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.

Efficient brain tumor segmentation using Swin transformer and enhanced local self-attention.

PURPOSE: Fully convolutional neural networks architectures have proven to be useful for brain tumor segmentation tasks. However, their performance in learning long-range dependencies is limited to their localized receptive fields. On the other hand, vision transformers (ViTs), essentially based on a multi-head self-attention mechanism, which generates attention maps to aggregate spatial information dynamically, have outperformed convolutional neural networks (CNNs). Inspired by the recent success of ViT models for the medical images segmentation, we propose in this paper a new network based on Swin transformer for semantic brain tumor segmentation. METHODS: The proposed method for brain tumor segmentation combines Transformer and CNN modules as an encoder-decoder structure. The encoder incorporates ELSA transformer blocks used to enhance local detailed feature extraction. The extracted feature representations are fed to the decoder part via skip connections. The encoder part includes channel squeeze and spatial excitation blocks, which enable the extracted features to be more informative both spatially and channel-wise. RESULTS: The method is evaluated on the public BraTS 2021 datasets containing 1251 cases of brain images, each with four 3D MRI modalities. Our proposed approach achieved excellent segmentation results with an average Dice score of 89.77% and an average Hausdorff distance of 8.90 mm. CONCLUSION: We developed an automated framework for brain tumor segmentation using Swin transformer and enhanced local self-attention. Experimental results show that our method outperforms state-of-th-art 3D algorithms for brain tumor segmentation.

Electroacupuncture alleviates neurological function via activating the Yap-OPA1 axis and mitochondrial fusion in rats with cerebral ischemia-reperfusion injury. / 电针通过Yesç›¸å ³è›‹ç™½-视神经萎缩蛋白1ä¿¡å·è½´æ¿€æ´»çº¿ç²’ä½“èžåˆåŠŸèƒ½å‡è½»å¤§é¼ è„‘ç¼ºè¡€å†çŒæ³¨æŸä¼¤çš„æœºåˆ¶ç ”ç©¶.

OBJECTIVES: To investigate the mechanism of electroacupuncture (EA) in alleviating cerebral ische-mia injury by activating the Yap-OPA1 signaling axis. METHODS: A total of 48 male SD rats were used in the present study. The focal CIRI model was established by occlusion of the middle cerebral artery and reperfusion (MCAO/R), followed by dividing the CIRI rats into model group, EA group and EA+Ver (Verteporfin, Yap antagonist) group (n=12 in each group). And another 12 normal rats were used as the sham operation group. For rats of the EA group, EA (4 Hz/20 Hz, 0.5 mA) was applied to "Baihui"(GV20) and "Shenting"(GV24) for 20 min, once daily for 7 days. The neurological deficit score (0 to 4 points) was given according to Longa's method. The infarct volume of rats in each group was assessed by TTC method, and the expression levels of Yes associated protein (Yap), Optic atrophy protein 1 (OPA1), mitofusin 1 (Mfn1), mitofusin 2 (Mfn2) proteins and mRNAs in cerebral cortex of infarcted side, as well as Bax (proapoptotic factor) and Bcl-1 (anti-apoptotic protein) proteins were detected by Westernblot, and real-time PCR, and the immunoactivity of Yap and OPA1 was detected by immunofluorescent staining. RESULTS: After modeling, the infarct volume, neurological deficit score and the expression of Bax were significantly increased (P<0.01), while the mRNA and protein expressions of Yap, OPA1, Mfn2, Mfn1, and Bcl-2 were significantly down-regulated in the model group relevant to the sham operation group (P<0.01, P<0.05). Compared with the model group, the neurological deficit score, infarct volume and the expression of Bax were significantly decreased (P<0.01), while the expression levels of Yap, OPA1, Mfn2, Mfn1 proteins and mRNAs and Bcl-2 protein, Yap and OPA1 immunofluorescence intensify were considerably up-regulated in the EA group (P<0.01, P<0.05). Following administration of Ver, the effects of EA in down-regulating the neurological score, infarct volume, and Bax expression and up-regulating the expressions of Yap, OPA1, Mfn1, Mfn2 proteins and mRNAs and Yap and OPA1 immunofluorescence intensify were eliminated. CONCLUSIONS: EA of GV20 and GV24 can improve the neurological function in rats with CIRI, which may be associated with its functions in activating mitochondrial fusion function and up-regulating Yap-OPA1 signaling axis.

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT.

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review.

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy regulations. Data augmentation techniques offer a solution by artificially increasing the number of training samples, but these techniques often produce limited and unconvincing results. To address this issue, a growing number of studies have proposed the use of deep generative models to generate more realistic and diverse data that conform to the true distribution of the data. In this review, we focus on three types of deep generative models for medical image augmentation: variational autoencoders, generative adversarial networks, and diffusion models. We provide an overview of the current state of the art in each of these models and discuss their potential for use in different downstream tasks in medical imaging, including classification, segmentation, and cross-modal translation. We also evaluate the strengths and limitations of each model and suggest directions for future research in this field. Our goal is to provide a comprehensive review about the use of deep generative models for medical image augmentation and to highlight the potential of these models for improving the performance of deep learning algorithms in medical image analysis.

Prediction of brain tumor recurrence location based on multi-modal fusion and nonlinear correlation learning.

Brain tumor is one of the leading causes of cancer death. The high-grade brain tumors are easier to recurrent even after standard treatment. Therefore, developing a method to predict brain tumor recurrence location plays an important role in the treatment planning and it can potentially prolong patient's survival time. There is still little work to deal with this issue. In this paper, we present a deep learning-based brain tumor recurrence location prediction network. Since the dataset is usually small, we propose to use transfer learning to improve the prediction. We first train a multi-modal brain tumor segmentation network on the public dataset BraTS 2021. Then, the pre-trained encoder is transferred to our private dataset for extracting the rich semantic features. Following that, a multi-scale multi-channel feature fusion model and a nonlinear correlation learning module are developed to learn the effective features. The correlation between multi-channel features is modeled by a nonlinear equation. To measure the similarity between the distributions of original features of one modality and the estimated correlated features of another modality, we propose to use Kullback-Leibler divergence. Based on this divergence, a correlation loss function is designed to maximize the similarity between the two feature distributions. Finally, two decoders are constructed to jointly segment the present brain tumor and predict its future tumor recurrence location. To the best of our knowledge, this is the first work that can segment the present tumor and at the same time predict future tumor recurrence location, making the treatment planning more efficient and precise. The experimental results demonstrated the effectiveness of our proposed method to predict the brain tumor recurrence location from the limited dataset.

[Electroacupuncture alleviates cerebral ischemia injury in rats by regulating melatonin-NLRP3 and inhibiting pyroptosis].

OBJECTIVE: To investigate the mechanism of electroacupuncture in alleviating cerebral ischemia injury in cerebral ischemia-reperfusion rats by regulating melatonin - NOD-like receptor protein 3 (NLRP3) mediated pyroptosis. METHODS: A total of 48 SD rats were randomly divided into sham operation group, model group, electroacupuncture (EA) group and EA +Luz group, with 12 rats in each group. The focal cerebral ischemia-reperfusion injury model was established by middle cerebral artery embolization. Rats of the EA group was treated with EA stimulation (4 Hz/20 Hz, 0.5 mA,20 min) at "Baihui" (GV20) and "Shenting" (GV24) once a day for 7 consecutive days; rats of EA+Luz group were given the same EA treatment and intraperitoneally administered melatonin receptor antagonist (luzindole, 30 mg/kg), once a day for 7 consecutive days. The neurological impairment was evaluated by Zea Longa score. The level of serum melatonin content at 12:00 and 24:00 was detected by ELISA. The percentage of cerebral infarction volume was evaluated by MRI of small animals. The apoptosis rate of nerve cells in cerebral cortex of infarct side was detected by TUNEL staining. The activation of microglia cells was detected by immunofluorescence staining. The expression levels of pyroptosis-related proteins NLRP3, Caspase-1 and interleukin (IL) -1ß were detected by Western blot. RESULTS: Compared with the sham operation group, the neural function score was significantly increased (P<0.01); the melatonin content was significantly decreased at 24:00 (P<0.01); the percentage of cerebral infarction volume, apoptosis rate of nerve cells in cerebral cortex area of infarction side, the expressions of NLRP3, Caspase-1 and IL-1ß proteins were significantly increased (P<0.01); and microglia cells were significantly activated in the model group.Compared with the model and EA +Luz groups, the nerve function score was significantly decreased (P<0.05); the percentage of cerebral infarction volume, the nerve cell apoptosis rate, the activation level of microglia cells, the expression levels of NLRP3, Caspase-1 and IL-1ß were significantly decreased (P<0.01, P<0.05) in the EA group. Compared with the model and EA+Luz groups, the melatonin content at 24:00 was significantly increased (P<0.01, P<0.05) in the EA group. CONCLUSION: EA at GV20 and GV24 can reduce the neurolo-gical injury in cerebral ischemia reperfusion model rats, which may be related to regulating the expression of endogenous melatonin, inhibiting cell scorchification and reducing cerebral ischemia injury.

A literature survey of MR-based brain tumor segmentation with missing modalities.

Multimodal MR brain tumor segmentation is one of the hottest issues in the community of medical image processing. However, acquiring the complete set of MR modalities is not always possible in clinical practice, due to the acquisition protocols, image corruption, scanner availability, scanning cost or allergies to certain contrast materials. The missing information can cause some restraints to brain tumor diagnosis, monitoring, treatment planning and prognosis. Thus, it is highly desirable to develop brain tumor segmentation methods to address the missing modalities problem. Based on the recent advancements, in this review, we provide a detailed analysis of the missing modality issue in MR-based brain tumor segmentation. First, we briefly introduce the biomedical background concerning brain tumor, MR imaging techniques, and the current challenges in brain tumor segmentation. Then, we provide a taxonomy of the state-of-the-art methods with five categories, namely, image synthesis-based method, latent feature space-based model, multi-source correlation-based method, knowledge distillation-based method, and domain adaptation-based method. In addition, the principles, architectures, benefits and limitations are elaborated in each method. Following that, the corresponding datasets and widely used evaluation metrics are described. Finally, we analyze the current challenges and provide a prospect for future development trends. This review aims to provide readers with a thorough knowledge of the recent contributions in the field of brain tumor segmentation with missing modalities and suggest potential future directions.

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.

Multi-task multi-scale learning for outcome prediction in 3D PET images.

BACKGROUND AND OBJECTIVES: Predicting patient response to treatment and survival in oncology is a prominent way towards precision medicine. To this end, radiomics has been proposed as a field of study where images are used instead of invasive methods. The first step in radiomic analysis in oncology is lesion segmentation. However, this task is time consuming and can be physician subjective. Automated tools based on supervised deep learning have made great progress in helping physicians. However, they are data hungry, and annotated data remains a major issue in the medical field where only a small subset of annotated images are available. METHODS: In this work, we propose a multi-task, multi-scale learning framework to predict patient's survival and response. We show that the encoder can leverage multiple tasks to extract meaningful and powerful features that improve radiomic performance. We also show that subsidiary tasks serve as an inductive bias so that the model can better generalize. RESULTS: Our model was tested and validated for treatment response and survival in esophageal and lung cancers, with an area under the ROC curve of 77% and 71% respectively, outperforming single-task learning methods. CONCLUSIONS: Multi-task multi-scale learning enables higher performance of radiomic analysis by extracting rich information from intratumoral and peritumoral regions.

Correction: Brochet et al. A Quantitative Comparison between Shannon and Tsallis-Havrda-Charvat Entropies Applied to Cancer Outcome Prediction. Entropy 2022, 24, 436.

Alexandre Huat, Sébastien Thureau, David Pasquier, Isabelle Gardin, Romain Modzelewski, David Gibon, Juliette Thariat and Vincent Grégoire were not included as authors in the original publication [...].

Learning-based Cancer Treatment Outcome Prognosis using Multimodal Biomarkers.

Predicting early in treatment whether a tumor is likely to be responsive is a difficult yet important task to support clinical decision-making. Studies have shown that multimodal biomarkers could provide complementary information and lead to more accurate treatment outcome prognosis than unimodal biomarkers. However, the prognosis accuracy could be affected by multimodal data heterogeneity and incompleteness. The small-sized and imbalance datasets also bring additional challenges for training a designed prognosis model. In this study, a modular framework employing multimodal biomarkers for cancer treatment outcome prediction was proposed. It includes four modules of synthetic data generation, deep feature extraction, multimodal feature fusion, and classification to address the challenges described above. The feasibility and advantages of the designed framework were demonstrated through an example study, in which the goal was to stratify oropharyngeal squamous cell carcinoma (OPSCC) patients with low- and high-risks of treatment failures by use of positron emission tomography (PET) image data and microRNA (miRNA) biomarkers. The superior prognosis performance and the comparison with other methods demonstrated the efficiency of the proposed framework and its ability of enabling seamless integration, validation and comparison of various algorithms in each module of the framework. The limitation and future work was discussed as well.

Weakly Supervised Tumor Detection in PET Using Class Response for Treatment Outcome Prediction.

It is proven that radiomic characteristics extracted from the tumor region are predictive. The first step in radiomic analysis is the segmentation of the lesion. However, this task is time consuming and requires a highly trained physician. This process could be automated using computer-aided detection (CAD) tools. Current state-of-the-art methods are trained in a supervised learning setting, which requires a lot of data that are usually not available in the medical imaging field. The challenge is to train one model to segment different types of tumors with only a weak segmentation ground truth. In this work, we propose a prediction framework including a 3D tumor segmentation in positron emission tomography (PET) images, based on a weakly supervised deep learning method, and an outcome prediction based on a 3D-CNN classifier applied to the segmented tumor regions. The key step is to locate the tumor in 3D. We propose to (1) calculate two maximum intensity projection (MIP) images from 3D PET images in two directions, (2) classify the MIP images into different types of cancers, (3) generate the class activation maps through a multitask learning approach with a weak prior knowledge, and (4) segment the 3D tumor region from the two 2D activation maps with a proposed new loss function for the multitask. The proposed approach achieves state-of-the-art prediction results with a small data set and with a weak segmentation ground truth. Our model was tested and validated for treatment response and survival in lung and esophageal cancers on 195 patients, with an area under the receiver operating characteristic curve (AUC) of 67% and 59%, respectively, and a dice coefficient of 73% and 0.77% for tumor segmentation.

A Quantitative Comparison between Shannon and Tsallis-Havrda-Charvat Entropies Applied to Cancer Outcome Prediction.

In this paper, we propose to quantitatively compare loss functions based on parameterized Tsallis-Havrda-Charvat entropy and classical Shannon entropy for the training of a deep network in the case of small datasets which are usually encountered in medical applications. Shannon cross-entropy is widely used as a loss function for most neural networks applied to the segmentation, classification and detection of images. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy. In this work, we compare these two entropies through a medical application for predicting recurrence in patients with head-neck and lung cancers after treatment. Based on both CT images and patient information, a multitask deep neural network is proposed to perform a recurrence prediction task using cross-entropy as a loss function and an image reconstruction task. Tsallis-Havrda-Charvat cross-entropy is a parameterized cross-entropy with the parameter α. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy for α=1. The influence of this parameter on the final prediction results is studied. In this paper, the experiments are conducted on two datasets including in total 580 patients, of whom 434 suffered from head-neck cancers and 146 from lung cancers. The results show that Tsallis-Havrda-Charvat entropy can achieve better performance in terms of prediction accuracy with some values of α.

Electroacupuncture Ameliorates Cognitive Impairment Through the Inhibition of NLRP3 Inflammasome Activation by Regulating Melatonin-Mediated Mitophagy in Stroke Rats.

Previous studies found that electroacupuncture (EA) at the Shenting (DU24) and Baihui (DU20) acupoints alleviates cognitive impairment in cerebral ischemia-reperfusion (I/R) injury rats. Nonetheless, the mechanisms of the anti-inflammatory effects of EA are unclear. Cerebral I/R injury was induced in rats by middle cerebral artery occlusion (MCAO). Following I/R injury, the rats underwent EA therapy at the Shenting (DU24) and Baihui (DU20) acupoints for seven successive days. The Morris water maze test, magnetic resonance imaging (MRI) and molecular biology assays were utilized to assess the establishment of the rat stroke model with cognitive impairment and the therapeutic effect of EA. EA treatment of rats subjected to MCAO showed a significant reduction in infarct volumes accompanied by cognitive recovery, as observed in Morris water maze test outcomes. The possible mechanisms by which EA treatment attenuates cognitive impairment are by regulating endogenous melatonin secretion through aralkylamine N-acetyltransferase gene (AANAT, a rate-limiting enzyme of melatonin) synthesis in the pineal gland in stroke rats. Simultaneously, through melatonin regulation, EA exerts neuroprotective effects by upregulating mitophagy-associated proteins and suppressing reactive oxygen species (ROS)-induced NLRP3 inflammasome activation after I/R injury. However, melatonin receptor inhibitor (luzindole) treatment reversed these changes. The findings from this research suggested that EA ameliorates cognitive impairment through the inhibition of NLRP3 inflammasome activation by regulating melatonin-mediated mitophagy in stroke rats.

[Electroacupuncture ameliorates ischemic injury in cerebral ischemia-reperfusion rats by regulating endogenous melatonin and inhibiting the activation of astrocytes].

OBJECTIVE: To observe the effect of electroacupuncture(EA)at "Baihui"(GV20) and "Shenting" (GV24) on the expression of melatonin synthesis rate-limiting enzyme-arylalkylamine N-acetyltransferase(AANAT)in pineal gland of rats with focal cerebral ischemia-reperfusion injury, so as to explore the mechanism of EA underlying improving ischemia-reperfusion injury. METHODS: Forty-eight SD rats were randomly divided into sham operation, model, EA and non-acupoint groups, with 12 rats in each group. The focal cerebral ischemia-reperfusion injury rat model was established by occlusion of the middle cerebral artery. Rats of the EA group received EA at GV20 and GV24, while those in the non-acupoint group received EA at non-acupoints below the costal margins on both sides for 20 min, once daily for 7 days. The neurological deficit score (0 to 4 points) was given after successful modeling according to Longa's method. Morris water maze test was used to assess the cognitive function of rat. ELISA was used to detect the plasma melatonin content, and PCR and Western blot were used to detect the mRNA and protein expressions of AANAT in the pineal gland, separately. Immunofluorescence staining was used to detect the activation of astrocytes and neuronal injury in the hippocampus. RESULTS: After focal cerebral ischemia-reperfusion injury and compared with the sham operation group, the neurological deficit score, the escape latency, and the expression of GFAP were significantly increased (P<0.01)，while the times of platform quadrant crossing, the secretion of melatonin at 24:00，AANAT mRNA and protein expression levels and NeuN protein expression were significantly down-regulated (P<0.01). After EA at GV20 and GV24, the above-mentioned indexes all reversed in the EA group relative to the model group, and there were significant differences between the two groups(P<0.01). Compared with the model group, the changes of the abovementioned indexes in the non-acupoint group were not statistically significant (P>0.05). CONCLUSION: EA at GV20 and GV24 can alleviate neurological deficit and improve cognitive function in cerebral ischemia-reperfusion rats，which may be related to its effects in up-regulating endogenous melatonin levels, inhibiting the activation of astrocytes and protecting damaged neurons in the hippocampus.

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.

Deep co-supervision and attention fusion strategy for automatic COVID-19 lung infection segmentation on CT images.

Due to the irregular shapes,various sizes and indistinguishable boundaries between the normal and infected tissues, it is still a challenging task to accurately segment the infected lesions of COVID-19 on CT images. In this paper, a novel segmentation scheme is proposed for the infections of COVID-19 by enhancing supervised information and fusing multi-scale feature maps of different levels based on the encoder-decoder architecture. To this end, a deep collaborative supervision (Co-supervision) scheme is proposed to guide the network learning the features of edges and semantics. More specifically, an Edge Supervised Module (ESM) is firstly designed to highlight low-level boundary features by incorporating the edge supervised information into the initial stage of down-sampling. Meanwhile, an Auxiliary Semantic Supervised Module (ASSM) is proposed to strengthen high-level semantic information by integrating mask supervised information into the later stage. Then an Attention Fusion Module (AFM) is developed to fuse multiple scale feature maps of different levels by using an attention mechanism to reduce the semantic gaps between high-level and low-level feature maps. Finally, the effectiveness of the proposed scheme is demonstrated on four various COVID-19 CT datasets. The results show that the proposed three modules are all promising. Based on the baseline (ResUnet), using ESM, ASSM, or AFM alone can respectively increase Dice metric by 1.12%, 1.95%,1.63% in our dataset, while the integration by incorporating three models together can rise 3.97%. Compared with the existing approaches in various datasets, the proposed method can obtain better segmentation performance in some main metrics, and can achieve the best generalization and comprehensive performance.

AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging:: Towards Radiophenomics.

Artificial intelligence (AI) techniques have significant potential to enable effective, robust, and automated image phenotyping including the identification of subtle patterns. AI-based detection searches the image space to find the regions of interest based on patterns and features. There is a spectrum of tumor histologies from benign to malignant that can be identified by AI-based classification approaches using image features. The extraction of minable information from images gives way to the field of "radiomics" and can be explored via explicit (handcrafted/engineered) and deep radiomics frameworks. Radiomics analysis has the potential to be used as a noninvasive technique for the accurate characterization of tumors to improve diagnosis and treatment monitoring. This work reviews AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks. We also discuss needed efforts to enable the translation of AI techniques to routine clinical workflows, and potential improvements and complementary techniques such as the use of natural language processing on electronic health records and neuro-symbolic AI techniques.