Automatic Segmentation Framework Research Articles

Implementation of Automatic Segmentation Framework as Preprocessing Step for Radiomics Analysis of Lung Anatomical Districts

Background: The advent of artificial intelligence has significantly impacted radiology, with radiomics emerging as a transformative approach that extracts quantitative data from medical images to improve diagnostic and therapeutic accuracy. This study aimed to enhance the radiomic workflow by applying deep learning, through transfer learning, for the automatic segmentation of lung regions in computed tomography scans as a preprocessing step. Methods: Leveraging a pipeline articulated in (i) patient-based data splitting, (ii) intensity normalization, (iii) voxel resampling, (iv) bed removal, (v) contrast enhancement and (vi) model training, a DeepLabV3+ convolutional neural network (CNN) was fine tuned to perform whole-lung-region segmentation. Results: The trained model achieved high accuracy, Dice coefficient (0.97) and BF (93.06%) scores, and it effectively preserved lung region areas and removed confounding anatomical regions such as the heart and the spine. Conclusions: This study introduces a deep learning framework for the automatic segmentation of lung regions in CT images, leveraging an articulated pipeline and demonstrating excellent performance of the model, effectively isolating lung regions while excluding confounding anatomical structures. Ultimately, this work paves the way for more efficient, automated preprocessing tools in lung cancer detection, with potential to significantly improve clinical decision making and patient outcomes.

Quantitative modeling of lenticulostriate arteries on 7-T TOF-MRA for cerebral small vessel disease.

We developed a framework for segmenting and modeling lenticulostriate arteries (LSAs) on 7-T time-of-flight magnetic resonance angiography and tested its performance on cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy (CADASIL) patients and controls. We prospectively included 29 CADASIL patients and 21 controls. The framework includes a small-patch convolutional neural network (SP-CNN) for fine segmentation, a random forest for modeling LSAs, and a screening model for removing wrong branches. The segmentation performance of our SP-CNN was compared to competitive networks. External validation with different resolution was performed on ten patients with aneurysms. Dice similarity coefficient (DSC) and Hausdorff distance (HD) between each network and manual segmentation were calculated. The modeling results of the centerlines, diameters, and lengths of LSAs were compared against manual labeling by four neurologists. The SP-CNN achieved higher DSC (92.741 ± 2.789, mean ± standard deviation) and lower HD (0.610 ± 0.141 mm) in the segmentation of LSAs. It also outperformed competitive networks in the external validation (DSC 82.6 ± 5.5, HD 0.829 ± 0.143 mm). The framework versus manual difference was lower than the manual inter-observer difference for the vessel length of primary branches (median -0.040 mm, interquartile range -0.209 to 0.059 mm) and secondary branches (0.202 mm, 0.016-0.537 mm), as well as for the offset of centerlines of primary branches (0.071 mm, 0.065-0.078 mm) and secondary branches (0.072, 0.064-0.080 mm), with p < 0.001 for all comparisons. Our framework for LSAs modeling/quantification demonstrated high reliability and accuracy when compared to manual labeling. NCT05902039 ( https://clinicaltrials.gov/study/NCT05902039?cond=NCT05902039 ). The proposed automatic segmentation and modeling framework offers precise quantification of the morphological parameters of lenticulostriate arteries. This innovative technology streamlines diagnosis and research of cerebral small vessel disease, eliminating the burden of manual labeling, facilitating cohort studies and clinical diagnosis. The morphology of LSAs is important in the diagnosis of CSVD but difficult to quantify. The proposed algorithm achieved the performance equivalent to manual labeling by neurologists. Our method can provide standardized quantitative results, reducing radiologists' workload in cohort studies.

Reproducibility of CT-based opportunistic vertebral volumetric bone mineral density measurements from an automated segmentation framework

BackgroundTo investigate the reproducibility of automated volumetric bone mineral density (vBMD) measurements from routine thoracoabdominal computed tomography (CT) assessed with segmentations by a convolutional neural network and automated correction of contrast phases, on diverse scanners, with scanner-specific asynchronous or scanner-agnostic calibrations.MethodsWe obtained 679 observations from 278 CT scans in 121 patients (77 males, 63.6%) studied from 04/2019 to 06/2020. Observations consisted of two vBMD measurements from Δdifferent reconstruction kernels (n = 169), Δcontrast phases (n = 133), scan Δsessions (n = 123), Δscanners (n = 63), or Δall of the aforementioned (n = 20), and observations lacking scanner-specific calibration (n = 171). Precision was assessed using root-mean-square error (RMSE) and root-mean-square coefficient of variation (RMSCV). Cross-measurement agreement was assessed using Bland-Altman plots; outliers within 95% confidence interval of the limits of agreement were reviewed.ResultsRepeated measurements from Δdifferent reconstruction kernels were highly precise (RMSE 3.0 mg/cm3; RMSCV 1.3%), even for consecutive scans with different Δcontrast phases (RMSCV 2.9%). Measurements from different Δscan sessions or Δscanners showed decreased precision (RMSCV 4.7% and 4.9%, respectively). Plot-review identified 12 outliers from different scan Δsessions, with signs of hydropic decompensation. Observations with Δall differences showed decreased precision compared to those lacking scanner-specific calibration (RMSCV 5.9 and 3.7, respectively).ConclusionAutomatic vBMD assessment from routine CT is precise across varying setups, when calibrated appropriately. Low precision was found in patients with signs of new or worsening hydropic decompensation, what should be considered an exclusion criterion for both opportunistic and dedicated quantitative CT.Relevance statementAutomated CT-based vBMD measurements are precise in various scenarios, including cross-session and cross-scanner settings, and may therefore facilitate opportunistic screening for osteoporosis and surveillance of BMD in patients undergoing routine clinical CT scans.Key PointsArtificial intelligence-based tools facilitate BMD measurements in routine clinical CT datasets.Automated BMD measurements are highly reproducible in various settings.Reliable, automated opportunistic osteoporosis diagnostics allow for large-scale application.Graphical

Road Anomaly Detection with Unknown Scenes Using DifferNet-Based Automatic Labeling Segmentation

Obstacle avoidance is essential for the effective operation of autonomous mobile robots, enabling them to detect and navigate around obstacles in their environment. While deep learning provides significant benefits for autonomous navigation, it typically requires large, accurately labeled datasets, making the data’s preparation and processing time-consuming and labor-intensive. To address this challenge, this study introduces a transfer learning (TL)-based automatic labeling segmentation (ALS) framework. This framework utilizes a pretrained attention-based network, DifferNet, to efficiently perform semantic segmentation tasks on new, unlabeled datasets. DifferNet leverages prior knowledge from the Cityscapes dataset to identify high-entropy areas as road obstacles by analyzing differences between the input and resynthesized images. The resulting road anomaly map was refined using depth information to produce a robust drivable area and map of road anomalies. Several off-the-shelf RGB-D semantic segmentation neural networks were trained using pseudo-labels generated by the ALS framework, with validation conducted on the GMRPD dataset. Experimental results demonstrated that the proposed ALS framework achieved mean precision, mean recall, and mean intersection over union (IoU) rates of 80.31%, 84.42%, and 71.99%, respectively. The ALS framework, through the use of transfer learning and the DifferNet network, offers an efficient solution for semantic segmentation of new, unlabeled datasets, underscoring its potential for improving obstacle avoidance in autonomous mobile robots.

Deep learning segmentation of organs-at-risk with integration into clinical workflow for pediatric brain radiotherapy.

Radiation therapy (RT) of pediatric brain cancer is known to be associated with long-term neurocognitive deficits. Although target and organs-at-risk (OARs) are contoured as part of treatment planning, other structures linked to cognitive functions are often not included. This paper introduces a novel automatic segmentation tool specifically designed for the unique challenges posed by pediatric patients undergoing brain RT, as well as its seamless integration into the existing clinical workflow. Images of 47 pediatric brain cancer patients aged 1 to 20 years old and 33 two-year-old healthy infants were used to train a vision transformer, UNesT, for the segmentation of five brain OARs. The trained model was then incorporated to clinical workflow via DICOM connections between a treatment planning system (TPS) and a server hosting the trained model such that scans are sent from TPS to the server, automatically segmented, and sent back to TPS for treatment planning. The proposed automatic segmentation framework achieved a median dice similarity coefficient of 0.928 (frontal white matter), 0.908 (corpus callosum), 0.933 (hippocampi), 0.819 (temporal lobes), and 0.960 (brainstem) with a mean±SD run time of 1.8±0.67s over 20 test cases. The pediatric brain segmentation tool showed promising performance on five OARs linked to neurocognitive functions and can easily be extended for additional structures. The proposed integration to the clinic enables easy access to the tool from clinical platforms and minimizes disruption to existing workflow while maximizing its benefits.

Automatic Osteoporosis Screening System Using Radiomics and Deep Learning from Low-Dose Chest CT Images.

Develop two fully automatic osteoporosis screening systems using deep learning (DL) and radiomics (Rad) techniques based on low-dose chest CT (LDCT) images and evaluate their diagnostic effectiveness. In total, 434 patients who underwent LDCT and bone mineral density (BMD) examination were retrospectively enrolled and divided into the development set (n = 333) and temporal validation set (n = 101). An automatic thoracic vertebra cancellous bone (TVCB) segmentation model was developed. The Dice similarity coefficient (DSC) was used to evaluate the segmentation performance. Furthermore, the three-class Rad and DL models were developed to distinguish osteoporosis, osteopenia, and normal bone mass. The diagnostic performance of these models was evaluated using the receiver operating characteristic (ROC) curve and decision curve analysis (DCA). The automatic segmentation model achieved excellent segmentation performance, with a mean DSC of 0.96 ± 0.02 in the temporal validation set. The Rad model was used to identify osteoporosis, osteopenia, and normal BMD in the temporal validation set, with respective area under the receiver operating characteristic curve (AUC) values of 0.943, 0.801, and 0.932. The DL model achieved higher AUC values of 0.983, 0.906, and 0.969 for the same categories in the same validation set. The Delong test affirmed that both models performed similarly in BMD assessment. However, the accuracy of the DL model is 81.2%, which is better than the 73.3% accuracy of the Rad model in the temporal validation set. Additionally, DCA indicated that the DL model provided a greater net benefit compared to the Rad model across the majority of the reasonable threshold probabilities Conclusions: The automated segmentation framework we developed can accurately segment cancellous bone on low-dose chest CT images. These predictive models, which are based on deep learning and radiomics, provided comparable diagnostic performance in automatic BMD assessment. Nevertheless, it is important to highlight that the DL model demonstrates higher accuracy and precision than the Rad model.

WDLS: Deep Level Set Learning for Weakly Supervised Aeroengine Defect Segmentation

With the rapid development of the aviation industry, videoscope inspection of aeroengines has become crucial for ensuring aircraft flight safety. Recently, deep learning, particularly convolutional neural networks (CNNs), have shown remarkable efficacy in videoscope inspection tasks. However, these methods usually require large-scale training labels with accurate annotation. In videoscope images, defects are often present at the micrometer level and require manual labeling by professional inspection personnel, posing further challenges to model training. To address these issues, Weakly-Supervised Deep Level Set (WDLS), a fully automatic framework for aeroengine defect segmentation, was proposed in this work. WDLS employs a multi-branch structure and an iterative learning strategy to combine a high-performance CNN architecture with level set evolution. First, the Similarity-Guided Region (SGR) detector was designed to generate class-specific segmentation proposals and initialize the level set function. Second, the Adaptive Local Parameter Prediction (ALPP) algorithm was proposed to integrate local priors and constraints into the energy function and optimize the iterative process. Finally, a self-supervised objective function named Convexified Level Set (CLS) was introduced to represent an improved level set formulation and obtain the final segmentation. The proposed framework is continuously differentiable and unified. Thus, it can be seamlessly embedded in any CNN without postprocessing. Furthermore, the method was evaluated on a new aeroengine dataset Turbo19 and a benchmark dataset. Experimental results demonstrated that the proposed framework meets real-time requirements and achieves better performance than state-of-the-art methods.

A hybrid approach for automatic segmentation and classification to detect tuberculosis.

Tuberculosis (TB) remains a significant global infectious disease, posing a considerable health threat, particularly in resource-constrained regions. Due to diverse datasets, radiologists face challenges in accurately diagnosing TB using X-ray images. This study aims to propose an innovative approach leveraging image processing techniques to enhance TB diagnostic accuracy within the automatic segmentation and classification (AuSC) framework for healthcare. The AuSC of detection of TB (AuSC-DTB) framework comprises several steps: image preprocessing involving resizing and median filtering, segmentation using the random walker algorithm, and feature extraction utilizing local binary pattern and histogram of gradient descriptors. The extracted features are then classified using the support vector machine classifier to distinguish between healthy and infected chest X-ray images. The effectiveness of the proposed technique was evaluated using four distinct datasets, such as Japanese Society of Radiological Technology (JSRT), Montgomery, National Library of Medicine (NLM), and Shenzhen. Experimental results demonstrate promising outcomes, with accuracy rates of 94%, 95%, 95%, and 93% achieved for JSRT, Montgomery, NLM, and Shenzhen datasets, respectively. Comparative analysis against recent studies indicates superior performance of the proposed hybrid approach. The presented hybrid approach within the AuSC framework showcases improved diagnostic accuracy for TB detection from diverse X-ray image datasets. Furthermore, this methodology holds promise for generalizing other diseases diagnosed through X-ray imaging. It can be adapted with computed tomography scans and magnetic resonance imaging images, extending its applicability in healthcare diagnostics.

ContourNet—An Automated Segmentation Framework for Detection of Colonic Polyps

ContourNet—An Automated Segmentation Framework for Detection of Colonic Polyps

Tumor Segmentation in Colorectal Ultrasound Images Using an Ensemble Transfer Learning Model: Towards Intra-Operative Margin Assessment

Tumor boundary identification during colorectal cancer surgery can be challenging, and incomplete tumor removal occurs in approximately 10% of the patients operated for advanced rectal cancer. In this paper, a deep learning framework for automatic tumor segmentation in colorectal ultrasound images was developed, to provide real-time guidance on resection margins using intra-operative ultrasound. A colorectal ultrasound dataset was acquired consisting of 179 images from 74 patients, with ground truth tumor annotations based on histopathology results. To address data scarcity, transfer learning techniques were used to optimize models pre-trained on breast ultrasound data for colorectal ultrasound data. A new custom gradient-based loss function (GWDice) was developed, which emphasizes the clinically relevant top margin of the tumor while training the networks. Lastly, ensemble learning methods were applied to combine tumor segmentation predictions of multiple individual models and further improve the overall tumor segmentation performance. Transfer learning outperformed training from scratch, with an average Dice coefficient over all individual networks of 0.78 compared to 0.68. The new GWDice loss function clearly decreased the average tumor margin prediction error from 1.08 mm to 0.92 mm, without compromising the segmentation of the overall tumor contour. Ensemble learning further improved the Dice coefficient to 0.84 and the tumor margin prediction error to 0.67 mm. Using transfer and ensemble learning strategies, good tumor segmentation performance was achieved despite the relatively small dataset. The developed US segmentation model may contribute to more accurate colorectal tumor resections by providing real-time intra-operative feedback on tumor margins.

A Segmentation Framework with Unsupervised Learning-Based Label Mapper for the Ventricular Target of Intracranial Germ Cell Tumor.

Intracranial germ cell tumors are rare tumors that mainly affect children and adolescents. Radiotherapy is the cornerstone of interdisciplinary treatment methods. Radiation of the whole ventricle system and the local tumor can reduce the complications in the late stage of radiotherapy while ensuring the curative effect. However, manually delineating the ventricular system is labor-intensive and time-consuming for physicians. The diverse ventricle shape and the hydrocephalus-induced ventricle dilation increase the difficulty of automatic segmentation algorithms. Therefore, this study proposed a fully automatic segmentation framework. Firstly, we designed a novel unsupervised learning-based label mapper, which is used to handle the ventricle shape variations and obtain the preliminary segmentation result. Then, to boost the segmentation performance of the framework, we improved the region growth algorithm and combined the fully connected conditional random field to optimize the preliminary results from both regional and voxel scales. In the case of only one set of annotated data is required, the average time cost is 153.01s, and the average target segmentation accuracy can reach 84.69%. Furthermore, we verified the algorithm in practical clinical applications. The results demonstrate that our proposed method is beneficial for physicians to delineate radiotherapy targets, which is feasible and clinically practical, and may fill the gap of automatic delineation methods for the ventricular target of intracranial germ celltumors.

A deep learning framework for intracranial aneurysms automatic segmentation and detection on magnetic resonance T1 images.

To design a deep learning-based framework for automatic segmentation and detection of intracranial aneurysms (IAs) on magnetic resonance T1 images and test the robustness and performance of framework. A retrospective diagnostic study was conducted based on 159 IAs from 136 patients who underwent the T1 images. Among them, 127 cases were randomly selected for training and validation, and 32 cases were used to assess the accuracy and consistency of our algorithm. We developed and assembled three convolutional neural networks for the segmentation and detection of IAs. The segmentation and detection performance of the model were compared with the ground truth, and various metrics were calculated at the voxel level, IAs level, and patient level to show the performance of our framework. Our assembled model achieved overall Dice, voxel-level sensitivity, specificity, balanced accuracy, and F1 score of 0.802, 0.874, 0.9998, 0.937, and 0.802, respectively. A coincidence greater than 0.7 between the aneurysms predicted by the model and the ground truth was considered as a true positive. For IAs detection, the sensitivity reached 90.63% with 0.58 false positives per case. The volume of IAs segmented by our model showed a high agreement and consistency with the volume of IAs labeled by experts. The deep learning framework is achievable and robust for IAs segmentation and detection. Our model offers more clinical application opportunities compared to digital subtraction angiography (DSA)-based, CTA-based, and MRA-based methods. Our deep learning framework effectively detects and segments intracranial aneurysms using clinical routine T1 sequences, showing remarkable effectiveness and offering great potential for improving the detection of latent intracranial aneurysms and enabling early identification. •There is no segmentation method based on clinical routine T1 images. Our study shows that the proper deep learning framework can effectively localize the intracranial aneurysms. •The T1-based segmentation and detection method is more universal than other angiography-based detection methods, which can potentially reduce missed diagnoses caused by the absence of angiography images. •The deep learning framework is robust and has the potential to be applied in a clinical setting.

Longitudinal association of epicardial and thoracic adipose tissues with coronary and cardiac characteristics in psoriasis

Backgrounds: Psoriasis is a disease of systemic inflammation associated with increased cardiometabolic risk. Epicardial adipose tissue (EAT) and thoracic adipose tissue (TAT) are contributing factors for atherosclerosis and cardiac dysfunction. We strove to assess the longitudinal impact of the EAT and TAT on coronary and cardiac characteristics in psoriasis. MethodsThe study consisted of 301 patients with baseline coronary computed tomography angiography (CTA), of which 139 had four-year follow up scans. EAT and TAT volumes from non-contrast computed tomography scans were quantified by an automated segmentation framework. Coronary plaque characteristics and left ventricular (LV) mass were quantified by CTA. ResultsWhen stratified by baseline EAT and TAT volume quartiles, a stepwise significant increase in cardiometabolic parameters was observed. EAT and TAT volumes associated with fibro-fatty burden (FFB) (TAT: ρ = 0.394, P < 0.001; EAT: ρ = 0.459, P < 0.001) in adjusted models. Only EAT had a significant four-year time-dependent association with FFB in fully adjusted models (β = 0.307 P = 0.003), whereas only TAT volume associated with myocardial injury in fully adjusted models (TAT: OR = 1.57 95 % CI = (1.00–2.60); EAT: OR = 1.46 95 % CI = (0.91–2.45). Higher quartiles of EAT and TAT had increased LV mass and developed strong correlation (TAT: ρ = 0.370, P < 0.001; EAT: ρ = 0.512, P < 0.001). ConclusionsOur study is the first to explore how both EAT and TAT volumes associate with increased cardiometabolic risk profile in an inflamed psoriasis cohorts and highlight the need for further studies on its use as a potential prognostic tool for high-risk coronary plaques and cardiac dysfunction.

A Comprehensive Deep Learning Framework for Automatic Target Volumes Segmentation in Post-Operative Stereotactic Partial Breast Irradiation (S-PBI)

In S-PBI, accurate delineation of post-surgical tumor bed volume (TBV) and clinical target volume (CTV) are crucial tasks to achieve effective radiotherapy outcomes. However, manual contouring is labor intensive, time consuming, and largely relies on the experience of clinicians. We aimed to propose a deep learning (DL) approach which mimics physicians' contouring practice to accurately segment target volumes in post-operative breast CT images. Our approach incorporated domain knowledge into a 3D U-Net based DL model for breast target volumes (TBV and CTV) delineation. Our TBV segmentation approach was inspired by the marker-guidance procedure in manual delineation, where the visual clues provided by the markers assist physicians in defining TBV. For this purpose, a distance-transformation coupled with a Gaussian filter was adopted to convert markers' locations on the CT images to saliency maps. Subsequently, the CT images and the corresponding saliency maps formed a two-channel input for the segmentation model. For CTV segmentation, TBV was incorporated as an input in addition to the CT images, guiding the model to encode the location-related image features. The architecture allowed the network to emulate the oncologist's manual delineation where CTV is derived from TBV via a margin expansion, followed by correcting the extensions for anatomical barriers of tumor invasion (e.g., skin, chest wall). We retrospectively collected 175 prone CT images from 35 post-operative breast cancer patients who received 5-fraction partial breast irradiation (PBI) regimen on a Co-60 prone based S-PBI unit. The 35 patients were randomly split into 25, 5, and 5 for model training, validation, and testing respectively. We evaluated the performance of the developed DL model on the testing dataset by comparing the predicted volumes with the manually delineated contours (ground truth) using Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), and average symmetric surface distance (ASD). For TBV segmentation, our model achieved mean (standard deviation) of 0.76 (±2.7), 6.76 (±1.83) mm, and 1.9 (±0.66) mm for DSC, HD95, and ASD respectively. For CTV segmentation, our model achieved 0.94 (±0.02), 2.46 (±0.5) mm, and 0.53 (±0.14) mm for DSC, HD95, and ASD respectively. The proposed auto-segmentation approach generated TBV and CTV masks in ∼11 seconds per CT volume, implying significantly improved efficiency compared to manual contouring. We developed a comprehensive DL framework mimicking clinical contouring practice for auto-segmentation of target volumes in S-PBI. The results demonstrated high levels of agreement between the predicted contours and physicians' manual contours. The approach is promising for improving the efficiency and accuracy of the on-line treatment planning workflow, such as adaptive based S-PBI.

A Multicenter Study on Deep Learning for Glioblastoma Auto-Segmentation with Prior Knowledge in Multimodal Imaging

A precise radiotherapy plan is required to ensure accurate delineation of gross tumor volumes (GTV) and clinical target volumes (CTV1 and CTV2) of glioblastomas (GBMs). However, traditional manual delineation is labor intensive and highly dependent on oncologists' experience. To construct and evaluate a deep learning-based automatic delineation method using prior knowledge in multimodal medical imaging to automate precise GTV, CTV1 and CTV2 contouring in GBM patients. We retrospectively collected the CT and MRI scans of 55 eligible patients with histologically proven high-grade glioma (HGG) from an institute, these scans were performed with non-enhanced CT (CT), contrast-enhanced T1-weighted (T1C) and T2-FLAIR (T2F) sequences. We proposed a two-stage automatic segmentation framework (PKMI-Net) for GTV, CTV1 and CTV2 based on deep learning using prior knowledge in multimodal medical imaging, and its segmentation performance was evaluated with dice similarity coefficient (DSC), 95% Harsdorff distance (HD95), average surface distance (ASD) and relative volume difference (RVD). To further investigate the generalizability of our method, we designed and conducted two evaluation strategies (Mix and Cross) on four multicenter datasets (including 55 patients, 37 patients, 21 patients and 35 patients). The evaluation results with an 11-patient test set from the single institute were summarized in Table 1, the proposed method demonstrated the best accuracy in segmenting, respectively, GTV, CTV1 and CTV, achieving a DSC of 0.94, 0.95 and 0.92; HD95 of 2.07 mm, 1.18 mm and 3.80 mm; ASD of 0.69 mm, 0.39 mm and 1.13 mm and RVE of 5.50%, 3.97% and 9.68%. In the multicenter evaluation, the segmentation performance of our method implemented with the Cross strategy was comparable to that with the Mix strategy, demonstrating that our method had high and stable generalizability across multicenter datasets in automatically segmenting GTV, CTV1 and CTV2. Our proposed method achieved promising results in automatically segmenting gliomas across various datasets, which could improve the quality and efficiency of glioblastoma radiotherapy.

Hippocampus segmentation after brain tumor resection via postoperative region synthesis

PurposeAccurately segmenting the hippocampus is an essential step in brain tumor radiotherapy planning. Some patients undergo brain tumor resection beforehand, which can significantly alter the postoperative regions’ appearances and intensity of the 3D MR images. However, there are limited tumor resection patient images for deep neural networks to be effective.MethodsWe propose a novel automatic hippocampus segmentation framework via postoperative image synthesis. The variational generative adversarial network consists of intensity alignment and a weight-map-guided feature fusion module, which transfers the postoperative regions to the preoperative images. In addition, to further boost the performance of hippocampus segmentation, We design a joint training strategy to optimize the image synthesis network and the segmentation task simultaneously.ResultsComprehensive experiments demonstrate that our proposed method on the dataset with 48 nasopharyngeal carcinoma patients and 67 brain tumor patients observes consistent improvements over state-of-the-art methods.ConclusionThe proposed postoperative image synthesis method act as a novel and powerful scheme to generate additional training data. Compared with existing deep learning methods, it achieves better accuracy for hippocampus segmentation of brain tumor patients who have undergone brain tumor resection. It can be used as an automatic contouring tool for hippocampus delineation in hippocampus-sparing radiotherapy.

Long-term reproducibility of opportunistically assessed vertebral bone mineral density and texture features in routine clinical multi-detector computed tomography using an automated segmentation framework.

To investigate reproducibility of texture features and volumetric bone mineral density (vBMD) extracted from trabecular bone in the thoracolumbar spine in routine clinical multi-detector computed tomography (MDCT) data in a single scanner environment. Patients who underwent two routine clinical thoraco-abdominal MDCT exams at a single scanner with a time interval of 6 to 26 months (n=203, 131 males; time interval mean, 13 months; median, 12 months) were included in this observational study. Exclusion criteria were metabolic and hematological disorders, bone metastases, use of bone-active medications, and history of osteoporotic vertebral fractures (VFs) or prior diagnosis of osteoporosis. A convolutional neural network (CNN)-based framework was used for automated spine labeling and segmentation (T5-L5), asynchronous Hounsfield unit (HU)-to-BMD calibration, and correction for the intravenous contrast medium phase. Vertebral vBMD and six texture features [varianceglobal, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP)] were extracted for mid- (T5-T8) and lower thoracic (T9-T12), and lumbar vertebrae (L1-L5), respectively. Relative annual changes were calculated in texture features and vBMD for each vertebral level and sorted by sex, and changes were checked for statistical significance (P<0.05) using paired t-tests. Root mean square coefficient of variation (RMSCV) and root mean square error (RMSE) were calculated as measures of variability. SRE, LRE, RLN, and RP exhibited substantial reproducibility with RMSCV-values below 2%, for both sexes and at all spine levels, while vBMD was less reproducible (RMSCV =11.9-16.2%). Entropy showed highest variability (RMSCV =4.34-7.69%) due to statistically significant increases [range, mean ± standard deviation: (4.40±5.78)% to (8.36±8.66)%, P<0.001]. RMSCV of varianceglobal ranged from 1.60% to 3.03%. Opportunistic assessment of texture features in a single scanner environment using the presented CNN-based framework yields substantial reproducibility, outperforming vBMD reproducibility. Lowest scan-rescan variability was found for higher-order texture features. Further studies are warranted to determine, whether microarchitectural changes to the trabecular bone may be assessed through texture features.

MCSF-Net: a multi-scale channel spatial fusion network for real-time polyp segmentation.

Colorectal cancer is a globally prevalent cancer type that necessitates prompt screening. Colonoscopy is the established diagnostic technique for identifying colorectal polyps. However, missed polyp rates remain a concern. Early detection of polyps, while still precancerous, is vital for minimizing cancer-related mortality and economic impact. In the clinical setting, precise segmentation of polyps from colonoscopy images can provide valuable diagnostic and surgical information. Recent advances in computer-aided diagnostic systems, specifically those based on deep learning techniques, have shown promise in improving the detection rates of missed polyps, and thereby assisting gastroenterologists in improving polyp identification. In the present investigation, we introduce MCSF-Net, a real-time automatic segmentation framework that utilizes a multi-scale channel space fusion network. The proposed architecture leverages a multi-scale fusion module in conjunction with spatial and channel attention mechanisms to effectively amalgamate high-dimensional multi-scale features. Additionally, a feature complementation module is employed to extract boundary cues from low-dimensional features, facilitating enhanced representation of low-level features while keeping computational complexity to a minimum. Furthermore, we incorporate shape blocks to facilitate better model supervision for precise identification of boundary features of polyps. Our extensive evaluation of the proposed MCSF-Net on five publicly available benchmark datasets reveals that it outperforms several existing state-of-the-art approaches with respect to different evaluation metrics. The proposed approach runs at an impressive ∼45 FPS, demonstrating notable advantages in terms of scalability and real-time segmentation.

Implementing automated 3D measurements to quantify reference values and side-to-side differences in the ankle syndesmosis

Detection of syndesmotic ankle instability remains challenging in clinical practice due to the limitations of two-dimensional (2D) measurements. The transition to automated three-dimensional (3D) measurement techniques is on the verge of a breakthrough but normative and side-to-side comparative data are missing. Therefore, our study aim was two-fold: (1) to establish 3D anatomical reference values of the ankle syndesmosis based on automated measurements and (2) to determine to what extent the ankle syndesmosis is symmetric across all 3D measurements. Patients without syndesmotic pathology with a non-weight-bearing CT scan (NWBCT; N = 38; Age = 51.6 ± 17.43 years) and weight-bearing CT scan (WBCT; N = 43; Age = 48.9 ± 14.3 years) were retrospectively included. After training and validation of a neural network to automate the segmentation of 3D ankle models, an iterative closest point registration was performed to superimpose the left on the right ankle. Subsequently, 3D measurements were manually and automatically computed using a custom-made algorithm and side-to-side comparison of these landmarks allowed one to investigate symmetry. Intra-observer analysis showed excellent agreements for all manual measurements (ICC range 0.85–0.99) and good (i.e. < 2.7° for the angles and < 0.5 mm for the distances) accuracy was found between the automated and manual measurements. A mean Dice coefficient of 0.99 was found for the automated segmentation framework. The established mean, standard deviation and range were provided for each 3D measurement. From these data, reference values were derived to differ physiological from pathological syndesmotic alignment. Furthermore, side-to-side symmetry was revealed when comparing left to right measurements (P > 0.05). In clinical practice, our novel algorithm could surmount the current limitations of manual 2D measurements and distinguish patients with a syndesmotic ankle lesion from normal variance.

RGSB-UNet: Hybrid Deep Learning Framework for Tumour Segmentation in Digital Pathology Images.

Colorectal cancer (CRC) is a prevalent gastrointestinal tumour with high incidence and mortality rates. Early screening for CRC can improve cure rates and reduce mortality. Recently, deep convolution neural network (CNN)-based pathological image diagnosis has been intensively studied to meet the challenge of time-consuming and labour-intense manual analysis of high-resolution whole slide images (WSIs). Despite the achievements made, deep CNN-based methods still suffer from some limitations, and the fundamental problem is that they cannot capture global features. To address this issue, we propose a hybrid deep learning framework (RGSB-UNet) for automatic tumour segmentation in WSIs. The framework adopts a UNet architecture that consists of the newly-designed residual ghost block with switchable normalization (RGS) and the bottleneck transformer (BoT) for downsampling to extract refined features, and the transposed convolution and 1 × 1 convolution with ReLU for upsampling to restore the feature map resolution to that of the original image. The proposed framework combines the advantages of the spatial-local correlation of CNNs and the long-distance feature dependencies of BoT, ensuring its capacity of extracting more refined features and robustness to varying batch sizes. Additionally, we consider a class-wise dice loss (CDL) function to train the segmentation network. The proposed network achieves state-of-the-art segmentation performance under small batch sizes. Experimental results on DigestPath2019 and GlaS datasets demonstrate that our proposed model produces superior evaluation scores and state-of-the-art segmentation results.