Assessing the quality of automatic image segmentation is crucial in clinical practice, but often very challenging due to the limited availability of ground truth annotations. Reverse Classification Accuracy (RCA) is an approach that estimates the quality of new predictions on unseen samples by training a segmenter on those predictions, and then evaluating it against existing annotated images. In this work we introduce ConfIC-RCA (Conformal In-Context RCA), a novel method for automatically estimating segmentation quality with statistical guarantees in the absence of ground-truth annotations, which consists of two main innovations. First, In-Context RCA, which leverages recent in-context learning models for image segmentation and incorporates retrieval-augmentation techniques to select the most relevant reference images. This approach enables efficient quality estimation with minimal reference data while avoiding the need of training additional models. Second, we introduce Conformal RCA, which extends both the original RCA framework and In-Context RCA to go beyond point estimation. Using tools from split conformal prediction, Conformal RCA produces prediction intervals for segmentation quality providing statistical guarantees that the true score lies within the estimated interval with a user-specified probability. Validated across 10 different medical imaging tasks in various organs and modalities, our methods demonstrate robust performance and computational efficiency, offering a promising solution for automated quality control in clinical workflows, where fast and reliable segmentation assessment is essential. The code is available at https://github.com/mcosarinsky/Conformal-In-Context-RCA.

Mental health is a significant global public health issue, and psychological support hotlines play a crucial role in providing mental health assistance and identifying suicide risks at an early stage. However, the emotional expressions conveyed during these calls remain underexplored in current research. This study introduces a novel method that combines pitch acoustic features with deep learning-based features to analyze and understand emotions expressed during hotline interactions. Using data from China's largest psychological support hotline, which includes 105 subjects, our method achieved an F1-score of 79.13% for negative binary emotion classification. Additionally, the proposed approach was validated on an open dataset for multi-class emotion classification, where it demonstrated better performance compared to the state-of-the-art methods. To explore its clinical relevance, we applied the model to analysis the frequency of negative emotions and the rate of emotional change in the conversation, comparing 46 subjects with suicidal behavior to those without. While the suicidal group exhibited more frequent emotional changes than the non-suicidal group, the difference was not statistically significant. Importantly, our findings suggest that emotional fluctuation intensity and frequency could serve as novel features for psychological assessment scales and suicide risk prediction. The proposed method provides valuable insights into emotional dynamics and has the potential to advance early intervention and improve suicide prevention strategies through integration with clinical tools and assessments. The source code is publicly available at: https://github.com/Sco-field/Speechemotionrecognition/tree/main.

Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Medical image analysis frequently encounters data scarcity challenges. Transfer learning has been effective in addressing this issue while conserving computational resources. The recent advent of foundational models like the DINOv2, which uses the vision transformer architecture, has opened new opportunities in the field and gathered significant interest. However, DINOv2's performance on clinical data still needs to be verified. In this paper, we performed a glioma grading task using three clinical modalities of brain MRI data. We compared the performance of various pre-trained deep learning models, including those based on ImageNet and DINOv2, in a transfer learning context. Our focus was on understanding the impact of the freezing mechanism on performance. We also validated our findings on three other types of public datasets: chest radiography, fundus radiography, and dermoscopy. Our findings indicate that in our clinical dataset, DINOv2's performance was not as strong as ImageNet-based pre-trained models, whereas in public datasets, DINOv2 generally outperformed other models, especially when using the frozen mechanism. Similar performance was observed with various sizes of DINOv2 models across different tasks. In summary, DINOv2 is viable for medical image classification tasks, particularly with data resembling natural images. However, its effectiveness may vary with data that significantly differs from natural images such as MRI. In addition, employing smaller versions of the model can be adequate for medical task, offering resource-saving benefits. Our codes are available at https://github.com/GuanghuiFU/medical_dino_eval.

Suicide and suicidal behaviors remain significant challenges for public policy and healthcare. In response, psy-chological support hotlines have been established worldwide to provide immediate help to individuals in mental crises. The effectiveness of these hotlines largely depends on accurately identifying callers' emotional states, particularly underlying negative emotions indicative of increased suicide risk. However, the high demand for psychological interventions often results in a shortage of professional operators, highlighting the need for an effective speech emotion recognition model. This model would automatically detect and analyze callers' emotions, facil-itating integration into hotline services. Additionally, it would enable large-scale data analysis of psychological support hotline interactions to explore psychological phenomena and behaviors across populations. Our study utilizes data from the Beijing psychological support hotline, the largest suicide hotline in China. We analyzed speech data from 105 callers containing 20,630 segments and categorized them into 11 types of negative emotions. We developed a negative emotion recognition model and a fine-grained multi-label classification model using a large-scale pretrained model. Our experiments indicate that the negative emotion recognition model achieves a maximum F1-score of 76.96%. However, it shows limited efficacy in the fine-grained multi-label classification task, with the best model achieving only a 41.74% weighted F1-score. We conducted an error analysis for this task, discussed potential future improvements, and considered the clinical application possibilities of our study. All the codes are public available at: https://github.com/cz10914/psy_hotline_analysis.

In the social media, users frequently express personal emotions, a subset of which may indicate potential suicidal tendencies. The implicit and varied forms of expression in internet language complicate accurate and rapid identification of suicidal intent on social media, thus creating challenges for timely intervention efforts. The development of deep learning models for suicide risk detection is a promising solution, but there is a notable lack of relevant datasets, especially in the Chinese context. To address this gap, this study presents a Chinese social media dataset designed for fine-grained suicide risk classification, focusing on indicators such as expressions of suicide intent, methods of suicide, and urgency of timing. Seven pre-trained models were evaluated in two tasks: high and low suicide risk, and fine-grained suicide risk classification on a level of 0 to 10. In our experiments, deep learning models show good performance in distinguishing between high and low suicide risk, with the best model achieving an F1 score of 88.39%. However, the results for fine-grained suicide risk classification were still unsatisfactory, with the best weighted F1 score of 50.89%. To address the issues of data imbalance and limited dataset size, we investigated both traditional and advanced, large language model based data augmentation techniques, demonstrating that data augmentation can enhance this model performance by up to 4.65% points in F1-score. Notably, the Chinese MentalBERT model, which was pre-trained on psychological domain data, shows superior performance in both tasks. This study provides valuable insights for automatic identification of suicidal individuals, facilitating timely psychological intervention on social media platforms. The source code and data are publicly available at: https://github.com/HongzhiQ/FineGrainedSuicideDetection.

Acute intracerebral hemorrhage is a life-threatening condition that demands immediate medical intervention. Intraparenchymal hemorrhage (IPH) and intraventricular hemorrhage (IVH) are critical subtypes of this condition. Clinically, when such hemorrhages are suspected, immediate CT scanning is essential to assess the extent of the bleeding and to facilitate the formulation of a targeted treatment plan. While current research in deep learning has largely focused on qualitative analyses, such as identifying subtypes of cerebral hemorrhages, there remains a significant gap in quantitative analysis crucial for enhancing clinical treatments. Addressing this gap, our paper introduces a dataset comprising 222 CT annotations, sourced from the RSNA 2019 Brain CT Hemorrhage Challenge and meticulously annotated at the voxel level for precise IPH and IVH segmentation. This dataset was utilized to train and evaluate seven advanced medical image segmentation algorithms, with the goal of refining the accuracy of segmentation for these hemorrhages. Our findings demonstrate that this dataset not only furthers the development of sophisticated segmentation algorithms but also substantially aids scientific research and clinical practice by improving the diagnosis and management of these severe hemorrhages. Our dataset and codes are available at https://github.com/songchangwei/3DCT-SD-IVH-ICH.

BACKGROUND: Screening of the brain computerised tomography (CT) images is a primary method currently used for initial detection of patients with brain trauma or other conditions. In recent years, deep learning technique has shown remarkable advantages in the clinical practice. Researchers have attempted to use deep learning methods to detect brain diseases from CT images. Methods often used to detect diseases choose images with visible lesions from full-slice brain CT scans, which need to be labelled by doctors. This is an inaccurate method because doctors detect brain disease from a full sequence scan of CT images and one patient may have multiple concurrent conditions in practice. The method cannot take into account the dependencies between the slices and the causal relationships among various brain diseases. Moreover, labelling images slice by slice spends much time and expense. Detecting multiple diseases from full slice brain CT images is, therefore, an important research subject with practical implications. RESULTS: In this paper, we propose a model called the slice dependencies learning model (SDLM). It learns image features from a series of variable length brain CT images and slice dependencies between different slices in a set of images to predict abnormalities. The model is necessary to only label the disease reflected in the full-slice brain scan. We use the CQ500 dataset to evaluate our proposed model, which contains 1194 full sets of CT scans from a total of 491 subjects. Each set of data from one subject contains scans with one to eight different slice thicknesses and various diseases that are captured in a range of 30 to 396 slices in a set. The evaluation results present that the precision is 67.57%, the recall is 61.04%, the F1 score is 0.6412, and the areas under the receiver operating characteristic curves (AUCs) is 0.8934. CONCLUSION: The proposed model is a new architecture that uses a full-slice brain CT scan for multi-label classification, unlike the traditional methods which only classify the brain images at the slice level. It has great potential for application to multi-label detection problems, especially with regard to the brain CT images.