Journal of Medical Imaging最新文献

Purpose: Centralized machine learning often struggles with limited data access and expert involvement. We investigate decentralized approaches that preserve data privacy while enabling collaborative model training for medical imaging tasks.

Approach: We explore asynchronous federated learning (FL) using the FL with buffered asynchronous aggregation (FedBuff) algorithm for classifying optical coherence tomography (OCT) retina images. Unlike synchronous algorithms such as FedAvg, which require all clients to participate simultaneously, FedBuff supports independent client updates. We compare its performance to both centralized models and FedAvg. In addition, we develop a browser-based proof-of-concept system using modern web technologies to assess the feasibility and limitations of interactive, collaborative learning in real-world settings.

Results: FedBuff performs well in binary OCT classification tasks but shows reduced accuracy in more complex, multiclass scenarios. FedAvg achieves results comparable to centralized training, consistent with previous findings. Although FedBuff underperforms compared with FedAvg and centralized models, it still delivers acceptable accuracy in less complex settings. The browser-based prototype demonstrates the potential for accessible, user-driven FL systems but also highlights technical limitations in current web standards, especially regarding local computation and communication efficiency.

Conclusion: Asynchronous FL via FedBuff offers a promising, privacy-preserving approach for medical image classification, particularly when synchronous participation is impractical. However, its scalability to complex classification tasks remains limited. Web-based implementations have the potential to broaden access to collaborative AI tools, but limitations of the current technologies need to be further investigated.

Purpose: Accurate cancer subtyping is essential for precision medicine but challenged by the computational demands of gigapixel whole-slide images (WSIs). Although transformer-based multiple instance learning (MIL) methods achieve strong performance, their quadratic complexity limits clinical deployment. We introduce LiteMIL, a computationally efficient cross-attention MIL, optimized for WSIs classification.

Approach: LiteMIL employs a single learnable query with multi-head cross-attention for bag-level aggregation from extracted features. We evaluated LiteMIL against five baselines (mean/max pooling, ABMIL, MAD-MIL, and TransMIL) on four TCGA datasets (breast: $n=875$ , kidney: $n=906$ , lung: $n=958$ , and TUPAC16: $n=821$ ) using nested cross-validation with patient-level splitting. Systematic ablation studies evaluated multi-query variants, attention heads, dropout rates, and architectural components.

Results: LiteMIL achieved competitive accuracy (average 83.5%), matching TransMIL, while offering substantial efficiency gains: $4.8\times$ fewer parameters (560K versus 2.67M), $2.9\times$ faster inference (1.6s versus 4.6s per fold), and $6.7\times$ lower Graphics Processing Unit (GPU) memory usage (1.15 GB versus 7.77 GB). LiteMIL excelled on lung (86.3% versus 85.0%), TUPAC16 (72% versus 71.4%), and matched kidney performance (89.9% versus 89.7%). Ablation studies revealed task-dependent multi-query performance benefits: $Q=4$ versus $Q=1$ improved morphologically heterogeneous tasks (breast/lung $+1.3\%$ each, $p<0.05$ ) but degraded on grading tasks (TUPAC16: $-1.6\%$ ), validating single-query optimality for focused attention scenarios.

Conclusions: LiteMIL provides a resource-efficient solution for WSI classification. The cross-attention architecture matches complex transformer performance while enabling deployment on consumer GPUs. Task-dependent design insights, single query for sparse discriminating features, multi-query for heterogeneous patterns, guide practical implementation. The architecture's efficiency, combined with compact features, makes LiteMIL suitable for clinical integration in settings with limited computational infrastructure.

Purpose: There are multiple commercially available, Food and Drug Administration (FDA)-cleared, artificial intelligence (AI)-based tools automating stroke evaluation in noncontrast computed tomography (NCCT). This study assessed the impact of variations in reconstruction kernel and slice thickness on two outputs of such a system: hypodense volume and Alberta Stroke Program Early CT Score (ASPECTS).

Approach: The NCCT series image data of 67 patients imaged with a CT stroke protocol were reconstructed with four kernels (H10s-smooth, H40s-medium, H60s-sharp, and H70h-very sharp) and three slice thicknesses (1.5, 3.0, and 5.0 mm) to create 1 reference condition (H40s/5.0 mm) and 11 nonreference conditions. The 12 reconstructions per patient were processed with a commercially available FDA-cleared software package that yields total hypodense volume (mL) and ASPECTS. A mixed-effect model was used to test the difference in hypodense volume, and an ordered logistic model was used to test the difference in e-ASPECTS.

Results: Hypodense volume differences from the reference condition ranged from $-14.6$ to 1.1 mL and were significant for all nonreference kernels (H10s $p=0.025$ , H60s $p<0.001$ , and H70h $p<0.001$ ) and for thinner slices (1.5 mm $p<0.001$ and 3.0 mm $p=0.002$ ). e-ASPECTS was invariant to the nonreference kernels and slice thicknesses, with a mean difference ranging from $-0.1$ to 0.5. No significant differences were found for any kernel or slice thickness (all $p>0.05$ ).

Conclusions: Automated hypodense volume measured with a commercially available, FDA-cleared software package is substantially impacted by reconstruction kernel and slice thickness. Conversely, automated ASPECTS is invariant to these reconstruction parameters.

Purpose: Thermal ablation is a minimally invasive therapy used for the treatment of small renal cell carcinoma tumors. Treatment success is evaluated on postablation computed tomography (CT) to determine if the ablation zone covered the tumor with an adequate treatment margin (often 5 to 10 mm). Incorrect margin identification can lead to treatment misassessment, resulting in unnecessary additional ablation. Therefore, segmentation of the renal ablation zone (RAZ) is crucial for treatment evaluation. We aim to develop and assess an accurate deep learning workflow for delineating the RAZ from surrounding tissues in kidney CT images.

Approach: We present an advanced deep learning method using the attention-based U-Net architecture to segment the RAZ. The workflow leverages the strengths of U-Net, enhanced with attention mechanisms, to improve the network's focus on the most relevant parts of the images, resulting in an accurate segmentation.

Results: Our model was trained and evaluated on a dataset comprising 76 patients' annotated RAZs in CT images. Analysis demonstrated that the proposed workflow achieved an accuracy $=0.97\pm 0.02$ , precision $=0.74\pm 0.23$ , $\text{recall}=0.73\pm 0.25$ , $\mathrm{DSC}=0.70\pm 0.22$ , Jaccard $=0.58\pm 0.22$ , specificity $=0.99\pm 0.01$ , Hausdorff distance $=6.70\pm 4.44\mathrm{mm}$ , and mean absolute boundary distance $=2.67\pm 2.22\mathrm{mm}$ .

Conclusions: We used 3D CT images with RAZs and, for the first time, addressed deep-learning-based RAZ segmentation using parallel CT images. Our framework can effectively segment RAZs, allowing clinicians to automatically determine the ablation margin, making our tool ready for clinical use. Prediction time is $\sim 1s$ per patient, enabling clinicians to perform quick reviews, especially in time-constrained settings.

Purpose: Accurate simulation of breast tissue deformation is essential for reliable image registration between 3D imaging modalities and 2D mammograms, where compression significantly alters tissue geometry. Although finite element analysis (FEA) provides high-fidelity modeling, it is computationally intensive and not well suited for rapid simulations. To address this, the physics-based graph neural network (PhysGNN) has been introduced as a computationally efficient approximation model trained on FEA-generated deformations. We extend prior work by evaluating the performance of PhysGNN on new digital breast phantoms and assessing the impact of training on multiple phantoms.

Approach: PhysGNN was trained on both single-phantom (per-geometry) and multiphantom (multigeometry) datasets generated from incremental FEA simulations. The digital breast phantoms represent the uncompressed state, serving as input geometries for predicting compressed configurations. A leave-one-deformation-out evaluation strategy was used to assess predictive performance under compression.

Results: Training on new digital phantoms confirmed the model's robust performance, though with some variability in prediction accuracy reflecting the diverse anatomical structures. Multiphantom training further enhanced this robustness and reduced prediction errors.

Conclusions: PhysGNN offers a computationally efficient alternative to FEA for simulating breast compression. The results showed that model performance remains robust when trained per-geometry, and further demonstrated that multigeometry training enhances predictive accuracy and robustness for the geometries included in the training set. This suggests a strong potential path toward developing reliable models for generating compressed breast volumes, which could facilitate image registration and algorithm development.

Purpose: Research in deep learning has shown a great advancement in the detection of melanoma. However, recent literature has emphasized a tendency of certain models to rely on disease-irrelevant visual artifacts such as dark corners, dense hair, or ruler marks. The dependence on these markers leads to biased models that do well for training but generalize poorly to heterogeneous clinical environments. To address these limitations in developing reliability in skin lesion detection, a lightweight cross-attention-based semantic dual (LCSD) transformer model was proposed.

Approach: The LCSD model extracts global-level semantic information, uses feature normalization to improve model accuracy, and employs semantic queries to improve domain generalization. Multihead attention is included with the semantic queries to refine global features. The cross-attention between feature maps and semantic query provides the model with a generalized encoding of the global context. The model improved the computational complexity from $O\left(n^{2}d\right)$ to $O(nmd+m^{2}d)$ , which makes the model suitable for the development of real-time and mobile applications.

Results: Empirical evaluation was conducted on three challenging datasets: Derm7pt-Dermoscopic, Derm7pt-Clinical, and PAD-UFES-20. The proposed model achieved classification accuracies of 82.82%, 72.95%, and 86.21%, respectively. These results demonstrate superior performance compared with conventional transformer-based models, highlighting both improved robustness and reduced computational cost.

Conclusion: The LCSD model mitigates the influence of irrelevant visual characteristics, enhances domain generalization, and ensures better adaptability across diverse clinical scenarios. Its lightweight design further supports deployment in mobile applications, making it a reliable and efficient solution for real-world melanoma detection.

Purpose: Colorectal cancer is the third most common cancer globally, with a high mortality rate due to metastatic progression, particularly in the liver. Surgical resection remains the main curative treatment, but only a small subset of patients is eligible for surgery at diagnosis. For patients with initially unresectable colorectal liver metastases (CRLM), neoadjuvant chemotherapy can downstage tumors, potentially making surgery feasible. We investigate whether radiomic signatures-quantitative imaging biomarkers derived from baseline computed tomography (CT) scans-can noninvasively predict chemotherapy response in patients with unresectable CRLM, offering a pathway toward personalized treatment planning.

Approach: We used radiomics combined with a stacking classifier (SC) to predict treatment outcome. Baseline CT imaging data from 355 patients with initially unresectable CRLM were analyzed using two regions of interest (ROIs) separately (all tumors in the liver and the largest tumor by volume). From each ROI, 107 radiomic features were extracted. The dataset was split into training and testing sets, and multiple machine learning models were trained and integrated via stacking to enhance prediction. Logistic regression coefficients were used to derive radiomic signatures.

Results: The SC achieved strong predictive performance, with an area under the receiver operating characteristic curve of up to 0.77 for response prediction. Logistic regression identified 12 and 7 predictive features for treatment response in all tumors and the largest tumor ROIs, respectively.

Conclusion: Our findings demonstrate that radiomic features from baseline CT scans can serve as robust, interpretable biomarkers for predicting chemotherapy response, offering insights to guide personalized treatment in unresectable CRLM.

Purpose: Papillary thyroid carcinoma (PTC) is a common thyroid cancer, and accurate preoperative assessment of lateral cervical lymph node metastasis is critical for surgical planning. Current methods are often subjective and prone to misdiagnosis. This study aims to improve the accuracy of metastasis evaluation using a deep learning-based segmentation method on enhanced computed tomography (CT) images.

Approach: We propose a YOLOv8-based deep learning model integrated with a deformable self-attention module to enhance metastatic lymph node segmentation. The model was trained on a large dataset of pathology-confirmed CT images from PTC patients.

Results: The model demonstrated diagnostic performance comparable to experienced physicians, with high precision in identifying metastatic nodes. The deformable self-attention module improved segmentation accuracy, with strong sensitivity and specificity.

Conclusion: This deep learning approach improves the accuracy of preoperative assessment for lateral cervical lymph node metastasis in PTC patients, aiding surgical planning, reducing misdiagnosis, and lowering medical costs. It shows promise for enhancing patient outcomes in PTC management.

Purpose: Skin lesion segmentation plays a significant role in the diagnosis and treatment of skin cancer. Accurate skin lesion segmentation is essential for skin cancer diagnosis and treatment but is challenged by ambiguous boundaries and diverse lesion shapes and sizes. We aim to improve segmentation performance with enhanced boundary preservation.

Approach: We propose BAF-UNet, a boundary-aware segmentation network. It integrates a multiscale boundary-aware feature fusion (BFF) module to combine low-level boundary features with high-level semantic information, and a boundary-aware vision transformer (BAViT) that incorporates boundary guidance into MobileViT to capture local and global context. A boundary-focused loss function is also introduced to prioritize edge accuracy during training. The model is evaluated on ISIC2016, ISIC2017, and PH2 datasets.

Results: Experiments demonstrate that BAF-UNet improves Dice scores and boundary accuracy compared to baseline models. The BFF and BAViT modules enhance boundary delineation while maintaining robustness across lesions of varying shapes and sizes.

Conclusions: BAF-UNet effectively integrates boundary guidance into feature fusion and transformer-based context modeling, significantly improving segmentation accuracy, particularly along lesion edges, and shows potential for clinical application in automated skin cancer diagnosis.

Purpose: Dynamic focusing of received ultrasound signals, or beamforming, is foundational for ultrasound imaging. Conventionally, it requires arrays of ultrasound sensors to estimate where sound came from using time-of-flight (TOF) measurements. We demonstrate passive beamforming with a single biaxial sensor and accurate passive acoustic mapping with two biaxial sensors using only direction of arrival (DOA) information.

Approach: We introduce two single-element biaxial beamforming algorithms and four biaxial image reconstruction algorithms for a two-element biaxial piezoceramic transducer array. Imaging of a hemispherical acoustic source is characterized in an acoustic scanning tank within the region $-30.29\mathrm{mm}$ $\le x\le$ 29.94 mm and 50.11 mm $\le z\le$ 90.45 mm relative to the center of the array. Imaging performance is contrasted with delay, sum, and integrate (DSAI) and delay, multiply, sum, and integrate (DMSAI) algorithms.

Results: Single-element biaxial beamforming can identify DOA with a median error (± interquartile range) of $0.36\pm 0.63\mathrm{deg}$ and median full-width half-prominence of $7.3\pm 8.6\mathrm{deg}$ . Using both array elements, DOA-only images demonstrate overall median localization error of 6.41 mm (lateral: 1.02 mm, axial: 5.85 mm, signal-to-noise ratio (SNR): 15.37) and DOA + TOF images demonstrate overall median error of 6.91 mm (lateral: 1.69 mm, axial: 6.11 mm, SNR: 18.37).

Conclusions: To the best of our knowledge, we provide the first demonstration of single-element beamforming using a single stationary piezoceramic and the first demonstration of passive ultrasound imaging without the use of TOF information. These results enable simpler, smaller, more cost-effective arrays for passive ultrasound imaging.