Image-based Diagnosis Research Articles

A case series of percutaneous transforamen ovale biopsies in cavernous sinus lesions.

The majority of cavernous sinus lesions are meningiomas, for which treatment (fractioned radiotherapy or radiosurgery), if indicated, is usually initiated upon image-based diagnosis. However, this region can be affected by a wide variety of pathological processes and the risk of misdiagnosis exists. As pathological diagnosis can be obtained by biopsy through the foramen ovale in selected cases, we asked the question as to whether systematically performing this procedure before treatment would provide additional, relevant diagnostic information. All the cases referred to our department between January 2008 and December 2019 for cavernous sinus lesions that were considered for treatment and anatomically suitable for transforamen ovale biopsy were included. Outcomes and subsequent treatment or follow-up data were collected. Thirty-five patients were included. Twenty-six were highly suspected to have meningioma or schwannoma at imaging, among whom biopsy allowed diagnosis confirmation in 17 cases (65%).For the nine patients for whom biopsy was indicated upon suspected malignancy or inflammatory disease on imaging, biopsy revealed three meningiomas and one lymphoma and was not contributory in five cases (56%), three of which underwent open surgery. Three patients (8.5%) had persistent neuralgia at the last follow-up. When cavernous sinus meningioma or schwannoma is highly suspected upon predefined imaging criteria by an experienced neuroradiologist, invasive exploration before treatment does not seem to be indicated. Otherwise, transforamen ovale biopsy might be consider in selected cases as a minimally invasive option to obtain pathological analysis.

Machine learning for medical imaging-based COVID-19 detection and diagnosis.

The novel coronavirus disease 2019 (COVID‐19) is considered to be a significant health challenge worldwide because of its rapid human‐to‐human transmission, leading to a rise in the number of infected people and deaths. The detection of COVID‐19 at the earliest stage is therefore of paramount importance for controlling the pandemic spread and reducing the mortality rate. The real‐time reverse transcription‐polymerase chain reaction, the primary method of diagnosis for coronavirus infection, has a relatively high false negative rate while detecting early stage disease. Meanwhile, the manifestations of COVID‐19, as seen through medical imaging methods such as computed tomography (CT), radiograph (X‐ray), and ultrasound imaging, show individual characteristics that differ from those of healthy cases or other types of pneumonia. Machine learning (ML) applications for COVID‐19 diagnosis, detection, and the assessment of disease severity based on medical imaging have gained considerable attention. Herein, we review the recent progress of ML in COVID‐19 detection with a particular focus on ML models using CT and X‐ray images published in high‐ranking journals, including a discussion of the predominant features of medical imaging in patients with COVID‐19. Deep Learning algorithms, particularly convolutional neural networks, have been utilized widely for image segmentation and classification to identify patients with COVID‐19 and many ML modules have achieved remarkable predictive results using datasets with limited sample sizes.

Congenital Obstructive Müllerian Anomaly: The Pitfalls of a Magnetic Resonance Imaging-Based Diagnosis and the Importance of Intraoperative Biopsy.

A retrospective cohort study of the concordance between the magnetic resonance imaging (MRI) diagnosis and final diagnosis in patients with Müllerian duct anomalies (MDAs) was conducted, and diagnostic clues were suggested. A total of 463 cases of young women who underwent pelvic MRIs from January 1995 to February 2019 at Seoul Asan Medical Center were reviewed. Interventions consisted of clinical examinations, abdominal or transvaginal/rectal ultrasound, MRI, and operative procedures, including hysteroscopy and laparoscopy. The concordance of the diagnosis between the results obtained with MRI and those obtained with surgeries was evaluated. It was found that a total of 225 cases (48.6%) showed genital tract anomalies on MRI. Among them, 105 cases (46.7%) underwent reconstructive surgery. Nineteen cases (8.4%) revealed discrepancies between the final diagnosis after surgery and the initial MRI findings and eleven cases (57.9%) had cervical anomalies. Incorrect findings associated with the MRIs were particularly evident in biopsied cases of cervical dysgenesis. A combination of physical examination, ultrasound, and MRI is suitable for preoperative work-up in the diagnoses of congenital obstructive anomalies. However, it is recommended that a pathologic confirmation of tissue at the caudal leading edge be made in obstructive genital anomalies, in cases of presumptive vaginal or cervical dysgenesis.

Detection of liver cirrhosis in standard T2-weighted MRI using deep transfer learning

ObjectivesTo investigate the diagnostic performance of deep transfer learning (DTL) to detect liver cirrhosis from clinical MRI.MethodsThe dataset for this retrospective analysis consisted of 713 (343 female) patients who underwent liver MRI between 2017 and 2019. In total, 553 of these subjects had a confirmed diagnosis of liver cirrhosis, while the remainder had no history of liver disease. T2-weighted MRI slices at the level of the caudate lobe were manually exported for DTL analysis. Data were randomly split into training, validation, and test sets (70%/15%/15%). A ResNet50 convolutional neural network (CNN) pre-trained on the ImageNet archive was used for cirrhosis detection with and without upstream liver segmentation. Classification performance for detection of liver cirrhosis was compared to two radiologists with different levels of experience (4th-year resident, board-certified radiologist). Segmentation was performed using a U-Net architecture built on a pre-trained ResNet34 encoder. Differences in classification accuracy were assessed by the χ2-test.ResultsDice coefficients for automatic segmentation were above 0.98 for both validation and test data. The classification accuracy of liver cirrhosis on validation (vACC) and test (tACC) data for the DTL pipeline with upstream liver segmentation (vACC = 0.99, tACC = 0.96) was significantly higher compared to the resident (vACC = 0.88, p < 0.01; tACC = 0.91, p = 0.01) and to the board-certified radiologist (vACC = 0.96, p < 0.01; tACC = 0.90, p < 0.01).ConclusionThis proof-of-principle study demonstrates the potential of DTL for detecting cirrhosis based on standard T2-weighted MRI. The presented method for image-based diagnosis of liver cirrhosis demonstrated expert-level classification accuracy.Key Points• A pipeline consisting of two convolutional neural networks (CNNs) pre-trained on an extensive natural image database (ImageNet archive) enables detection of liver cirrhosis on standard T2-weighted MRI.• High classification accuracy can be achieved even without altering the pre-trained parameters of the convolutional neural networks.• Other abdominal structures apart from the liver were relevant for detection when the network was trained on unsegmented images.

The use of artificial intelligence for the diagnosis of bladder cancer: a review and perspectives.

White light cystoscopy is the current standard for primary diagnosis and surveillance of bladder cancer. However, cancer changes can be subtle and may be easily missed. With the advancement of deep learning (DL), image recognition by artificial intelligence (AI) proves a high accuracy for image-based diagnosis. AI can be a solution to enhance bladder cancer diagnosis on cystoscopy. An algorithm that classifies cystoscopic images into normal and tumour images is essential for AI cystoscopy. To develop this AI-based system requires a training dataset, an appropriate type of DL algorithm for the learning process and a specific outcome classification. A large data volume with minimal class imbalance, data accuracy and representativeness are pre-requisite for a good dataset. Algorithms developed during the past two years to detect bladder tumour achieved high performance with a pooled sensitivity of 89.7% and specificity of 96.1%. The area under the curve ranged from 0.960 to 0.980, and the accuracy ranged from 85.6 to 96.9%. There were also favourable results in the various attempts to enhance detection of flat lesions or carcinoma-in-situ. AI cystoscopy is a possible solution in clinical practice to enhance bladder cancer diagnosis, improve tumour clearance during transurethral resection of bladder tumour and detect recurrent tumours upon surveillance.

Artificial intelligence in medicine and gynecology-the wrong track or promise of cure?

Künstliche Intelligenz (KI) hat in den letzten Jahren eine neue Reifephase erreicht und entwickelt sich zum Treiber der Digitalisierung in allen Lebensbereichen. Die KI ist eine Querschnittstechnologie, die für alle Bereiche der Medizin mit Bild‑, Text- und Biodaten von großer Bedeutung ist. Es gibt keinen medizinischen Bereich, der nicht von KI beeinflusst werden wird. Dabei spielt die klinische Entscheidungsunterstützung eine wichtige Rolle. KI-Methoden etablieren sich gerade beim medizinischen Workflow-Management und bei der Vorhersage des Behandlungserfolgs bzw. des Behandlungsergebnisses. KI-Systeme können bereits in Bilddiagnose und im Patientenmanagement unterstützen, aber keine kritischen Entscheidungen vorschlagen. Die jeweiligen Präventions- oder Therapiemaßnahmen können mit KI-Unterstützung sinnvoller bewertet werden, allerdings ist die Abdeckung der Krankheiten noch viel zu gering, um robuste Systeme für den klinischen Alltag zu erstellen. Der flächendeckende Einsatz setzt Fortbildungsmaßnahmen für Ärzte voraus, um die Entscheidung treffen zu können, wann auf automatische Entscheidungsunterstützung vertraut werden kann.

A Visually Interpretable Deep Learning Framework for Histopathological Image-Based Skin Cancer Diagnosis.

Owing to the high incidence rate and the severe impact of skin cancer, the precise diagnosis of malignant skin tumors is a significant goal, especially considering treatment is normally effective if the tumor is detected early. Limited published histopathological image sets and the lack of an intuitive correspondence between the features of lesion areas and a certain type of skin cancer pose a challenge to the establishment of high-quality and interpretable computer-aided diagnostic (CAD) systems. To solve this problem, a light-weight attention mechanism-based deep learning framework, namely, DRANet, is proposed to differentiate 11 types of skin diseases based on a real histopathological image set collected by us during the last 10 years. The CAD system can output not only the name of a certain disease but also a visualized diagnostic report showing possible areas related to the disease. The experimental results demonstrate that the DRANet obtains significantly better performance than baseline models (i.e., InceptionV3, ResNet50, VGG16, and VGG19) with comparable parameter size and competitive accuracy with fewer model parameters. Visualized results produced by the hidden layers of the DRANet actually highlight part of the class-specific regions of diagnostic points and are valuable for decision making in the diagnosis of skin diseases.

Machine Learning Models for Image-Based Diagnosis and Prognosis of COVID-19: Systematic Review.

BackgroundAccurate and timely diagnosis and effective prognosis of the disease is important to provide the best possible care for patients with COVID-19 and reduce the burden on the health care system. Machine learning methods can play a vital role in the diagnosis of COVID-19 by processing chest x-ray images.ObjectiveThe aim of this study is to summarize information on the use of intelligent models for the diagnosis and prognosis of COVID-19 to help with early and timely diagnosis, minimize prolonged diagnosis, and improve overall health care.MethodsA systematic search of databases, including PubMed, Web of Science, IEEE, ProQuest, Scopus, bioRxiv, and medRxiv, was performed for COVID-19–related studies published up to May 24, 2020. This study was performed in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. All original research articles describing the application of image processing for the prediction and diagnosis of COVID-19 were considered in the analysis. Two reviewers independently assessed the published papers to determine eligibility for inclusion in the analysis. Risk of bias was evaluated using the Prediction Model Risk of Bias Assessment Tool.ResultsOf the 629 articles retrieved, 44 articles were included. We identified 4 prognosis models for calculating prediction of disease severity and estimation of confinement time for individual patients, and 40 diagnostic models for detecting COVID-19 from normal or other pneumonias. Most included studies used deep learning methods based on convolutional neural networks, which have been widely used as a classification algorithm. The most frequently reported predictors of prognosis in patients with COVID-19 included age, computed tomography data, gender, comorbidities, symptoms, and laboratory findings. Deep convolutional neural networks obtained better results compared with non–neural network–based methods. Moreover, all of the models were found to be at high risk of bias due to the lack of information about the study population, intended groups, and inappropriate reporting.ConclusionsMachine learning models used for the diagnosis and prognosis of COVID-19 showed excellent discriminative performance. However, these models were at high risk of bias, because of various reasons such as inadequate information about study participants, randomization process, and the lack of external validation, which may have resulted in the optimistic reporting of these models. Hence, our findings do not recommend any of the current models to be used in practice for the diagnosis and prognosis of COVID-19.

Neuropathological correlation supports automated image-based differential diagnosis in parkinsonism.

Up to 25% of patients diagnosed as idiopathic Parkinson's disease (IPD) have an atypical parkinsonian syndrome (APS). We had previously validated an automated image-based algorithm to discriminate between IPD, multiple system atrophy (MSA), and progressive supranuclear palsy (PSP). While the algorithm was accurate with respect to the final clinical diagnosis after long-term expert follow-up, its relationship to the initial referral diagnosis and to the neuropathological gold standard is not known. Patients with an uncertain diagnosis of parkinsonism were referred for 18F-fluorodeoxyglucose (FDG) PET to classify patients as IPD or as APS based on the automated algorithm. Patients were followed by a movement disorder specialist and subsequently underwent neuropathological examination. The image-based classification was compared to the neuropathological diagnosis in 15 patients with parkinsonism. At the time of referral to PET, the clinical impression was only 66.7% accurate. The algorithm correctly identified 80% of the cases as IPD or APS (p = 0.02) and 87.5% of the APS cases as MSA or PSP (p = 0.03). The final clinical diagnosis was 93.3% accurate (p < 0.001), but needed several years of expert follow-up. The image-based classifications agreed well with autopsy and can help to improve diagnostic accuracy during the period of clinical uncertainty.

A non-intrusive approach for fault detection and diagnosis of water distribution systems based on image sensors, audio sensors and an inspection robot

Fault diagnosis is important to maintain the normal operation of air-conditioning systems, reduce the energy consumption in buildings, and increase the service life of air-conditioning system equipment. We present a novel approach for fault detection and diagnosis system that relies on image and audio sensors and relevant algorithms.This paper proposes a fault diagnosis algorithm based on a robot that can automatically capture audio and image signals from microphone arrays and cameras during inspection in a chiller room. It includes audio- and image-based fault diagnosis algorithms. The validity of the algorithm combined with sensors is verified using data from actual equipment in a chiller room.The audio-based algorithm, which can monitor the abnormal sound of pumps to detect faults, utilizes Fourier transform, a finite impulse response digital filter, and an autoregressive integrated moving average model. We analyze the frequency domain of the pump signal and set the appropriate threshold to monitor abnormal signals based on the fitted model. Meanwhile, the image-based algorithms are divided into three sections to achieve three functions: 1) an AlexNet convolutional neural network is modified to classify the images of the chiller room equipment obtained by the visible light camera; 2) image morphology methods and trigonometric functions are used to read the dials’ indicators acquired by the visible light camera; and 3) optical character recognition is used to obtain the highest temperature value in the infrared image of the pump captured by the infrared camera, which helps maintenance staff verify the operation of the pump and detect faults as soon as possible.These diagnostic algorithms are non-intrusive, low cost, and easy to deploy. Combined with real-time data collection from the sensors on the robot, the algorithms can effectively improve the intelligence of the equipment room and allocate human resources more reasonably.

Harnessing X-Ray Energy-Dependent Attenuation of Bismuth-Based Nanoprobes for Accurate Diagnosis of Liver Fibrosis.

Timely detection of liver fibrosis by X‐ray computed tomography (CT) can prevent its progression to fatal liver diseases. However, it remains quite challenging because conventional CT can only identify the difference in density instead of X‐ray attenuation characteristics. Spectral CT can generate monochromatic imaging to specify X‐ray attenuation characteristics of the scanned matter. Herein, an X‐ray energy‐dependent attenuation strategy originated from bismuth (Bi)‐based nanoprobes (BiF3@PDA@HA) is proposed for the accurate diagnosis of liver fibrosis. Bi element in BiF3@PDA@HA can exhibit characteristic attenuation depending on different levels of X‐ray energy via spectral CT, and that is challenging for conventional CT. In this study, selectively accumulating BiF3@PDA@HA nanoprobes in the hepatic fibrosis areas can significantly elevate CT value for 40 Hounsfield units on 70 keV monochromatic images, successfully differentiating from healthy livers and achieving the diagnosis of liver fibrosis. Furthermore, the enhancement produced by the BiF3@PDA@HA nanoprobes in vivo increases as the monochromatic energy decreases from 70 to 40 keV, optimizing the conspicuity of the diseased areas. As a proof of concept, the strategically designed nanoprobes with energy‐dependent attenuation characteristics not only expand the scope of CT application, but also hold excellent potential for precise imaging‐based disease diagnosis.

Arrhythmic Mitral Valve Prolapse: Introducing an Era of Multimodality Imaging-Based Diagnosis and Risk Stratification.

Mitral valve prolapse is a common cardiac condition, with an estimated prevalence between 1% and 3%. Most patients have a benign course, but ever since its initial description mitral valve prolapse has been associated to sudden cardiac death. Although the causal relationship between mitral valve prolapse and sudden cardiac death has never been clearly demonstrated, different factors have been implicated in arrhythmogenesis in patients with mitral valve prolapse. In this work, we offer a comprehensive overview of the etiology and the genetic background, epidemiology, pathophysiology, and we focus on the state-of-the-art imaging-based diagnosis of mitral valve prolapse. Going beyond the classical, well-described clinical factors, such as young age, female gender and auscultatory findings, we investigate multimodality imaging features, such as alterations of anatomy and function of the mitral valve and its leaflets, the structural and contractile anomalies of the myocardium, all of which have been associated to sudden cardiac death.

Convolutional Neural Network for Skin Lesion Classification: Understanding the Fundamentals Through Hands-On Learning.

Deep learning architectures for the classification of images have shown outstanding results in a variety of disciplines, including dermatology. The expectations generated by deep learning for, e.g., image-based diagnosis have created the need for non-experts to become familiar with the working principles of these algorithms. In our opinion, getting hands-on experience with these tools through a simplified but accurate model can facilitate their understanding in an intuitive way. The visualization of the results of the operations performed by deep learning algorithms on dermatological images can help students to grasp concepts like convolution, even without an advanced mathematical background. In addition, the possibility to tune hyperparameters and even to tweak computer code further empower the reach of an intuitive comprehension of these processes, without requiring advanced computational and theoretical skills. This is nowadays possible thanks to recent advances that have helped to lower technical and technological barriers associated with the use of these tools, making them accessible to a broader community. Therefore, we propose a hands-on pedagogical activity that dissects the procedures to train a convolutional neural network on a dataset containing images of skin lesions associated with different skin cancer categories. The activity is available open-source and its execution does not require the installation of software. We further provide a step-by-step description of the algorithm and of its functions, following the development of the building blocks of the computer code, guiding the reader through the execution of a realistic example, including the visualization and the evaluation of the results.

Image-based diagnosis of residual or recurrent nasopharyngeal carcinoma may be a phantom tumor phenomenon.

Some nasopharyngeal carcinoma (NPC) patients may present convincing radiological evidence mimicking residual or recurrent tumor after radiotherapy. However, by means of biopsies and long term follow-up, the radiologically diagnosed residuals/recurrences are not always what they appear to be. We report our experience on this “phantom tumor” phenomenon. This may help to avoid the unnecessary and devastating re-irradiation subsequent to the incorrect diagnosis.In this longitudinal cohort study, we collected 19 patients of image-based diagnosis of residual/recurrent NPC during the period from Feb, 2010 to Nov. 2016, and then observed them until June, 2019. They were subsequently confirmed to have no residual/recurrent lesions by histological or clinical measures. Image findings and pathological features were analyzed.Six patients showed residual tumors after completion of radiotherapy and 13 were radiologically diagnosed to have recurrences based on magnetic resonance imaging (MRI) criteria 6 to 206 months after radiotherapy. There were 3 types of image patterns: extensive recurrent skull base lesions (10/19); a persistent or residual primary lesion (3/19); lesions both in the nasopharynx and skull base (6/19). Fourteen patients had biopsy of the lesions. The histological diagnoses included necrosis/ inflammation in 10 (52.7%), granulation tissue with inflammation in 2, and reactive epithelial cell in 1. Five patients had no pathological proof and were judged to have no real recurrence/residual tumor based on the absence of detectable plasma EB virus DNA and subjective judgment. These 5 patients have remained well after an interval of 38–121 months without anti-cancer treatments.Image-based diagnosis of residual or recurrent nasopharyngeal carcinoma may be unreliable. False positivity, the “phantom tumor phenomenon”, is not uncommon in post-radiotherapy MRI. This is particularly true if the images show extensive skull base involvement at 5 years or more after completion of radiotherapy. MRI findings compatible with NPC features must be treated as a real threat until proved otherwise. However, the balance between under- and over-diagnosis must be carefully sought. Without a pathological confirmation, the diagnosis of residual or recurrent NPC must be made taking into account physical examination results, endoscopic findings and Epstein-Barr virus viral load. A subjective medical judgment is needed based on clinical and laboratory data and the unique anatomic complexities of the nasopharynx.

Molecular imaging of orthotopic prostate cancer with nanobubble ultrasound contrast agents targeted to PSMA

Ultrasound imaging is routinely used to guide prostate biopsies, yet delineation of tumors within the prostate gland is extremely challenging, even with microbubble (MB) contrast. A more effective ultrasound protocol is needed that can effectively localize malignancies for targeted biopsy or aid in patient selection and treatment planning for organ-sparing focal therapy. This study focused on evaluating the application of a novel nanobubble ultrasound contrast agent targeted to the prostate specific membrane antigen (PSMA-targeted NBs) in ultrasound imaging of prostate cancer (PCa) in vivo using a clinically relevant orthotopic tumor model in nude mice. Our results demonstrated that PSMA-targeted NBs had increased extravasation and retention in PSMA-expressing orthotopic mouse tumors. These processes are reflected in significantly different time intensity curve (TIC) and several kinetic parameters for targeted versus non-targeted NBs or LUMASON MBs. These, may in turn, lead to improved image-based detection and diagnosis of PCa in the future.

Self-speculation of clinical features based on knowledge distillation for accurate ocular disease classification

Ocular diseases can lead to irreversible vision impairment if not treated timely. Various imaging techniques have been developed to aid in the detection of ocular diseases, including the widely employed color fundus photography. Nevertheless, early-stage ocular diseases are difficult to be accurately diagnosed because of the few visible symptoms, and automatic ocular disease classification based only on imaging is extremely challenging. In this paper, we propose a knowledge distillation-based method to improve the performance of imaging-based automatic ocular disease classification models. Specifically, two deep neural networks are optimized sequentially. A teacher network is trained that can exploit the information from inputs of both color fundus photographs and radiologists provided clinical features. Then, through distilling the knowledge of the teacher model, a student network is learned that can self-speculate the clinical features-relevant information from the sole inputs of images. Extensive experiments validate that our student model can largely recover the performance of the teacher model and thus, the proposed method can significantly enhance the imaging-based ocular disease diagnosis without the reliance on clinical features.

A Coarse-to-Fine Deformable Transformation Framework for Unsupervised Multi-Contrast MR Image Registration with Dual Consistency Constraint.

Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning. Nevertheless, the efficiency and performance of the existing registration algorithms can still be improved. In this paper, we propose a novel unsupervised learning-based framework to achieve accurate and efficient multi-contrast MR image registration. Specifically, an end-to-end coarse-to-fine network architecture consisting of affine and deformable transformations is designed to improve the robustness and achieve end-to-end registration. Furthermore, a dual consistency constraint and a new prior knowledge-based loss function are developed to enhance the registration performances. The proposed method has been evaluated on a clinical dataset containing 555 cases, and encouraging performances have been achieved. Compared to the commonly utilized registration methods, including VoxelMorph, SyN, and LT-Net, the proposed method achieves better registration performance with a Dice score of 0.8397± 0.0756 in identifying stroke lesions. With regards to the registration speed, our method is about 10 times faster than the most competitive method of SyN (Affine) when testing on a CPU. Moreover, we prove that our method can still perform well on more challenging tasks with lacking scanning information data, showing the high robustness for the clinical application.

Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Networks.

Simple SummaryThe assistance of computer image analysis that automatically identifies tissue or cell types has greatly improved histopathologic interpretation and diagnosis accuracy. In this paper, the Convolutional Neural Network (CNN) has been adapted to predict and classify lymph node metastasis in breast cancer. We observe that image resolutions of lymph node metastasis datasets in breast cancer usually are quite smaller than the designed model input resolution, which defects the performance of the proposed model. To mitigate this problem, we propose a boosted CNN architecture and a novel data augmentation method called Random Center Cropping (RCC). Different from traditional image cropping methods only suitable for resolution images in large scale, RCC not only enlarges the scale of datasets but also preserves the resolution and the center area of images. In addition, the downsampling scale of the network is diminished to be more suitable for small resolution images. Furthermore, we introduce attention and feature fusion mechanisms to enhance the semantic information of image features extracted by CNN. Experiments illustrate that our methods significantly boost performance of fundamental CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% in Rectified Patch Camelyon (RPCam) datasets, respectively.(1) Purpose: To improve the capability of EfficientNet, including developing a cropping method called Random Center Cropping (RCC) to retain the original image resolution and significant features on the images’ center area, reducing the downsampling scale of EfficientNet to facilitate the small resolution images of RPCam datasets, and integrating attention and Feature Fusion (FF) mechanisms with EfficientNet to obtain features containing rich semantic information. (2) Methods: We adopt the Convolutional Neural Network (CNN) to detect and classify lymph node metastasis in breast cancer. (3) Results: Experiments illustrate that our methods significantly boost performance of basic CNN architectures, where the best-performed method achieves an accuracy of 97.96% ± 0.03% and an Area Under the Curve (AUC) of 99.68% ± 0.01% on RPCam datasets, respectively. (4) Conclusions: (1) To our limited knowledge, we are the only study to explore the power of EfficientNet on Metastatic Breast Cancer (MBC) classification, and elaborate experiments are conducted to compare the performance of EfficientNet with other state-of-the-art CNN models. It might provide inspiration for researchers who are interested in image-based diagnosis using Deep Learning (DL). (2) We design a novel data augmentation method named RCC to promote the data enrichment of small resolution datasets. (3) All of our four technological improvements boost the performance of the original EfficientNet.

Learning-based algorithms for vessel tracking: A review.

Developing efficient vessel-tracking algorithms is crucial for imaging-based diagnosis and treatment of vascular diseases. Vessel tracking aims to solve recognition problems such as key (seed) point detection, centerline extraction, and vascular segmentation. Extensive image-processing techniques have been developed to overcome the problems of vessel tracking that are mainly attributed to the complex morphologies of vessels and image characteristics of angiography. This paper presents a literature review on vessel-tracking methods, focusing on machine-learning-based methods. First, the conventional machine-learning-based algorithms are reviewed, and then, a general survey of deep-learning-based frameworks is provided. On the basis of the reviewed methods, the evaluation issues are introduced. The paper is concluded with discussions about the remaining exigencies and future research.

Mechanical dissimilarity of defects in welded joints via Grassmann manifold and machine learning

Assessing the harmfulness of defects based on images is becoming more and more common in industry. At present, these defects can be inserted in digital twins that aim to replicate in a mechanical model what is observed on a component so that an image-based diagnosis can be further conducted. However, the variety of defects, the complexity of their shape, and the computational complexity of finite element models related to their digital twin make this kind of diagnosis too slow for any practical application. We show that a classification of observed defects enables the definition of a dictionary of digital twins. These digital twins prove to be representative of model-reduction purposes while preserving an acceptable accuracy for stress prediction. Nonsupervised machine learning is used for both the classification issue and the construction of reduced digital twins. The dictionary items are medoids found by a k-medoids clustering algorithm. Medoids are assumed to be well distributed in the training dataset according to a metric or a dissimilarity measurement. In this paper, we propose a new dissimilarity measurement between defects. It is theoretically founded according to approximation errors in hyper-reduced predictions. In doing so, defect classes are defined according to their mechanical effect and not directly according to their morphology. In practice, each defect in the training dataset is encoded as a point on a Grassmann manifold. This methodology is evaluated through a test set of observed defects totally different from the training dataset of defects used to compute the dictionary of digital twins. The most appropriate item in the dictionary for model reduction is selected according to an error indicator related to the hyper-reduced prediction of stresses. No plasticity effect is considered here (merely isotropic elastic materials), which is a strong assumption but which is not critical for the purpose of this work. In spite of the large variety of defects, we provide accurate predictions of stresses for most of defects in the test set.