Automatic anatomical localization is critical for radiology report generation. While many studies focus on lesion detection and segmentation, anatomical localization-accurately describing lesion positions in radiology reports-has received less attention. Conventional segmentation-based methods are limited to organ-level localization and often fail in severe disease cases due to low segmentation accuracy. To address these limitations, we reformulate anatomical localization as an image-to-text retrieval task. Specifically, we propose a CLIP-based framework that aligns lesion image patches with anatomically descriptive text embeddings in a shared multimodal space. By projecting lesion features into the semantic space and retrieving the most relevant anatomical descriptions in a coarse-to-fine manner, our method achieves fine-grained lesion localization with high accuracy across the entire body. Our main contributions are as follows: (1) hierarchical anatomical retrieval, which organizes 387 locations into a two-level hierarchy, by retrieving from the first level of 124 coarse categories to narrow down the search space and reduce localization complexity; (2) augmented location descriptions, which integrate domain-specific anatomical knowledge for enhancing semantic representation and improving visual-text alignment; and (3) semi-hard negative sample mining, which improves training stability and discriminative learning by avoiding selecting the overly similar negative samples that may introduce label noise or semantic ambiguity. We validate our method on two whole-body PET/CT datasets, achieving an 84.13% localization accuracy on the internal test set and 80.42% on the external test set, with a per-lesion inference time of 34 ms. The proposed framework also demonstrated superior robustness in complex clinical cases compared to segmentation-based approaches.

Aneurysm segmentation in computed tomography angiography (CTA) images is essential for medical intervention aimed at preventing subarachnoid hemorrhages. However, most existing studies tend to overlook the topological characteristics of arteries related to aneurysms, often resulting in suboptimal performance in aneurysm segmentation. To address this challenge, we propose an artery-aware global-to-local framework for aneurysm segmentation (AASeg) using CTA images of head and neck. This framework consists of two key components: 1) a centerline graph network (CG-Net) for aneurysm global localization, and 2) a point cloud network (PC-Net) for local aneurysm segmentation. The centerline graph is generated by extracting artery centerline structures from vessel masks obtained through a pre-trained model for head and neck vessel segmentation. This representation serves as a high-level representation of the artery structure, allowing for analysis of aneurysms along the entire arteries. It facilitates aneurysm localization via aneurysm-segment graph classification along the arteries. Then, local region of aneurysm segment can be sampled from the vessel mask according to the aneurysm-segment graph. Subsequently, aneurysm segmentation is performed on the point cloud constructed from the aneurysm segment through the PC-Net. Extensive experiments show that the proposed framework achieves state-of-the-art performance in aneurysm localization on a main dataset and an external testing dataset, with Recall of 84.1% and 80.7%, false positives per case of 1.72 and 1.69, and segmentation DSC of 66.1% and 60.2%, respectively.

Anatomical labeling of head and neck vessels is a vital step for cerebrovascular disease diagnosis. However, it remains challenging to automatically and accurately label vessels in computed tomography angiography (CTA) since head and neck vessels are tortuous, branched, and often spatially close to nearby vasculature. To address these challenges, we propose a novel topology-aware graph network (TaG-Net) for vessel labeling. It combines the advantages of volumetric image segmentation in the voxel space and centerline labeling in the line space, wherein the voxel space provides detailed local appearance information, and line space offers high-level anatomical and topological information of vessels through the vascular graph constructed from centerlines. First, we extract centerlines from the initial vessel segmentation and construct a vascular graph from them. Then, we conduct vascular graph labeling using TaG-Net, in which techniques of topology-preserving sampling, topology-aware feature grouping, and multi-scale vascular graph are designed. After that, the labeled vascular graph is utilized to improve volumetric segmentation via vessel completion. Finally, the head and neck vessels of 18 segments are labeled by assigning centerline labels to the refined segmentation. We have conducted experiments on CTA images of 401 subjects, and experimental results show superior vessel segmentation and labeling of our method compared to other state-of-the-art methods.

Knee osteoarthritis (OA) is the most common osteoarthritis and a leading cause of disability. Cartilage defects are regarded as major manifestations of knee OA, which are visible by magnetic resonance imaging (MRI). Thus early detection and assessment for knee cartilage defects are important for protecting patients from knee OA. In this way, many attempts have been made on knee cartilage defect assessment by applying convolutional neural networks (CNNs) to knee MRI. However, the physiologic characteristics of the cartilage may hinder such efforts: the cartilage is a thin curved layer, implying that only a small portion of voxels in knee MRI can contribute to the cartilage defect assessment; heterogeneous scanning protocols further challenge the feasibility of the CNNs in clinical practice; the CNN-based knee cartilage evaluation results lack interpretability. To address these challenges, we model the cartilages structure and appearance from knee MRI into a graph representation, which is capable of handling highly diverse clinical data. Then, guided by the cartilage graph representation, we design a non-Euclidean deep learning network with the self-attention mechanism, to extract cartilage features in the local and global, and to derive the final assessment with a visualized result. Our comprehensive experiments show that the proposed method yields superior performance in knee cartilage defect assessment, plus its convenient 3D visualization for interpretability.

Skeletal bone age assessment is a common clinical practice to investigate endocrinology, and genetic and growth disorders of children. However, clinical interpretation and bone age analyses are time-consuming, labor intensive, and often subject to inter-observer variability. This advocates the need of a fully automated method for bone age assessment. We propose a regression convolutional neural network (CNN) to automatically assess the pediatric bone age from hand radiograph. Our network is specifically trained to place more attention to those bone age related regions in the X-ray images. Specifically, we first adopt the attention module to process all images and generate the coarse/fine attention maps as inputs for the regression network. Then, the regression CNN follows the supervision of the dynamic attention loss during training; thus, it can estimate the bone age of the hard (or "outlier") images more accurately. The experimental results show that our method achieves an average discrepancy of 5.2-5.3 months between clinical and automatic bone age evaluations on two large datasets. In conclusion, we propose a fully automated deep learning solution to process X-ray images of the hand for bone age assessment, with the accuracy comparable to human experts but with much better efficiency.

Accurate measurement of left ventricular volumes and Ejection Fraction from cine MRI is of paramount importance to the evaluation of cardiovascular functions, yet it usually requires laborious and tedious work of trained experts to interpret them. To facilitate this procedure, numerous computer aided diagnosis (CAD) methods and tools have been proposed, most of which focus on the left or right ventricle segmentation. However, the identification of ES and ED frames from cardiac sequences is largely ignored, which is a key procedure in the automated workflow. This seemingly easy task is quite challenging, due to the requirement of high accuracy ( i.e. , precisely identifying specific frames from a sequence) and subtle differences among consecutive frames. Recently, with the rapid growth of annotated data and the increasing computational power, deep learning methods have been widely exploited in medical image analysis. In this paper, we propose a novel deep learning architecture, named as temporal regression network (TempReg-Net), to accurately identify specific frames from MRI sequences, by integrating the Convolutional Neural Network (CNN) with the Recurrent Neural Network (RNN). Specifically, a CNN encodes the spatial information of a cardiac sequence, and a RNN decodes the temporal information. In addition, we design a new loss function in our network to constrain the structure of predicted labels, which further improves the performance. Our approach is extensively validated on thousands of cardiac sequences and the average difference is merely 0.4 frames, comparing favorably with previous systems. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Lumbar spondylolisthesis is one of the most common spinal diseases. It is caused by the anterior shift of a lumbar vertebrae relative to subjacent vertebrae. In current clinical practices, staging of spondylolisthesis is often conducted in a qualitative way. Although meyerding grading opens the door to stage spondylolisthesis in a more quantitative way, it relies on the manual measurement, which is time consuming and irreproducible. Thus, an automatic measurement algorithm becomes desirable for spondylolisthesis diagnosis and staging. However, there are two challenges. 1) Accurate detection of the most anterior and posterior points on the superior and inferior surfaces of each lumbar vertebrae. Due to the small size of the vertebrae, slight errors of detection may lead to significant measurement errors, hence, wrong disease stages. 2) Automatic localize and label each lumbar vertebrae is required to provide the semantic meaning of the measurement. It is difficult since different lumbar vertebraes have high similarity of both shape and image appearance. To resolve these challenges, a new auto measurement framework is proposed with two major contributions: First, a learning based spine labeling method that integrates both the image appearance and spine geometry information is designed to detect lumbar vertebrae. Second, a hierarchical method using both the population information from atlases and domain-specific information in the target image is proposed for most anterior and posterior points positioning. Validated on 258 CT spondylolisthesis patients, our method shows very similar results to manual measurements by radiologists and significantly increases the measurement efficiency.

In general image recognition problems, discriminative information often lies in local image patches. For example, most human identity information exists in the image patches containing human faces. The same situation stays in medical images as well. "Bodypart identity" of a transversal slice-which bodypart the slice comes from-is often indicated by local image information, e.g., a cardiac slice and an aorta arch slice are only differentiated by the mediastinum region. In this work, we design a multi-stage deep learning framework for image classification and apply it on bodypart recognition. Specifically, the proposed framework aims at: 1) discover the local regions that are discriminative and non-informative to the image classification problem, and 2) learn a image-level classifier based on these local regions. We achieve these two tasks by the two stages of learning scheme, respectively. In the pre-train stage, a convolutional neural network (CNN) is learned in a multi-instance learning fashion to extract the most discriminative and and non-informative local patches from the training slices. In the boosting stage, the pre-learned CNN is further boosted by these local patches for image classification. The CNN learned by exploiting the discriminative local appearances becomes more accurate than those learned from global image context. The key hallmark of our method is that it automatically discovers the discriminative and non-informative local patches through multi-instance deep learning. Thus, no manual annotation is required. Our method is validated on a synthetic dataset and a large scale CT dataset. It achieves better performances than state-of-the-art approaches, including the standard deep CNN.

Image-guided radiotherapy (IGRT) requires fast and accurate localization of the prostate in 3-D treatment-guided radiotherapy, which is challenging due to low tissue contrast and large anatomical variation across patients. On the other hand, the IGRT workflow involves collecting a series of computed tomography (CT) images from the same patient under treatment. These images contain valuable patient-specific information yet are often neglected by previous works. In this paper, we propose a novel learning framework, namely incremental learning with selective memory (ILSM), to effectively learn the patient-specific appearance characteristics from these patient-specific images. Specifically, starting with a population-based discriminative appearance model, ILSM aims to "personalize" the model to fit patient-specific appearance characteristics. The model is personalized with two steps: backward pruning that discards obsolete population-based knowledge and forward learning that incorporates patient-specific characteristics. By effectively combining the patient-specific characteristics with the general population statistics, the incrementally learned appearance model can localize the prostate of a specific patient much more accurately. This work has three contributions: 1) the proposed incremental learning framework can capture patient-specific characteristics more effectively, compared to traditional learning schemes, such as pure patient-specific learning, population-based learning, and mixture learning with patient-specific and population data; 2) this learning framework does not have any parametric model assumption, hence, allowing the adoption of any discriminative classifier; and 3) using ILSM, we can localize the prostate in treatment CTs accurately (DSC ∼ 0.89 ) and fast ( ∼ 4 s), which satisfies the real-world clinical requirements of IGRT.

Image appearance cues are often used to derive object shapes, which is usually one of the key steps of image understanding tasks. However, when image appearance cues are weak or misleading, shape priors become critical to infer and refine the shape derived by these appearance cues. Effective modeling of shape priors is challenging because: 1) shape variation is complex and cannot always be modeled by a parametric probability distribution; 2) a shape instance derived from image appearance cues (input shape) may have gross errors; and 3) local details of the input shape are difficult to preserve if they are not statistically significant in the training data. In this paper we propose a novel Sparse Shape Composition model (SSC) to deal with these three challenges in a unified framework. In our method, training shapes are adaptively composed to infer/refine an input shape. The a-priori information is thus implicitly incorporated on-the-fly. Our model leverages two sparsity observations of the input shape instance: 1) the input shape can be approximately represented by a sparse linear combination of training shapes; 2) parts of the input shape may contain gross errors but such errors are usually sparse. Using L1 norm relaxation, our model is formulated as a convex optimization problem, which is solved by an efficient alternating minimization framework. Our method is extensively validated on two real world medical applications, 2D lung localization in X-ray images and 3D liver segmentation in low-dose CT scans. Compared to state-of-the-art methods, our model exhibits better performance in both studies.

Diagnostic magnetic resonance (MR) image quality is highly dependent on the position and orientation of the slice groups, due to the intrinsic high in-slice and low through-slice resolutions of MR imaging. Hence, the higher speed, accuracy, and reproducibility of automatic slice positioning, make it highly desirable over manual slice positioning. However, imaging artifacts, diseases, joint articulation, variations across ages and demographics as well as the extremely high performance requirements prevent state-of-the-art methods, such as volumetric registration, to be an off-the-shelf solution. In this paper, we address all these issues through an automatic slice positioning framework based on redundant and hierarchical learning. Our method has two hallmarks that are specifically designed to achieve high robustness and accuracy. 1) A redundant set of anatomy detectors are learned to provide local appearance cues. These detections are pruned and assembled according to a distributed anatomy model, which captures group-wise spatial configurations among anatomy primitives. This strategy brings about a high level of robustness and works even if a large portion of the target is distorted, missing, or occluded. 2) The detectors are learned and invoked in a hierarchical fashion, with each local detection scheduled and iterated according to its intrinsic invariance property. This iterative alignment process is shown to dramatically improve alignment accuracy. The proposed system is extensively validated on a large dataset including 744 clinical MR scans. Compared to state-of-the-art methods, our method exhibits superior performance in terms of robustness, accuracy, and reproducibility. The methodology is general and can be applied to other anatomies and other imaging modalities.

In this paper, a method for maximizing the probability of prostate cancer detection via biopsy is presented, by combining image analysis and optimization techniques. This method consists of three major steps. First, a statistical atlas of the spatial distribution of prostate cancer is constructed from histological images obtained from radical prostatectomy specimen. Second, a probabilistic optimization framework is employed to optimize the biopsy strategy, so that the probability of cancer detection is maximized under needle placement uncertainties. Finally, the optimized biopsy strategy generated in the atlas space is mapped to a specific patient space using an automated segmentation and elastic registration method. Cross-validation experiments showed that the predictive power of the optimized biopsy strategy for cancer detection reached the 94%-96% levels for 6-7 biopsy cores, which is significantly better than standard random-systematic biopsy protocols, thereby encouraging further investigation of optimized biopsy strategies in prospective clinical studies.

This paper presents a novel deformable model for automatic segmentation of prostates from three-dimensional ultrasound images, by statistical matching of both shape and texture. A set of Gabor-support vector machines (G-SVMs) are positioned on different patches of the model surface, and trained to adaptively capture texture priors of ultrasound images for differentiation of prostate and nonprostate tissues in different zones around prostate boundary. Each G-SVM consists of a Gabor filter bank for extraction of rotation-invariant texture features and a kernel support vector machine for robust differentiation of textures. In the deformable segmentation procedure, these pretrained G-SVMs are used to tentatively label voxels around the surface of deformable model as prostate or nonprostate tissues by a statistical texture matching. Subsequently, the surface of deformable model is driven to the boundary between the tentatively labeled prostate and non-prostate tissues. Since the step of tissue labeling and the step of label-based surface deformation are dependent on each other, these two steps are repeated until they converge. Experimental results by using both synthesized and real data show the good performance of the proposed model in segmenting prostates from ultrasound images.

This paper presents a statistical shape model for the automatic prostate segmentation in transrectal ultrasound images. A Gabor filter bank is first used to characterize the prostate boundaries in ultrasound images in both multiple scales and multiple orientations. The Gabor features are further reconstructed to be invariant to the rotation of the ultrasound probe and incorporated in the prostate model as image attributes for guiding the deformable segmentation. A hierarchical deformation strategy is then employed, in which the model adaptively focuses on the similarity of different Gabor features at different deformation stages using a multiresolution technique, i.e., coarse features first and fine features later. A number of successful experiments validate the algorithm.