding structure. Then, mandible labels were checked and corrected by a head and neck specialist to get the reference standard. At last, by varying the ratios of noisy labels in the training set, deep networks were trained and tested for mandible segmentation. The trained models were further tested on other two public datasets. Experimental results indicated that the network trained with noisy labels had worse segmentation than that trained with reference standard, and in general, fewer noisy labels led to better performance. When using 20% or less noisy cases for training, no significant difference was found on the segmentation results between the models trained by noisy or reference annotation. Cross-dataset validation results verified that the models trained with noisy data achieved competitive performance to that trained with reference standard. This study suggests that the involved network is robust to noisy annotation to some extent in mandible segmentation from CT images. It also highlights the importance of labeling quality in deep learning. In the future work, extra attention should be paid to how to utilize a small number of reference standard samples to improve the performance of deep learning with noisy annotation.

We propose a novel BIRADS-SSDL network that integrates clinically-approved breast lesion characteristics (BIRADS features) into task-oriented semi-supervised deep learning (SSDL) for accurate diagnosis of ultrasound (US) images with a small training dataset. Breast US images are converted to BIRADS-oriented feature maps (BFMs) using a distance-transformation coupled with a Gaussian filter. Then, the converted BFMs are used as the input of an SSDL network, which performs unsupervised stacked convolutional auto-encoder (SCAE) image reconstruction guided by lesion classification. This integrated multi-task learning allows SCAE to extract image features with the constraints from the lesion classification task, while the lesion classification is achieved by utilizing the SCAE encoder features with a convolutional network. We trained the BIRADS-SSDL network with an alternative learning strategy by balancing the reconstruction error and classification label prediction error. To demonstrate the effectiveness of our approach, we evaluated it using two breast US image datasets. We compared the performance of the BIRADS-SSDL network with conventional SCAE and SSDL methods that use the original images as inputs, as well as with an SCAE that use BFMs as inputs. The experimental results on two breast US datasets show that BIRADS-SSDL ranked the best among the four networks, with a classification accuracy of around 94.23 ± 3.33% and 84.38 ± 3.11% on two datasets. In the case of experiments across two datasets collected from two different institutions/and US devices, the developed BIRADS-SSDL is generalizable across the different US devices and institutions without overfitting to a single dataset and achieved satisfactory results. Furthermore, we investigate the performance of the proposed method by varying the model training strategies, lesion boundary accuracy, and Gaussian filter parameters. The experimental results showed that a pre-training strategy can help to speed up model convergence during training but with no improvement of the classification accuracy on the testing dataset. The classification accuracy decreases as the segmentation accuracy decreases. The proposed BIRADS-SSDL achieves the best results among the compared methods in each case and has the capacity to deal with multiple different datasets under one model. Compared with state-of-the-art methods, BIRADS-SSDL could be promising for effective breast US computer-aided diagnosis using small datasets.

Breast ultrasound (US) is an effective imaging modality for breast cancer diagnosis. US computer-aided diagnosis (CAD) systems have been developed for decades and have employed either conventional handcrafted features or modern automatic deep-learned features, the former relying on clinical experience and the latter demanding large datasets. In this paper, we developed a novel BASDL method that integrates clinical-approved breast lesion boundary characteristics (features) into a semi-supervised deep learning (SDL) to achieve accurate diagnosis with a small training dataset. Original breast US images are converted to boundary-oriented feature maps (BFMs) using a distance-transformation coupled with a Gaussian filter. Then, the converted BFMs are used as the input of SDL network, which is characterized as lesion classification guided unsupervised image reconstruction based on stacked convolutional auto-encode (SCAE). We compared the performance of BASDL with conventional SCAE method and SDL method that used the original images as inputs, as well as SCAE method that used BFMs as inputs. Experimental results on two breast US datasets show that BASDL ranked the best among the four networks, with classification accuracy around 92.00±2.38%, which indicated that BASDL could be promising for effective breast US lesion CAD using small datasets.

With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient's PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

Deep inspiration breath hold (DIBH) with surface supervising is a common technique for cardiac dose reduction in left breast cancer radiotherapy. Surface supervision accuracy relies on the characteristics of surface region. In this study, a convolutional neural network (CNN) based automatic region-of-interest (ROI) selection method was proposed to select an optimal surface ROI for DIBH surface monitoring. The curvature entropy and the normal of each vertex on the breast cancer patient surface were calculated and formed as representative maps for ROI selection learning. 900 ROIs were randomly extracted from each patient's surface representative map, and the corresponding rigid ROI registration errors (REs) were calculated. The VGG-16 (a 16-layer network structure developed by Visual Geometry Group(VGG) from University of Oxford) pre-trained on a large natural image database ImageNet were fine-tuned using 27 thousand extracted ROIs and the corresponding REs from thirty patients. The RE prediction accuracy of the trained model was validated on additional ten patients. Satisfactory RE predictive accuracies were achieved with the root mean square error (RMSE)/mean absolute error (MAE) smaller than 1 mm/0.7 mm in translations and 0.45°/0.35° in rotations, respectively. The REs of the model selected ROIs on ten testing cases is close to the minimal predicted RE with mean RE differences  <1 mm and  <0.5° for translation and rotation, respectively. The proposed RE predictive model can be utilized for selecting a quasi-optimal ROI in left breast cancer DIBH radiotherapy (DIBH-RT).

Detection and segmentation of brain metastases (BMs) play a pivotal role in diagnosis, treatment planning, and follow-up evaluations for effective BM management. Given the rising prevalence of BM cases and its predominantly multiple onsets, automated segmentation is becoming necessary in stereotactic radiosurgery. It not only alleviates the clinician's manual workload and improves clinical workflow efficiency but also ensures treatment safety, ultimately improving patient care. Recent strides in machine learning, particularly in deep learning (DL), have revolutionized medical image segmentation, achieving state-of-the-art results. This review aims to analyze auto-segmentation strategies, characterize the utilized data, and assess the performance of cutting-edge BM segmentation methodologies. Additionally, we delve into the challenges confronting BM segmentation and share insights gleaned from our algorithmic and clinical implementation experiences. [ABSTRACT FROM AUTHOR]

Purpose: Stereotactic radiosurgery (SRS) has become a standard of care for patients' with brain metastases (BMs). However, the manual multiple BMs delineation can be time‐consuming and could create an efficiency bottleneck in SRS workflow. There is a clinical need for automatic delineation and quantitative evaluation tools. In this study, building on our previous developed deep learning‐based segmentation algorithms, we developed a web‐based automated BMs segmentation and labeling platform to assist the SRS clinical workflow. Method: This platform was developed based on the Django framework, including a web client and a back‐end server. The web client enables interactions as database access, data import, and image viewing. The server performs the segmentation and labeling tasks including: skull stripping; deep learning‐based BMs segmentation; and affine registration‐based BMs labeling. Additionally, the client can display BMs contours with corresponding atlas labels, and allows further postprocessing tasks including: (a) adjusting window levels; (b) displaying/hiding specific contours; (c) removing false‐positive contours; (d) exporting contours as DICOM RTStruct files; etc. Results: We evaluated this platform on 10 clinical cases with BMs number varied from 12‐81 per case. The overall operation took about 4–5 min per patient. The segmentation accuracy was evaluated between the manual contour and automatic segmentation with several metrics. The averaged center of mass shift was 1.55 ± 0.36 mm, the Hausdorff distance was 2.98 ± 0.63 mm, the mean of surface‐to‐surface distance (SSD) was 1.06 ± 0.31 mm, and the standard deviation of SSD was 0.80 ± 0.16 mm. In addition, the initial averaged false‐positive over union (FPoU) and false‐negative rate (FNR) were 0.43 ± 0.19 and 0.15 ± 0.10 respectively. After case‐specific postprocessing, the averaged FPoU and FNR were 0.19 ± 0.10 and 0.15 ± 0.10 respectively. Conclusion: The evaluated web‐based BMs segmentation and labeling platform can substantially improve the clinical efficiency compared to manual contouring. This platform can be a useful tool for assisting SRS treatment planning and treatment follow‐up. [ABSTRACT FROM AUTHOR]