Limited Annotated Data Research Articles

Self-supervised-RCNN for medical image segmentation with limited data annotation.

Many successful methods developed for medical image analysis based on machine learning use supervised learning approaches, which often require large datasets annotated by experts to achieve high accuracy. However, medical data annotation is time-consuming and expensive, especially for segmentation tasks. To overcome the problem of learning with limited labeled medical image data, an alternative deep learning training strategy based on self-supervised pretraining on unlabeled imaging data is proposed in this work. For the pretraining, different distortions are arbitrarily applied to random areas of unlabeled images. Next, a Mask-RCNN architecture is trained to localize the distortion location and recover the original image pixels. This pretrained model is assumed to gain knowledge of the relevant texture in the images from the self-supervised pretraining on unlabeled imaging data. This provides a good basis for fine-tuning the model to segment the structure of interest using a limited amount of labeled training data. The effectiveness of the proposed method in different pretraining and fine-tuning scenarios was evaluated based on the Osteoarthritis Initiative dataset with the aim of segmenting effusions in MRI datasets of the knee. Applying the proposed self-supervised pretraining method improved the Dice score by up to 18% compared to training the models using only the limited annotated data. The proposed self-supervised learning approach can be applied to many other medical image analysis tasks including anomaly detection, segmentation, and classification.

Synthetic MRI-Assisted and Self-Supervised Adaptive Segmentation of Organs-at-Risk (OARs) in MRI-Based Radiation Therapy

This study proposes a self-supervised solution for OAR segmentation, combining patch-based adaptation and unsupervised synthesis of T2-weighted MRI data to finetune the segmentation model. The aim is to improve adaptation to patient anatomy, overcome limited annotated MRI data, and enhance the generalizability of automatic segmentation models for gynecological cancers. The study used a patch-based cycle consistent generative adversarial network (cycle-GAN) for unsupervised MRI synthesis from CT scans of 20 patients, and a residual U-Net model for OARs segmentation. The segmentation model was trained and validated on synthetic MRI (sMRI) of 103 and 25 patient scans respectively, then finetuned on 78 MRI scans from radiation therapy fractions of 15 additional patients through three-fold cross validation. Self-supervised adaptation was applied, incorporating affine and elastic deformations, intensity shifting, and scaling. The model was trained on 96 × 96 × 96 sub-volumes and validated on entire pelvic sections of the same images. A combination of Dice and weighted cross entropy (CE) losses, with weights assigned for bladder (1), small bowel (1), rectum (2), sigmoid (2), left femoral head (0), and right femoral head (0), was used for OAR segmentation. The performance was evaluated against the model trained only on a limited number of acquired MRI data, as well as sMRI pretrained models with encoder weight freezing and either equal weighting or soft-tissue adjusted weighting. Our sMRI-assisted approach showed improved performance for challenging pelvic OARs compared to the method using only the acquired MRI data. The self-supervised fraction-adaptive segmentation results indicated better performance in target soft-tissues when using at least one treatment fraction for organ-specific adaptation. Our framework leverages pre-existing CT planning data for gynecological cancers to enhance the segmentation performance of OARs during MR-guided adaptive treatments. This approach offers substantial benefits for the radiation therapy workflow, including reduced variability in per-fraction segmentation and clinical burden. Further studies that involve human expert evaluations will be conducted to assess the practicality of this approach in radiation therapy.

Multi-sensor data fusion-enabled semi-supervised optimal temperature-guided PCL framework for machinery fault diagnosis

Due to the extremely limited prior knowledge, machinery fault diagnosis under varying working conditions with limited annotation data is a very challenging task in practical industrial scenarios. To solve this issue, a multi-sensor data fusion-enabled semi-supervised optimal temperature-guided prototypical contrastive learning (OTPCL) framework is proposed for machinery fault diagnosis under varying working conditions with limited annotation data. First, a multi-sensor data adaptive weighting strategy (MSAWS) is built to reintegrate the multi-sensor data by adaptively learning the important information of different sensor data and assigning the corresponding weights. Then, an OTPCL method is proposed to reduce the domain shift between the source and target domains, where the vital parameter named the temperature coefficient are adaptively optimized for enhancing the ability of discriminant domain-invariant feature extraction. Finally, a semi-supervised learning (SSL) framework is constructed by combining the MSAWS, the OTPCL and a domain-shared classifier for machinery fault diagnosis. In two experimental analyses on machinery varying working conditions with limited annotation data, the superiority of the proposed MSAWS is validated by respectively using our fused multi-sensor data and different original single-sensor data for the SSL framework. The proposed method obviously outperforms the five advanced domain adaptation methods including CORAL, MMD, CMMD, JDA and PCL.

A deep learning approach for automated segmentation of magnetic bright points in the solar photosphere

Context. Magnetic bright points (MBPs) are small, bright, and conspicuous magnetic structures observed in the solar photosphere and are widely recognized as tracers of magnetic flux tubes. Previous studies have underscored the significance of MBPs in elucidating the mechanisms of coronal heating. The continuous advancement of solar telescopes and observation techniques has significantly enhanced the resolution of solar images, enabling a more detailed examination of MBP structures. In light of the growing availability of MBP observation images, the implementation of large-scale automated and precise MBP segmentation methods holds tremendous potential to facilitate significant progress in solar physics research. Aims. The objective of this study is to propose a deep learning network called MBP-TransCNN that enables the automatic and precise pixel-level segmentation of MBPs in large quantities, even with limited annotated data. This network is designed to effectively handle MBPs of various shapes and backgrounds, including those with complex features. Methods. First, we normalized our sample of MBP images. We then followed this with elastic deformation and rotation translation to enhance the images and expand the dataset. Next, a dual-branch encoder was used to extract the features of the MBPs, and a Transformer-based global attention mechanism was used to extract global contextual information, while a convolutional neural network (CNN) was used to extract detailed local information. Afterwards, an edge aware module was proposed to extract detailed edge features of MBPs, which were used to optimize the segmentation results. Focal loss was used during the training process to address the problem of the small number of MBP samples. Results. The average values of precision, recall, F1, pixel accuracy, and intersection over union of the MBP-TransCNN are 0.976, 0.827, 0.893, 0.999, and 0.808, respectively. Experimental results show that the proposed MBP-TransCNN deep learning network can quickly and accurately segment the fine structure of MBPs.

Bayesian active summarization

Bayesian Active Learning has had significant impact to various NLP problems, but nevertheless its application to text summarization has been explored very little. We introduce Bayesian Active Summarization (BAS), as a method of combining active learning methods with state-of-the-art summarization models. Our findings suggest that BAS achieves better and more robust performance, compared to random selection, particularly for small and very small data annotation budgets. More specifically, applying BAS with a summarization model like PEGASUS we managed to reach 95% of the performance of the fully trained model, using less than 150 training samples. Furthermore, we have reduced standard deviation by 18% compared to the conventional random selection strategy. Using BAS we showcase it is possible to leverage large summarization models to effectively solve real-world problems with very limited annotated data.

Semi-Supervised Medical Image Segmentation With Voxel Stability and Reliability Constraints.

Semi-supervised learning is becoming an effective solution in medical image segmentation because annotations are costly and tedious to acquire. Methods based on the teacher-student model use consistency regularization and uncertainty estimation and have shown good potential in dealing with limited annotated data. Nevertheless, the existing teacher-student model is seriously limited by the exponential moving average algorithm, which leads to the optimization trap. Moreover, the classic uncertainty estimation method calculates the global uncertainty for images but does not consider local region-level uncertainty, which is unsuitable for medical images with blurry regions. In this paper, the Voxel Stability and Reliability Constraint (VSRC) model is proposed to address these issues. Specifically, the Voxel Stability Constraint (VSC) strategy is introduced to optimize parameters and exchange effective knowledge between two independent initialized models, which can break through the performance bottleneck and avoid model collapse. Moreover, a new uncertainty estimation strategy, the Voxel Reliability Constraint (VRC), is proposed for use in our semi-supervised model to consider the uncertainty at the local region level. We further extend our model to auxiliary tasks and propose a task-level consistency regularization with uncertainty estimation. Extensive experiments on two 3D medical image datasets demonstrate that our method outperforms other state-of-the-art semi-supervised medical image segmentation methods under limited supervision. The source code and pre-trained models of this method are available at https://github.com/zyvcks/JBHI-VSRC.

SS-TBN: A Semi-Supervised Tri-Branch Network for COVID-19 Screening and Lesion Segmentation.

Insufficient annotated data and minor lung lesions pose big challenges for computed tomography (CT)-aided automatic COVID-19 diagnosis at an early outbreak stage. To address this issue, we propose a Semi-Supervised Tri-Branch Network (SS-TBN). First, we develop a joint TBN model for dual-task application scenarios of image segmentation and classification such as CT-based COVID-19 diagnosis, in which pixel-level lesion segmentation and slice-level infection classification branches are simultaneously trained via lesion attention, and individual-level diagnosis branch aggregates slice-level outputs for COVID-19 screening. Second, we propose a novel hybrid semi-supervised learning method to make full use of unlabeled data, combining a new double-threshold pseudo labeling method specifically designed to the joint model and a new inter-slice consistency regularization method specifically tailored to CT images. Besides two publicly available external datasets, we collect internal and our own external datasets including 210,395 images (1,420 cases vs. 498 controls) from ten hospitals. Experimental results show that the proposed method achieves state-of-the-art performance in COVID-19 classification with limited annotated data even if lesions are subtle, and that segmentation results promote interpretability for diagnosis, suggesting the potential of the SS-TBN in early screening in insufficient labeled data situations at the early stage of a pandemic outbreak like COVID-19.

A contrastive learning framework for Event Detection via semantic type prototype representation modelling

The diversity of natural language expressions for describing events poses a challenge for the task of Event Detection (ED) with machine learning methods. To detect and classify event mentions, ED models essentially need to construct a semantic linkage between representations of the mentions and a set of target types. Unfortunately, most existing models use meaningless homogeneous one-hot vectors to represent the event type classes in ED, ignoring the fact that the event type labels also consist of meaningful words and can provide important clues for type representation learning. In this paper, we propose a Contrastive Semantic Prototype Representation Learning Framework for Event Detection (SemPRE), which exploits the pre-defined event type label words to inject the semantic information of the types and guide event detection. Specifically, we utilize pre-trained BERT to fuse text and event type into a joint representation space, and employ a contrastive-regularized module to enhance cross-type interaction. We conduct extensive experiments on the ACE 2005 and MAVEN benchmark datasets. The performance results show that our proposed SemPRE model achieves state-of-the-art performance on the datasets and outperforms existing baselines on limited annotated data and without using any external resources. Further analysis shows that our model is also effective in detecting multiple events and ambiguous trigger words.

Semi-supervised Medical Image Segmentation with Multiscale Contrastive Learning and Cross-Supervision.

We propose a semi-supervised segmentation method based on multiscale contrastive learning to solve the problem of shortage of annotations in medical image segmentation tasks. We apply perturbations to the input image and encoded features and make the output as consistent as possible by cross-supervision, which is a way to improve the generalizability of the model. Two scales of contrastive learning, patch-level and pixel-level, are employed to enhance the intra-class compactness and inter-class separability of the features. We evaluate the proposed model using three public datasets for brain tumor,left atrial, and cellular nuclei segmentation. The experiments showed that our model outperforms state-of-the-art methods.Clinical relevance- The proposed method can be used for medical image segmentation with limited annotated data and achieve comparable performance to the fully annotated situation. Such an approach can be easily extended to other clinical applications.

Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation.

Supervised deep learning-based methods yield accurate results for medical image segmentation. However, they require large labeled datasets for this, and obtaining them is a laborious task that requires clinical expertise. Semi/self-supervised learning-based approaches address this limitation by exploiting unlabeled data along with limited annotated data. Recent self-supervised learning methods use contrastive loss to learn good global level representations from unlabeled images and achieve high performance in classification tasks on popular natural image datasets like ImageNet. In pixel-level prediction tasks such as segmentation, it is crucial to also learn good local level representations along with global representations to achieve better accuracy. However, the impact of the existing local contrastive loss-based methods remains limited for learning good local representations because similar and dissimilar local regions are defined based on random augmentations and spatial proximity; not based on the semantic label of local regions due to lack of large-scale expert annotations in the semi/self-supervised setting. In this paper, we propose a local contrastive loss to learn good pixel level features useful for segmentation by exploiting semantic label information obtained from pseudo-labels of unlabeled images alongside limited annotated images with ground truth (GT) labels. In particular, we define the proposed contrastive loss to encourage similar representations for the pixels that have the same pseudo-label/GT label while being dissimilar to the representation of pixels with different pseudo-label/GT label in the dataset. We perform pseudo-label based self-training and train the network by jointly optimizing the proposed contrastive loss on both labeled and unlabeled sets and segmentation loss on only the limited labeled set. We evaluated the proposed approach on three public medical datasets of cardiac and prostate anatomies, and obtain high segmentation performance with a limited labeled set of one or two 3D volumes. Extensive comparisons with the state-of-the-art semi-supervised and data augmentation methods and concurrent contrastive learning methods demonstrate the substantial improvement achieved by the proposed method. The code is made publicly available at https://github.com/krishnabits001/pseudo_label_contrastive_training.

RDBridge: a knowledge graph of rare diseases based on large-scale text mining.

Despite low prevalence, rare diseases affect 300 million people worldwide. Research on pathogenesis and drug development lags due to limited commercial potential, insufficient epidemiological data, and a dearth of publications. The unique characteristics of rare diseases, including limited annotated data, intricate processes for extracting pertinent entity relationships, and difficulties in standardizing data, represent challenges for text mining. We developed a rare disease data acquisition framework using text mining and knowledge graphs and constructed the most comprehensive rare disease knowledge graph to date, Rare Disease Bridge (RDBridge). RDBridge offers search functions for genes, potential drugs, pathways, literature, and medical imaging data that will support mechanistic research, drug development, diagnosis, and treatment for rare diseases. RDBridge is freely available at http://rdb.lifesynther.com/. Supplementary data are available at Bioinformatics online.

DeepInfusion: A dynamic infusion based-neuro-symbolic AI model for segmentation of intracranial aneurysms

The detection and segmentation of cerebral aneurysms is a crucial step in the development of a clinical decision support system for estimating aneurysm rupture risk. However, accurately identifying and segmenting regions of interest in two-dimensional (2D) medical images is often challenging, particularly when using deep learning (DL) methods on small datasets with limited annotated data. The accuracy of DL approaches is often affected by the availability of large, annotated training datasets that are required for effective deep learning. Additionally, when using DL to differentiate aneurysms from arterial loops in 2D DSA images, DL can fail to detect aneurysms in areas where dye concentration is low. To address these issues and enhance the reliability and accuracy of aneurysm detection and segmentation methods, incorporating medical expert-advised, hand-crafted features can provide a clinical perspective to DL methods. This approach can help to improve the performance of DL methods by providing additional information that is not captured in the data. To this end, a novel Neuro-symbolic AI-based DeepInfusion model is proposed which allows for the infusion of human intellect through hand-crafted features into deep neural networks (DNNs), thus combining the strengths of DL with the knowledge and expertise of medical professionals. The proposed approach includes a novel technique for dynamic layer selection and feature weight adjustment during the model infusion process. The performance of the DeepInfusion model is evaluated on an in-house prepared dataset of 409 DSA images, and experimental results demonstrate the effectiveness of the proposed method for the segmentation of cerebral aneurysms. The model achieves an IOU score of 96.76% and an F1-score of 94.15% on unseen DSA images. The model is also tested on two publicly available datasets of Kvasir-SEG polyp and DRIVE for vessel segmentation of retinal images. The results show a significant improvement compared to existing methods, which indicates the generalizability of the approach in medical segmentation. The complete code for DeepInfusion is available on our GitHub repository at https://github.com/smileslab/deep-infusion/blob/main/deepinfusion.ipynb.

A multimodal medical image contrastive learning algorithm with domain adaptive denormalization

Recently, deep learning has achieved impressive results in medical image tasks. However, this method usually requires large-scale annotated data, and medical images are expensive to annotate, so it is a challenge to learn efficiently from the limited annotated data. Currently, the two commonly used methods are transfer learning and self-supervised learning. However, these two methods have been little studied in multimodal medical images, so this study proposes a contrastive learning method for multimodal medical images. The method takes images of different modalities of the same patient as positive samples, which effectively increases the number of positive samples in the training process and helps the model to fully learn the similarities and differences of lesions on images of different modalities, thus improving the model's understanding of medical images and diagnostic accuracy. The commonly used data augmentation methods are not suitable for multimodal images, so this paper proposes a domain adaptive denormalization method to transform the source domain images with the help of statistical information of the target domain. In this study, the method is validated with two different multimodal medical image classification tasks: in the microvascular infiltration recognition task, the method achieves an accuracy of (74.79 ± 0.74)% and an F1 score of (78.37 ± 1.94)%, which are improved as compared with other conventional learning methods; for the brain tumor pathology grading task, the method also achieves significant improvements. The results show that the method achieves good results on multimodal medical images and can provide a reference solution for pre-training multimodal medical images.

T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions

Text summarization is a prominent task in natural language processing (NLP) that condenses lengthy texts into concise summaries. Despite the success of existing supervised models, they often rely on datasets of well-constructed text pairs, which can be insufficient for languages with limited annotated data, such as Chinese. To address this issue, we propose a semi-supervised learning method for text summarization. Our method is inspired by the cycle-consistent adversarial network (CycleGAN) and considers text summarization as a style transfer task. The model is trained by using a similar procedure and loss function to those of CycleGAN and learns to transfer the style of a document to its summary and vice versa. Our method can be applied to multiple languages, but this paper focuses on its performance on Chinese documents. We trained a T5-based model and evaluated it on two datasets, CSL and LCSTS, and the results demonstrate the effectiveness of the proposed method.

SCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification.

The automatic classification of electrocardiogram (ECG) signals has played an important role in cardiovascular diseases diagnosis and prediction. With recent advancements in deep neural networks (DNNs), particularly Convolutional Neural Networks (CNNs), learning deep features automatically from the original data is becoming an effective and widespread approach in a variety of intelligent tasks including biomedical and health informatics. However, most of the existing approaches are trained on either 1D CNNs or 2D CNNs, and they suffer from the limitations of random phenomena (i.e. random initial weights). Furthermore, the ability to train such DNNs in a supervised manner in healthcare is often limited due to the scarcity of labeled training data. To address the problems of weight initialization and limited annotated data, in this work, we leverage recent self-supervised learning technique, namely, contrastive learning, and present supervised contrastive learning (sCL). Different from existing self-supervised contrastive learning approaches, which often generate false negatives because of random selection of negative anchors, our contrastive learning makes use of labeled data to pull the same class closer together and push different classes far apart to avoid potential false negatives. Furthermore, unlike other kinds of signals (e.g. speech, image, video), ECG signal is sensitive to changes, and inappropriate transformation could directly affect diagnosis results. To deal with this issue, we present two semantic transformations, i.e. semantic split-join and semantic weighted peaks noise smoothing. The proposed deep neural network sCL-ST with supervised contrastive learning and semantic transformations is trained as an end-to-end framework for the multi-label classification of 12-lead ECGs. Our sCL-ST network contains two sub-networks i.e. pre-text task and down-stream task. Our experimental results have been evaluated on 12-lead PhysioNet 2020 dataset and shown that our proposed network outperforms the state-of-the-art existing approaches.

Attention-guided cascaded network with pixel-importance-balance loss for retinal vessel segmentation.

Accurate retinal vessel segmentation from fundus images is essential for eye disease diagnosis. Many deep learning methods have shown great performance in this task but still struggle with limited annotated data. To alleviate this issue, we propose an Attention-Guided Cascaded Network (AGC-Net) that learns more valuable vessel features from a few fundus images. Attention-guided cascaded network consists of two stages: the coarse stage produces a rough vessel prediction map from the fundus image, and the fine stage refines the missing vessel details from this map. In attention-guided cascaded network, we incorporate an inter-stage attention module (ISAM) to cascade the backbone of these two stages, which helps the fine stage focus on vessel regions for better refinement. We also propose Pixel-Importance-Balance Loss (PIB Loss) to train the model, which avoids gradient domination by non-vascular pixels during backpropagation. We evaluate our methods on two mainstream fundus image datasets (i.e., DRIVE and CHASE-DB1) and achieve AUCs of 0.9882 and 0.9914, respectively. Experimental results show that our method outperforms other state-of-the-art methods in performance.

Cascaded Vehicle Matching and Short-Term Spatial-Temporal Network for Smoky Vehicle Detection

Vehicle exhaust is the main source of air pollution with the rapid increase of fuel vehicles. Automatic smoky vehicle detection in videos is a superior solution to traditional expensive remote sensing with ultraviolet-infrared light devices for environmental protection agencies. However, it is challenging to distinguish vehicle smoke from shadow and wet regions in cluttered roads, and could be worse due to limited annotated data. In this paper, we first introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images, facilitating the effective training of advanced deep learning models. To enable a fair algorithm comparison, we also built a smoky vehicle video dataset including 163 long videos with segment-level annotations. Second, we present a novel efficient cascaded framework for smoky vehicle detection which largely integrates prior knowledge and advanced deep networks. Specifically, it starts from an improved frame-based smoke detector with a high recall rate, and then applies a vehicle matching strategy to fast eliminate non-vehicle smoke proposals, and finally refines the detection with an elaborately-designed short-term spatial-temporal network in consecutive frames. Extensive experiments in four metrics demonstrated that our framework is significantly superior to hand-crafted feature based methods and recent advanced methods.

A Feedback-Enhanced Two-Stage Framework for judicial machine reading comprehension

Machine Reading Comprehension (MRC) is the task of teaching machines to understand and answer questions based on a given text. In the judicial domain, MRC has garnered attention as a novel strategy for addressing a variety of legal issues. Judicial MRC generally requires interpretability, meaning that the model should not only answer the question correctly but also provide supporting evidence sentences. A straightforward approach is to handle the two tasks separately, which ignores the relation between the two tasks and leads to the loss of annotated information. To make better use of the limited judicial MRC annotation data, we simulate the strategies used by humans in solving MRC problems and propose the Feedback-Enhanced Two-Stage Framework for Machine Reading Comprehension (FETSF-MRC). This framework consists of two cascaded modules: (a) a scanning module that identifies evidence sentences and (b) a detailed reading module that focuses on the evidence to identify candidate answers and provides feedback to the scanning module. Experiments on two Chinese judicial reading comprehension datasets (CJRC, CAIL2020) and an open-domain English dataset HotpotQA show that FETSF-MRC achieves superior performance compared to several baselines. FETSF-MRC outperforms the best baseline by 1.12% and 1.49% in joint F1 score on the CJRC and CAIL2020 datasets, respectively, and achieves 73.74% joint F1 score on the HotpotQA.

Vehicle Recognition Based on Carrier-Free UWB Radars Using Contrastive Multi-View Learning

A novel carrier-free ultrawideband (UWB) radar-based automatic vehicle recognition system is reported. We provide complete transceiver units, design a UWB Vivaldi antenna with centimeter-scale dimensions and bandwidth from 0.89 to 5.02 GHz, and propose the multi-view-based contrastive learning algorithm for target recognition. Simulated results of the antenna are compared with measured results and are shown to be in good agreement. Though target recognition benefits from large, curated labeled data, its application to problems with limited annotated data remains a challenge. In addition, the target-aspect sensitive issue also impacts the performance of models. For that, we combine contrastive learning with unlabeled multi-view data to learn target-aspect-invariant representations. The experiments on the different datasets demonstrate the effectiveness and generalization of our method.

Semi-Supervised Medical Image Segmentation Guided by Bi-Directional Constrained Dual-Task Consistency

Medical image processing tasks represented by multi-object segmentation are of great significance for surgical planning, robot-assisted surgery, and surgical safety. However, the exceptionally low contrast among tissues and limited available annotated data makes developing an automatic segmentation algorithm for pelvic CT challenging. A bi-direction constrained dual-task consistency model named PICT is proposed to improve segmentation quality by leveraging free unlabeled data. First, to learn more unmarked data features, it encourages the model prediction of the interpolated image to be consistent with the interpolation of the model prediction at the pixel, model, and data levels. Moreover, to constrain the error prediction of interpolation interference, PICT designs an auxiliary pseudo-supervision task that focuses on the underlying information of non-interpolation data. Finally, an effective loss algorithm for both consistency tasks is designed to ensure the complementary manner and produce more reliable predictions. Quantitative experiments show that the proposed PICT achieves 87.18%, 96.42%, and 79.41% mean DSC score on ACDC, CTPelvic1k, and the individual Multi-tissue Pelvis dataset with gains of around 0.8%, 0.5%, and 1% compared to the state-of-the-art semi-supervised method. Compared to the baseline supervised method, the PICT brings over 3-9% improvements. The developed PICT model can effectively leverage unlabeled data to improve segmentation quality of low contrast medical images. The segmentation result could improve the precision of surgical path planning and provide input for robot-assisted surgery.