Deep neural networks (DNNs) offer significant promise for improving breast cancer diagnosis in medical imaging. However, these models are highly susceptible to adversarial attacks—small, imperceptible changes that can mislead classifiers—raising critical concerns about their reliability and security. Traditional attacks rely on fixed-norm perturbations, misaligning with human perception. In contrast, diffusion-based attacks require pre-trained models, demanding substantial data when these models are unavailable, limiting practical use in data-scarce scenarios. In medical imaging, however, this is often unfeasible due to the limited availability of datasets. Building on recent advancements in learnable prompts, we propose Prompt2Perturb (P2P), a novel language-guided attack method capable of generating meaningful attack examples driven by text instructions. During the prompt learning phase, our approach leverages learnable prompts within the text encoder to create subtle, yet impactful, perturbations that remain imperceptible while guiding the model towards targeted outcomes. In contrast to current prompt learning-based approaches, our P2P stands out by directly updating text embeddings, avoiding the need for retraining diffusion models. Further, we leverage the finding that optimizing only the early diffusion steps boosts efficiency while ensuring that the generated adversarial examples incorporate subtle noise, thus preserving ultrasound image quality without introducing noticeable artifacts. We show that our method outperforms state-of-the-art attack techniques across three breast ultrasound datasets in FID and LPIPS. Moreover, the generated images are both more natural in appearance and more effective compared to existing adversarial attacks. Our Code is publicly available on GitHub.

Implicit neural representations (INRs) use neural networks to provide continuous and resolution-independent representations of complex signals with a small number of parameters. However, existing INR models often fail to capture important frequency components specific to each task. To address this issue, in this paper, we propose a Fourier Kolmogorov-Arnold network (FKAN) for INRs. The proposed FKAN utilizes learnable activation functions modeled as Fourier series in the first layer to effectively control and learn the task-specific frequency components. The activation functions with learnable Fourier coefficients improve the ability of the network to capture complex patterns and details, which is beneficial for high-resolution and high-dimensional data. Experimental results show that our proposed FKAN model outperforms four state-of-the-art baseline schemes, and improves the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) for the image representation task and intersection over union (loU) for the 3D occupancy volume representation task, respectively. The code is available at github.com/Ali-Meh619/FKAN.

Collective insights from a group of experts have always proven to outperform an individual's best diagnostic for clinical tasks. For the task of medical image segmentation, existing research on AI-based alternatives focuses more on developing models that can imitate the best individual rather than harnessing the power of expert groups. In this paper, we introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent stochastic sampling process of diffusion using only minimal additional learning. We demonstrate on three different medical image modalities- CT, ultrasound, and MRI that our model is capable of producing several possible variants while capturing the frequencies of their occurrences. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks in terms of accuracy while preserving naturally occurring variation. We also propose a new metric to evaluate the diversity as well as the accuracy of segmentation predictions that aligns with the interest of clinical practice of collective insights. Implementation code: https://github.com/aimansnigdha/Ambiguous-Medical-Image-Segmentation-using-Diffusion-Models.

Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of these "traditional" encoder-decoder based approaches, we observed that they perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. This issue can be attributed to the increase in receptive field size as we go deeper into the encoder. The extra focus on learning high level features causes U-Net based approaches to learn less information about low-level features which are crucial for detecting small structures. To overcome this issue, we propose using an overcomplete convolutional architecture where we project the input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network. We design a new architecture for im- age segmentation- KiU-Net which has two branches: (1) an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U-Net which learns high level features. Furthermore, we also propose KiU-Net 3D which is a 3D convolutional architecture for volumetric segmentation. We perform a detailed study of KiU-Net by performing experiments on five different datasets covering various image modalities. We achieve a good performance with an additional benefit of fewer parameters and faster convergence. We also demonstrate that the extensions of KiU-Net based on residual blocks and dense blocks result in further performance improvements. Code: https://github.com/jeya-maria-jose/KiU-Net-pytorch.

Automatic segmentation of bone surfaces from ultrasound images is of great interest in the ultrasound-guided computer assisted orthopedic surgery field. These automatic segmentations help the system locate where the bone surface is in the image which can allow for proper surgical manipulation. Most recently, methods based on deep learning have achieved promising results. However, a drawback is that these methods require a large number of training dataset. Therefore, the main objective of this work is the investigation of how large-scale simulated ultrasound data can be used to improve the accuracy of deep learning-based segmentation methods. A transfer learning network and a mixed network approach were used to evaluate how well the large-scale simulated data worked to segment ultrasound bone surfaces. The Sorensen-Dice Coefficient and Average Euclidean Distance values were calculated to determine that by using simulated bone ultrasound data, the success of traditional deep learning methods increases compared to using small-scale real ultrasound data only. Initial results show improvements in segmentation performance can be obtained by combining simulated ultrasound data with in vivo ultrasound scans.

Most conventional spine interventions are performed under X-ray fluoroscopy guidance. In recent years, there has been a growing interest to develop nonionizing imaging alternatives to guide these procedures. Ultrasound guidance has emerged as a leading alternative. However, a challenging problem is automatic identification of the spinal anatomy in ultrasound data. In this paper, we propose a local phase-based bone feature enhancement technique that can robustly identify the spine surface in ultrasound images. The local phase information is obtained using a gradient energy tensor filter. This information is used to construct local phase tensors in ultrasound images, which highlight the spine surface. We show that our proposed approach results in a more distinct enhancement of the bone surfaces compared to recently proposed techniques based on monogenic scale-space filters and logarithmic Gabor filters. We also demonstrate that registration accuracy of a statistical shape+pose model of the spine to 3-D ultrasound images can be significantly improved, using the proposed method, compared to those obtained using monogenic scale-space filters and logarithmic Gabor filters.