With the growing number of images generated daily in radiological practices and the digitization of historical studies, we face large databases where metadata can be incomplete or incorrect. Content-based image retrieval (CBIR) can help to manage these datasets by efficiently locating and retrieving relevant information by only using image data as a query. Recent studies have shown the potential use of pre-trained vision embeddings for CBIR in the context of radiology image retrieval for specific tasks like single organ retrieval or distinguishing between normal and abnormal tissues. However, a comprehensive benchmark for the retrieval of 3D volumetric medical images is still lacking. In this study, we establish a benchmark for multi-class volumetric retrieval for different retrieval modes. The retrieval modes are defined based on end-point use-cases which include Full-Scan Retrieval, Targeted-Region Retrieval, and Precise-Localization Retrieval. We utilize the TotalSegmentator dataset, comprising 104 detailed anatomical structures, to evaluate the performance of embeddings derived from pre-trained models across the proposed retrieval modes. We show the potential of CBIR for organ retrieval by achieving a retrieval recall of 1.0 for diverse anatomical regions with a wide size range. The methodology presented in this paper utilizes publicly available image data and embedding models without requiring any task-specific fine-tuning. This benchmark aims to enable further development and allow for a more consistent evaluation of CBIR approaches in the context of 3D medical imaging.

Audio-based classification techniques for body sounds have long been studied to aid in the diagnosis of respiratory diseases. While most research is centered on the use of coughs as the main acoustic biomarker, other body sounds also have the potential to detect respiratory diseases. Recent studies on the coronavirus disease 2019 (COVID-19) have suggested that breath and speech sounds, in addition to cough, correlate with the disease. Our study proposes fused audio instance and representation (FAIR) as a method for respiratory disease detection. FAIR relies on constructing a joint feature vector from various body sounds represented in waveform and spectrogram form. We conduct experiments on the use case of COVID-19 detection by combining waveform and spectrogram representation of body sounds. Our findings show that the use of self-attention to combine extracted features from cough, breath, and speech sounds leads to the best performance with an area under the receiver operating characteristic curve (AUC) score of 0.8658, a sensitivity of 0.8057, and a specificity of 0.7958. Compared to models trained solely on spectrograms or waveforms, the use of both representations results in an improved AUC score, demonstrating that combining spectrogram and waveform representation helps to enrich the extracted features and outperforms the models that use only one representation. While this study focuses on COVID-19, FAIR’s flexibility allows it to combine various multi-modal and multi-instance features in many other diagnostic applications, potentially leading to more accurate diagnoses across a wider range of diseases.

De-identification of medical images is a critical step to ensure privacy during data sharing in research and clinical settings. The initial step in this process involves detecting Protected Health Information (PHI), which can be found in image metadata or imprinted within image pixels. Despite the importance of such systems, there has been limited evaluation of existing AI-based solutions, creating barriers to the development of reliable and robust tools. In this study, we present an AI-based pipeline for PHI detection, comprising three key modules: text detection, text extraction, and text analysis. We benchmark three models—YOLOv11, EasyOCR, and GPT-4o— across different setups corresponding to these modules, evaluating their performance on two different datasets encompassing multiple imaging modalities and PHI categories. Our findings indicate that the optimal setup involves utilizing dedicated vision and language models for each module, which achieves a commendable balance in performance, latency, and cost associated with the usage of large language models (LLMs). Additionally, we show that the application of LLMs not only involves identifying PHI content but also enhances OCR tasks and facilitates an end-to-end PHI detection pipeline, showcasing promising outcomes through our analysis.

Transfer learning has become a standard practice to mitigate the lack of labeled data in medical classification tasks. Whereas finetuning a downstream task using supervised ImageNet pretrained features is straightforward and extensively investigated in many works, there is little study on the usefulness of self-supervised pretraining. In this paper, we assess the transferability of ImageNet self-supervisedpretraining by evaluating the performance of models initialized with pretrained features from three self-supervised techniques (SimCLR, SwAV, and DINO) on selected medical classification tasks. The chosen tasks cover tumor detection in sentinel axillary lymph node images, diabetic retinopathy classification in fundus images, and multiple pathological condition classification in chest X-ray images. We demonstrate that self-supervised pretrained models yield richer embeddings than their supervised counterpart, which benefits downstream tasks in view of both linear evaluation and finetuning. For example, in view of linear evaluation at acritically small subset of the data, we see an improvement up to 14.79% in Kappa score in the diabetic retinopathy classification task, 5.4% in AUC in the tumor classification task, 7.03% AUC in the pneumonia detection, and 9.4% in AUC in the detection of pathological conditions in chest X-ray. In addition, we introduce Dynamic Visual Meta-Embedding (DVME) as an end-to-end transfer learning approach that fuses pretrained embeddings from multiple models. We show that the collective representation obtained by DVME leads to a significant improvement in the performance of selected tasks compared to using a single pretrained model approach and can be generalized to any combination of pretrained models.

A wide range of imaging techniques and data formats available for medical images make accurate retrieval from image databases challenging. Efficient retrieval systems are crucial in advancing medical research, enabling large-scale studies and innovative diagnostic tools. Thus, addressing the challenges of medical image retrieval is essential for the continued enhancement of healthcare and research. In this study, we evaluated the feasibility of employing four state-of-the-art pretrained models for medical image retrieval at modality, body region, and organ levels and compared the results of two similarity indexing approaches. Since the employed networks take 2D images, we analyzed the impacts of weighting and sampling strategies to incorporate 3D information during retrieval of 3D volumes. We showed that medical image retrieval is feasible using pretrained networks without any additional training or fine-tuning steps. Using pretrained embeddings, we achieved a recall of 1 for various tasks at modality, body region, and organ level.