Towards more precise automatic analysis: a systematic review of deep learning-based multi-organ segmentation.

Accurate segmentation of multiple organs in the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation methods have far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. We searched Google Scholar for papers published from January 1, 2016 to December 31, 2023, using keywords "multi-organ segmentation" and "deep learning", resulting in 327 papers. We followed the PRISMA guidelines for paper selection, and 195 studies were deemed to be within the scope of this review. We summarized the two main aspects involved in multi-organ segmentation: datasets and methods. Regarding datasets, we provided an overview of existing public datasets and conducted an in-depth analysis. Concerning methods, we categorized existing approaches into three major classes: fully supervised, weakly supervised and semi-supervised, based on whether they require complete label information. We summarized the achievements of these methods in terms of segmentation accuracy. In the discussion and conclusion section, we outlined and summarized the current trends in multi-organ segmentation.

A comprehensive survey on deep active learning in medical image analysis.

Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets. Yet, the high cost of annotating medical images severely hampers the development of deep learning in this field. To reduce annotation costs, active learning aims to select the most informative samples for annotation and train high-performance models with as few labeled samples as possible. In this survey, we review the core methods of active learning, including the evaluation of informativeness and sampling strategy. For the first time, we provide a detailed summary of the integration of active learning with other label-efficient techniques, such as semi-supervised, self-supervised learning, and so on. We also summarize active learning works that are specifically tailored to medical image analysis. Additionally, we conduct a thorough comparative analysis of the performance of different AL methods in medical image analysis with experiments. In the end, we offer our perspectives on the future trends and challenges of active learning and its applications in medical image analysis. An accompanying paper list and code for the comparative analysis is available in https://github.com/LightersWang/Awesome-Active-Learning-for-Medical-Image-Analysis.

Preoperative Molecular Subtype Classification Prediction of Ovarian Cancer Based on Multi-Parametric Magnetic Resonance Imaging Multi-Sequence Feature Fusion Network.

In the study of the deep learning classification of medical images, deep learning models are applied to analyze images, aiming to achieve the goals of assisting diagnosis and preoperative assessment. Currently, most research classifies and predicts normal and cancer cells by inputting single-parameter images into trained models. However, for ovarian cancer (OC), identifying its different subtypes is crucial for predicting disease prognosis. In particular, the need to distinguish high-grade serous carcinoma from clear cell carcinoma preoperatively through non-invasive means has not been fully addressed. This study proposes a deep learning (DL) method based on the fusion of multi-parametric magnetic resonance imaging (mpMRI) data, aimed at improving the accuracy of preoperative ovarian cancer subtype classification. By constructing a new deep learning network architecture that integrates various sequence features, this architecture achieves the high-precision prediction of the typing of high-grade serous carcinoma and clear cell carcinoma, achieving an AUC of 91.62% and an AP of 95.13% in the classification of ovarian cancer subtypes.

Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation.

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning including unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemmas in multi-organ segmentation. We first review the fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends.

Structural diversity in the membrane-bound hIAPP dimer correlated with distinct membrane disruption mechanisms.

Amyloid deposits of the human islet amyloid polypeptide (hIAPP) have been identified in 90% of patients with type II diabetes. Cellular membranes accelerate the hIAPP fibrillation, and the integrity of membranes is also disrupted at the same time, leading to the apoptosis of ß cells in pancreas. The molecular mechanism of hIAPP-induced membrane disruption, especially during the initial membrane disruption stage, has not been well understood yet. Herein, we carried out extensive all-atom molecular dynamics simulations investigating the hIAPP dimerization process in the anionic POPG membrane, to provide the detailed molecular mechanisms during the initial hIAPP aggregation stage in the membrane environment. Compared to the hIAPP monomer on the membrane, we observed not only an increase of α-helical structures, but also a substantial increase of ß-sheet structures upon spontaneous dimerization. Moreover, the random coiled and α-helical dimer structures insert deep into the membrane interior with a few inter-chain contacts at the C-terminal region, while the ß-sheet-rich structures reside on the membrane surface accompanied by strong inter-chain hydrophobic interactions. The coexistence of α and ß structures constitutes a diverse structural ensemble of the membrane-bound hIAPP dimer. From α-helical to ß-sheet structures, the degree of membrane disruption decreases gradually, and thus the membrane damage induced by random coiled and α-helical structures precedes that induced by ß-sheet structures. We speculate that insertion of random coiled and α-helical structures contributes to the initial stage of membrane damage, while ß-sheet structures on the membrane surface are more involved in the later stage of fibril-induced membrane disruption.

Genomic characterization and immunotherapy for microsatellite instability-high in cholangiocarcinoma.

BACKGROUND: Microsatellite instability-high (MSI-H) is a unique genomic status in many cancers. However, its role in the genomic features and immunotherapy in cholangiocarcinoma (CCA) is unclear. This study aimed to systematically investigate the genomic characterization and immunotherapy efficacy of MSI-H patients with CCA. METHODS: We enrolled 887 patients with CCA in this study. Tumor samples were collected for next-generation sequencing. Differences in genomic alterations between the MSI-H and microsatellite stability (MSS) groups were analyzed. We also investigated the survival of PD-1 inhibitor-based immunotherapy between two groups of 139 patients with advanced CCA. RESULTS: Differential genetic alterations between the MSI-H and MSS groups included mutations in ARID1A, ACVR2A, TGFBR2, KMT2D, RNF43, and PBRM1 which were enriched in MSI-H groups. Patients with an MSI-H status have a significantly higher tumor mutation burden (TMB) (median 41.7 vs. 3.1 muts/Mb, P < 0.001) and more positive programmed death ligand 1 (PD-L1) expression (37.5% vs. 11.9%, P < 0.001) than those with an MSS status. Among patients receiving PD-1 inhibitor-based therapy, those with MSI-H had a longer median overall survival (OS, hazard ratio (HR) = 0.17, P = 0.001) and progression-free survival (PFS, HR = 0.14, P < 0.001) than patients with MSS. Integrating MSI-H and PD-L1 expression status (combined positive score ≥ 5) could distinguish the efficacy of immunotherapy. CONCLUSIONS: MSI-H status was associated with a higher TMB value and more positive PD-L1 expression in CCA tumors. Moreover, in patients with advanced CCA who received PD-1 inhibitor-based immunotherapy, MSI-H and positive PD-L1 expression were associated with improved both OS and PFS. TRIAL REGISTRATION: This study was registered on ClinicalTrials.gov on 07/01/2017 (NCT03892577).

Negative Instance Guided Self-Distillation Framework for Whole Slide Image Analysis.

Histopathology image classification is an important clinical task, and current deep learning-based whole-slide image (WSI) classification methods typically cut WSIs into small patches and cast the problem as multi-instance learning. The mainstream approach is to train a bag-level classifier, but their performance on both slide classification and positive patch localization is limited because the instance-level information is not fully explored. In this article, we propose a negative instance-guided, self-distillation framework to directly train an instance-level classifier end-to-end. Instead of depending only on the self-supervised training of the teacher and the student classifiers in a typical self-distillation framework, we input the true negative instances into the student classifier to guide the classifier to better distinguish positive and negative instances. In addition, we propose a prediction bank to constrain the distribution of pseudo instance labels generated by the teacher classifier to prevent the self-distillation from falling into the degeneration of classifying all instances as negative. We conduct extensive experiments and analysis on three publicly available pathological datasets: CAMELYON16, PANDA, and TCGA, as well as an in-house pathological dataset for cervical cancer lymph node metastasis prediction. The results show that our method outperforms existing methods by a large margin. Code will be publicly available.

MmisAT and MmisP: an efficient and accurate suite of variant analysis toolkit for primary mitochondrial diseases.

Recent advances in next-generation sequencing (NGS) technology have greatly accelerated the need for efficient annotation to accurately interpret clinically relevant genetic variants in human diseases. Therefore, it is crucial to develop appropriate analytical tools to improve the interpretation of disease variants. Given the unique genetic characteristics of mitochondria, including haplogroup, heteroplasmy, and maternal inheritance, we developed a suite of variant analysis toolkits specifically designed for primary mitochondrial diseases: the Mitochondrial Missense Variant Annotation Tool (MmisAT) and the Mitochondrial Missense Variant Pathogenicity Predictor (MmisP). MmisAT can handle protein-coding variants from both nuclear DNA and mtDNA and generate 349 annotation types across six categories. It processes 4.78 million variant data in 76 min, making it a valuable resource for clinical and research applications. Additionally, MmisP provides pathogenicity scores to predict the pathogenicity of genetic variations in mitochondrial disease. It has been validated using cross-validation and external datasets and demonstrated higher overall discriminant accuracy with a receiver operating characteristic (ROC) curve area under the curve (AUC) of 0.94, outperforming existing pathogenicity predictors. In conclusion, the MmisAT is an efficient tool that greatly facilitates the process of variant annotation, expanding the scope of variant annotation information. Furthermore, the development of MmisP provides valuable insights into the creation of disease-specific, phenotype-specific, and even gene-specific predictors of pathogenicity, further advancing our understanding of specific fields.

A Structure-Aware Framework of Unsupervised Cross-Modality Domain Adaptation via Frequency and Spatial Knowledge Distillation.

Unsupervised domain adaptation (UDA) aims to train a model on a labeled source domain and adapt it to an unlabeled target domain. In medical image segmentation field, most existing UDA methods rely on adversarial learning to address the domain gap between different image modalities. However, this process is complicated and inefficient. In this paper, we propose a simple yet effective UDA method based on both frequency and spatial domain transfer under a multi-teacher distillation framework. In the frequency domain, we introduce non-subsampled contourlet transform for identifying domain-invariant and domain-variant frequency components (DIFs and DVFs) and replace the DVFs of the source domain images with those of the target domain images while keeping the DIFs unchanged to narrow the domain gap. In the spatial domain, we propose a batch momentum update-based histogram matching strategy to minimize the domain-variant image style bias. Additionally, we further propose a dual contrastive learning module at both image and pixel levels to learn structure-related information. Our proposed method outperforms state-of-the-art methods on two cross-modality medical image segmentation datasets (cardiac and abdominal). Codes are avaliable at https://github.com/slliuEric/FSUDA.

Improving brain tumor segmentation with anatomical prior-informed pre-training.

Introduction: Precise delineation of glioblastoma in multi-parameter magnetic resonance images is pivotal for neurosurgery and subsequent treatment monitoring. Transformer models have shown promise in brain tumor segmentation, but their efficacy heavily depends on a substantial amount of annotated data. To address the scarcity of annotated data and improve model robustness, self-supervised learning methods using masked autoencoders have been devised. Nevertheless, these methods have not incorporated the anatomical priors of brain structures. Methods: This study proposed an anatomical prior-informed masking strategy to enhance the pre-training of masked autoencoders, which combines data-driven reconstruction with anatomical knowledge. We investigate the likelihood of tumor presence in various brain structures, and this information is then utilized to guide the masking procedure. Results: Compared with random masking, our method enables the pre-training to concentrate on regions that are more pertinent to downstream segmentation. Experiments conducted on the BraTS21 dataset demonstrate that our proposed method surpasses the performance of state-of-the-art self-supervised learning techniques. It enhances brain tumor segmentation in terms of both accuracy and data efficiency. Discussion: Tailored mechanisms designed to extract valuable information from extensive data could enhance computational efficiency and performance, resulting in increased precision. It's still promising to integrate anatomical priors and vision approaches.

Molecular epidemiology and phylogenetic analyses of human adenovirus in pediatric patients with acute respiratory infections from Hangzhou during COVID-19 pandemic.

Background: Acute Respiratory Infections (ARIs) are a major cause of morbidity and mortality worldwide. Human Adenovirus (HAdV), responsible for 5%-10% of children's ARIs, is one of the most prevalent pathogens. Our study aimed to analyze the epidemiology and phylogenesis of HAdV in pediatric patients with ARIs in Hangzhou during the COVID-19 pandemic. Method: Between November 2020 and March 2021, we collected 1,442 nasopharyngeal swabs from children with ARIs at Children's Hospital, Zhejiang University School of Medicine. Epidemiological statistics, phylogenetic and amino acid (AA) mutation analysis were conducted. Results: Our findings revealed that 386 (26.77%) samples tested positive for HAdV, with the highest rate in children aged 6-18 years and the lowest in children aged 0-1 year, indicating a different age preference of HAdV compared with pre-pandemic period. Outpatients had a significantly higher positive rate than inpatients. Moreover, patients with HAdV-coinfection exhibited more severe clinical symptoms than those with HAdV-single infection. Our phylogenetic analysis demonstrated that species HAdV-C (type 1, 2, 6) were the predominant circulating strains in Hangzhou during the COVID-19 pandemic. Further AA mutation analysis identified seventeen mutations of particular concern for biological characterization. Conclusion: In conclusion, our study provides valuable epidemiological and molecular data that will aid in epidemiological surveillance, antiviral therapies and the development of specific vaccine types, leading to improve public health.

A touch-free human-robot collaborative surgical navigation robotic system based on hand gesture recognition.

Robot-assisted minimally invasive surgery (RAMIS) has gained significant traction in clinical practice in recent years. However, most surgical robots rely on touch-based human-robot interaction (HRI), which increases the risk of bacterial diffusion. This risk is particularly concerning when surgeons must operate various equipment with their bare hands, necessitating repeated sterilization. Thus, achieving touch-free and precise manipulation with a surgical robot is challenging. To address this challenge, we propose a novel HRI interface based on gesture recognition, leveraging hand-keypoint regression and hand-shape reconstruction methods. By encoding the 21 keypoints from the recognized hand gesture, the robot can successfully perform the corresponding action according to predefined rules, which enables the robot to perform fine-tuning of surgical instruments without the need for physical contact with the surgeon. We evaluated the surgical applicability of the proposed system through both phantom and cadaver studies. In the phantom experiment, the average needle tip location error was 0.51 mm, and the mean angle error was 0.34 degrees. In the simulated nasopharyngeal carcinoma biopsy experiment, the needle insertion error was 0.16 mm, and the angle error was 0.10 degrees. These results indicate that the proposed system achieves clinically acceptable accuracy and can assist surgeons in performing contactless surgery with hand gesture interaction.

Label correlation transformer for automated chest X-ray diagnosis with reliable interpretability.

Computer-aided diagnosis of chest X-ray (CXR) images can help reduce the huge workload of radiologists and avoid the inter-observer variability in large-scale early disease screening. Recently, most state-of-the-art studies employ deep learning techniques to address this problem through multi-label classification. However, existing methods still suffer from low classification accuracy and poor interpretability for each diagnostic task. This study aims to propose a novel transformer-based deep learning model for automated CXR diagnosis with high performance and reliable interpretability. We introduce a novel transformer architecture into this problem and utilize the unique query structure of transformer to capture the global and local information of the images and the correlation between labels. In addition, we propose a new loss function to help the model find correlations between the labels in CXR images. To achieve accurate and reliable interpretability, we generate heatmaps using the proposed transformer model and compare with the true pathogenic regions labeled by the physicians. The proposed model achieves a mean AUC of 0.831 on chest X-ray 14 and 0.875 on PadChest dataset, which outperforms existing state-of-the-art methods. The attention heatmaps show that our model could focus on the exact corresponding areas of related truly labeled pathogenic regions. The proposed model effectively improves the performance of CXR multi-label classification and the interpretability of label correlations, thus providing new evidence and methods for automated clinical diagnosis.

Multi-task learning-based histologic subtype classification of non-small cell lung cancer.

PURPOSE: In clinical applications, accurate histologic subtype classification of lung cancer is important for determining appropriate treatment plans. The purpose of this paper is to evaluate the role of multi-task learning in the classification of adenocarcinoma and squamous cell carcinoma. MATERIAL AND METHODS: In this paper, we propose a novel multi-task learning model for histologic subtype classification of non-small cell lung cancer based on computed tomography (CT) images. The model consists of a histologic subtype classification branch and a staging branch, which share a part of the feature extraction layers and are simultaneously trained. By optimizing on the two tasks simultaneously, our model could achieve high accuracy in histologic subtype classification of non-small cell lung cancer without relying on physician's precise labeling of tumor areas. In this study, 402 cases from The Cancer Imaging Archive (TCIA) were used in total, and they were split into training set (n = 258), internal test set (n = 66) and external test set (n = 78). RESULTS: Compared with the radiomics method and single-task networks, our multi-task model could reach an AUC of 0.843 and 0.732 on internal and external test set, respectively. In addition, multi-task network can achieve higher accuracy and specificity than single-task network. CONCLUSION: Compared with the radiomics methods and single-task networks, our multi-task learning model could improve the accuracy of histologic subtype classification of non-small cell lung cancer by sharing network layers, which no longer relies on the physician's precise labeling of lesion regions and could further reduce the manual workload of physicians.

Distinct binding interactions trigger opposite conformational modulations on pathogenic and wildtype Huntingtin exon 1 proteins.

Abnormal elongation of the polyglutamine tract transforms exon 1 of the Huntingtin protein (Htt-exon-1) from wildtype to pathogenic form, and causes Huntington's disease. As an intrinsically disordered protein, the structural ensemble of Htt-exon-1 is highly heterogeneous and the detailed conformation of toxic species is still under debate. Ispinesib, a potential small-molecule drug, has been identified to selectively link the pathogenic Htt-exon-1 into the autophagosome to degrade, thus opening an innovative therapeutic direction. However, the molecular mechanisms behind this selectivity remain largely elusive. Herein, we carry out extensive molecular dynamics simulations with an enhanced sampling method to investigate the ispinesib inducing conformational changes of pathogenic and wildtype Htt-exon-1 and the corresponding binding mechanisms. Our simulations reveal that the ispinesib binding induces opposite conformational changes in pathogenic and wildtype Htt-exon-1, i.e., the 'entropy collapse' with significant reduction of ß-sheets versus the 'entropy expansion' with a slight increase of α-helices. Network analyses further reveal that there are two stable binding sites in the pathogenic Htt-exon-1, while the binding on the wildtype Htt-exon-1 is highly dynamic and non-specific. These dramatic differences originate from the underlying distinct binding interactions. More specifically, stronger hydrogen bonds serve as the specific binding anchors in pathogenic Htt-exon-1, while stronger hydrophobic interactions dominate in the dynamic binding with wildtype Htt-exon-1. Our simulations provide an atomistic mechanism for the ispinesib selective binding on the pathogenic Htt-exon-1, and further shed light on the general mechanisms of small molecule modulation on intrinsically disordered proteins.

Towards label-efficient automatic diagnosis and analysis: a comprehensive survey of advanced deep learning-based weakly-supervised, semi-supervised and self-supervised techniques in histopathological image analysis.

Histopathological images contain abundant phenotypic information and pathological patterns, which are the gold standards for disease diagnosis and essential for the prediction of patient prognosis and treatment outcome. In recent years, computer-automated analysis techniques for histopathological images have been urgently required in clinical practice, and deep learning methods represented by convolutional neural networks have gradually become the mainstream in the field of digital pathology. However, obtaining large numbers of fine-grained annotated data in this field is a very expensive and difficult task, which hinders the further development of traditional supervised algorithms based on large numbers of annotated data. More recent studies have started to liberate from the traditional supervised paradigm, and the most representative ones are the studies on weakly supervised learning paradigm based on weak annotation, semi-supervised learning paradigm based on limited annotation, and self-supervised learning paradigm based on pathological image representation learning. These new methods have led a new wave of automatic pathological image diagnosis and analysis targeted at annotation efficiency. With a survey of over 130 papers, we present a comprehensive and systematic review of the latest studies on weakly supervised learning, semi-supervised learning, and self-supervised learning in the field of computational pathology from both technical and methodological perspectives. Finally, we present the key challenges and future trends for these techniques.

Alternative splicing patterns reveal prognostic indicator in muscle-invasive bladder cancer.

BACKGROUND: Bladder cancer is one of the most lethal malignancy in urological system, and 20-25% of bladder cancer patients are muscle invasive with unfavorable prognosis. However, the role of alternative splicing (AS) in muscle-invasive bladder cancer (MIBC) remains to be elucidated. METHODS: Percent spliced in (PSI) data obtained from the Cancer Genome Atlas (TCGA) SpliceSeq database (n = 394) were utilized to evaluate the AS events in MIBC. Prognosis-associated AS events were screened out by univariate Cox regression. LASSO Cox regression was used to identify reliable prognostic patterns in a training set and further validated in a test set. Splicing regulatory networks were constructed by correlations between PSI of AS events and RNA expression of splicing factors. RESULTS: As a result, a total of 2589 prognosis-related AS events in MIBC were identified. Pathways of spliceosomal complex (FDR = 0.017), DNA-directed RNA polymerase II, core complex (FDR = 0.032), and base excision repair (FDR = 0.038) were observed to be significantly enriched. Additionally, we noticed that most of the prognosis-related AS events were favorable factors. According to the LASSO and multivariate Cox regression analyses, 15-AS-based signature was established with the area under curve (AUC) of 0.709, 0.823, and 0.857 at 1-, 3-, and 5- years, respectively. The MIBC patients were further divided into high- and low-risk groups based on median risk sores. Interestingly, we observed that the prevalence of FGFR3 with mutations and focal amplification was significantly higher in low-risk group. Functional and immune infiltration analysis suggested potential signaling pathways and distinct immune states between these two groups. Moreover, splicing correlation network displayed a regulatory mode of prognostic splicing factors (SF) in MIBC patients. CONCLUSIONS: This study not only provided novel insights into deciphering the possible mechanism of tumorgenesis and pathogenesis but also help refine risk stratification systems and potential treatment of decision-making for MIBC.

Vertebrae Labeling via End-to-End Integral Regression Localization and Multi-Label Classification Network.

Accurate identification and localization of the vertebrae in CT scans is a critical and standard pre-processing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural networks, and most of them use heatmaps to locate the vertebrae's centroid. However, the process of obtaining vertebrae's centroid coordinates using heatmaps is non-differentiable, so it is impossible to train the network to label the vertebrae directly. Therefore, for end-to-end differential training of vertebrae coordinates on CT scans, a robust and accurate automatic vertebral labeling algorithm is proposed in this study. First, a novel end-to-end integral regression localization and multi-label classification network is developed, which can capture multi-scale features and also utilize the residual module and skip connection to fuse the multi-level features. Second, to solve the problem that the process of finding coordinates is non-differentiable and the spatial structure of location being destroyed, an integral regression module is used in the localization network. It combines the advantages of heatmaps representation and direct regression coordinates to achieve end-to-end training and can be compatible with any key point detection methods of medical images based on heatmaps. Finally, multi-label classification of vertebrae is carried out to improve the identification rate, which uses bidirectional long short-term memory (Bi-LSTM) online to enhance the learning of long contextual information of vertebrae. The proposed method is evaluated on a challenging data set, and the results are significantly better than state-of-the-art methods (identification rate is 91.1% and the mean localization error is 2.2 mm). The method is evaluated on a new CT data set, and the results show that our method has good generalization.

Dynamic boundary-insensitive loss for magnetic resonance medical image segmentation.

PURPOSE: A deep learning method has achieved great success in MR medical image segmentation. One challenge in applying deep learning segmentation models to clinical practice is their poor generalization mainly due to limited labeled training samples, inter-site heterogeneity of different datasets, and ambiguous boundary definition, etc. The objective of this work is to develop a dynamic boundary-insensitive (DBI) loss to address this poor generalization caused by an uncertain boundary. METHODS: The DBI loss is designed to assign higher penalties to misclassified voxels farther from the boundaries in each training iteration to reduce the sensitivity of the segmentation model to the uncertain boundary. The weighting factor of the DBI loss can be adjusted adaptively without any manual setting and adjustment. Extensive experiments were conducted to verify the performance of our DBI loss and its variant, DiceDBI, on four heterogeneous prostate MRI datasets for prostate zonal segmentation and whole prostate segmentation. RESULTS: Experimental results show that our DBI loss, when combined with Dice loss, outperforms all competing loss functions in dice similarity coefficient (DSC) and improves the segmentation performance across all datasets consistently, especially on unseen datasets and when segmenting small or narrow targets. CONCLUSIONS: The proposed DiceDBI loss will be valuable for enhancement of the generalization performance of the segmentation model.