Accurate standard plane acquisition in fetal ultrasound (US) videos is crucial for fetal growth assessment, anomaly detection, and adherence to clinical guidelines. However, manually selecting standard frames is time-consuming and prone to intra- and inter-sonographer variability. Existing methods primarily rely on image-based approaches that capture standard frames and then classify the input frames across different anatomies. This ignores the dynamic nature of video acquisition and its interpretation. To address these challenges, we introduce Multi-Tier Class-Aware Token Transformer (MCAT); a visual query-based video clip localization (VQ-VCL) method to assist sonographers by enabling them to capture a quick US sweep. By then providing a visual query of the anatomy they wish to analyze, MCAT returns the video clip containing the standard frames for that anatomy, facilitating thorough screening for potential anomalies. We evaluate MCAT on two ultrasound video datasets and a natural image VQ-VCL dataset based on Ego4D. Our model outperforms state-of-the-art methods by 10% and 13% mtIoU on the ultrasound datasets and by 5.35% mtIoU on the Ego4D dataset, using 96% fewer tokens. MCAT’s efficiency and accuracy have significant potential implications for public health, especially in low- and middle-income countries (LMICs), where it may enhance prenatal care by streamlining standard plane acquisition, simplifying US based screening, diagnosis and allowing sonographers to examine more patients.

Large Vision-Language Models (VLMs), possessing millions or billions of parameters, typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative is to fine-tune these foundation models on end-user devices, such as in medical clinics and hospitals, without sending data to a server. These local clients typically have limited computing power and small datasets, which are not enough for fully fine-tuning large VLMs on their own. A naive solution to these scenarios is to leverage parameter-efficient fine-tuning (PEFT) strategies such as adapters and apply federated learning (FL) algorithms to combine the learned adapter weights, thereby respecting the resource limitations and data privacy of the clients. However, this approach does not fully leverage the knowledge from multiple adapters trained on diverse data distributions and for diverse tasks. The adapters are adversely impacted by data heterogeneity and task heterogeneity across clients resulting in sub-optimal convergence. To this end, we propose a novel framework called FedPIA that improves upon the naive combinations of FL and PEFT by introducing Permutation and Integration of the local Adapters in the server and global Adapters in the clients exploiting Wasserstein barycenters for improved blending of client-specific and client-agnostic knowledge. This layerwise permutation helps to bridge the gap in the parameter space of local and global adapters before integration. We conduct over 2000 client-level experiments utilizing 48 medical image datasets across five different medical vision-language FL task settings encompassing visual question answering as well as image and report-based multi-label disease detection. Our experiments involving diverse client settings, ten different modalities, and two VLM backbones demonstrate that FedPIA consistently outperforms the state-of-the-art PEFT-FL baselines.

Federated Learning (FL) in healthcare ensures patient privacy by allowing hospitals to collaboratively train machine learning models while keeping sensitive medical data secure and localized. Most existing research in FL has concentrated on unimodal scenarios, where all healthcare institutes share the same type of data. However, in real-world healthcare situations, some clients may have access to multiple types of data pertaining to the same disease. Multimodal Federated Learning (MMFL) utilizes multiple modalities to build a more powerful FL model than its unimodal counterpart. However, the impact of missing modality in different clients, called modality incongruity, has been greatly overlooked. This paper, for the first time, analyses the impact of modality incongruity and reveals its connection with data heterogeneity across participating clients. We particularly inspect whether incongruent MMFL with unimodal and multimodal clients is more beneficial than unimodal FL. Furthermore, we examine three potential routes of addressing this issue. Firstly, we study the effectiveness of various self-attention mechanisms towards incongruity-agnostic information fusion in MMFL. Secondly, we introduce a modality imputation network (MIN) pre-trained in a multimodal client for modality translation in unimodal clients and investigate its potential towards mitigating the missing modality problem. Thirdly, we introduce several client-level and server-level regularization techniques including Modality-aware knowledge Distillation (MAD) and Leave-one-out teacher (LOOT) towards mitigating modality incongruity effects. Experiments are conducted with Chest X-Ray and radiology reports under several MMFL settings on two publicly available real-world datasets, MIMIC-CXR and Open-I.

Effective training of large Vision-Language Models (VLMs) on resource-constrained client devices in Federated Learning (FL) requires the usage of parameter-efficient finetuning (PEFT) strategies. To this end, we demonstrate the impact of two factors viz., client-specific layer importance score that selects the most important VLM layers for finetuning and inter-client layer diversity score that encourages diverse layer selection across clients for optimal VLM layer selection. We first theoretically motivate and leverage the principal eigenvalue magnitude of layerwise Neural Tangent Kernels and show its effectiveness as client-specific layer importance score. Next, we propose a novel layer updating strategy dubbed F3OCUS that jointly optimizes the layer importance and diversity factors by employing a data-free, multi-objective, meta-heuristic optimization on the server. We explore 5 different meta-heuristic algorithms and compare their effectiveness for selecting model layers and adapter layers towards PEFT-FL. Furthermore, we release a new MedVQA-FL dataset involving overall 707,962 VQA triplets and 9 modality-specific clients and utilize it to train and evaluate our method. Overall, we conduct more than 10,000 client-level experiments on 6 Vision-Language FL task settings involving 58 medical image datasets and 4 different VLM architectures of varying sizes to demonstrate the effectiveness of the proposed method. Project Page: https://pramitsaha.github.io/FOCUS/

Self-supervised learning (SSL) has achieved major advances in natural images and video understanding, but challenges remain in domains like echocardiography (heart ultrasound) due to subtle anatomical structures, complex temporal dynamics, and the current lack of domain-specific pre-trained models. Existing SSL approaches such as contrastive, masked modeling, and clustering-based methods struggle with high intersample similarity, sensitivity to low PSNR inputs common in ultrasound, or aggressive augmentations that distort clinically relevant features. We present DISCOVR (Distilled Image Supervision for Cross Modal Video Representation), a self-supervised dual-branch framework for cardiac ultrasound video representation learning. DISCOVR combines a clustering-based video encoder that models temporal dynamics with an online image encoder that extracts fine-grained spatial semantics. These branches are connected through a semantic cluster distillation loss that transfers anatomical knowledge from the evolving image encoder to the video encoder, enabling temporally coherent representations enriched with fine-grained semantic understanding. Evaluated on six echocardiography datasets spanning fetal, pediatric, and adult populations, DISCOVR outperforms both specialized video anomaly detection methods and state-of-the-art video-SSL baselines in zero-shot and linear probing setups, achieving superior segmentation transfer and strong downstream performance on clinically relevant tasks such as LVEF prediction. **Code available at:** [https://github.com/mdivyanshu97/DISCOVR](https://github.com/mdivyanshu97/DISCOVR)

Fetal echocardiography offers non-invasive and real-time imaging acquisition of fetal heart images to identify congenital heart conditions. Manual acquisition of standard heart views is time-consuming, whereas automated detection remains challenging due to high spatial similarity across anatomical views with subtle local image appearance variations. To address these challenges, we introduce a very lightweight frequency-guided deep learning-based model named HarmonicEchoNet that can automatically detect heart standard views in a transverse sweep or freehand ultrasound scan of the fetal heart. HarmonicEchoNet uses harmonic convolution blocks (HCBs) and a harmonic spatial and channel squeeze-and-excitation (hscSE) module. The HCBs apply a Discrete Cosine Transform (DCT)-based harmonic decomposition to input features, which are then combined using learned weights. The hscSE module identifies significant regions in the spatial domain to improve feature extraction of the fetal heart anatomical structures, capturing both spatial and channel-wise dependencies in an ultrasound image. The combination of these modules improves model performance relative to recent CNN-based, transformer-based, and CNN+transformer-based image classification models. We use four datasets from two private studies, PULSE (Perception Ultrasound by Learning Sonographic Experience) and CAIFE (Clinical Artificial Intelligence in Fetal Echocardiography), to develop and evaluate HarmonicEchoNet models. Experimental results show that HarmonicEchoNet is 10-15 times faster than ConvNeXt, DeiT, and VOLO, with an inference time of just 3.9 ms. It also achieves 2%-7% accuracy improvement in classifying fetal heart standard planes compared to these baselines. Furthermore, with just 19.9 million parameters compared to ConvNeXt's 196.24 million, HarmonicEchoNet is nearly ten times more parameter-efficient.