Joint Tumor Segmentation in PET-CT Images Using Co-Clustering and Fusion Based on Belief Functions

A review of uncertainty quantification in medical image analysis: Probabilistic and non-probabilistic methods

The comprehensive integration of machine learning healthcare models within clinical practice remains suboptimal, notwithstanding the proliferation of high-performing solutions reported in the literature. A predominant factor hindering widespread adoption pertains to an insufficiency of evidence affirming the reliability of the aforementioned models. Recently, uncertainty quantification methods have been proposed as a potential solution to quantify the reliability of machine learning models and thus increase the interpretability and acceptability of the results. In this review, we offer a comprehensive overview of the prevailing methods proposed to quantify the uncertainty inherent in machine learning models developed for various medical image tasks. Contrary to earlier reviews that exclusively focused on probabilistic methods, this review also explores non-probabilistic approaches, thereby furnishing a more holistic survey of research pertaining to uncertainty quantification for machine learning models. Analysis of medical images with the summary and discussion on medical applications and the corresponding uncertainty evaluation protocols are presented, which focus on the specific challenges of uncertainty in medical image analysis. We also highlight some potential future research work at the end. Generally, this review aims to allow researchers from both clinical and technical backgrounds to gain a quick and yet in-depth understanding of the research in uncertainty quantification for medical image analysis machine learning models.

Evidence modeling for reliability learning and interpretable decision-making under multi-modality medical image segmentation

Reliability learning and interpretable decision-making are crucial for multi-modality medical image segmentation. Although many works have attempted multi-modality medical image segmentation, they rarely explore how much reliability is provided by each modality for segmentation. Moreover, the existing approach of decision-making such as the softmax function lacks the interpretability for multi-modality fusion. In this study, we proposed a novel approach named contextual discounted evidential network (CDE-Net) for reliability learning and interpretable decision-making under multi-modality medical image segmentation. Specifically, the CDE-Net first models the semantic evidence by uncertainty measurement using the proposed evidential decision-making module. Then, it leverages the contextual discounted fusion layer to learn the reliability provided by each modality. Finally, a multi-level loss function is deployed for the optimization of evidence modeling and reliability learning. Moreover, this study elaborates on the framework interpretability by discussing the consistency between pixel attribution maps and the learned reliability coefficients. Extensive experiments are conducted on both multi-modality brain and liver datasets. The CDE-Net gains high performance with an average Dice score of 0.914 for brain tumor segmentation and 0.913 for liver tumor segmentation, which proves CDE-Net has great potential to facilitate the interpretation of artificial intelligence-based multi-modality medical image fusion.

Efficient model-informed co-segmentation of tumors on PET/CT driven by clustering and classification information

Automatic tumor segmentation via positron emission tomography (PET) and computed tomography (CT) images plays a critical role in the prevention, diagnosis, and treatment of this disease via radiation oncology. However, segmenting these tumors is challenging due to the heterogeneity of grayscale levels and fuzzy boundaries. To address these issues, in this paper, an efficient model-informed PET/CT tumor co-segmentation method that combines fuzzy C-means clustering and Bayesian classification information is proposed. To alleviate the grayscale heterogeneity of multi-modal images, in this method, a novel grayscale similar region term is designed based on the background region information of PET and the foreground region information of CT. An edge stop function is innovatively presented to enhance the localization of fuzzy edges by incorporating the fuzzy C-means clustering strategy. To improve the segmentation accuracy further, a unique data fidelity term is introduced based on PET images by combining the distribution characteristics of pixel points in PET images. Finally, experimental validation on datasets of head and neck tumor (HECKTOR) and non-small cell lung cancer (NSCLC) demonstrated impressive values for three key evaluation metrics, including DSC, RVD and HD5, achieved impressive values of 0.85, 5.32, and 0.17, respectively. These compelling results indicate that image segmentation methods based on mathematical models exhibit outstanding performance in handling grayscale heterogeneity and fuzzy boundaries in multi-modal images.

Location-Aware Encoding for Lesion Detection in 68Ga-DOTATATE Positron Emission Tomography Images

OBJECTIVE

Lesion detection with positron emission tomography (PET) imaging is critical for tumor staging, treatment planning, and advancing novel therapies to improve patient outcomes, especially for neuroendocrine tumors (NETs). Current lesion detection methods often require manual cropping of regions/volumes of interest (ROIs/VOIs) a priori, or rely on multi-stage, cascaded models, or use multi-modality imaging to detect lesions in PET images. This leads to significant inefficiency, high variability and/or potential accumulative errors in lesion quantification. To tackle this issue, we propose a novel single-stage lesion detection method using only PET images.

METHODS

We design and incorporate a new, plug-and-play codebook learning module into a U-Net-like neural network and promote lesion location-specific feature learning at multiple scales. We explicitly regularize the codebook learning with direct supervision at the network's multi-level hidden layers and enforce the network to learn multi-scale discriminative features with respect to predicting lesion positions. The network automatically combines the predictions from the codebook learning module and other layers via a learnable fusion layer.

RESULTS

We evaluate the proposed method on a real-world clinical 68Ga-DOTATATE PET image dataset, and our method produces significantly better lesion detection performance than recent state-of-the-art approaches.

CONCLUSION

We present a novel deep learning method for single-stage lesion detection in PET imaging data, with no ROI/VOI cropping in advance, no multi-stage modeling and no multi-modality data.

SIGNIFICANCE

This study provides a new perspective for effective and efficient lesion identification in PET, potentially accelerating novel therapeutic regimen development for NETs and ultimately improving patient outcomes including survival.

Attention-guided multi-scale context aggregation network for multi-modal brain glioma segmentation

BACKGROUND

Accurate segmentation of brain glioma is a critical prerequisite for clinical diagnosis, surgical planning and treatment evaluation. In current clinical workflow, physicians typically perform delineation of brain tumor subregions slice-by-slice, which is more susceptible to variabilities in raters and also time-consuming. Besides, even though convolutional neural networks (CNNs) are driving progress, the performance of standard models still have some room for further improvement.

PURPOSE

To deal with these issues, this paper proposes an attention-guided multi-scale context aggregation network (AMCA-Net) for the accurate segmentation of brain glioma in the magnetic resonance imaging (MRI) images with multi-modalities.

METHODS

AMCA-Net extracts the multi-scale features from the MRI images and fuses the extracted discriminative features via a self-attention mechanism for brain glioma segmentation. The extraction is performed via a series of down-sampling, convolution layers, and the global context information guidance (GCIG) modules are developed to fuse the features extracted for contextual features. At the end of the down-sampling, a multi-scale fusion (MSF) module is designed to exploit and combine all the extracted multi-scale features. Each of the GCIG and MSF modules contain a channel attention (CA) module that can adaptively calibrate feature responses and emphasize the most relevant features. Finally, multiple predictions with different resolutions are fused through different weightings given by a multi-resolution adaptation (MRA) module instead of the use of averaging or max-pooling to improve the final segmentation results.

RESULTS

Datasets used in this paper are publicly accessible, that is, the Multimodal Brain Tumor Segmentation Challenges 2018 (BraTS2018) and 2019 (BraTS2019). BraTS2018 contains 285 patient cases and BraTS2019 contains 335 cases. Simulations show that the AMCA-Net has better or comparable performance against that of the other state-of-the-art models. In terms of the Dice score and Hausdorff 95 for the BraTS2018 dataset, 90.4% and 10.2 mm for the whole tumor region (WT), 83.9% and 7.4 mm for the tumor core region (TC), 80.2% and 4.3 mm for the enhancing tumor region (ET), whereas the Dice score and Hausdorff 95 for the BraTS2019 dataset, 91.0% and 10.7 mm for the WT, 84.2% and 8.4 mm for the TC, 80.1% and 4.8 mm for the ET.

CONCLUSIONS

The proposed AMCA-Net performs comparably well in comparison to several state-of-the-art neural net models in identifying the areas involving the peritumoral edema, enhancing tumor, and necrotic and non-enhancing tumor core of brain glioma, which has great potential for clinical practice. In future research, we will further explore the feasibility of applying AMCA-Net to other similar segmentation tasks.

OSC-CO2: coattention and cosegmentation framework for plant state change with multiple features

Cosegmentation and coattention are extensions of traditional segmentation methods aimed at detecting a common object (or objects) in a group of images. Current cosegmentation and coattention methods are ineffective for objects, such as plants, that change their morphological state while being captured in different modalities and views. The Object State Change using Coattention-Cosegmentation (OSC-CO2) is an end-to-end unsupervised deep-learning framework that enhances traditional segmentation techniques, processing, analyzing, selecting, and combining suitable segmentation results that may contain most of our target object's pixels, and then displaying a final segmented image. The framework leverages coattention-based convolutional neural networks (CNNs) and cosegmentation-based dense Conditional Random Fields (CRFs) to address segmentation accuracy in high-dimensional plant imagery with evolving plant objects. The efficacy of OSC-CO2 is demonstrated using plant growth sequences imaged with infrared, visible, and fluorescence cameras in multiple views using a remote sensing, high-throughput phenotyping platform, and is evaluated using Jaccard index and precision measures. We also introduce CosegPP+, a dataset that is structured and can provide quantitative information on the efficacy of our framework. Results show that OSC-CO2 out performed state-of-the art segmentation and cosegmentation methods by improving segementation accuracy by 3% to 45%.

Deep Hyperspherical Clustering for Skin Lesion Medical Image Segmentation

Diagnosis of skin lesions based on imaging techniques remains a challenging task because data (knowledge) uncertainty may reduce accuracy and lead to imprecise results. This paper investigates a new deep hyperspherical clustering (DHC) method for skin lesion medical image segmentation by combining deep convolutional neural networks and the theory of belief functions (TBF). The proposed DHC aims to eliminate the dependence on labeled data, improve segmentation performance, and characterize the imprecision caused by data (knowledge) uncertainty. First, the SLIC superpixel algorithm is employed to group the image into multiple meaningful superpixels, aiming to maximize the use of context without destroying the boundary information. Second, an autoencoder network is designed to transform the superpixels' information into potential features. Third, a hypersphere loss is developed to train the autoencoder network. The loss is defined to map the input to a pair of hyperspheres so that the network can perceive tiny differences. Finally, the result is redistributed to characterize the imprecision caused by data (knowledge) uncertainty based on the TBF. The proposed DHC method can well characterize the imprecision between skin lesions and non-lesions, which is particularly important for the medical procedures. A series of experiments on four dermoscopic benchmark datasets demonstrate that the proposed DHC yields better segmentation performance, increasing the accuracy of the predictions while can perceive imprecise regions compared to other typical methods.

3D PET/CT Tumor Co-Segmentation Based on Background Subtraction Hybrid Active Contour Model

Accurate tumor segmentation in medical images plays an important role in clinical diagnosis and disease analysis. However, medical images usually have great complexity, such as low contrast of computed tomography (CT) or low spatial resolution of positron emission tomography (PET). In the actual radiotherapy plan, multimodal imaging technology, such as PET/CT, is often used. PET images provide basic metabolic information and CT images provide anatomical details. In this paper, we propose a 3D PET/CT tumor co-segmentation framework based on active contour model. First, a new edge stop function (ESF) based on PET image and CT image is defined, which combines the grayscale standard deviation information of the image and is more effective for blurry medical image edges. Second, we propose a background subtraction model to solve the problem of uneven grayscale level in medical images. Apart from that, the calculation format adopts the level set algorithm based on the additive operator splitting (AOS) format. The solution is unconditionally stable and eliminates the dependence on time step size. Experimental results on a dataset of 50 pairs of PET/CT images of non-small cell lung cancer patients show that the proposed method has a good performance for tumor segmentation.

Dynamic Cross-Task Representation Adaptation for Clinical Targets Co-Segmentation in CT Image-Guided Post-Prostatectomy Radiotherapy

Adjuvant and salvage radiotherapy after radical prostatectomy requires precise delineations of prostate bed (PB), i.e., the clinical target volume, and surrounding organs at risk (OARs) to optimize radiotherapy planning. Segmenting PB is particularly challenging even for clinicians, e.g., from the planning computed tomography (CT) images, as it is an invisible/virtual target after the operative removal of the cancerous prostate gland. Very recently, a few deep learning-based methods have been proposed to automatically contour non-contrast PB by leveraging its spatial reliance on adjacent OARs (i.e., the bladder and rectum) with much more clear boundaries, mimicking the clinical workflow of experienced clinicians. Although achieving state-of-the-art results from both the clinical and technical aspects, these existing methods improperly ignore the gap between the hierarchical feature representations needed for segmenting those fundamentally different clinical targets (i.e., PB and OARs), which in turn limits their delineation accuracy. This paper proposes an asymmetric multi-task network integrating dynamic cross-task representation adaptation (i.e., DyAdapt) for accurate and efficient co-segmentation of PB and OARs in one-pass from CT images. In the learning-to-learn framework, the DyAdapt modules adaptively transfer the hierarchical feature representations from the source task of OARs segmentation to match up with the target (and more challenging) task of PB segmentation, conditioned on the dynamic inter-task associations learned from the learning states of the feed-forward path. On a real-patient dataset, our method led to state-of-the-art results of PB and OARs co-segmentation. Code is available at https://github.com/ladderlab-xjtu/DyAdapt.

Automated Lung Cancer Segmentation Using a PET and CT Dual-Modality Deep Learning Neural Network

PURPOSE

To develop an automated lung tumor segmentation method for radiation therapy planning based on deep learning and dual-modality positron emission tomography (PET) and computed tomography (CT) images.

METHODS AND MATERIALS

A 3-dimensional (3D) convolutional neural network using inputs from diagnostic PETs and simulation CTs was constructed with 2 parallel convolution paths for independent feature extraction at multiple resolution levels and a single deconvolution path. At each resolution level, the extracted features from the convolution arms were concatenated and fed through the skip connections into the deconvolution path that produced the tumor segmentation. Our network was trained/validated/tested by a 3:1:1 split on 290 pairs of PET and CT images from patients with lung cancer treated at our clinic, with manual physician contours as the ground truth. A stratified training strategy based on the magnitude of the gross tumor volume (GTV) was investigated to improve performance, especially for small tumors. Multiple radiation oncologists assessed the clinical acceptability of the network-produced segmentations.

RESULTS

The mean Dice similarity coefficient, Hausdorff distance, and bidirectional local distance comparing manual versus automated contours were 0.79 ± 0.10, 5.8 ± 3.2 mm, and 2.8 ± 1.5 mm for the unstratified 3D dual-modality model. Stratification delivered the best results when the model for the large GTVs (>25 mL) was trained with all-size GTVs and the model for the small GTVs (<25 mL) was trained with small GTVs only. The best combined Dice similarity coefficient, Hausdorff distance, and bidirectional local distance from the 2 stratified models on their corresponding test data sets were 0.83 ± 0.07, 5.9 ± 2.5 mm, and 2.8 ± 1.4 mm, respectively. In the multiobserver review, 91.25% manual versus 88.75% automatic contours were accepted or accepted with modifications.

CONCLUSIONS

By using an expansive clinical PET and CT image database and a dual-modality architecture, the proposed 3D network with a novel GTVbased stratification strategy generated clinically useful lung cancer contours that were highly acceptable on physician review.

Multi-scale feature similarity-based weakly supervised lymphoma segmentation in PET/CT images

Accurate lymphoma segmentation in PET/CT images is important for evaluating Diffuse Large B-Cell Lymphoma (DLBCL) prognosis. As systemic multiple lymphomas, DLBCL lesions vary in number and size for different patients, which makes DLBCL labeling labor-intensive and time-consuming. To reduce the reliance on accurately labeled datasets, a weakly supervised deep learning method based on multi-scale feature similarity is proposed for automatic lymphoma segmentation. Weak labeling was performed by randomly dawning a small and salient lymphoma volume for the patient without accurate labels. A 3D V-Net is used as the backbone of the segmentation network and image features extracted in different convolutional layers are fused with the Atrous Spatial Pyramid Pooling (ASPP) module to generate multi-scale feature representations of input images. By imposing multi-scale feature consistency constraints on the predicted tumor regions as well as the labeled tumor regions, weakly labeled data can also be effectively used for network training. The cosine similarity, which has strong generalization, is exploited here to measure feature distances. The proposed method is evaluated with a PET/CT dataset of 147 lymphoma patients. Experimental results show that when using data, half of which have accurate labels and the other half have weak labels, the proposed method performed similarly to a fully supervised segmentation network and achieved an average Dice Similarity Coefficient (DSC) of 71.47%. The proposed method is able to reduce the requirement for expert annotations in deep learning-based lymphoma segmentation.

Intelligent Labeling of Tumor Lesions Based on Positron Emission Tomography/Computed Tomography

Positron emission tomography/computed tomography (PET/CT) plays a vital role in diagnosing tumors. However, PET/CT imaging relies primarily on manual interpretation and labeling by medical professionals. An enormous workload will affect the training samples' construction for deep learning. The labeling of tumor lesions in PET/CT images involves the intersection of computer graphics and medicine, such as registration, a fusion of medical images, and labeling of lesions. This paper extends the linear interpolation, enhances it in a specific area of the PET image, and uses the outer frame scaling of the PET/CT image and the least-squares residual affine method. The PET and CT images are subjected to wavelet transformation and then synthesized in proportion to form a PET/CT fusion image. According to the absorption of 18F-FDG (fluoro deoxy glucose) SUV in the PET image, the professionals randomly select a point in the focus area in the fusion image, and the system will automatically select the seed point of the focus area to delineate the tumor focus with the regional growth method. Finally, the focus delineated on the PET and CT fusion images is automatically mapped to CT images in the form of polygons, and rectangular segmentation and labeling are formed. This study took the actual PET/CT of patients with lymphatic cancer as an example. The semiautomatic labeling of the system and the manual labeling of imaging specialists were compared and verified. The recognition rate was 93.35%, and the misjudgment rate was 6.52%.

Sedimentary structure discrimination with hyperspectral imaging in sediment cores

Hyperspectral imaging (HSI) is a non-destructive, high-resolution imaging technique that is currently under significant development for analyzing geological areas with remote devices or natural samples in a laboratory. In both cases, the hyperspectral image provides several sedimentary structures that must be separated to temporally and spatially describe the sample. Sediment sequences are composed of successive deposits (strata, homogenite, flood) that are visible depending on sample properties. The classical methods to identify them are time-consuming, have a low spatial resolution (millimeters) and are generally based on naked-eye counting. In this study, we compare several supervised classification algorithms to discriminate sedimentological structures in lake sediments. Instantaneous events in lake sediments are generally linked to extreme geodynamical events (e.g., floods, earthquakes), so their identification and counting are essential to understand long-term fluctuations and improve hazard assessments. Identification and counting are done by reconstructing a chronicle of event layer occurrence, including estimation of deposit thicknesses. Here, we applied two hyperspectral imaging sensors (Visible Near-Infrared, VNIR, 60 μm, 400-1000 nm; Short Wave Infrared, SWIR, 200 μm, 1000-2500 nm) on three sediment cores from different lake systems. We highlight that the SWIR sensor is the optimal one for creating robust classification models with discriminant analyses (prediction accuracies of 0.87-0.98). Indeed, the VNIR sensor is impacted by the surface reliefs and structures that are not in the learning set, which causes mis-classification. These observations are also valid for the combined sensor (VNIR-SWIR) and the RGB images. Several spatial and spectral pre-processing were also compared and enabled one to highlight discriminant information specific to a sample and a sensor. These works show that the combined use of hyperspectral imaging and machine learning improves the characterization of sedimentary structures compared to conventional methods.

Improving Breast Tumor Segmentation in PET via Attentive Transformation Based Normalization

Positron Emission Tomography (PET) has become a preferred imaging modality for cancer diagnosis, radiotherapy planning, and treatment responses monitoring. Accurate and automatic tumor segmentation is the fundamental requirement for these clinical applications. Deep convolutional neural networks have become the state-of-the-art in PET tumor segmentation. The normalization process is one of the key components for accelerating network training and improving the performance of the network. However, existing normalization methods either introduce batch noise into the instance PET image by calculating statistics on batch level or introduce background noise into every single pixel by sharing the same learnable parameters spatially. In this paper, we proposed an attentive transformation (AT)-based normalization method for PET tumor segmentation. We exploit the distinguishability of breast tumor in PET images and dynamically generate dedicated and pixel-dependent learnable parameters in normalization via the transformation on a combination of channel-wise and spatial-wise attentive responses. The attentive learnable parameters allow to re-calibrate features pixel-by-pixel to focus on the high-uptake area while attenuating the background noise of PET images. Our experimental results on two real clinical datasets show that the AT-based normalization method improves breast tumor segmentation performance when compared with the existing normalization methods.

Segmentation of multicorrelated images with copula models and conditionally random fields

Purpose: Multisource images are interesting in medical imaging. Indeed, multisource images enable the use of complementary information of different sources such as for T1 and T2 modalities in MRI imaging. However, such multisource data can also be subject to redundancy and correlation. The question is how to efficiently fuse the multisource information without reinforcing the redundancy. We propose a method for segmenting multisource images that are statistically correlated. Approach: The method that we propose is the continuation of a prior work in which we introduce the copula model in hidden Markov fields (HMF). To achieve the multisource segmentations, we use a functional measure of dependency called "copula." This copula is incorporated in the conditionally random fields (CRF). Contrary to HMF, where we consider a prior knowledge on the hidden states modeled by an HMF, in CRF, there is no prior information and only the distribution of the hidden states conditionally to the observations can be known. This conditional distribution depends on the data and can be modeled by an energy function composed of two terms. The first one groups the voxels having similar intensities in the same class. As for the second term, it encourages a pair of voxels to be in the same class if the difference between their intensities is not too big. Results: A comparison between HMF and CRF is performed via theory and experimentations using both simulated and real data from BRATS 2013. Moreover, our method is compared with different state-of-the-art methods, which include supervised (convolutional neural networks) and unsupervised (hierarchical MRF). Our unsupervised method gives similar results as decision trees for synthetic images and as convolutional neural networks for real images; both methods are supervised. Conclusions: We compare two statistical methods using the copula: HMF and CRF to deal with multicorrelated images. We demonstrate the interest of using copula. In both models, the copula considerably improves the results compared with individual segmentations.

EFNet: evidence fusion network for tumor segmentation from PET-CT volumes

Precise delineation of target tumor from positron emission tomography-computed tomography (PET-CT) is a key step in clinical practice and radiation therapy. PET-CT co-segmentation actually uses the complementary information of two modalities to reduce the uncertainty of single-modal segmentation, so as to obtain more accurate segmentation results. At present, the PET-CT segmentation methods based on fully convolutional neural network (FCN) mainly adopt image fusion and feature fusion. The current fusion strategies do not consider the uncertainty of multi-modal segmentation and complex feature fusion consumes more computing resources, especially when dealing with 3D volumes. In this work, we analyze the PET-CT co-segmentation from the perspective of uncertainty, and propose evidence fusion network (EFNet). The network respectively outputs PET result and CT result containing uncertainty by proposed evidence loss, which are used as PET evidence and CT evidence. Then we use evidence fusion to reduce uncertainty of single-modal evidence. The final segmentation result is obtained based on evidence fusion of PET evidence and CT evidence. EFNet uses the basic 3D U-Net as backbone and only uses simple unidirectional feature fusion. In addition, EFNet can separately train and predict PET evidence and CT evidence, without the need for parallel training of two branch networks. We do experiments on the soft-tissue-sarcomas and lymphoma datasets. Compared with 3D U-Net, our proposed method improves the Dice by 8% and 5% respectively. Compared with the complex feature fusion method, our proposed method improves the Dice by 7% and 2% respectively. Our results show that in PET-CT segmentation methods based on FCN, by outputting uncertainty evidence and evidence fusion, the network can be simplified and the segmentation results can be improved.

Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging

Artificial intelligence (AI) techniques for image-based segmentation have garnered much attention in recent years. Convolutional neural networks have shown impressive results and potential toward fully automated segmentation in medical imaging, and particularly PET imaging. To cope with the limited access to annotated data needed in supervised AI methods, given tedious and prone-to-error manual delineations, semi-supervised and unsupervised AI techniques have also been explored for segmentation of tumors or normal organs in single- and bimodality scans. This work reviews existing AI techniques for segmentation tasks and the evaluation criteria for translational AI-based segmentation efforts toward routine adoption in clinical workflows.

Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation

Multimodal positron emission tomography-computed tomography (PET-CT) is used routinely in the assessment of cancer. PET-CT combines the high sensitivity for tumor detection of PET and anatomical information from CT. Tumor segmentation is a critical element of PET-CT but at present, the performance of existing automated methods for this challenging task is low. Segmentation tends to be done manually by different imaging experts, which is labor-intensive and prone to errors and inconsistency. Previous automated segmentation methods largely focused on fusing information that is extracted separately from the PET and CT modalities, with the underlying assumption that each modality contains complementary information. However, these methods do not fully exploit the high PET tumor sensitivity that can guide the segmentation. We introduce a deep learning-based framework in multimodal PET-CT segmentation with a multimodal spatial attention module (MSAM). The MSAM automatically learns to emphasize regions (spatial areas) related to tumors and suppress normal regions with physiologic high-uptake from the PET input. The resulting spatial attention maps are subsequently employed to target a convolutional neural network (CNN) backbone for segmentation of areas with higher tumor likelihood from the CT image. Our experimental results on two clinical PET-CT datasets of non-small cell lung cancer (NSCLC) and soft tissue sarcoma (STS) validate the effectiveness of our framework in these different cancer types. We show that our MSAM, with a conventional U-Net backbone, surpasses the state-of-the-art lung tumor segmentation approach by a margin of 7.6% in Dice similarity coefficient (DSC).

Latent Correlation Representation Learning for Brain Tumor Segmentation With Missing MRI Modalities

Magnetic Resonance Imaging (MRI) is a widely used imaging technique to assess brain tumor. Accurately segmenting brain tumor from MR images is the key to clinical diagnostics and treatment planning. In addition, multi-modal MR images can provide complementary information for accurate brain tumor segmentation. However, it's common to miss some imaging modalities in clinical practice. In this paper, we present a novel brain tumor segmentation algorithm with missing modalities. Since it exists a strong correlation between multi-modalities, a correlation model is proposed to specially represent the latent multi-source correlation. Thanks to the obtained correlation representation, the segmentation becomes more robust in the case of missing modality. First, the individual representation produced by each encoder is used to estimate the modality independent parameter. Then, the correlation model transforms all the individual representations to the latent multi-source correlation representations. Finally, the correlation representations across modalities are fused via attention mechanism into a shared representation to emphasize the most important features for segmentation. We evaluate our model on BraTS 2018 and BraTS 2019 dataset, it outperforms the current state-of-the-art methods and produces robust results when one or more modalities are missing.

Fusion based on attention mechanism and context constraint for multi-modal brain tumor segmentation

This paper presents a 3D brain tumor segmentation network from multi-sequence MRI datasets based on deep learning. We propose a three-stage network: generating constraints, fusion under constraints and final segmentation. In the first stage, an initial 3D U-Net segmentation network is introduced to produce an additional context constraint for each tumor region. Under the obtained constraint, multi-sequence MRI are then fused using an attention mechanism to achieve three single tumor region segmentations. Considering the location relationship of the tumor regions, a new loss function is introduced to deal with the multiple class segmentation problem. Finally, a second 3D U-Net network is applied to combine and refine the three single prediction results. In each stage, only 8 initial filters are used, allowing to decrease significantly the number of parameters to be estimated. We evaluated our method on BraTS 2017 dataset. The results are promising in terms of dice score, hausdorff distance, and the amount of memory required for training.

DeepTarget: Gross tumor and clinical target volume segmentation in esophageal cancer radiotherapy

Gross tumor volume (GTV) and clinical target volume (CTV) delineation are two critical steps in the cancer radiotherapy planning. GTV defines the primary treatment area of the gross tumor, while CTV outlines the sub-clinical malignant disease. Automatic GTV and CTV segmentation are both challenging for distinct reasons: GTV segmentation relies on the radiotherapy computed tomography (RTCT) image appearance, which suffers from poor contrast with the surrounding tissues, while CTV delineation relies on a mixture of predefined and judgement-based margins. High intra- and inter-user variability makes this a particularly difficult task. We develop tailored methods solving each task in the esophageal cancer radiotherapy, together leading to a comprehensive solution for the target contouring task. Specifically, we integrate the RTCT and positron emission tomography (PET) modalities together into a two-stream chained deep fusion framework taking advantage of both modalities to facilitate more accurate GTV segmentation. For CTV segmentation, since it is highly context-dependent-it must encompass the GTV and involved lymph nodes while also avoiding excessive exposure to the organs at risk-we formulate it as a deep contextual appearance-based problem using encoded spatial distances of these anatomical structures. This better emulates the margin- and appearance-based CTV delineation performed by oncologists. Adding to our contributions, for the GTV segmentation we propose a simple yet effective progressive semantically-nested network (PSNN) backbone that outperforms more complicated models. Our work is the first to provide a comprehensive solution for the esophageal GTV and CTV segmentation in radiotherapy planning. Extensive 4-fold cross-validation on 148 esophageal cancer patients, the largest analysis to date, was carried out for both tasks. The results demonstrate that our GTV and CTV segmentation approaches significantly improve the performance over previous state-of-the-art works, e.g., by 8.7% increases in Dice score (DSC) and 32.9mm reduction in Hausdorff distance (HD) for GTV segmentation, and by 3.4% increases in DSC and 29.4mm reduction in HD for CTV segmentation.

Deep Multi-Scale Mesh Feature Learning for Automated Labeling of Raw Dental Surfaces From 3D Intraoral Scanners

Precisely labeling teeth on digitalized 3D dental surface models is the precondition for tooth position rearrangements in orthodontic treatment planning. However, it is a challenging task primarily due to the abnormal and varying appearance of patients' teeth. The emerging utilization of intraoral scanners (IOSs) in clinics further increases the difficulty in automated tooth labeling, as the raw surfaces acquired by IOS are typically low-quality at gingival and deep intraoral regions. In recent years, some pioneering end-to-end methods (e.g., PointNet) have been proposed in the communities of computer vision and graphics to consume directly raw surface for 3D shape segmentation. Although these methods are potentially applicable to our task, most of them fail to capture fine-grained local geometric context that is critical to the identification of small teeth with varying shapes and appearances. In this paper, we propose an end-to-end deep-learning method, called MeshSegNet, for automated tooth labeling on raw dental surfaces. Using multiple raw surface attributes as inputs, MeshSegNet integrates a series of graph-constrained learning modules along its forward path to hierarchically extract multi-scale local contextual features. Then, a dense fusion strategy is applied to combine local-to-global geometric features for the learning of higher-level features for mesh cell annotation. The predictions produced by our MeshSegNet are further post-processed by a graph-cut refinement step for final segmentation. We evaluated MeshSegNet using a real-patient dataset consisting of raw maxillary surfaces acquired by 3D IOS. Experimental results, performed 5-fold cross-validation, demonstrate that MeshSegNet significantly outperforms state-of-the-art deep learning methods for 3D shape segmentation.

Gradient-based generation of intermediate images for heterogeneous tumor segmentation within hybrid PET/MRI scans

Segmentation of tumors from hybrid PET/MRI scans plays an essential role in accurate diagnosis and treatment planning. However, when treating tumors, several challenges, notably heterogeneity and the problem of leaking into surrounding tissues with similar high uptake, have to be considered. To address these issues, we propose an automated method for accurate delineation of tumors in hybrid PET/MRI scans. The method is mainly based on creating intermediate images. In fact, an automatic detection technique that determines a preliminary Interesting Uptake Region (IUR) is firstly performed. To overcome the leakage problem, a separation technique is adopted to generate the final IUR. Then, smart seeds are provided for the Graph Cut (GC) technique to obtain the tumor map. To create intermediate images that tend to reduce heterogeneity faced on the original images, the tumor map gradient is combined with the gradient image. Lastly, segmentation based on the GC_sum^max technique is applied to the generated images. The proposed method has been validated on PET phantoms as well as on real-world PET/MRI scans of prostate, liver and pancreatic tumors. Experimental comparison revealed the superiority of the proposed method over state-of-the-art methods. This confirms the crucial role of automatically creating intermediate images in addressing the problem of wrongly estimating arc weights for heterogeneous targets.

Pediatric Brain Tissue Segmentation from MRI using Clustering: a Preliminary Study

Brain Tissue Segmentation (BTS) in young children and neonates is not a trivial task due to peculiar characteristics of the developing brain. The aim of this study is to present the preliminary results of new atlas-free BTS (afBTS) algorithm of MR images for pediatric applications, based on clustering. The algorithm works on axial T1, T2 and FLAIR sequences. First, the Cerebrospinal Fluid (CSF) is identified using the Region Growing algorithm. The remaining voxels are processed with the k-means algorithm in order to separate White Matter (WM) and Grey Matter (GM). The afBTS algorithm was applied to a population of 13 neonates; the segmentations were evaluated by two expert pediatric neuroradiologists and compared with an atlas-based algorithm. The results were promising: afBTS allowed reconstruction of WM and CSF with an image quality comparable to the reference of standard while lower segmentation quality was obtained for the GM segmentation.

Evolving Role of PET-Based Novel Quantitative Techniques in the Management of Hematological Malignancies

"The role of ¹⁸F-fluorodeoxyglucose PET/computed tomography in hematological malignancies continues to expand in disease diagnosis, staging, and management. A key advantage of PET over other imaging modalities is its ability to quantify tracer uptake, which can be used to determine degree of disease activity. Although tracer uptake with PET is conventionally measured in focal lesions, novel quantitative techniques are being investigated that set objective protocols and produce robust parameters that represent total disease activity portrayed by PET. This article discusses recent advances in PET quantification that can improve reliability and accuracy of characterizing hematological malignancies."