On the use of contrastive learning for standard-plane classification in fetal ultrasound imaging.

BACKGROUND: To investigate the effectiveness of contrastive learning, in particular SimClr, in reducing the need for large annotated ultrasound (US) image datasets for fetal standard plane identification. METHODS: We explore SimClr advantage in the cases of both low and high inter-class variability, considering at the same time how classification performance varies according to different amounts of labels used. This evaluation is performed by exploiting contrastive learning through different training strategies. We apply both quantitative and qualitative analyses, using standard metrics (F1-score, sensitivity, and precision), Class Activation Mapping (CAM), and t-Distributed Stochastic Neighbor Embedding (t-SNE). RESULTS: When dealing with high inter-class variability classification tasks, contrastive learning does not bring a significant advantage; whereas it results to be relevant for low inter-class variability classification, specifically when initialized with ImageNet weights. CONCLUSIONS: Contrastive learning approaches are typically used when a large number of unlabeled data is available, which is not representative of US datasets. We proved that SimClr either as pre-training with backbone initialized via ImageNet weights or used in an end-to-end dual-task may impact positively the performance over standard transfer learning approaches, under a scenario in which the dataset is small and characterized by low inter-class variability.

Knowledge distillation on individual vertebrae segmentation exploiting 3D U-Net.

Recent advances in medical imaging have highlighted the critical development of algorithms for individual vertebral segmentation on computed tomography (CT) scans. Essential for diagnostic accuracy and treatment planning in orthopaedics, neurosurgery and oncology, these algorithms face challenges in clinical implementation, including integration into healthcare systems. Consequently, our focus lies in exploring the application of knowledge distillation (KD) methods to train shallower networks capable of efficiently segmenting vertebrae in CT scans. This approach aims to reduce segmentation time, enhance suitability for emergency cases, and optimize computational and memory resource efficiency. Building upon prior research in the field, a two-step segmentation approach was employed. Firstly, the spine's location was determined by predicting a heatmap, indicating the probability of each voxel belonging to the spine. Subsequently, an iterative segmentation of vertebrae was performed from the top to the bottom of the CT volume over the located spine, using a memory instance to record the already segmented vertebrae. KD methods were implemented by training a teacher network with performance similar to that found in the literature, and this knowledge was distilled to a shallower network (student). Two KD methods were applied: (1) using the soft outputs of both networks and (2) matching logits. Two publicly available datasets, comprising 319 CT scans from 300 patients and a total of 611 cervical, 2387 thoracic, and 1507 lumbar vertebrae, were used. To ensure dataset balance and robustness, effective data augmentation methods were applied, including cleaning the memory instance to replicate the first vertebra segmentation. The teacher network achieved an average Dice similarity coefficient (DSC) of 88.22% and a Hausdorff distance (HD) of 7.71 mm, showcasing performance similar to other approaches in the literature. Through knowledge distillation from the teacher network, the student network's performance improved, with an average DSC increasing from 75.78% to 84.70% and an HD decreasing from 15.17 mm to 8.08 mm. Compared to other methods, our teacher network exhibited up to 99.09% fewer parameters, 90.02% faster inference time, 88.46% shorter total segmentation time, and 89.36% less associated carbon (CO2) emission rate. Regarding our student network, it featured 75.00% fewer parameters than our teacher, resulting in a 36.15% reduction in inference time, a 33.33% decrease in total segmentation time, and a 42.96% reduction in CO2 emissions. This study marks the first exploration of applying KD to the problem of individual vertebrae segmentation in CT, demonstrating the feasibility of achieving comparable performance to existing methods using smaller neural networks.

Classifying Vocal Folds Fixation from Endoscopic Videos with Machine Learning.

Vocal folds motility evaluation is paramount in both the assessment of functional deficits and in the accurate staging of neoplastic disease of the glottis. Diagnostic endoscopy, and in particular videoendoscopy, is nowadays the method through which the motility is estimated. The clinical diagnosis, however, relies on the examination of the videoendoscopic frames, which is a subjective and professional-dependent task. Hence, a more rigorous, objective, reliable, and repeatable method is needed. To support clinicians, this paper proposes a machine learning (ML) approach for vocal cords motility classification. From the endoscopic videos of 186 patients with both vocal cords preserved motility and fixation, a dataset of 558 images relative to the two classes was extracted. Successively, a number of features was retrieved from the images and used to train and test four well-grounded ML classifiers. From test results, the best performance was achieved using XGBoost, with precision = 0.82, recall = 0.82, F1 score = 0.82, and accuracy = 0.82. After comparing the most relevant ML models, we believe that this approach could provide precise and reliable support to clinical evaluation.Clinical Relevance- This research represents an important advancement in the state-of-the-art of computer-assisted otolaryngology, to develop an effective tool for motility assessment in the clinical practice.

Instance segmentation of upper aerodigestive tract cancer: site-specific outcomes.

Objective: To achieve instance segmentation of upper aerodigestive tract (UADT) neoplasms using a deep learning (DL) algorithm, and to identify differences in its diagnostic performance in three different sites: larynx/hypopharynx, oral cavity and oropharynx. Methods: A total of 1034 endoscopic images from 323 patients were examined under narrow band imaging (NBI). The Mask R-CNN algorithm was used for the analysis. The dataset split was: 935 training, 48 validation and 51 testing images. Dice Similarity Coefficient (Dsc) was the main outcome measure. Results: Instance segmentation was effective in 76.5% of images. The mean Dsc was 0.90 ± 0.05. The algorithm correctly predicted 77.8%, 86.7% and 55.5% of lesions in the larynx/hypopharynx, oral cavity, and oropharynx, respectively. The mean Dsc was 0.90 ± 0.05 for the larynx/hypopharynx, 0.60 ± 0.26 for the oral cavity, and 0.81 ± 0.30 for the oropharynx. The analysis showed inferior diagnostic results in the oral cavity compared with the larynx/hypopharynx (p < 0.001). Conclusions: The study confirms the feasibility of instance segmentation of UADT using DL algorithms and shows inferior diagnostic results in the oral cavity compared with other anatomic areas.

A review on deep-learning algorithms for fetal ultrasound-image analysis.

Deep-learning (DL) algorithms are becoming the standard for processing ultrasound (US) fetal images. A number of survey papers in the field is today available, but most of them are focusing on a broader area of medical-image analysis or not covering all fetal US DL applications. This paper surveys the most recent work in the field, with a total of 153 research papers published after 2017. Papers are analyzed and commented from both the methodology and the application perspective. We categorized the papers into (i) fetal standard-plane detection, (ii) anatomical structure analysis and (iii) biometry parameter estimation. For each category, main limitations and open issues are presented. Summary tables are included to facilitate the comparison among the different approaches. In addition, emerging applications are also outlined. Publicly-available datasets and performance metrics commonly used to assess algorithm performance are summarized, too. This paper ends with a critical summary of the current state of the art on DL algorithms for fetal US image analysis and a discussion on current challenges that have to be tackled by researchers working in the field to translate the research methodology into actual clinical practice.

A deep learning approach to median nerve evaluation in ultrasound images of carpal tunnel inlet.

Ultrasound (US) imaging is recognized as a useful support for Carpal Tunnel Syndrome (CTS) assessment through the evaluation of median nerve morphology. However, US is still far to be systematically adopted to evaluate this common entrapment neuropathy, due to US intrinsic challenges, such as its operator dependency and the lack of standard protocols. To support sonographers, the present study proposes a fully-automatic deep learning approach to median nerve segmentation from US images. We collected and annotated a dataset of 246 images acquired in clinical practice involving 103 rheumatic patients, regardless of anatomical variants (bifid nerve, closed vessels). We developed a Mask R-CNN with two additional transposed layers at segmentation head to accurately segment the median nerve directly on transverse US images. We calculated the cross-sectional area (CSA) of the predicted median nerve. Proposed model achieved good performances both in median nerve detection and segmentation: Precision (Prec), Recall (Rec), Mean Average Precision (mAP) and Dice Similarity Coefficient (DSC) values are 0.916 ± 0.245, 0.938 ± 0.233, 0.936 ± 0.235 and 0.868 ± 0.201, respectively. The CSA values measured on true positive predictions were comparable with the sonographer manual measurements with a mean absolute error (MAE) of 0.918 mm2. Experimental results showed the potential of proposed model, which identified and segmented the median nerve section in normal anatomy images, while still struggling when dealing with infrequent anatomical variants. Future research will expand the dataset including a wider spectrum of normal anatomy and pathology to support sonographers in daily practice.

Artificial intelligence in clinical endoscopy: Insights in the field of videomics.

Artificial intelligence is being increasingly seen as a useful tool in medicine. Specifically, these technologies have the objective to extract insights from complex datasets that cannot easily be analyzed by conventional statistical methods. While promising results have been obtained for various -omics datasets, radiological images, and histopathologic slides, analysis of videoendoscopic frames still represents a major challenge. In this context, videomics represents a burgeoning field wherein several methods of computer vision are systematically used to organize unstructured data from frames obtained during diagnostic videoendoscopy. Recent studies have focused on five broad tasks with increasing complexity: quality assessment of endoscopic images, classification of pathologic and nonpathologic frames, detection of lesions inside frames, segmentation of pathologic lesions, and in-depth characterization of neoplastic lesions. Herein, we present a broad overview of the field, with a focus on conceptual key points and future perspectives.

Learning-Based Median Nerve Segmentation From Ultrasound Images For Carpal Tunnel Syndrome Evaluation.

Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy. Ultrasound imaging (US) may help to diagnose and assess CTS, through the evaluation of median nerve morphology. To support sonographers, this paper proposes a fully-automatic deep-learning approach to median nerve segmentation from US images. The approach relies on Mask R-CNN, a convolutional neural network that is trained end-to-end. The segmentation head of Mask R-CNN is here evaluated with three different configurations, with the goal of studying the effect of the segmentation-head output resolution on the overall Mask R-CNN segmentation performance. For this study, we collected and annotated a dataset of 151 images acquired in the actual clinical practice from 53 subjects with CTS. To our knowledge, this is the largest dataset in the field in terms of subjects. We achieved a median Dice similarity coefficient equal to 0.931 (IQR = 0.027), demonstrating the potentiality of the proposed approach. These results are a promising step towards providing an effective tool for CTS assessment in the actual clinical practice.