25 October 2023 in IEEE Transactions on Medical Imaging
Representational transfer from publicly available models is a promising technique for improving medical image classification, especially in long-tailed datasets with rare diseases. However, existing methods often overlook the frequency-dependent behavior of these models, thereby limiting their effectiveness in transferring representations and generalizations to rare diseases. In this paper, we propose FoPro-KD, a novel framework that leverages the power of frequency patterns learned from frozen pre-trained models to enhance their transferability and compression, presenting a few unique insights: 1) We demonstrate that leveraging representations from publicly available pre-trained models can substantially improve performance, specifically for rare classes, even when utilizing representations from a smaller pre-trained model. 2) We observe that pre-trained models exhibit frequency preferences, which we explore using our proposed Fourier Prompt Generator (FPG), allowing us to manipulate specific frequencies in the input image, enhancing the discriminative representational transfer. 3) By amplifying or diminishing these frequencies in the input image, we enable Effective Knowledge Distillation (EKD). EKD facilitates the transfer of knowledge from pre-trained models to smaller models. Through extensive experiments in long-tailed gastrointestinal image recognition and skin lesion classification, where rare diseases are prevalent, our FoPro-KD framework outperforms existing methods, enabling more accessible medical models for rare disease classification.
14 June 2025 in Scientific Data
FSFung Hou Kumoi Mineaki Howard Sum
Fung Hou Kumoi Mineaki Howard Sum
+3
Fenestration and dehiscence (FD) pose significant challenges in dental treatments as they adversely affect oral health. Although cone-beam computed tomography (CBCT) provides precise diagnostics, its extensive time requirements and radiation exposure limit its routine use for monitoring. Currently, there is no public dataset that combines intraoral photographs and corresponding CBCT images; this limits the development of deep learning algorithms for the automated detection of FD and other potential diseases. In this paper, we present FDTooth, a dataset that includes both intraoral photographs and CBCT images of 241 patients aged between 9 and 55 years. FDTooth contains 1,800 precise bounding boxes annotated on intraoral photographs, with gold-standard ground truth extracted from CBCT. We developed a baseline model for automated FD detection in intraoral photographs. The developed dataset and model can serve as valuable resources for research on interdisciplinary dental diagnostics, offering clinicians a non-invasive, efficient method for early FD screening without invasive procedures.
14 March 2026 in Medical Image Analysis
7 March 2026 in Medical Image Analysis
21 September 2025 in arXiv
Cardiovascular diseases (CVDs) remain the leading cause of mortality globally, and echocardiography is critical for diagnosis of both common and congenital cardiac conditions. However, echocardiographic data for certain pathologies are scarce, hindering the development of robust automated diagnosis models. In this work, we propose Echo-Path, a novel generative framework to produce echocardiogram videos conditioned on specific cardiac pathologies. Echo-Path can synthesize realistic ultrasound video sequences that exhibit targeted abnormalities, focusing here on atrial septal defect (ASD) and pulmonary arterial hypertension (PAH). Our approach introduces a pathology-conditioning mechanism into a state-of-the-art echo video generator, allowing the model to learn and control disease-specific structural and motion patterns in the heart. Quantitative evaluation demonstrates that the synthetic videos achieve low distribution distances, indicating high visual fidelity. Clinically, the generated echoes exhibit plausible pathology markers. Furthermore, classifiers trained on our synthetic data generalize well to real data and, when used to augment real training sets, it improves downstream diagnosis of ASD and PAH by 7\% and 8\% respectively. Code, weights and dataset are available here https://github.com/Marshall-mk/EchoPathv1