Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos

Breast lesion segmentation in ultrasound (US) videos is essential for diagnosing and treating axillary lymph node metastasis. However, the lack of a well-established and large-scale ultrasound video dataset with high-quality annotations has posed a persistent challenge for the research community. To overcome this issue, we meticulously curated a US video breast lesion segmentation dataset comprising 572 videos and 34,300 annotated frames, covering a wide range of realistic clinical scenarios. Furthermore, we propose a novel frequency and localization feature aggregation network (FLA-Net) that learns temporal features from the frequency domain and predicts additional lesion location positions to assist with breast lesion segmentation. We also devise a localization-based contrastive loss to reduce the lesion location distance between neighboring video frames within the same video and enlarge the location distances between frames from different ultrasound videos. Our experiments on our annotated dataset and two public video polyp segmentation datasets demonstrate that our proposed FLA-Net achieves state-of-the-art performance in breast lesion segmentation in US videos and video polyp segmentation while significantly reducing time and space complexity. Our model and dataset are available at https://github.com/jhl-Det/FLA-Net.

Layer-wise Representation Fusion for Compositional Generalization

Despite successes across a broad range of applications, sequence-to-sequence models' construct of solutions are argued to be less compositional than human-like generalization. There is mounting evidence that one of the reasons hindering compositional generalization is representations of the encoder and decoder uppermost layer are entangled. In other words, the syntactic and semantic representations of sequences are twisted inappropriately. However, most previous studies mainly concentrate on enhancing token-level semantic information to alleviate the representations entanglement problem, rather than composing and using the syntactic and semantic representations of sequences appropriately as humans do. In addition, we explain why the entanglement problem exists from the perspective of recent studies about training deeper Transformer, mainly owing to the ``shallow'' residual connections and its simple, one-step operations, which fails to fuse previous layers' information effectively. Starting from this finding and inspired by humans' strategies, we propose \textsc{FuSion} (\textbf{Fu}sing \textbf{S}yntactic and Semant\textbf{i}c Representati\textbf{on}s), an extension to sequence-to-sequence models to learn to fuse previous layers' information back into the encoding and decoding process appropriately through introducing a \emph{fuse-attention module} at each encoder and decoder layer. \textsc{FuSion} achieves competitive and even \textbf{state-of-the-art} results on two realistic benchmarks, which empirically demonstrates the effectiveness of our proposal.