Prostate volume prediction on MRI: tools, accuracy and variability.

OBJECTIVE: A reliable estimation of prostate volume (PV) is essential to prostate cancer management. The objective of our multi-rater study was to compare intra- and inter-rater variability of PV from manual planimetry and ellipsoid formulas. METHODS: Forty treatment-naive patients who underwent prostate MRI were selected from a local database. PV and corresponding PSA density (PSAd) were estimated on 3D T2-weighted MRI (3 T) by 7 independent radiologists using the traditional ellipsoid formula (TEF), the newer biproximate ellipsoid formula (BPEF), and the manual planimetry method (MPM) used as ground truth. Intra- and inter-rater variability was calculated using the mixed model-based intraclass correlation coefficient (ICC). RESULTS: Mean volumes were 67.00 (± 36.61), 66.07 (± 35.03), and 64.77 (± 38.27) cm3 with the TEF, BPEF, and MPM methods, respectively. Both TEF and BPEF overestimated PV relative to MPM, with the former presenting significant differences (+ 1.91 cm3, IQ = [- 0.33 cm3, 5.07 cm3], p val = 0.03). Both intra- (ICC > 0.90) and inter-rater (ICC > 0.90) reproducibility were excellent. MPM had the highest inter-rater reproducibility (ICC = 0.999). Inter-rater PV variation led to discrepancies in classification according to the clinical criterion of PSAd > 0.15 ng/mL for 2 patients (5%), 7 patients (17.5%), and 9 patients (22.5%) when using MPM, TEF, and BPEF, respectively. CONCLUSION: PV measurements using ellipsoid formulas and MPM are highly reproducible. MPM is a robust method for PV assessment and PSAd calculation, with the lowest variability. TEF showed a high degree of concordance with MPM but a slight overestimation of PV. Precise anatomic landmarks as defined with the BPEF led to a more accurate PV estimation, but also to a higher variability. KEY POINTS: • Manual planimetry used for prostate volume estimation is robust and reproducible, with the lowest variability between readers. • Ellipsoid formulas are accurate and reproducible but with higher variability between readers. • The traditional ellipsoid formula tends to overestimate prostate volume.

A model of brain morphological changes related to aging and Alzheimer's disease from cross-sectional assessments.

In this study we propose a deformation-based framework to jointly model the influence of aging and Alzheimer's disease (AD) on the brain morphological evolution. Our approach combines a spatio-temporal description of both processes into a generative model. A reference morphology is deformed along specific trajectories to match subject specific morphologies. It is used to define two imaging progression markers: 1) a morphological age and 2) a disease score. These markers can be computed regionally in any brain region. The approach is evaluated on brain structural magnetic resonance images (MRI) from the ADNI database. The model is first estimated on a control population using longitudinal data, then, for each testing subject, the markers are computed cross-sectionally for each acquisition. The longitudinal evolution of these markers is then studied in relation with the clinical diagnosis of the subjects and used to generate possible morphological evolutions. In the model, the morphological changes associated with normal aging are mainly found around the ventricles, while the Alzheimer's disease specific changes are located in the temporal lobe and the hippocampal area. The statistical analysis of these markers highlights differences between clinical conditions even though the inter-subject variability is quite high. The model is also generative since it can be used to simulate plausible morphological trajectories associated with the disease. Our method quantifies two interpretable scalar imaging biomarkers assessing respectively the effects of aging and disease on brain morphology, at the individual and population level. These markers confirm the presence of an accelerated apparent aging component in Alzheimer's patients but they also highlight specific morphological changes that can help discriminate clinical conditions even in prodromal stages. More generally, the joint modeling of normal and pathological evolutions shows promising results to describe age-related brain diseases over long time scales.

Correction to: Neuro-radiological characteristics of adult diffuse grade II and III insular gliomas classified according to WHO 2016.

In the initial, online publication, the authors' given names were captured as family names and vice versa. The names are correctly shown here. The original article has been corrected.

Neuro-radiological characteristics of adult diffuse grade II and III insular gliomas classified according to WHO 2016.

INTRODUCTION: The phenotypic heterogeneity of diffuse gliomas is still inconsistently explained by known molecular abnormalities. Here, we report the molecular and radiological features of diffuse grade WHO II and III gliomas involving the insula and its potential impact on prognosis. METHODS: Clinical, pathological, molecular and neuro-radiological features of 43 consecutive patients who underwent a surgical resection between 2006 and 2013 for a grade II and III gliomas involving the insula was retrospectively analyzed. RESULTS: Median age was 44.4 years. Eight patients had oligodendrogliomas, IDH mutant (IDHmut) and 1p/19q-codeleted (6 grade II, 2 grade III). Twenty-eight patients had diffuse astrocytomas, IDHmut (22 grade II and 6 grade III) and seven patients had grade II diffuse astrocytomas, IDHwt (A-IDHwt). Vimentin staining was exclusively recorded in tumor cells from A-IDHwt (p = 0.001). Mean cerebral blood volume (CBV) (p = 0.018), maximal value of CBV (p = 0.017) and ratio of the corrected CBV (p = 0.022) were lower for A-IDHwt. Volumetric segmentation of ADC allowed the identification of the tumor cores, which were smaller in A-IDHwt (p < 0.001). The tumor occurrences of A-IDHwt were exclusively located into the temporo-insular region. Median progression-free survival (PFS) and overall survival (OS) were 50.9 months (95% CI: 26.7-75.0) and 80.9 months (60.1-101.6). By multivariate analysis, A-IDHwt (p = 0.009; p = 0.019), 7p gain and 10q loss (p = 0.009; p = 0.016) and vimentin positive staining (p = 0.011; p = 0.029) were associated with poor PFS and OS respectively. CONCLUSIONS: Insular low-grade A-IDHwt presented with poor prognosis despite a smaller tumor core and no evidence of increased perfusion on MR imaging.

[The age of artificial intelligence in lung cancer pathology: Between hope, gloom and perspectives]. / La pathologie cancéreuse pulmonaire à l'heure de l'intelligence artificielle : entre espoir, désespoir et perspectives.

Histopathology is the fundamental tool of pathology used for more than a century to establish the final diagnosis of lung cancer. In addition, the phenotypic data contained in the histological images reflects the overall effect of molecular alterations on the behavior of cancer cells and provides a practical visual reading of the aggressiveness of the disease. However, the human evaluation of the histological images is sometimes subjective and may lack reproducibility. Therefore, computational analysis of histological imaging using so-called "artificial intelligence" (AI) approaches has recently received considerable attention to improve this diagnostic accuracy. Thus, computational analysis of lung cancer images has recently been evaluated for the optimization of histological or cytological classification, prognostic prediction or genomic profile of patients with lung cancer. This rapidly growing field constantly demonstrates great power in the field of computing medical imaging by producing highly accurate detection, segmentation or recognition tasks. However, there are still several challenges or issues to be addressed in order to successfully succeed the actual transfer into clinical routine. The objective of this review is to emphasize recent applications of AI in pulmonary cancer pathology, but also to clarify the advantages and limitations of this approach, as well as the perspectives to be implemented for a potential transfer into clinical routine.

Biophysical Modeling Predicts Ventricular Tachycardia Inducibility and Circuit Morphology: A Combined Clinical Validation and Computer Modeling Approach.

INTRODUCTION: Computational modeling of cardiac arrhythmogenesis and arrhythmia maintenance has made a significant contribution to the understanding of the underlying mechanisms of arrhythmia. We hypothesized that a cardiac model using personalized electro-anatomical parameters could define the underlying ventricular tachycardia (VT) substrate and predict reentrant VT circuits. We used a combined modeling and clinical approach in order to validate the concept. METHODS AND RESULTS: Non-contact electroanatomic mapping studies were performed in 7 patients (5 ischemics, 2 non-ischemics). Three ischemic cardiomyopathy patients underwent a clinical VT stimulation study. Anatomical information was obtained from cardiac magnetic resonance imaging (CMR) including high-resolution scar imaging. A simplified biophysical mono-domain action potential model personalized with the patients' anatomical and electrical information was used to perform in silico VT stimulation studies for comparison. The personalized in silico VT stimulations were able to predict VT inducibility as well as the macroscopic characteristics of the VT circuits in patients who had clinical VT stimulation studies. The patients with positive clinical VT stimulation studies had wider distribution of action potential duration restitution curve (APD-RC) slopes and APDs than the patient with a negative VT stimulation study. The exit points of reentrant VT circuits encompassed a higher percentage of the maximum APD-RC slope compared to the scar and non-scar areas, 32%, 4%, and 0.2%, respectively. CONCLUSIONS: VT stimulation studies can be simulated in silico using a personalized biophysical cardiac model. Myocardial spatial heterogeneity of APD restitution properties and conductivity may help predict the location of crucial entry/exit points of reentrant VT circuits.

Impact of the surgical experience on cochleostomy location: a comparative temporal bone study between endaural and posterior tympanotomy approaches for cochlear implantation.

The goal of this study was to evaluate, in the hands of an inexperienced surgeon, the cochleostomy location of an endaural approach (MINV) compared to the conventional posterior tympanotomy (MPT) approach. Since 2010, we use in the ENT department of Nice a new surgical endaural approach to perform cochlear implantation. In the hands of an inexperienced surgeon, the position of the cochleostomy has not yet been studied in detail for this technique. This is a prospective study of 24 human heads. Straight electrode arrays were implanted by an inexperienced surgeon: on one side using MPT and on the other side using MINV. The cochleostomies were all antero-inferior, but they were performed through an endaural approach with the MINV or a posterior tympanotomy approach with the MPT. The positioning of the cochleostomies into the scala tympani was evaluated by microdissection. Cochleostomies performed through the endaural approach were well placed into the scala tympani more frequently than those performed through the posterior tympanotomy approach (87.5 and 16.7 %, respectively, p ≤ 0.001). This study highlights the biggest challenge for an inexperienced surgeon to achieve a reliable cochleostomy through a posterior tympanotomy, which requires years of experience. In case of an uncomfortable view through a posterior tympanotomy, an inexperienced surgeon might be able to successfully perform a cochleostomy through an endaural (combined approach) or an extended round window approach in order to avoid opening the scala vestibuli.

Mutual Information Guided Diffusion for Zero-shot Cross-modality Medical Image Translation.

Cross-modality data translation has attracted great interest in medical image computing. Deep generative models show performance improvement in addressing related challenges. Nevertheless, as a fundamental challenge in image translation, the problem of zero-shot learning cross-modality image translation with fidelity remains unanswered. To bridge this gap, we propose a novel unsupervised zero-shot learning method called Mutual Information guided Diffusion Model, which learns to translate an unseen source image to the target modality by leveraging the inherent statistical consistency of Mutual Information between different modalities. To overcome the prohibitive high dimensional Mutual Information calculation, we propose a differentiable local-wise mutual information layer for conditioning the iterative denoising process. The Local-wise-Mutual-Information-Layer captures identical cross-modality features in the statistical domain, offering diffusion guidance without relying on direct mappings between the source and target domains. This advantage allows our method to adapt to changing source domains without the need for retraining, making it highly practical when sufficient labeled source domain data is not available. We demonstrate the superior performance of MIDiffusion in zero-shot cross-modality translation tasks through empirical comparisons with other generative models, including adversarial-based and diffusion-based models. Finally, we showcase the real-world application of MIDiffusion in 3D zero-shot learning-based cross-modality image segmentation tasks.

Reference standard for the evaluation of automatic segmentation algorithms: Quantification of inter observer variability of manual delineation of prostate contour on MRI.

PURPOSE: The purpose of this study was to investigate the relationship between inter-reader variability in manual prostate contour segmentation on magnetic resonance imaging (MRI) examinations and determine the optimal number of readers required to establish a reliable reference standard. MATERIALS AND METHODS: Seven radiologists with various experiences independently performed manual segmentation of the prostate contour (whole-gland [WG] and transition zone [TZ]) on 40 prostate MRI examinations obtained in 40 patients. Inter-reader variability in prostate contour delineations was estimated using standard metrics (Dice similarity coefficient [DSC], Hausdorff distance and volume-based metrics). The impact of the number of readers (from two to seven) on segmentation variability was assessed using pairwise metrics (consistency) and metrics with respect to a reference segmentation (conformity), obtained either with majority voting or simultaneous truth and performance level estimation (STAPLE) algorithm. RESULTS: The average segmentation DSC for two readers in pairwise comparison was 0.919 for WG and 0.876 for TZ. Variability decreased with the number of readers: the interquartile ranges of the DSC were 0.076 (WG) / 0.021 (TZ) for configurations with two readers, 0.005 (WG) / 0.012 (TZ) for configurations with three readers, and 0.002 (WG) / 0.0037 (TZ) for configurations with six readers. The interquartile range decreased slightly faster between two and three readers than between three and six readers. When using consensus methods, variability often reached its minimum with three readers (with STAPLE, DSC = 0.96 [range: 0.945-0.971] for WG and DSC = 0.94 [range: 0.912-0.957] for TZ, and interquartile range was minimal for configurations with three readers. CONCLUSION: The number of readers affects the inter-reader variability, in terms of inter-reader consistency and conformity to a reference. Variability is minimal for three readers, or three readers represent a tipping point in the variability evolution, with both pairwise-based metrics or metrics with respect to a reference. Accordingly, three readers may represent an optimal number to determine references for artificial intelligence applications.

WhARIO: whole-slide-image-based survival analysis for patients treated with immunotherapy.

Purpose: Immune checkpoint inhibitors (ICIs) are now one of the standards of care for patients with lung cancer and have greatly improved both progression-free and overall survival, although <20% of the patients respond to the treatment, and some face acute adverse events. Although a few predictive biomarkers have integrated the clinical workflow, they require additional modalities on top of whole-slide images and lack efficiency or robustness. In this work, we propose a biomarker of immunotherapy outcome derived solely from the analysis of histology slides. Approach: We develop a three-step framework, combining contrastive learning and nonparametric clustering to distinguish tissue patterns within the slides, before exploiting the adjacencies of previously defined regions to derive features and train a proportional hazards model for survival analysis. We test our approach on an in-house dataset of 193 patients from 5 medical centers and compare it with the gold standard tumor proportion score (TPS) biomarker. Results: On a fivefold cross-validation (CV) of the entire dataset, the whole-slide image-based survival analysis for patients treated with immunotherapy (WhARIO) features are able to separate a low- and a high-risk group of patients with a hazard ratio (HR) of 2.29 (CI95=1.48 to 3.56), whereas the TPS 1% reference threshold only reaches a HR of 1.81 (CI95=1.21 to 2.69). Combining the two yields a higher HR of 2.60 (CI95=1.72 to 3.94). Additional experiments on the same dataset, where one out of five centers is excluded from the CV and used as a test set, confirm these trends. Conclusions: Our uniquely designed WhARIO features are an efficient predictor of survival for lung cancer patients who received ICI treatment. We achieve similar performance to the current gold standard biomarker, without the need to access other imaging modalities, and show that both can be used together to reach even better results.

MS-CLAM: Mixed supervision for the classification and localization of tumors in Whole Slide Images.

Given the size of digitized Whole Slide Images (WSIs), it is generally laborious and time-consuming for pathologists to exhaustively delineate objects within them, especially with datasets containing hundreds of slides to annotate. Most of the time, only slide-level labels are available, giving rise to the development of weakly-supervised models. However, it is often difficult to obtain from such models accurate object localization, e.g., patches with tumor cells in a tumor detection task, as they are mainly designed for slide-level classification. Using the attention-based deep Multiple Instance Learning (MIL) model as our base weakly-supervised model, we propose to use mixed supervision - i.e., the use of both slide-level and patch-level labels - to improve both the classification and the localization performances of the original model, using only a limited amount of patch-level labeled slides. In addition, we propose an attention loss term to regularize the attention between key instances, and a paired batch method to create balanced batches for the model. First, we show that the changes made to the model already improve its performance and interpretability in the weakly-supervised setting. Furthermore, when using only between 12 and 62% of the total available patch-level annotations, we can reach performance close to fully-supervised models on the tumor classification datasets DigestPath2019 and Camelyon16.

Deep clustering for abdominal organ classification in ultrasound imaging.

Purpose: The purpose of this study is to examine the utilization of unlabeled data for abdominal organ classification in multi-label (non-mutually exclusive classes) ultrasound images, as an alternative to the conventional transfer learning approach. Approach: We present a new method for classifying abdominal organs in ultrasound images. Unlike previous approaches that only relied on labeled data, we consider the use of both labeled and unlabeled data. To explore this approach, we first examine the application of deep clustering for pretraining a classification model. We then compare two training methods, fine-tuning with labeled data through supervised learning and fine-tuning with both labeled and unlabeled data using semisupervised learning. All experiments were conducted on a large dataset of unlabeled images (nu=84967) and a small set of labeled images (ns=2742) comprising progressively 10%, 20%, 50%, and 100% of the images. Results: We show that for supervised fine-tuning, deep clustering is an effective pre-training method, with performance matching that of ImageNet pre-training using five times less labeled data. For semi-supervised learning, deep clustering pre-training also yields higher performance when the amount of labeled data is limited. Best performance is obtained with deep clustering pre-training combined with semi-supervised learning and 2742 labeled example images with an F1-score weighted average of 84.1%. Conclusions: This method can be used as a tool to preprocess large unprocessed databases, thus reducing the need for prior annotations of abdominal ultrasound studies for the training of image classification algorithms, which in turn could improve the clinical use of ultrasound images.

Anatomical Variations of the Human Cochlea Using an Image Analysis Tool.

Understanding cochlear anatomy is crucial for developing less traumatic electrode arrays and insertion guidance for cochlear implantation. The human cochlea shows considerable variability in size and morphology. This study analyses 1000+ clinical temporal bone CT images using a web-based image analysis tool. Cochlear size and shape parameters were obtained to determine population statistics and perform regression and correlation analysis. The analysis revealed that cochlear morphology follows Gaussian distribution, while cochlear dimensions A and B are not well-correlated to each other. Additionally, dimension B is more correlated to duct lengths, the wrapping factor and volume than dimension A. The scala tympani size varies considerably among the population, with the size generally decreasing along insertion depth with dimensional jumps through the trajectory. The mean scala tympani radius was 0.32 mm near the 720° insertion angle. Inter-individual variability was four times that of intra-individual variation. On average, the dimensions of both ears are similar. However, statistically significant differences in clinical dimensions were observed between ears of the same patient, suggesting that size and shape are not the same. Harnessing deep learning-based, automated image analysis tools, our results yielded important insights into cochlear morphology and implant development, helping to reduce insertion trauma and preserving residual hearing.

Robust Bayesian fusion of continuous segmentation maps.

The fusion of probability maps is required when trying to analyse a collection of image labels or probability maps produced by several segmentation algorithms or human raters. The challenge is to weight the combination of maps correctly, in order to reflect the agreement among raters, the presence of outliers and the spatial uncertainty in the consensus. In this paper, we address several shortcomings of prior work in continuous label fusion. We introduce a novel approach to jointly estimate a reliable consensus map and to assess the presence of outliers and the confidence in each rater. Our robust approach is based on heavy-tailed distributions allowing local estimates of raters performances. In particular, we investigate the Laplace, the Student's t and the generalized double Pareto distributions, and compare them with respect to the classical Gaussian likelihood used in prior works. We unify these distributions into a common tractable inference scheme based on variational calculus and scale mixture representations. Moreover, the introduction of bias and spatial priors leads to proper rater bias estimates and control over the smoothness of the consensus map. Finally, we propose an approach that clusters raters based on variational boosting, and thus may produce several alternative consensus maps. Our approach was successfully tested on MR prostate delineations and on lung nodule segmentations from the LIDC-IDRI dataset.

Automatic zonal segmentation of the prostate from 2D and 3D T2-weighted MRI and evaluation for clinical use.

Purpose: An accurate zonal segmentation of the prostate is required for prostate cancer (PCa) management with MRI. Approach: The aim of this work is to present UFNet, a deep learning-based method for automatic zonal segmentation of the prostate from T2-weighted (T2w) MRI. It takes into account the image anisotropy, includes both spatial and channelwise attention mechanisms and uses loss functions to enforce prostate partition. The method was applied on a private multicentric three-dimensional T2w MRI dataset and on the public two-dimensional T2w MRI dataset ProstateX. To assess the model performance, the structures segmented by the algorithm on the private dataset were compared with those obtained by seven radiologists of various experience levels. Results: On the private dataset, we obtained a Dice score (DSC) of 93.90 ± 2.85 for the whole gland (WG), 91.00 ± 4.34 for the transition zone (TZ), and 79.08 ± 7.08 for the peripheral zone (PZ). Results were significantly better than other compared networks' ( p - value < 0.05 ). On ProstateX, we obtained a DSC of 90.90 ± 2.94 for WG, 86.84 ± 4.33 for TZ, and 78.40 ± 7.31 for PZ. These results are similar to state-of-the art results and, on the private dataset, are coherent with those obtained by radiologists. Zonal locations and sectorial positions of lesions annotated by radiologists were also preserved. Conclusions: Deep learning-based methods can provide an accurate zonal segmentation of the prostate leading to a consistent zonal location and sectorial position of lesions, and therefore can be used as a helping tool for PCa diagnosis.

Super-Resolved Microbubble Localization in Single-Channel Ultrasound RF Signals Using Deep Learning.

Recently, super-resolution ultrasound imaging with ultrasound localization microscopy (ULM) has received much attention. However, ULM relies on low concentrations of microbubbles in the blood vessels, ultimately resulting in long acquisition times. Here, we present an alternative super-resolution approach, based on direct deconvolution of single-channel ultrasound radio-frequency (RF) signals with a one-dimensional dilated convolutional neural network (CNN). This work focuses on low-frequency ultrasound (1.7 MHz) for deep imaging (10 cm) of a dense cloud of monodisperse microbubbles (up to 1000 microbubbles in the measurement volume, corresponding to an average echo overlap of 94%). Data are generated with a simulator that uses a large range of acoustic pressures (5-250 kPa) and captures the full, nonlinear response of resonant, lipid-coated microbubbles. The network is trained with a novel dual-loss function, which features elements of both a classification loss and a regression loss and improves the detection-localization characteristics of the output. Whereas imposing a localization tolerance of 0 yields poor detection metrics, imposing a localization tolerance corresponding to 4% of the wavelength yields a precision and recall of both 0.90. Furthermore, the detection improves with increasing acoustic pressure and deteriorates with increasing microbubble density. The potential of the presented approach to super-resolution ultrasound imaging is demonstrated with a delay-and-sum reconstruction with deconvolved element data. The resulting image shows an order-of-magnitude gain in axial resolution compared to a delay-and-sum reconstruction with unprocessed element data.

Bayesian logistic shape model inference: Application to cochlear image segmentation.

Incorporating shape information is essential for the delineation of many organs and anatomical structures in medical images. While previous work has mainly focused on parametric spatial transformations applied to reference template shapes, in this paper, we address the Bayesian inference of parametric shape models for segmenting medical images with the objective of providing interpretable results. The proposed framework defines a likelihood appearance probability and a prior label probability based on a generic shape function through a logistic function. A reference length parameter defined in the sigmoid controls the trade-off between shape and appearance information. The inference of shape parameters is performed within an Expectation-Maximisation approach in which a Gauss-Newton optimization stage provides an approximation of the posterior probability of the shape parameters. This framework is applied to the segmentation of cochlear structures from clinical CT images constrained by a 10-parameter shape model. It is evaluated on three different datasets, one of which includes more than 200 patient images. The results show performances comparable to supervised methods and better than previously proposed unsupervised ones. It also enables an analysis of parameter distributions and the quantification of segmentation uncertainty, including the effect of the shape model.

Automatic segmentation of prostate zonal anatomy on MRI: a systematic review of the literature.

OBJECTIVES: Accurate zonal segmentation of prostate boundaries on MRI is a critical prerequisite for automated prostate cancer detection based on PI-RADS. Many articles have been published describing deep learning methods offering great promise for fast and accurate segmentation of prostate zonal anatomy. The objective of this review was to provide a detailed analysis and comparison of applicability and efficiency of the published methods for automatic segmentation of prostate zonal anatomy by systematically reviewing the current literature. METHODS: A Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) was conducted until June 30, 2021, using PubMed, ScienceDirect, Web of Science and EMBase databases. Risk of bias and applicability based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria adjusted with Checklist for Artificial Intelligence in Medical Imaging (CLAIM) were assessed. RESULTS: A total of 458 articles were identified, and 33 were included and reviewed. Only 2 articles had a low risk of bias for all four QUADAS-2 domains. In the remaining, insufficient details about database constitution and segmentation protocol provided sources of bias (inclusion criteria, MRI acquisition, ground truth). Eighteen different types of terminology for prostate zone segmentation were found, while 4 anatomic zones are described on MRI. Only 2 authors used a blinded reading, and 4 assessed inter-observer variability. CONCLUSIONS: Our review identified numerous methodological flaws and underlined biases precluding us from performing quantitative analysis for this review. This implies low robustness and low applicability in clinical practice of the evaluated methods. Actually, there is not yet consensus on quality criteria for database constitution and zonal segmentation methodology.

Deep Learning for the Detection, Localization, and Characterization of Focal Liver Lesions on Abdominal US Images.

Purpose: To train and assess the performance of a deep learning-based network designed to detect, localize, and characterize focal liver lesions (FLLs) in the liver parenchyma on abdominal US images. Materials and Methods: In this retrospective, multicenter, institutional review board-approved study, two object detectors, Faster region-based convolutional neural network (Faster R-CNN) and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018). Performance of the networks was analyzed on a test set of 48 additional patients (n = 155 B-mode abdominal US images obtained in 2019) and compared with the performance of three caregivers (one nonexpert and two experts) blinded to the clinical history. The sign test was used to compare accuracy, specificity, sensitivity, and positive predictive value among all raters. Results: DETR achieved a specificity of 90% (95% CI: 75, 100) and a sensitivity of 97% (95% CI: 97, 97) for the detection of FLLs. The performance of DETR met or exceeded that of the three caregivers for this task. DETR correctly localized 80% of the lesions, and it achieved a specificity of 81% (95% CI: 67, 91) and a sensitivity of 82% (95% CI: 62, 100) for FLL characterization (benign vs malignant) among lesions localized by all raters. The performance of DETR met or exceeded that of two experts and Faster R-CNN for these tasks. Conclusion: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images. Supplemental material is available for this article. RSNA, 2022Keywords: Computer-aided Diagnosis (CAD), Ultrasound, Abdomen/GI, Liver, Tissue Characterization, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN).