The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training images and expert annotations. This work describes a fully 3D prototypical few-shot segmentation algorithm, such that the trained networks can be effectively adapted to clinically interesting structures that are absent in training, using only a few labelled images from a different institute. First, to compensate for the widely recognised spatial variability between institutions in episodic adaptation of novel classes, a novel spatial registration mechanism is integrated into prototypical learning, consisting of a segmentation head and an spatial alignment module. Second, to assist the training with observed imperfect alignment, support mask conditioning module is proposed to further utilise the annotation available from the support images. Extensive experiments are presented in an application of segmenting eight anatomical structures important for interventional planning, using a data set of 589 pelvic T2-weighted MR images, acquired at seven institutes. The results demonstrate the efficacy in each of the 3D formulation, the spatial registration, and the support mask conditioning, all of which made positive contributions independently or collectively. Compared with the previously proposed 2D alternatives, the few-shot segmentation performance was improved with statistical significance, regardless whether the support data come from the same or different institutes.

for automated localization of clinically significant prostate cancer (csPCa) in bi-parametric MR imaging (bpMRI). Deep attention mechanisms drive its detection network, targeting salient structures and highly discriminative feature dimensions across multiple resolutions. Its goal is to accurately identify csPCa lesions from indolent cancer and the wide range of benign pathology that can afflict the prostate gland. Simultaneously, a decoupled residual classifier is used to achieve consistent false positive reduction, without sacrificing high sensitivity or computational efficiency. In order to guide model generalization with domain-specific clinical knowledge, a probabilistic anatomical prior is used to encode the spatial prevalence and zonal distinction of csPCa. Using a large dataset of 1950 prostate bpMRI paired with radiologically-estimated annotations, we hypothesize that such CNN-based models can be trained to detect biopsy-confirmed malignancies in an independent cohort. For 486 institutional testing scans, the 3D CAD system achieves 83.69±5.22% and 93.19±2.96% detection sensitivity at 0.50 and 1.46 false positive(s) per patient, respectively, with 0.882±0.030 AUROC in patient-based diagnosis -significantly outperforming four state-of-the-art baseline architectures (U-SEResNet, UNet++, nnU-Net, Attention U-Net) from recent literature. For 296 external biopsy-confirmed testing scans, the ensembled CAD system shares moderate agreement with a consensus of expert radiologists (76.69%; kappa = 0.51±0.04) and independent pathologists (81.08%; kappa = 0.56±0.06); demonstrating strong generalization to histologically-confirmed csPCa diagnosis.

Multi-parametric prostate MRI (mpMRI) is a powerful tool to diagnose prostate cancer, though difficult to interpret even for experienced radiologists. A common radiological procedure is to compare a magnetic resonance image with similarly diagnosed cases. To assist the radiological image interpretation process, computerized Content-Based Image Retrieval systems (CBIRs) can therefore be employed to improve the reporting workflow and increase its accuracy. In this article, we propose a new, supervised siamese deep learning architecture able to handle multi-modal and multi-view MR images with similar PIRADS score. An experimental comparison with well-established deep learning-based CBIRs (namely standard siamese networks and autoencoders) showed significantly improved performance with respect to both diagnostic (ROC-AUC), and information retrieval metrics (Precision-Recall, Discounted Cumulative Gain and Mean Average Precision). Finally, the new proposed multi-view siamese network is general in design, facilitating a broad use in diagnostic medical imaging retrieval.

Segmentation algorithms are typically evaluated by comparison to an accepted reference standard. The cost of generating accurate reference standards for medical image segmentation can be substantial. Since the study cost and the likelihood of detecting a clinically meaningful difference in accuracy both depend on the size and on the quality of the study reference standard, balancing these trade-offs supports the efficient use of research resources. In this work, we derive a statistical power calculation that enables researchers to estimate the appropriate sample size to detect clinically meaningful differences in segmentation accuracy (i.e. the proportion of voxels matching the reference standard) between two algorithms. Furthermore, we derive a formula to relate reference standard errors to their effect on the sample sizes of studies using lower-quality (but potentially more affordable and practically available) reference standards. The accuracy of the derived sample size formula was estimated through Monte Carlo simulation, demonstrating, with 95% confidence, a predicted statistical power within 4% of simulated values across a range of model parameters. This corresponds to sample size errors of less than 4 subjects and errors in the detectable accuracy difference less than 0.6%. The applicability of the formula to real-world data was assessed using bootstrap resampling simulations for pairs of algorithms from the PROMISE12 prostate MR segmentation challenge data set. The model predicted the simulated power for the majority of algorithm pairs within 4% for simulated experiments using a high-quality reference standard and within 6% for simulated experiments using a low-quality reference standard. A case study, also based on the PROMISE12 data, illustrates using the formulae to evaluate whether to use a lower-quality reference standard in a prostate segmentation study.

Determining corresponding regions between an MRI and an X-ray mammogram is a clinically useful task that is challenging for radiologists due to the large deformation that the breast undergoes between the two image acquisitions. In this work we propose an intensity-based image registration framework, where the biomechanical transformation model parameters and the rigid-body transformation parameters are optimised simultaneously. Patient-specific biomechanical modelling of the breast derived from diagnostic, prone MRI has been previously used for this task. However, the high computational time associated with breast compression simulation using commercial packages, did not allow the optimisation of both pose and FEM parameters in the same framework. We use a fast explicit Finite Element (FE) solver that runs on a graphics card, enabling the FEM-based transformation model to be fully integrated into the optimisation scheme. The transformation model has seven degrees of freedom, which include parameters for both the initial rigid-body pose of the breast prior to mammographic compression, and those of the biomechanical model. The framework was tested on ten clinical cases and the results were compared against an affine transformation model, previously proposed for the same task. The mean registration error was 11.6±3.8mm for the CC and 11±5.4mm for the MLO view registrations, indicating that this could be a useful clinical tool.

Prostate cancer is one of the major causes of cancer death for men in the western world. Magnetic resonance imaging (MRI) is being increasingly used as a modality to detect prostate cancer. Therefore, computer-aided detection of prostate cancer in MRI images has become an active area of research. In this paper we investigate a fully automated computer-aided detection system which consists of two stages. In the first stage, we detect initial candidates using multi-atlas-based prostate segmentation, voxel feature extraction, classification and local maxima detection. The second stage segments the candidate regions and using classification we obtain cancer likelihoods for each candidate. Features represent pharmacokinetic behavior, symmetry and appearance, among others. The system is evaluated on a large consecutive cohort of 347 patients with MR-guided biopsy as the reference standard. This set contained 165 patients with cancer and 182 patients without prostate cancer. Performance evaluation is based on lesion-based free-response receiver operating characteristic curve and patient-based receiver operating characteristic analysis. The system is also compared to the prospective clinical performance of radiologists. Results show a sensitivity of 0.42, 0.75, and 0.89 at 0.1, 1, and 10 false positives per normal case. In clinical workflow the system could potentially be used to improve the sensitivity of the radiologist. At the high specificity reading setting, which is typical in screening situations, the system does not perform significantly different from the radiologist and could be used as an independent second reader instead of a second radiologist. Furthermore, the system has potential in a first-reader setting.

A computer-aided diagnosis (CAD) system for the classification of lesions as malignant or benign in automated 3-D breast ultrasound (ABUS) images, is presented. Lesions are automatically segmented when a seed point is provided, using dynamic programming in combination with a spiral scanning technique. A novel aspect of ABUS imaging is the presence of spiculation patterns in coronal planes perpendicular to the transducer. Spiculation patterns are characteristic for malignant lesions. Therefore, we compute spiculation features and combine them with features related to echotexture, echogenicity, shape, posterior acoustic behavior and margins. Classification experiments were performed using a support vector machine classifier and evaluation was done with leave-one-patient-out cross-validation. Receiver operator characteristic (ROC) analysis was used to determine performance of the system on a dataset of 201 lesions. We found that spiculation was among the most discriminative features. Using all features, the area under the ROC curve (A(z)) was 0.93, which was significantly higher than the performance without spiculation features (A(z)=0.90, p=0.02). On a subset of 88 cases, classification performance of CAD (A(z)=0.90) was comparable to the average performance of 10 readers (A(z)=0.87).

A method is presented for estimation of dense breast tissue volume from mammograms obtained with full-field digital mammography (FFDM). The thickness of dense tissue mapping to a pixel is determined by using a physical model of image acquisition. This model is based on the assumption that the breast is composed of two types of tissue, fat and parenchyma. Effective linear attenuation coefficients of these tissues are derived from empirical data as a function of tube voltage (kVp), anode material, filtration, and compressed breast thickness. By employing these, tissue composition at a given pixel is computed after performing breast thickness compensation, using a reference value for fatty tissue determined by the maximum pixel value in the breast tissue projection. Validation has been performed using 22 FFDM cases acquired with a GE Senographe 2000D by comparing the volume estimates with volumes obtained by semi-automatic segmentation of breast magnetic resonance imaging (MRI) data. The correlation between MRI and mammography volumes was 0.94 on a per image basis and 0.97 on a per patient basis. Using the dense tissue volumes from MRI data as the gold standard, the average relative error of the volume estimates was 13.6%.