Accurate Tumor Segmentation Research Articles

IMG-05. A MULTI-INSTITUTIONAL AND MULTI-HISTOLOGY PEDIATRIC-SPECIFIC BRAIN TUMOR SUBREGION SEGMENTATION TOOL: FACILITATING RAPNO-BASED ASSESSMENT OF TREATMENT RESPONSE

Abstract Current response assessment in pediatric brain tumors (PBTs), as recommended by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working group, relies on 2D measurements of changes in tumor size. However, there is growing evidence of underestimation of tumor size in PBTs using 2D compared to volumetric (3D) measurement approach. Accordingly, automated methods that reduce manual burden and intra- and inter-rater variability in segmenting tumor subregions and volumetric evaluations are warranted to facilitate tumor response assessment of PBTs. We have developed a fully automatic deep learning (DL) model using the nnUNet architecture on a large cohort of multi-institutional and multi-histology PBTs. The model was trained on widely available standard multiparametric MRI sequences (T1-pre, T1-post, T2, T2-FLAIR) for segmentation of the whole tumor and RAPNO-recommended subregions, including enhancing tumor (ET), non-enhancing tumor (NET), cystic components (CC), and peritumoral edema (ED). As a prerequisite step for accurate tumor segmentation, we also generated another DL model based on DeepMedic for brain extraction from mpMRIs. The models were trained on an institutional cohort of 151 subjects and independently tested on 64 subjects from the internal and 29 patients from external institutions. The trained models showed excellent performance with median Dice scores of 0.98±0.02/0.97±0.02 for brain tissue segmentation, 0.92±0.08/0.90±0.17 for whole tumor segmentation, 0.76±0.31/0.87±0.29 for ET subregion, and 0.82±0.15/0.80±0.28 for segmentation of non-enhancing components (combination of NET, CC, and ED) in internal/external test sets, respectively. The automated segmentation demonstrated strong agreement with expert segmentations in volumetric measurement of tumor components, with Pearson’s correlation coefficients of 0.97, 0.97, 0.99, and 0.79 (p<0.0001) for ET, NET, CC, and ED regions, respectively. Our proposed multi-institutional and multi-histology automated segmentation method has the potential to aid clinical neuro-oncology practice by providing reliable and reproducible volumetric measurements for treatment response assessment.

Coco-Attention for Tumor Segmentation in Weakly Paired Multimodal MRI Images

Multimodal magnetic resonance imaging (MRI) contains complementary information in anatomical and functional images that help the accurate diagnosis and treatment evaluation of lung cancers. However, effectively exploiting the complementary information in chest MRI images remains challenging due to the lack of rigorous registration. In this paper, a novel method is proposed that can effectively exploit the complementary information in weakly paired images for accurate tumor segmentation, namely coco-attention mechanism. Coco-attention module consists of two parts: the multi-modal co-attention (MultiCo-attn) and the multi-level coordinate attention (MultiCord-attn). The former aims to obtain tumor-aware deep features for accurate tumor localization, and the latter aims to highlight tumor area for more precise segmentation. Specifically, the MultiCo-attn extracts complementary information from multimodal high-dimensional semantic features using a bidirectional algorithm to generate attention maps focused on tumor region, and then uses the attention maps to enhance the feature representations. The MultiCord-attn leverages multi-level feature information to highlight tumor regions by adjusting the weight of each point in the feature. We evaluate the proposed method on lung tumor segmentation with a clinical dataset of 90 chest MRI scans of non-small cell lung cancer (NSCLC). The results show that the proposed method is effective for tumor segmentation in weakly paired images and achieves significant improvement (p < 0.005) over several commonly used multimodal segmentation methods. Furthermore, the ablation experiment results confirm the effectiveness and interpretability of the proposed coco-attention module.

Early Stage Liver Disease Prediction using Image Processing

Abstract: Liver diseases have become increasingly common due to sedentary lifestyles and lack of physical activity, particularly in urban areas and metropolitan cities. This has resulted in millions of deaths every year, with liver cancer being a major contributor. However, inaccurate detection of liver tumors has led to many fatalities. Medical image segmentation is a challenging task when it comes to detecting liver tumors in CT images. Therefore, this project aims to improve the accuracy of tumor detection and segmentation using various image processing techniques, such as pre-processing, enhancement, and clustering algorithms. Early detection is critical in preventing liver cancer fatalities, and this project focuses on improving classification performance to aid in early detection. In this paper, we will describe the steps taken to select the best model and develop a necessary system for predicting liver disease.

Early Stage Liver Disease Prediction using Image Processing

Abstract: Liver diseases have become increasingly common due to sedentary lifestyles and lack of physical activity, particularly in urban areas and metropolitan cities. This has resulted in millions of deaths every year, with liver cancer being a major contributor. However, inaccurate detection of liver tumors has led to many fatalities. Medical image segmentation is a challenging task when it comes to detecting liver tumors in CT images. Therefore, this project aims to improve the accuracy of tumor detection and segmentation using various image processing techniques, such as pre-processing, enhancement, and clustering algorithms. Early detection is critical in preventing liver cancer fatalities, and this project focuses on improving classification performance to aid in early detection. In this paper, we will describe the steps taken to select the best model and develop a necessary system for predicting liver disease.

Rethinking the unpretentious U-net for medical ultrasound image segmentation

Breast tumor segmentation from ultrasound images is one of the key steps that help us characterize and localize tumor regions. However, variable tumor morphology, blurred boundaries, and similar intensity distributions bring challenges for radiologists to segment breast tumors manually. During clinical diagnosis, there are higher demands on the segmentation accuracy and efficiency of breast ultrasound images, so there is an urgent need for an automated method to improve the segmentation accuracy as a technical tool to assist diagnosis. Inspired by the U-net and its many variations, this paper proposed an unpretentious nested U-net (NU-net) for accurate and efficient breast tumor segmentation. The key idea is to utilize U-nets with different depths and shared weights to achieve robust characterization of breast tumors. Specifically, we first utilize the deeper U-net (fifteen layers) as the backbone network to extract more sufficient breast tumor features. Then, we developed a multi-output U-net to be taken as the bond between the encoder and the decoder to enhance the network adaptability for breast tumors with different scales. Finally, the short-connection based on multi-step down-sampling is used to enhance the correlation of long-range information of encoded features. Extensive experimental results with fifteen state-of-the-art segmentation methods on three public breast ultrasound datasets demonstrate that our method has a more competitive segmentation performance on breast tumors. Furthermore, the robustness of our approach is further illustrated by the segmentation of renal ultrasound images. The source code is publicly available on https://github.com/CGPxy/NU-net.

DMCT-Net: dual modules convolution transformer network for head and neck tumor segmentation in PET/CT

Objective. Accurate segmentation of head and neck (H&N) tumors is critical in radiotherapy. However, the existing methods lack effective strategies to integrate local and global information, strong semantic information and context information, and spatial and channel features, which are effective clues to improve the accuracy of tumor segmentation. In this paper, we propose a novel method called dual modules convolution transformer network (DMCT-Net) for H&N tumor segmentation in the fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) images. Approach. The DMCT-Net consists of the convolution transformer block (CTB), the squeeze and excitation (SE) pool module, and the multi-attention fusion (MAF) module. First, the CTB is designed to capture the remote dependency and local multi-scale receptive field information by using the standard convolution, the dilated convolution, and the transformer operation. Second, to extract feature information from different angles, we construct the SE pool module, which not only extracts strong semantic features and context features simultaneously but also uses the SE normalization to adaptively fuse features and adjust feature distribution. Third, the MAF module is proposed to combine the global context information, channel information, and voxel-wise local spatial information. Besides, we adopt the up-sampling auxiliary paths to supplement the multi-scale information. Main results. The experimental results show that the method has better or more competitive segmentation performance than several advanced methods on three datasets. The best segmentation metric scores are as follows: DSC of 0.781, HD95 of 3.044, precision of 0.798, and sensitivity of 0.857. Comparative experiments based on bimodal and single modal indicate that bimodal input provides more sufficient and effective information for improving tumor segmentation performance. Ablation experiments verify the effectiveness and significance of each module. Significance. We propose a new network for 3D H&N tumor segmentation in FDG-PET/CT images, which achieves high accuracy.

An anatomy-aware framework for automatic segmentation of parotid tumor from multimodal MRI

Magnetic Resonance Imaging (MRI) plays an important role in diagnosing the parotid tumor, where accurate segmentation of tumors is highly desired for determining appropriate treatment plans and avoiding unnecessary surgery. However, the task remains nontrivial and challenging due to ambiguous boundaries and various sizes of the tumor, as well as the presence of a large number of anatomical structures around the parotid gland that are similar to the tumor. To overcome these problems, we propose a novel anatomy-aware framework for automatic segmentation of parotid tumors from multimodal MRI. First, a Transformer-based multimodal fusion network PT-Net is proposed in this paper. The encoder of PT-Net extracts and fuses contextual information from three modalities of MRI from coarse to fine, to obtain cross-modality and multi-scale tumor information. The decoder stacks the feature maps of different modalities and calibrates the multimodal information using the channel attention mechanism. Second, considering that the segmentation model is prone to be disturbed by similar anatomical structures and make wrong predictions, we design anatomy-aware loss. By calculating the distance between the activation regions of the prediction segmentation and the ground truth, our loss function forces the model to distinguish similar anatomical structures with the tumor and make correct predictions. Extensive experiments with MRI scans of the parotid tumor showed that our PT-Net achieved higher segmentation accuracy than existing networks. The anatomy-aware loss outperformed state-of-the-art loss functions for parotid tumor segmentation. Our framework can potentially improve the quality of preoperative diagnosis and surgery planning of parotid tumors.

2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

BackgroundKidney tumors have become increasingly prevalent among adults and are now considered one of the most common types of tumors. Accurate segmentation of kidney tumors can help physicians assess tumor complexity and aggressiveness before surgery. However, segmenting kidney tumors manually can be difficult because of their heterogeneity.MethodsThis paper proposes a 2.5D MFFAU-Net (multi-level Feature Fusion Attention U-Net) to segment kidneys, tumors and cysts. First, we propose a 2.5D model for learning to combine and represent a given slice in 2D slices, thereby introducing 3D information to balance memory consumption and model complexity. Then, we propose a ResConv architecture in MFFAU-Net and use the high-level and low-level feature in the model. Finally, we use multi-level information to analyze the spatial features between slices to segment kidneys and tumors.ResultsThe 2.5D MFFAU-Net was evaluated on KiTS19 and KiTS21 kidney datasets and demonstrated an average dice score of 0.924 and 0.875, respectively, and an average Surface dice (SD) score of 0.794 in KiTS21.ConclusionThe 2.5D MFFAU-Net model can effectively segment kidney tumors, and the results are comparable to those obtained with high-performance 3D CNN models, and have the potential to serve as a point of reference in clinical practice.

Feature fusion and latent feature learning guided brain tumor segmentation and missing modality recovery network

Accurate brain tumor segmentation is an essential step for clinical diagnosis and surgical treatment. Multimodal brain tumor segmentation strongly relies on an effective fusion method and an excellent segmentation network. However, it is common to have some missing MR modalities in clinical scenarios due to image corruption, acquisition protocol, scanner availability and scanning cost, which can heavily decrease the tumor segmentation accuracy, and also cause information loss for down-streaming disease analysis. To address this issue, I propose a novel multimodal feature fusion and latent feature learning guided deep neural network. On the one hand, the proposed network can help to segment brain tumors when one or more modalities are missing. On the other hand, it can retrieve the missing modalities to compensate for incomplete data. The proposed network consists of three key components. First, a Multimodal Feature Fusion Module (MFFM) is proposed to effectively fuse the complementary information from different modalities, consisting of a Cross-Modality Fusion Module (CMFM) and a Multi-Scale Fusion Module (MSFM). Second, a Spatial Consistency-based Latent Feature Learning Module (SC-LFLM) is presented to exploit multimodal latent correlation and extract the relevant features to benefit segmentation. Third, the Multi-Task Learning (MTL) paths are integrated to supervise the segmentation and recover the missing modalities. The proposed method is evaluated on BraTS 2018 dataset, and it can achieve superior segmentation results when one or more modalities are missing, compared with the state-of-the-art methods. Furthermore, the proposed modules can be easily adapted to other multimodal network architectures and research fields.

CBCT-guided adaptive radiotherapy using self-supervised sequential domain adaptation with uncertainty estimation.

Adaptive radiotherapy (ART) is an advanced technology in modern cancer treatment that incorporates progressive changes in patient anatomy into active plan/dose adaption during the fractionated treatment. However, the clinical application relies on the accurate segmentation of cancer tumors on low-quality on-board images, which has posed challenges for both manual delineation and deep learning-based models. In this paper, we propose a novel sequence transduction deep neural network with an attention mechanism to learn the shrinkage of the cancer tumor based on patients' weekly cone-beam computed tomography (CBCT). We design a self-supervised domain adaption (SDA) method to learn and adapt the rich textural and spatial features from pre-treatment high-quality computed tomography (CT) to CBCT modality in order to address the poor image quality and lack of labels. We also provide uncertainty estimation for sequential segmentation, which aids not only in the risk management of treatment planning but also in the calibration and reliability of the model. Our experimental results based on a clinical non-small cell lung cancer (NSCLC) dataset with sixteen patients and ninety-six longitudinal CBCTs show that our model correctly learns weekly deformation of the tumor over time with an average dice score of 0.92 on the immediate next step, and is able to predict multiple steps (up to 5 weeks) for future patient treatments with an average dice score reduction of 0.05. By incorporating the tumor shrinkage predictions into a weekly re-planning strategy, our proposed method demonstrates a significant decrease in the risk of radiation-induced pneumonitis up to 35% while maintaining the high tumor control probability.

Segmentation of rectal tumor from multi-parametric MRI images using an attention-based fusion network.

Accurate segmentation of rectal tumors is the most crucial task in determining the stage of rectal cancer and developing suitable therapies. However, complex image backgrounds, irregular edge, and poor contrast hinder the related research. This study presents an attention-based multi-modal fusion module to effectively integrate complementary information from different MRI images and suppress redundancy. In addition, a deep learning-based segmentation model (AF-UNet) is designed to achieve accurate segmentation of rectal tumors. This model takes multi-parametric MRI images as input and effectively integrates the features from different multi-parametric MRI images by embedding the attention fusion module. Finally, three types of MRI images (T2, ADC, DWI) of 250 patients with rectal cancer were collected, with the tumor regions delineated by two oncologists. The experimental results show that the proposed method is superior to the most advanced image segmentation method with a Dice coefficient of [Formula: see text], which is also better than other multi-modal fusion methods. Framework of the AF-UNet. This model takes multi-modal MRI images as input, and integrates complementary information using attention mechanism and suppresses redundancy.

MDFU-Net: Multiscale dilated features up-sampling network for accurate segmentation of tumor from heterogeneous brain data

The existing methods for accurate brain tumor (BT) segmentation based on homogeneous datasets show significant performance degradation in actual clinical applications and lacked heterogeneous data analysis. To address these issues, we designed a deep learning-based multiscale dilated features up-sampling network (MDFU-Net) for accurate BT segmentation from heterogeneous brain data. Our method primarily uses the strength of multiscale dilated features (MDF) inside the encoder module to improve the segmentation performance. For the final segmentation, a simple yet effective decoder module is designed to process the dense spatial MDF. For experiments, our MDFU-Net is trained on one dataset and tested with another dataset in a heterogeneous environment, showing quantitative results of the Dice similarity coefficient (DC) of 62.66%, intersection over union (IoU) of 56.96%, specificity (Spe) of 99.29%, and sensitivity (Sen) of 51.98%, which were higher than those of the state-of-the-art methods. There are several reasons for the lower values of the evaluation metrics of the heterogeneous dataset, including the change in characteristics of different MRI modalities, the presence of minor lesions, and a highly imbalanced dataset. Moreover, the experimental results for a homogeneous dataset showed that our MDFU-Net achieved a DC of 82.96%, IoU of 74.94%, Spe of 99.89%, and Sen of 68.05%, which were also higher than those of the state-of-the-art methods. Our system, which is based on heterogeneous brain data as well as homogeneous brain data, can be advantageous to radiologists and medical experts.

Realistic CT data augmentation for accurate deep-learning based segmentation of head and neck tumors in kV images acquired during radiation therapy.

Using radiation therapy (RT) to treat head and neck (H&N) cancers requires precise targeting of the tumor to avoid damaging the surrounding healthy organs. Immobilisation masks and planning target volume margins are used to attempt to mitigate patient motion during treatment, however patient motion can still occur. Patient motion during RT can lead to decreased treatment effectiveness and a higher chance of treatment related side effects. Tracking tumor motion would enable motion compensation during RT, leading to more accurate dose delivery. The purpose of this paper is to develop a method to detect and segment the tumor in kV images acquired during RT. Unlike previous tumor segmentation methods for kV images, in this paper a process for generating realistic and synthetic CT deformations was developed to augment the training data, and make the segmentation method robust to patient motion. Detecting the tumor in 2D kV images is a necessary step towards 3D tracking of the tumor position during treatment. In this paper a conditional generative adversarial network (cGAN) is presented that can detect and segment the gross tumor volume (GTV) in kV images acquired during H&N RT. Retrospective data from 15 H&N cancer patients obtained from the Cancer Imaging Archive were used to train and test patient-specific cGANs. The training data consisted of digitally reconstructed radiographs (DRRs) generated from each patient's planning CT and contoured GTV. Training data was augmented by using synthetically deformed CTs to generate additional DRRs (in total 39600 DRRs per patient or 25200 DRRs for nasopharyngeal patients) containing realistic patient motion. The method for deforming the CTs was a novel deformation method based on simulating head rotation and internal tumor motion. The testing dataset consisted of 1080 DRRs for each patient, obtained by deforming the planning CT and GTV at different magnitudes to the training data. The accuracy of the generated segmentations was evaluated by measuring the segmentation centroid error, Dice similarity coefficient (DSC) and mean surface distance (MSD). This paper evaluated the hypothesis that when patient motion occurs, using a cGAN to segment the GTV would create a more accurate segmentation than no-tracking segmentations from the original contoured GTV, the current standard-of-care. This hypothesis was tested using the 1-tailed Mann-Whitney U-test. The magnitude of our cGAN segmentation centroid error was (mean ± standard deviation) 1.1 ± 0.8 millimeters and the DSC and MSD values were 0.90 ± 0.03 and 1.6 ± 0.5 millimeters respectively. Our cGAN segmentation method reduced the segmentation centroid error (p<0.001), and MSD (p = 0.031) when compared to the no-tracking segmentation, but did not significantly increase the DSC (p = 0.294). The accuracy of our cGAN segmentation method demonstrates the feasibility of this method for H&N cancer patients during RT. Accurate tumor segmentation of H&N tumors would allow for intrafraction monitoring methods to compensate for tumor motion during treatment, ensuring more accurate dose delivery and enabling better H&N cancer patient outcomes. This article is protected by copyright. All rights reserved.

Liver Tumor Segmentation using Deep Learning Techniques

Liver tumor segmentation plays a critical role in medical imaging analysis, especially in cancer diagnosis and treatment planning. Accurate segmentation of liver tumors is essential. There has been growing interest in developing automated methods for liver tumor segmentation, practically using deep learning algorithms. In this paper, we use the convolutional neural networks (CNNs), on large datasets of liver images, labelled with the tumor regions. A U-net architecture is builtwith cross connections. The encoder and decoder portion of the Unet is built using a 34 layerResNet. The model was trained on Liver Tumor Segmentation challenge (LITS) dataset of liver CT scans and evaluated on a separate test dataset. The results demonstrated that the proposed method produced great segmentation accuracy and an average dice score of 0.95

Accuracy of deformable image registration-based intra-fraction motion management in Magnetic Resonance-guided radiotherapy

Intra-fraction motion management is key in Stereotactic Ablative Radiotherapy (SABR) gated delivery. This study assessed the accuracy of automatic tumor segmentation in the delivery of MR-guided radiotherapy (MRgRT) by comparing it to manual delineations performed by experienced observers. Twenty patients previously treated with MR-guided SABR for thoracic and abdominal tumors were included. Five observers with at least two years of experience in MRgRT manually delineated the gross tumor volume (GTV) for 20 patients on 240 frames of a cine MRI on a sagittal plane. Deformable Image Registration (DIR) based GTV contours were propagated using four different algorithms from a reference frame to subsequent frames.Geometrical analysis based on the Dice Similarity Coefficient (DSC), centroid distance and Hausdorff Distance (HDD) were performed to assess the inter-observer variability and the accuracy of automatic segmentation. A Confidence Value (CV) metric for the reliability of the tumor auto-contouring was also calculated. Inter-observer delineation variability resulted in mean DSC of 0.89, HDD of 5.8mm and centroid distance of 1.7mm. Tumor auto-contouring by the four DIR algorithms resulted in an excellent agreement with the manual delineations by the experienced observers. Mean DSC for each algorithm across all patients wasgreater than0.90, whereas the HDD and centroid distances were below 4.0mm and 1.5mm, respectively. The CV showed a strong correlation with the DSC. DIR-based auto-contouring in MRgRT exhibited a high level of agreement with the manual contouring performed by experts, allowing accurate gated delivery.

A multi-label CNN model for the automatic detection and segmentation of gliomas using [18F]FET PET imaging.

The aim of this study was to develop a convolutional neural network (CNN) for the automatic detection and segmentation of gliomas using [18F]fluoroethyl-L-tyrosine ([18F]FET) PET. Ninety-three patients (84 in-house/7 external) who underwent a 20-40-min static [18F]FET PET scan were retrospectively included. Lesions and background regions were defined by two nuclear medicine physicians using the MIM software, such that delineations by one expert reader served as ground truth for training and testing the CNN model, while delineations by the second expert reader were used to evaluate inter-reader agreement. A multi-label CNN was developed to segment the lesion and background region while a single-label CNN was implemented for a lesion-only segmentation. Lesion detectability was evaluated by classifying [18F]FET PET scans as negative when no tumor was segmented and vice versa, while segmentation performance was assessed using the dice similarity coefficient (DSC) and segmented tumor volume. The quantitative accuracy was evaluated using the maximal and mean tumor to mean background uptake ratio (TBRmax/TBRmean). CNN models were trained and tested by a threefold cross-validation (CV) using the in-house data, while the external data was used for an independent evaluation to assess the generalizability of the two CNN models. Based on the threefold CV, the multi-label CNN model achieved 88.9% sensitivity and 96.5% precision for discriminating between positive and negative [18F]FET PET scans compared to a 35.3% sensitivity and 83.1% precision obtained with the single-label CNN model. In addition, the multi-label CNN allowed an accurate estimation of the maximal/mean lesion and mean background uptake, resulting in an accurate TBRmax/TBRmean estimation compared to a semi-automatic approach. In terms of lesion segmentation, the multi-label CNN model (DSC = 74.6 ± 23.1%) demonstrated equal performance as the single-label CNN model (DSC = 73.7 ± 23.2%) with tumor volumes estimated by the single-label and multi-label model (22.9 ± 23.6ml and 23.1 ± 24.3ml, respectively) closely approximating the tumor volumes estimated by the expert reader (24.1 ± 24.4ml). DSCs of both CNN models were in line with the DSCs by the second expert reader compared with the lesion segmentations by the first expert reader, while detection and segmentation performance of both CNN models as determined with the in-house data were confirmed by the independent evaluation using external data. The proposed multi-label CNN model detected positive [18F]FET PET scans with high sensitivity and precision. Once detected, an accurate tumor segmentation and estimation of background activity was achieved resulting in an automatic and accurate TBRmax/TBRmean estimation, such that user interaction and potential inter-reader variability can be minimized.

Boundary-oriented Network for Automatic Breast Tumor Segmentation in Ultrasound Images.

Breast cancer is considered as the most prevalent cancer. Using ultrasound images is a momentous clinical diagnosis method to locate breast tumors. However, accurate segmentation of breast tumors remains an open problem due to ultrasound artifacts, low contrast, and complicated tumor shapes in ultrasound images. To address this issue, we proposed a boundary-oriented network (BO-Net) for boosting breast tumor segmentation in ultrasound images. The BO-Net boosts tumor segmentation performance from two perspectives. Firstly, a boundary-oriented module (BOM) was designed to capture the weak boundaries of breast tumors by learning additional breast tumor boundary maps. Second, we focus on enhanced feature extraction, which takes advantage of the Atrous Spatial Pyramid Pooling (ASPP) module and Squeeze-and-Excitation (SE) block to obtain multi-scale and efficient feature information. We evaluate our network on two public datasets: Dataset B and BUSI. For the Dataset B, our network achieves 0.8685 in Dice, 0.7846 in Jaccard, 0.8604 in Precision, 0.9078 in Recall, and 0.9928 in Specificity. For the BUSI dataset, our network achieves 0.7954 in Dice, 0.7033 in Jaccard, 0.8275 in Precision, 0.8251 in Recall, and 0.9814 in Specificity. Experimental results show that BO-Net outperforms the state-of-the-art segmentation methods for breast tumor segmentation in ultrasound images. It demonstrates that focusing on boundary and feature enhancement creates more efficient and robust breast tumor segmentation.

AI-Based Automated Lipomatous Tumor Segmentation in MR Images: Ensemble Solution to Heterogeneous Data

Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 pm 0.16, 0.73 pm 0.168, and 0.99 pm 0.012, respectively, while for SL predictions were 0.80 pm 0.184, 0.78 pm 0.193, and 1.00 pm 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.

Large-Kernel Attention for 3D Medical Image Segmentation

Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.

PDF-UNet: A semi-supervised method for segmentation of breast tumor images using a U-shaped pyramid-dilated network

Rapid and precise segmentation of breast tumors is a severe challenge for the global research community to diagnose breast cancer in younger females. An ultrasound system is a non-invasive and efficient way of breast screening. The area, shape, and texture of different breast tumors play a vital role for clinicians in making accurate diagnostic decisions. Furthermore, the limited availability of breast tumor annotated datasets is another challenge for properly training deep neural networks. This research proposes a semi-supervised learning-based method, which incorporates a Data expansion network (DEN), Probability map generator network (PMG), and U-shaped pyramid-dilated fusion network (PDF-UNet) for accurate breast tumor segmentation. The first DEN network is trained on breast unannotated tumor images and generates synthetic images for the data expansion task. The second PMG network generates corresponding probability map images against synthetic unannotated images. Finally, we proposed a segmentation network (PDF-UNet), a modified variant of UNet, to segment the breast tumor images. The results demonstrate that compared with classical UNet, our proposed PDF-UNet achieves an increment of DSC (2.42%) on the Mendeley dataset and an increment of DSC (1.52%) observed on the SIIT dataset. The results reflect that the proposed method is effective when annotated breast ultrasound data is insufficient to train the network. Furthermore, the proposed method can be helpful in relieving the annotation burden of radiologists. The implementation source code is available at GitHub: https://github.com/ahmedeqbal/PDF-UNet.