Cervical cancer is a malignant tumor that endangers women's life and health. While deep learning has enhanced the accuracy of cervical cell classification, there remain obstacles impeding further performance enhancement, including the similarities between different categories, variability between single cells and cell clusters, as well as the accuracy of annotations. To address these issues, a novel multi-task collaborative framework for cervical cell classification is proposed. Specifically, to solve the similarity between different categories, we propose a grouping cell contrast auxiliary branch, which divides cervical cells into different groups and utilizes supervised contrastive learning to learn representative feature between different categories. And we introduce a multi-level cell classification auxiliary branch that simultaneously performs 5-class, 3-class, and 2-class classification tasks, and explicitly constrains the inter-class relationship learning of cervical cells. Furthermore, to solve the variations within the same category of single cells and cell clusters, we propose an image reconstruction auxiliary branch, which encourages the model to learn more contextual features. Finally, to solve subjectivity and accuracy of annotations, we introduce a soft label distillation auxiliary branch, which constrains the consistency of probability distributions between the encoder and the momentum encoder. It is worth noting that these auxiliary branches only work during training and will not add additional computational consumption during inference. We validate on the HSJCC, DSCC and SIPaKMeD datasets. Compared to existing methods, our approach has achieved outstanding performance and effectively mitigates the issues raised, demonstrating its effectiveness in automated cervical cell classification.

Hyperspectral imaging is a promising imaging modality, and has attracted increasing research attention by compressive sensing such as coded aperture snapshot spectral imaging (CASSI), for simultaneously capturing abundant information in spatial, spectral and temporal domains. Hyperspectral image (HSI) reconstruction in the CASSI aims to retrieve the original 3D signal upon the 2D compressed snapshot. Recently, deep learning has extensively been employed for HSI reconstruction via manually designing network architectures, and usually causes complicated and massive-computational models, which are difficult for being embedding in the real imaging systems. This study aims to leverage network architecture search to automatically design effective and efficient network architectures for HSI reconstruction. Specifically, we exploit gradient-based search strategies and prepare optional operations (cells) with adaptive receptive field such as dilate and deformable convolutional layers to construct a flexible hierarchical search space. Through sharing cells within different levels of features and utilizing an early stopping technique, we achieve a computational and memory efficient NAS strategy to automatically design an effective lightweight model for HSI reconstruction. Extensive experimental results have demonstrated that the network architecture achieved by our proposed NAS has much smaller model size and a lower computational cost while produce better or comparable HSI reconstruction performance compared with the state-of-the-art methods.

In tumor diagnosis, due to subtle differences in the imaging appearance of different diseases, accurately classifying lesions based on solely imaging data proves challenging. Existing machine learning and deep learning methods face limitations due to the small sample size of medical datasets and the intricate nature of disease image manifestations. This paper proposes a novel lesion classification method to fully explore distinctions among confused lesion features associated with different diseases. The proposed method comprises three key steps: Firstly, a lesion feature calculation method using dynamic fusion of global attention and local attention is proposed. The weight of global attention and local attention is dynamically allocated, and the global and local features are fused by dynamic weight. Secondly, feature dimension reduction is realized to improve the effect of distinguishable features using sparse autoencoder and polynomial constraint loss function. Finally, to improve the performance of classification, the monarch butterfly optimization algorithm based on adaptive neighborhood search radius method is used to optimize the parameters of multi-kernel support vector machine. The private PET/CT image classification dataset of lymphoma and Still’s disease was used to validate our results. The experimental results demonstrate that the method's efficacy in lymphoma and Still’ disease classification tasks, achieving an accuracy (ACC) of 82.8% and an area under the curve (AUC) of 87.1%, respectively.

Positron emission tomography-computed tomography (PET/CT) is an essential imaging instrument for lymphoma diagnosis and prognosis. PET/CT image based automatic lymphoma segmentation is increasingly used in the clinical community. U-Net-like deep learning methods have been widely used for PET/CT in this task. However, their performance is limited by the lack of sufficient annotated data, due to the existence of tumor heterogeneity. To address this issue, we propose an unsupervised image generation scheme to improve the performance of another independent supervised U-Net for lymphoma segmentation by capturing metabolic anomaly appearance (MAA). Firstly, we propose an anatomical-metabolic consistency generative adversarial network (AMC-GAN) as an auxiliary branch of U-Net. Specifically, AMC-GAN learns normal anatomical and metabolic information representations using co-aligned whole-body PET/CT scans. In the generator of AMC-GAN, we propose a complementary attention block to enhance the feature representation of low-intensity areas. Then, the trained AMC-GAN is used to reconstruct the corresponding pseudo-normal PET scans to capture MAAs. Finally, combined with the original PET/CT images, MAAs are used as the prior information for improving the performance of lymphoma segmentation. Experiments are conducted on a clinical dataset containing 191 normal subjects and 53 patients with lymphomas. The results demonstrate that the anatomical-metabolic consistency representations obtained from unlabeled paired PET/CT scans can be helpful for more accurate lymphoma segmentation, which suggest the potential of our approach to support physician diagnosis in practical clinical applications.

Accurate segmentation of the hepatic vein can improve the precision of liver disease diagnosis and treatment. Since the hepatic venous system is a small target and sparsely distributed, with various and diverse morphology, data labeling is difficult. Therefore, automatic hepatic vein segmentation is extremely challenging. We propose a lightweight contextual and morphological awareness network and design a novel morphology aware module based on attention mechanism and a 3D reconstruction module. The morphology aware module can obtain the slice similarity awareness mapping, which can enhance the continuous area of the hepatic veins in two adjacent slices through attention weighting. The 3D reconstruction module connects the 2D encoder and the 3D decoder to obtain the learning ability of 3D context with a very small amount of parameters. Compared with other SOTA methods, using the proposed method demonstrates an enhancement in the dice coefficient with few parameters on the two datasets. A small number of parameters can reduce hardware requirements and potentially have stronger generalization, which is an advantage in clinical deployment.

Intracerebral hemorrhage is the subtype of stroke with the highest mortality rate, especially when it also causes secondary intraventricular hemorrhage. The optimal surgical option for intracerebral hemorrhage remains one of the most controversial areas of neurosurgery. We aim to develop a deep learning model for the automatic segmentation of intraparenchymal and intraventricular hemorrhage for clinical catheter puncture path planning. First, we develop a 3D U-Net embedded with a multi-scale boundary aware module and a consistency loss for segmenting two types of hematoma in computed tomography images. The multi-scale boundary aware module can improve the model's ability to understand the two types of hematoma boundaries. The consistency loss can reduce the probability of classifying a pixel into two categories at the same time. Since different hematoma volumes and locations have different treatments. We also measure hematoma volume, estimate centroid deviation, and compare with clinical methods. Finally, we plan the puncture path and conduct clinical validation. We collected a total of 351 cases, and the test set contained 103 cases. For intraparenchymal hematomas, the accuracy can reach 96 % when the proposed method is applied for path planning. For intraventricular hematomas, the proposed model's segmentation efficiency and centroid prediction are superior to other comparable models. Experimental results and clinical practice show that the proposed model has potential for clinical application. In addition, our proposed method has no complicated modules and improves efficiency, with generalization ability.

Collaborative learning methods for medical image segmentation are often variants of UNet, where the constructions of classifiers depend on each other and their outputs are supervised independently. However, they cannot explicitly ensure that optimizing auxiliary classifier heads leads to improved segmentation of target classifier. To resolve this problem, we propose a structured collaborative learning (SCL) method, which consists of a context-aware structured classifier population generation (CA-SCPG) module, where the feature propagation of the target classifier path is directly enhanced by the outputs of auxiliary classifiers via a light-weighted high-level context-aware dense connection (HLCA-DC) mechanism, and a knowledge-aware structured classifier population supervision (KA-SCPS) module, where the auxiliary classifiers are properly supervised under the guidance of target classifier's segmentations. Specifically, SCL is proposed based on a recurrent-dense-siamese decoder (RDS-Decoder), which consists of multiple siamese-decoder paths. CA-SCPG enhances the feature propagation of the decoder paths by HLCA-DC, which densely reuses previous decoder paths' output predictions to belong to the target classes as inputs to the latter decoder paths. KA-SCPS supervises the classifier heads simultaneously with KA-SCPS loss, which consists of a generalized weighted cross-entropy loss for deep class-imbalanced learning and a novel knowledge-aware Dice loss (KA-DL). KA-DL is a weighted Dice loss broadcasting knowledges learnt by the target classifier to other classifier heads, harmonizing the learning process of the classifier population. Experiments are performed based on PET/CT volumes with malignant melanoma, lymphoma, or lung cancer. Experimental results demonstrate the superiority of our SCL, when compared to the state-of-the-art methods and baselines.

Lymphoma is cancer originated in the lymphatic system. Clinically, automatic and accurate lymphoma segmentation is critical yet challenging. Recently, UNet-like architectures are widely used for medical image segmentation. The pure UNet-like architectures can model the spatial correlation between the feature maps very well, whereas they discard the critical temporal correlation. Some prior works combine UNet with recurrent neural networks (RNNs) to utilize the spatial and temporal correlation simultaneously. However, it is inconvenient to incorporate some advanced techniques proposed for UNet to RNNs, which hampers their further improvements. In this paper, we propose a recurrent dense siamese decoder architecture, which simulates RNNs and can densely utilize the spatial temporal correlation between the decoder feature maps following a "UNet" approach. We combine it with a modified hyper dense encoder. Therefore, the proposed model is a UNet with a hyper dense encoder and a recurrent dense siamese decoder (HD-RDS-UNet). To stabilize the training process, we propose a weighted Dice loss with stable gradient and self-adaptive parameters. We perform patient-independent five-fold cross-validation on 3D volumes collected from whole-body PET/CT scans of patients with lymphomas. The experimental results show that the volume-wise average Dice score and sensitivity are 85.58% and 94.63%, respectively. The patient-wise average Dice score and sensitivity are 85.85% and 95.01%, respectively. The different configurations of HD-RDS-UNet consistently show superiority in the performance comparison. Besides, a trained HD-RDS-UNet can be easily pruned, resulting in significantly reduced inference time and memory usage, while keeping very good segmentation performance.

Accurate lymphoma segmentation on Positron Emission Tomography (PET) images is of great importance for medical diagnoses, such as for distinguishing benign and malignant. To this end, this paper proposes an adaptive weighting and scalable distance regularized level set evolution (AW-SDRLSE) method for delineating lymphoma boundaries on 2D PET slices. There are three important characteristics with respect to AW-SDRLSE: 1) A scalable distance regularization term is proposed and a parameter q can control the contour's convergence rate and precision in theory. 2) A novel dynamic annular mask is proposed to calculate mean intensities of local interior and exterior regions and further define the region energy term. 3) As the level set method is sensitive to parameters, we thus propose an adaptive weighting strategy for the length and area energy terms using local region intensity and boundary direction information. AW-SDRLSE is evaluated on 90 cases of real PET data with a mean Dice coefficient of 0.8796. Comparative results demonstrate the accuracy and robustness of AW-SDRLSE as well as its performance advantages as compared with related level set methods. In addition, experimental results indicate that AW-SDRLSE can be a fine segmentation method for improving the lymphoma segmentation results obtained by deep learning (DL) methods significantly.

Accurate classification on pathological images is a significant research focus such as for non-Hodgkin lymphomas (NHL). To this end, this paper proposes a hierarchical classification model based on the labels' statistics for three NHL pathological images, including chronic lymphocytic leukemia (CLL), follicular lymphoma (FL) and mantle cell lymphoma (MCL). First, each pathological image is converted onto the grayscale channel and then divided into 130 non-overlapped patches with 100100 pixels. Next, the sparse autoencoder (SAE), an unsupervised feature extraction method, is utilized to learn the representations of all patches and meanwhile texture features are extracted on these patches which are considered as the hand-craft features. Following this process, we can obtain a 680-dimension feature set. Finally, a hierarchical classification model trained by these 680-dimension features is applied to classify NHL as CLL, FL and MCL, where the label of each NHL pathological image is determined via the output labels of its 130 patches. The experimental results and comparisons demonstrate the advantages of the proposed hierarchical classification model.

Organ segmentation on computed tomography (CT) images is of great importance in medical diagnoses and treatment. This paper proposes organ location determination and contour sparse representation methods (OLD-CSR) for multiorgan segmentation (liver, kidney, and spleen) on abdomen CT images using an extreme learning machine classifier. First, a location determination method is designed to obtain location information of each organ, which is used for coarse segmentation. Second, for coarse-to-fine segmentation, a contour gradient and rate change based feature point extraction method is proposed. A sparse optimization model is developed for refining the contour feature points. Experimentations with 153 CT images demonstrate the performance advantages of OLD-CSR as compared with related work.

This paper proposes a novel liver cancer identification method based on PSO-SVM. First, the region of interest (ROI) is determined by Lazy-Snapping, and various texture features are extracted from ROI. Afterwards, F-score algorithm is applied to select relevant features, based on which liver cancer classifier is designed by combining parallel Support Vector Machine (SVM) with Particle Swarm Optimization (PSO) algorithm. PSO is used to automatically choose parameters for SVM, and the advantage is that it makes the choice of parameter more objective and avoids the randomicity and subjectivity in the traditional SVM whose parameters are decided through trial and error. The experiment results on real-world datasets show that the proposed parallel PSO-SVM training algorithm improves the prediction accuracy of liver cancer.

Liver segmentation on computed tomography (CT) images is a challenging task due to the anatomic complexity and the imaging system noises. In this paper a complex algorithm based on active contour is proposed to automatically extract the liver region in abdominal CT images. Combined with threshold segmentation, morphology image processing and active contour models, we can automatically extract the initial contour and segment the liver slice by slice, Experimental results show that the proposed method gives automatic and accurate liver structure segmentation.