RESUMO
PURPOSE: Using machine learning, we developed a proprietary ultrasound software called the Spine Level Identification (SLIDE) system, which automatically identifies lumbar landmarks in real time as the operator slides the transducer over the lumber spine. Here, we assessed the agreement between SLIDE and manual palpation and traditional lumbar ultrasound (LUS) for determining the primary target L3-4 interspace. METHODS: Upon institutional ethics approval and informed consent, 76 healthy term parturients scheduled for elective Caesarean delivery were recruited. The L3-4 interspace was identified by manual palpation and then by the SLIDE method. The reference standard was located using traditional LUS by an experienced operator. The primary outcome was the L3-4 interspace identification agreement of manual palpation and SLIDE with the reference standard, as percentage agreement and Gwet's agreement coefficient (AC1). RESULTS: The raw agreement was 70% with Gwet's agreement coefficient (AC1) = 0.59 (95% confidence interval [CI], 0.41 to 0.77) for manual palpation and 84% with Gwet's AC1 = 0.82 (95% CI, 0.70 to 0.93) for SLIDE. When the levels differ from the reference, the manual palpation method identified L2-3 more often than L4-5 while the SLIDE method identified equally above or below L3-4. The SLIDE system had greater agreement than palpation in locating L3-4 and all other lumber interspaces after controlling for body mass index (adjusted odds ratio, 2.99; 95% CI, 1.21 to 8.7; P = 0.02). CONCLUSION: The SLIDE system had higher agreement with traditional ultrasound than manual palpation did in identifying L3-4 and all other lumber interspaces after adjusting for BMI in healthy term obstetric patients. Future studies should examine factors that affect agreement and ways to improve SLIDE for clinical integration. STUDY REGISTRATION: www. CLINICALTRIALS: gov (NCT02982317); registered 5 December 2016.
RéSUMé: OBJECTIF: À l'aide de l'apprentissage automatique, nous avons développé un logiciel d'échographie propriétaire appelé SLIDE (pour Spine Level Identification, c.-à-d. système d'identification du niveau vertébral), qui identifie automatiquement les points de repère lombaires en temps réel lorsque l'opérateur fait passer le transducteur sur la colonne lombaire. Ici, nous avons évalué l'agrément entre le SLIDE et la palpation manuelle et l'échographie lombaire traditionnelle pour déterminer l'espace intervertébral cible principal L3L4. MéTHODE: Après avoir obtenu l'approbation du comité d'éthique de l'établissement et le consentement éclairé, 76 parturientes en bonne santé et à terme devant bénéficier d'un accouchement par césarienne programmée ont été recrutées. L'espace intervertébral L3L4 a été identifié par palpation manuelle puis avec le logiciel SLIDE. L'étalon de référence a été localisé à l'aide d'une échographie lombaire traditionnelle par un opérateur expérimenté. Le critère d'évaluation principal était l'agrément entre l'identification de l'espace intervertébral L3L4 par palpation manuelle et par logiciel SLIDE avec l'étalon de référence, en pourcentage d'agrément et coefficient d'agrément de Gwet (CA1). RéSULTATS: L'agrément brut était de 70 % avec le coefficient d'agrément de Gwet (CA1) = 0,59 (intervalle de confiance [IC] à 95 %, 0,41 à 0,77) pour la palpation manuelle et de 84 % avec le CA1 de Gwet = 0,82 (IC 95 %, 0,70 à 0,93) pour le logiciel SLIDE. Lorsque les niveaux lombaires différaient de la référence, la méthode de palpation manuelle a identifié L2L3 plus souvent que L4L5, tandis que la méthode SLIDE a identifié les vertèbres supérieures ou inférieures à L3L4 de manière égale. Le système SLIDE a affiché un agrément plus important que la palpation pour localiser L3L4 et tous les autres espaces intervertébraux lombaires après ajustement pour tenir compte de l'indice de masse corporelle (rapport de cotes ajusté, 2,99; IC 95 %, 1,21 à 8,7; P = 0,02). CONCLUSION: Le système SLIDE avait affiché un agrément plus élevé avec l'échographie traditionnelle que la palpation manuelle pour identifier le niveau L3L4 et tous les autres espaces intervertébraux lombaires après ajustement pour tenir compte de l'IMC chez les patientes obstétricales à terme en bonne santé. Une étude future devrait examiner les facteurs qui affectent l'agrément et les moyens d'améliorer le logiciel SLIDE pour une intégration clinique. ENREGISTREMENT DE L'éTUDE: www.clinicaltrials.gov (NCT02982317); enregistrée le 5 décembre 2016.
Assuntos
Região Lombossacral , Palpação , Feminino , Humanos , Vértebras Lombares/diagnóstico por imagem , Palpação/métodos , Gravidez , Software , Coluna Vertebral , UltrassonografiaRESUMO
In the midst of the COVID-19 pandemic, unprecedented pressure has been added to healthcare systems around the globe. Imaging is a crucial component in the management of COVID-19 patients. Point-of-care ultrasound (POCUS) such as hand-carried ultrasound emerges in the COVID-19 era as a tool that can simplify the imaging process of COVID-19 patients, and potentially reduce the strain on healthcare providers and healthcare resources. The preliminary evidence available suggests an increasing role of POCUS in diagnosing, monitoring, and risk-stratifying COVID-19 patients. This scoping review aims to delineate the challenges in imaging COVID-19 patients, discuss the cardiopulmonary complications of COVID-19 and their respective sonographic findings, and summarize the current data and recommendations available. There is currently a critical gap in knowledge in the role of POCUS in the COVID-19 era. Nonetheless, it is crucial to summarize the current preliminary data available in order to help fill this gap in knowledge for future studies.
Assuntos
COVID-19/diagnóstico , Pulmão/diagnóstico por imagem , Pandemias , Sistemas Automatizados de Assistência Junto ao Leito/normas , Ultrassonografia/métodos , COVID-19/epidemiologia , HumanosRESUMO
PURPOSE: Optimizing patient position and needle puncture site are important factors for successful neuraxial anesthesia. Two paramedian approaches are commonly utilized and we sought to determine whether variations of the seated position would increase the chance of puncture success. METHODS: We simulated paramedian needle passes on three-dimensional lumbar spine models registered to volumetric ultrasound data acquired from ten healthy volunteers in three different positions: 1) prone; 2) seated with thoracic and lumbar flexion; and 3) seated as in position 2, but with a 10° dorsal tilt. Simulated paramedian needle passes from the right side performed on validated models were used to determine L2-3 and L3-4 neuraxial target size and success. We selected two paramedian puncture sites according to standard anesthesia textbook descriptions: 10 mm lateral and 10 mm caudal from inferior edge of the superior spinous process as described by Miller, and 10 mm lateral from the superior edge of the inferior spinous process as described by Barash. RESULTS: A significant increase in the area available for dural puncture was found in the L2-3 (61-62 mm2) and L3-4 (76-79 mm2) vertebral levels for all seated positions relative to the prone position (P < 0.001). Similarly, a significant increase in the total number of successful punctures was found in the L2-3 (77-79) and L3-4 (119-120) vertebral levels for all seated positions relative to the prone position (P < 0.001). No differences were found between seated positions. The Barash puncture site achieved a higher number of successful punctures than the Miller puncture site in both the L2-3 (19) and L3-4 (84) vertebral levels (P < 0.001). CONCLUSION: An added dorsal table tilt did not increase puncture success in the seated position. The landmarks for puncture site described by Barash resulted in significantly more successful punctures compared with those described by Miller in all positions.
RéSUMé: OBJECTIF: L'optimisation de la position du patient et celle du site de ponction de l'aiguille sont des facteurs importants pour la réussite d'une anesthésie neuraxiale. Deux approches paramédianes sont fréquemment utilisées et nous avons tenté de déterminer si des variations de la position assise augmenteraient la probabilité de réussite de la ponction. MéTHODE: Nous avons simulé les passages paramédians de l'aiguille sur des modèles tridimensionnels de la colonne lombaire adaptés à partir de données d'échographie volumétriques acquises auprès de dix volontaires sains placés dans trois positions différentes : 1) couché sur le ventre; 2) assis en flexion thoraco-lombaire; et 3) assis comme en position 2, mais avec une inclinaison dorsale de 10°. Les passages paramédians simulés de l'aiguille du côté droit réalisés sur des modèles validés ont été utilisés pour déterminer la taille des cibles neuraxiales L23 et L34 ainsi que la réussite de la ponction. Nous avons sélectionné deux sites de ponction paramédians selon les descriptions de deux manuels d'anesthésie standard, soit 10 mm en latéral et 10 mm en caudal depuis le bord inférieur de l'apophyse épineuse supérieure tel que décrit par celui de Miller, et 10 mm en latéral depuis le bord supérieur de l'apophyse épineuse inférieure, tel que décrit par celui de Barash. RéSULTATS: Une augmentation significative de la surface disponible pour la ponction durale a été observée aux niveaux vertébraux L23 (6162 mm2) et L34 (7679 mm2) dans les deux positions assises par rapport à la position ventrale (P < 0,001). De la même manière, nous avons observé une augmentation significative du nombre total de ponctions durales réussies aux niveaux vertébraux L23 (7779) et L34 (119120) dans les deux positions assises par rapport à la position ventrale (P < 0,001). Aucune différence n'a été observée entre les deux positions assises. Le site de ponction selon le manuel de Barash a permis la réalisation d'un nombre plus élevé de ponctions réussies que le site de ponction selon celui de Miller, tant au niveau vertébral L23 (19) qu'au niveau L34 (84) (P < 0,001). CONCLUSION: L'ajout d'une inclinaison du plan dorsal n'a pas augmenté le taux de réussite de la ponction en position assise. Les repères utilisés pour le site de ponction décrits par le manuel de Barash ont entraîné un nombre significativement plus élevé de ponctions réussies que ceux décrits par celui de Miller, toutes positions confondues.
Assuntos
Raquianestesia , Voluntários Saudáveis , Humanos , Vértebras Lombares/diagnóstico por imagem , Região Lombossacral/diagnóstico por imagem , Sistema de Registros , UltrassonografiaRESUMO
In photoacoustic tomography (PAT), delivering high energy pulses through optical fiber is critical for achieving high quality imaging. A fiber coupling scheme with a beam homogenizer is demonstrated for coupling high energy pulses in a single multimode fiber. This scheme can benefit PAT applications that require miniaturized illumination or internal illumination with a small fiber. The beam homogenizer is achieved by using a cross cylindrical lens array, which provides a periodic spatial modulation on the phase of the input light. Thus the lens array acts as a phase grating which diffracts the beam into a 2D diffraction pattern. Both theoretical analysis and experiments demonstrate that the focused beam can be split into a 2D spot array that can reduce the peak power on the fiber tip surface and thus enhance the coupling performance. The theoretical analysis of the intensity distribution of the focused beam is carried out by Fourier optics. In experiments, coupled energy at 48 mJ/pulse and 60 mJ/pulse have been achieved and the corresponding coupling efficiency is 70% and 90% in a 1000-µm and a 1500-µm-core-diameter fiber, respectively. The high energy pulses delivered by the multimode fiber are further tested for PAT imaging in phantoms. PAT imaging of a printed dot array shows a large illumination area of 7 cm2 under 5 mm thick chicken breast tissue. In vivo imaging is also demonstrated on the human forearm. The large improvement in coupling energy can potentially benefit PAT with single fiber delivery to achieve large area imaging and deep penetration detection.
RESUMO
Although commercial linear array transducers are widely used in clinical ultrasound, their application in photoacoustic tomography (PAT) is still limited due to the limited-view problem that restricts the image quality. In this paper, we propose a simple approach to address the limited-view problem in 2D by using two linear array transducers to receive PAT signal from different orientations. The positions of the two transducers can be adjusted to fit the specific geometry of an imaging site. This approach is made possible by using a new calibration method, where the relative position between the two transducers can be calibrated using ultrasound by transmitting ultrasound wave with one transducer while receiving with the other. The calibration results are then applied in the subsequent PAT imaging to incorporate the detected acoustic signals from both transducers and thereby increase the detection view. In this calibration method, no calibration phantom is required which largely simplifies and shortens the process. The efficacy of the calibration and improvement on the PAT image quality are demonstrated through phantom studies and in vivo imaging.
RESUMO
The Insight Segmentation and Registration Toolkit (ITK) is a software library used for image analysis, visualization, and image-guided surgery applications. ITK is a collection of C++ classes that poses the challenge of a steep learning curve should the user not have appropriate C++ programming experience. To remove the programming complexities and facilitate rapid prototyping, an implementation of ITK within a higher-level visual programming environment is presented: SimITK. ITK functionalities are automatically wrapped into "blocks" within Simulink, the visual programming environment of MATLAB, where these blocks can be connected to form workflows: visual schematics that closely represent the structure of a C++ program. The heavily templated C++ nature of ITK does not facilitate direct interaction between Simulink and ITK; an intermediary is required to convert respective data types and allow intercommunication. As such, a SimITK "Virtual Block" has been developed that serves as a wrapper around an ITK class which is capable of resolving the ITK data types to native Simulink data types. Part of the challenge surrounding this implementation involves automatically capturing and storing the pertinent class information that need to be refined from an initial state prior to being reflected within the final block representation. The primary result from the SimITK wrapping procedure is multiple Simulink block libraries. From these libraries, blocks are selected and interconnected to demonstrate two examples: a 3D segmentation workflow and a 3D multimodal registration workflow. Compared to their pure-code equivalents, the workflows highlight ITK usability through an alternative visual interpretation of the code that abstracts away potentially confusing technicalities.
Assuntos
Diagnóstico por Imagem , Processamento de Imagem Assistida por Computador/métodos , Software , Algoritmos , Humanos , Imageamento Tridimensional , Aplicações da Informática Médica , Integração de Sistemas , Interface Usuário-ComputadorRESUMO
In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. However, catastrophic forgetting occurs, decreasing the performance of earlier classes when adapting the model to new data. Prior proposed methodologies to overcome this require perpetual storage of previous samples, posing potential practical concerns regarding privacy and storage regulations in healthcare. To this end, we propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes. Our key contributions include acquiring synthetic data known as Continual Class-Specific Impression (CCSI) for previously inaccessible trained classes and presenting a methodology to effectively utilize this data for updating networks when introducing new classes. We obtain CCSI by employing data inversion over gradients of the trained classification model on previous classes starting from the mean image of each class inspired by common landmarks shared among medical images and utilizing continual normalization layers statistics as a regularizer in this pixel-wise optimization process. Subsequently, we update the network by combining the synthesized data with new class data and incorporate several losses, including an intra-domain contrastive loss to generalize the deep network trained on the synthesized data to real data, a margin loss to increase separation among previous classes and new ones, and a cosine-normalized cross-entropy loss to alleviate the adverse effects of imbalanced distributions in training data. Extensive experiments show that the proposed framework achieves state-of-the-art performance on four of the public MedMNIST datasets and in-house echocardiography cine series, with an improvement in classification accuracy of up to 51% compared to baseline data-free methods. Our code is available at https://github.com/ubc-tea/Continual-Impression-CCSI.
Assuntos
Aprendizado Profundo , Humanos , Algoritmos , Interpretação de Imagem Assistida por Computador/métodosRESUMO
PURPOSE: Deep learning-based analysis of micro-ultrasound images to detect cancerous lesions is a promising tool for improving prostate cancer (PCa) diagnosis. An ideal model should confidently identify cancer while responding with appropriate uncertainty when presented with out-of-distribution inputs that arise during deployment due to imaging artifacts and the biological heterogeneity of patients and prostatic tissue. METHODS: Using micro-ultrasound data from 693 patients across 5 clinical centers who underwent micro-ultrasound guided prostate biopsy, we train and evaluate convolutional neural network models for PCa detection. To improve robustness to out-of-distribution inputs, we employ and comprehensively benchmark several state-of-the-art uncertainty estimation methods. RESULTS: PCa detection models achieve performance scores up to 76 % average AUROC with a 10-fold cross validation setup. Models with uncertainty estimation obtain expected calibration error scores as low as 2 % , indicating that confident predictions are very likely to be correct. Visualizations of the model output demonstrate that the model correctly identifies healthy versus malignant tissue. CONCLUSION: Deep learning models have been developed to confidently detect PCa lesions from micro-ultrasound. The performance of these models, determined from a large and diverse dataset, is competitive with visual analysis of magnetic resonance imaging, the clinical benchmark to identify PCa lesions for targeted biopsy. Deep learning with micro-ultrasound should be further studied as an avenue for targeted prostate biopsy.
Assuntos
Aprendizado Profundo , Neoplasias da Próstata , Humanos , Masculino , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/patologia , Neoplasias da Próstata/diagnóstico , Biópsia Guiada por Imagem/métodos , Ultrassonografia/métodos , Redes Neurais de Computação , Ultrassonografia de Intervenção/métodosRESUMO
PURPOSE: The standard of care for prostate cancer (PCa) diagnosis is the histopathological analysis of tissue samples obtained via transrectal ultrasound (TRUS) guided biopsy. Models built with deep neural networks (DNNs) hold the potential for direct PCa detection from TRUS, which allows targeted biopsy and subsequently enhances outcomes. Yet, there are ongoing challenges with training robust models, stemming from issues such as noisy labels, out-of-distribution (OOD) data, and limited labeled data. METHODS: This study presents LensePro, a unified method that not only excels in label efficiency but also demonstrates robustness against label noise and OOD data. LensePro comprises two key stages: first, self-supervised learning to extract high-quality feature representations from abundant unlabeled TRUS data and, second, label noise-tolerant prototype-based learning to classify the extracted features. RESULTS: Using data from 124 patients who underwent systematic prostate biopsy, LensePro achieves an AUROC, sensitivity, and specificity of 77.9%, 85.9%, and 57.5%, respectively, for detecting PCa in ultrasound. Our model shows it is effective for detecting OOD data in test time, critical for clinical deployment. Ablation studies demonstrate that each component of our method improves PCa detection by addressing one of the three challenges, reinforcing the benefits of a unified approach. CONCLUSION: Through comprehensive experiments, LensePro demonstrates its state-of-the-art performance for TRUS-based PCa detection. Although further research is necessary to confirm its clinical applicability, LensePro marks a notable advancement in enhancing automated computer-aided systems for detecting prostate cancer in ultrasound.
Assuntos
Redes Neurais de Computação , Neoplasias da Próstata , Humanos , Masculino , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/patologia , Neoplasias da Próstata/diagnóstico , Biópsia Guiada por Imagem/métodos , Sensibilidade e Especificidade , Ultrassonografia/métodos , Aprendizado Profundo , Ultrassonografia de Intervenção/métodosRESUMO
PURPOSE: Real-time assessment of surgical margins is critical for favorable outcomes in cancer patients. The iKnife is a mass spectrometry device that has demonstrated potential for margin detection in cancer surgery. Previous studies have shown that using deep learning on iKnife data can facilitate real-time tissue characterization. However, none of the existing literature on the iKnife facilitate the use of publicly available, state-of-the-art pretrained networks or datasets that have been used in computer vision and other domains. METHODS: In a new framework we call ImSpect, we convert 1D iKnife data, captured during basal cell carcinoma (BCC) surgery, into 2D images in order to capitalize on state-of-the-art image classification networks. We also use self-supervision to leverage large amounts of unlabeled, intraoperative data to accommodate the data requirements of these networks. RESULTS: Through extensive ablation studies, we show that we can surpass previous benchmarks of margin evaluation in BCC surgery using iKnife data, achieving an area under the receiver operating characteristic curve (AUC) of 81%. We also depict the attention maps of the developed DL models to evaluate the biological relevance of the embedding space CONCLUSIONS: We propose a new method for characterizing tissue at the surgical margins, using mass spectrometry data from cancer surgery.
Assuntos
Carcinoma Basocelular , Margens de Excisão , Espectrometria de Massas , Neoplasias Cutâneas , Humanos , Espectrometria de Massas/métodos , Carcinoma Basocelular/cirurgia , Carcinoma Basocelular/diagnóstico por imagem , Carcinoma Basocelular/patologia , Neoplasias Cutâneas/cirurgia , Neoplasias Cutâneas/diagnóstico por imagem , Aprendizado de Máquina Supervisionado , Aprendizado ProfundoRESUMO
BACKGROUND: Automated rhythm detection on echocardiography through artificial intelligence (AI) has yet to be fully realized. We propose an AI model trained to identify atrial fibrillation (AF) using apical 4-chamber (AP4) cines without requiring electrocardiogram (ECG) data. METHODS: Transthoracic echocardiography studies of consecutive patients ≥ 18 years old at our tertiary care centre were retrospectively reviewed for AF and sinus rhythm. The study was first interpreted by level III-trained echocardiography cardiologists as the gold standard for rhythm diagnosis based on ECG rhythm strip and imaging assessment, which was also verified with a 12-lead ECG around the time of the study. AP4 cines with three cardiac cycles were then extracted from these studies with the rhythm strip and Doppler information removed and introduced to the deep learning model ResNet(2+1)D with an 80:10:10 training-validation-test split ratio. RESULTS: 634 patient studies (1205 cines) were included. After training, the AI model achieved high accuracy on validation for detection of both AF and sinus rhythm (mean F1-score = 0.92; AUROC = 0.95). Performance was consistent on the test dataset (mean F1-score = 0.94, AUROC = 0.98) when using the cardiologist's assessment of the ECG rhythm strip as the gold standard, who had access to the full study and external ECG data, while the AI model did not. CONCLUSIONS: AF detection by AI on echocardiography without ECG appears accurate when compared to an echocardiography cardiologist's assessment of the ECG rhythm strip as the gold standard. This has potential clinical implications in point-of-care ultrasound and stroke risk stratification.
RESUMO
Left ventricular (LV) geometric patterns aid clinicians in the diagnosis and prognostication of various cardiomyopathies. The aim of this study is to assess the accuracy and reproducibility of LV dimensions and wall thickness using deep learning (DL) models. A total of 30,080 unique studies were included; 24,013 studies were used to train a convolutional neural network model to automatically assess, at end-diastole, LV internal diameter (LVID), interventricular septal wall thickness (IVS), posterior wall thickness (PWT), and LV mass. The model was trained to select end-diastolic frames with the largest LVID and to identify four landmarks, marking the dimensions of LVID, IVS, and PWT using manually labeled landmarks as reference. The model was validated with 3,014 echocardiographic cines and the accuracy of the model was evaluated with a test set of 3,053 echocardiographic cines. The model accurately measured LVID, IVS, PWT, and LV mass compared to study report values with a mean relative error of 5.40%, 11.73%, 12.76%, and 13.93%, respectively. The ð 2 of the model for the LVID, IVS, PWT, and the LV mass was 0.88, 0.63, 0.50, and 0.87, respectively. The novel DL model developed in this study was accurate for LV dimension assessment without the need to select end-diastolic frames manually. DL automated measurements of IVS and PWT were less accurate with greater wall thickness. Validation studies in larger and more diverse populations are ongoing.
RESUMO
BACKGROUND: Machine learning (ML) algorithms can accurately estimate left ventricular ejection fraction (LVEF) from echocardiography, but their performance on cardiac point-of-care ultrasound (POCUS) is not well understood. OBJECTIVES: We evaluate the performance of an ML model for estimation of LVEF on cardiac POCUS compared with Level III echocardiographers' interpretation and formal echo reported LVEF. METHODS: Clinicians at a tertiary care heart failure clinic prospectively scanned 138 participants using hand-carried devices. Video data were analyzed offline by an ML model for LVEF. We compared the ML model's performance with Level III echocardiographers' interpretation and echo reported LVEF. RESULTS: There were 138 participants scanned, yielding 1257 videos. The ML model generated LVEF predictions on 341 videos. We observed a good intraclass correlation (ICC) between the ML model's predictions and the reference standards (ICC = 0.77-0.84). When comparing LVEF estimates for randomized single POCUS videos, the ICC between the ML model and Level III echocardiographers' estimates was 0.772, and it was 0.778 for videos where quantitative LVEF was feasible. When the Level III echocardiographer reviewed all POCUS videos for a participant, the ICC improved to 0.794 and 0.843 when only accounting for studies that could be segmented. The ML model's LVEF estimates also correlated well with LVEF derived from formal echocardiogram reports (ICC = 0.798). CONCLUSION: Our results suggest that clinician-driven cardiac POCUS produces ML model LVEF estimates that correlate well with expert interpretation and echo reported LVEF.
RESUMO
Endometrial cancer (EC) has four molecular subtypes with strong prognostic value and therapeutic implications. The most common subtype (NSMP; No Specific Molecular Profile) is assigned after exclusion of the defining features of the other three molecular subtypes and includes patients with heterogeneous clinical outcomes. In this study, we employ artificial intelligence (AI)-powered histopathology image analysis to differentiate between p53abn and NSMP EC subtypes and consequently identify a sub-group of NSMP EC patients that has markedly inferior progression-free and disease-specific survival (termed 'p53abn-like NSMP'), in a discovery cohort of 368 patients and two independent validation cohorts of 290 and 614 from other centers. Shallow whole genome sequencing reveals a higher burden of copy number abnormalities in the 'p53abn-like NSMP' group compared to NSMP, suggesting that this group is biologically distinct compared to other NSMP ECs. Our work demonstrates the power of AI to detect prognostically different and otherwise unrecognizable subsets of EC where conventional and standard molecular or pathologic criteria fall short, refining image-based tumor classification. This study's findings are applicable exclusively to females.
Assuntos
Inteligência Artificial , Neoplasias do Endométrio , Humanos , Feminino , Neoplasias do Endométrio/patologia , Neoplasias do Endométrio/genética , Pessoa de Meia-Idade , Idoso , Processamento de Imagem Assistida por Computador/métodos , Prognóstico , Variações do Número de Cópias de DNA , Sequenciamento Completo do Genoma , Proteína Supressora de Tumor p53/genética , Estudos de CoortesRESUMO
Deep learning-based analysis of high-frequency, high-resolution micro-ultrasound data shows great promise for prostate cancer (PCa) detection. Previous approaches to analysis of ultrasound data largely follow a supervised learning (SL) paradigm. Ground truth labels for ultrasound images used for training deep networks often include coarse annotations generated from the histopathological analysis of tissue samples obtained via biopsy. This creates inherent limitations on the availability and quality of labeled data, posing major challenges to the success of SL methods. However, unlabeled prostate ultrasound data are more abundant. In this work, we successfully apply self-supervised representation learning to micro-ultrasound data. Using ultrasound data from 1028 biopsy cores of 391 subjects obtained in two clinical centers, we demonstrate that feature representations learned with this method can be used to classify cancer from noncancer tissue, obtaining an AUROC score of 91% on an independent test set. To the best of our knowledge, this is the first successful end-to-end self-SL (SSL) approach for PCa detection using ultrasound data. Our method outperforms baseline SL approaches, generalizes well between different data centers, and scales well in performance as more unlabeled data are added, making it a promising approach for future research using large volumes of unlabeled data. Our code is publicly available at https://www.github.com/MahdiGilany/SSL_micro_ultrasound.
Assuntos
Próstata , Neoplasias da Próstata , Masculino , Humanos , Próstata/diagnóstico por imagem , Neoplasias da Próstata/diagnóstico por imagem , Ultrassonografia/métodos , Aprendizado de Máquina SupervisionadoRESUMO
PURPOSE: A large body of previous machine learning methods for ultrasound-based prostate cancer detection classify small regions of interest (ROIs) of ultrasound signals that lie within a larger needle trace corresponding to a prostate tissue biopsy (called biopsy core). These ROI-scale models suffer from weak labeling as histopathology results available for biopsy cores only approximate the distribution of cancer in the ROIs. ROI-scale models do not take advantage of contextual information that are normally considered by pathologists, i.e., they do not consider information about surrounding tissue and larger-scale trends when identifying cancer. We aim to improve cancer detection by taking a multi-scale, i.e., ROI-scale and biopsy core-scale, approach. METHODS: Our multi-scale approach combines (i) an "ROI-scale" model trained using self-supervised learning to extract features from small ROIs and (ii) a "core-scale" transformer model that processes a collection of extracted features from multiple ROIs in the needle trace region to predict the tissue type of the corresponding core. Attention maps, as a by-product, allow us to localize cancer at the ROI scale. RESULTS: We analyze this method using a dataset of micro-ultrasound acquired from 578 patients who underwent prostate biopsy, and compare our model to baseline models and other large-scale studies in the literature. Our model shows consistent and substantial performance improvements compared to ROI-scale-only models. It achieves [Formula: see text] AUROC, a statistically significant improvement over ROI-scale classification. We also compare our method to large studies on prostate cancer detection, using other imaging modalities. CONCLUSIONS: Taking a multi-scale approach that leverages contextual information improves prostate cancer detection compared to ROI-scale-only models. The proposed model achieves a statistically significant improvement in performance and outperforms other large-scale studies in the literature. Our code is publicly available at www.github.com/med-i-lab/TRUSFormer .
Assuntos
Próstata , Neoplasias da Próstata , Masculino , Humanos , Próstata/diagnóstico por imagem , Próstata/patologia , Biópsia Guiada por Imagem/métodos , Neoplasias da Próstata/diagnóstico por imagem , Neoplasias da Próstata/patologia , Ultrassonografia/métodos , PelveRESUMO
We sought to determine the cardiac ultrasound view of greatest quality using a machine learning (ML) approach on a cohort of transthoracic echocardiograms (TTE) with abnormal left ventricular (LV) systolic function. We utilize an ML model to determine the TTE view of highest quality when scanned by sonographers. A random sample of TTEs with reported LV dysfunction from 09/25/2017-01/15/2019 were downloaded from the regional database. Component video files were analyzed using ML models that jointly classified view and image quality. The model consisted of convolutional layers for extracting spatial features and Long Short-term Memory units to temporally aggregate the frame-wise spatial embeddings. We report the view-specific quality scores for each TTE. Pair-wise comparisons amongst views were performed with Wilcoxon signed-rank test. Of 1,145 TTEs analyzed by the ML model, 74.5% were from males and mean LV ejection fraction was 43.1 ± 9.9%. Maximum quality score was best for the apical 4 chamber (AP4) view (70.6 ± 13.9%, p<0.001 compared to all other views) and worst for the apical 2 chamber (AP2) view (60.4 ± 15.4%, p<0.001 for all views except parasternal short-axis view at mitral/papillary muscle level, PSAX M/PM). In TTEs scanned by professional sonographers, the view with greatest ML-derived quality was the AP4 view.
Assuntos
Ecocardiografia , Disfunção Ventricular Esquerda , Masculino , Humanos , Valor Preditivo dos Testes , Ecocardiografia/métodos , Disfunção Ventricular Esquerda/diagnóstico por imagem , Função Ventricular Esquerda/fisiologia , Volume Sistólico , Aprendizado de MáquinaRESUMO
BACKGROUND: There is limited data on the residual echocardiographic findings including strain analysis among post-coronavirus disease (COVID) patients. The aim of our study is to prospectively phenotype post-COVID patients. METHODS: All patients discharged following acute COVID infection were systematically followed in the post-COVID-19 Recovery Clinic at Vancouver General Hospital and St. Paul's Hospital. At 4-18 weeks post diagnosis, patients underwent comprehensive echocardiographic assessment. Left ventricular ejection fraction (LVEF) was assessed by 3D, 2D Biplane Simpson's, or visual estimate. LV global longitudinal strain (GLS) was measured using a vendor-independent 2D speckle-tracking software (TomTec). RESULTS: A total of 127 patients (53% female, mean age 58 years) were included in our analyses. At baseline, cardiac conditions were present in 58% of the patients (15% coronary artery disease, 4% heart failure, 44% hypertension, 10% atrial fibrillation) while the remainder were free of cardiac conditions. COVID-19 serious complications were present in 79% of the patients (76% pneumonia, 37% intensive care unit admission, 21% intubation, 1% myocarditis). Normal LVEF was seen in 96% of the cohort and 97% had normal right ventricular systolic function. A high proportion (53%) had abnormal LV GLS defined as < 18%. Average LV GLS of septal and inferior segments were lower compared to that of other segments. Among patients without pre-existing cardiac conditions, LVEF was abnormal in only 1.9%, but LV GLS was abnormal in 46% of the patients. CONCLUSIONS: Most post-COVID patients had normal LVEF at 4-18 weeks post diagnosis, but over half had abnormal LV GLS.
RESUMO
Lung ultrasound (LUS) is an important imaging modality used by emergency physicians to assess pulmonary congestion at the patient bedside. B-line artifacts in LUS videos are key findings associated with pulmonary congestion. Not only can the interpretation of LUS be challenging for novice operators, but visual quantification of B-lines remains subject to observer variability. In this work, we investigate the strengths and weaknesses of multiple deep learning approaches for automated B-line detection and localization in LUS videos. We curate and publish, BEDLUS, a new ultrasound dataset comprising 1,419 videos from 113 patients with a total of 15,755 expert-annotated B-lines. Based on this dataset, we present a benchmark of established deep learning methods applied to the task of B-line detection. To pave the way for interpretable quantification of B-lines, we propose a novel "single-point" approach to B-line localization using only the point of origin. Our results show that (a) the area under the receiver operating characteristic curve ranges from 0.864 to 0.955 for the benchmarked detection methods, (b) within this range, the best performance is achieved by models that leverage multiple successive frames as input, and (c) the proposed single-point approach for B-line localization reaches an F 1-score of 0.65, performing on par with the inter-observer agreement. The dataset and developed methods can facilitate further biomedical research on automated interpretation of lung ultrasound with the potential to expand the clinical utility.
Assuntos
Aprendizado Profundo , Edema Pulmonar , Humanos , Pulmão/diagnóstico por imagem , Ultrassonografia/métodos , Edema Pulmonar/diagnóstico , TóraxRESUMO
PURPOSE: Fusion of intraprocedure ultrasound and preprocedure CT data is proposed for guidance in percutaneous spinal injections, a common procedure for pain management. CT scan of the lumbar spine is usually collected in a supine position, whereas spinal injections are performed in prone or sitting positions. This leads to a difference in the spine curvature between CT and ultrasound images; as such, a single-body rigid registration approach cannot be used for the whole lumbar vertebrae. METHODS: To compensate for the difference in the spinal curvature between the two imaging modalities, a multibody rigid registration algorithm is presented. The approach utilizes a point-based registration technique based on the unscented Kalman filter (UKF), taking as input segmented vertebrae surfaces in both CT and ultrasound data. Ultrasound images are automatically segmented using a dynamic programming method, while the CT images are semiautomatically segmented using thresholding. The registration approach is designed to simultaneously align individual groups of points segmented from each vertebra in the two imaging modalities. A biomechanical model is developed to constrain the vertebrae transformation parameters during the registration and to ensure convergence. RESULTS: The proposed methodology is evaluated on human spine phantoms and a sheep cadaver. Registrations on phantom data have a mean target registration error (TRE) of 1.99 mm in the region of interest and converged in 87% of cases. Registrations on sheep cadaver have a mean target registration error of 2.2 mm and converged in 82% of cases. CONCLUSIONS: The proposed technique can robustly and simultaneously register several vertebrae extracted from CT images to the ultrasound volumes. The registration error below 2.2 mm is sufficient for most spinal injections.