Prediction of antiepileptic drug treatment outcomes of patients with newly diagnosed epilepsy by machine learning
پیش بینی نتایج درمان دارویی ضد صرع بیماران مبتلا به صرع تازه کشف شده با یادگیری ماشین-2019
Objective: The objective of this study was to build a supervised machine learning-based classifier, which can accurately predict the outcomes of antiepileptic drug (AED) treatment of patients with newly diagnosed epilepsy. Methods: We collected information from 287 patients with newly diagnosed epilepsy between 2009 and 2017 at the Second Affiliated Hospital of Zhejiang University. Patients were prospectively followed up for at least 3 years. A number of features, including demographic features,medical history, and auxiliary examinations (electroencephalogram [EEG] and magnetic resonance imaging [MRI]) are selected to distinguish patients with different remission outcomes. Seizure outcomes classified as remission and never remission. In addition, remission is further divided into early remission and late remission. Five classical machine learning algorithms, i.e., Decision Tree, Random Forest, Support Vector Machine, XGBoost, and Logistic Regression, are selected and trained by our dataset to get classification models. Results: Our study shows that 1) comparedwith the other four algorithms, the XGBoost algorithmbased machine learning model achieves the best prediction performance of the AEDtreatment outcomes between remission and never remission patientswith an F1 score of 0.947 and an area under the curve (AUC) value of 0.979; 2) The best discriminative factor for remission and never remission patients is higher number of seizures before treatment (N3); 3) XGBoost-based machine learning model also offers the best prediction between early remission and later remission patients, with an F1 score of 0.836 and an AUC value of 0.918; 4) multiple seizure type has the highest dependence to the categories of early and late remission patients. Significances: Our XGBoost-based machine learning classifier accurately predicts the most probable AED treatment outcome of a patient after he/she finishes all the standard examinations for the epilepsy disease. The classifiers prediction result could help disease guide counseling and eventually improve treatment strategies
Keywords: Machine learning | Epilepsy | Epilepsy remission | Antiepileptic drug | Outcome prediction
Improving Workflow Efficiency for Mammography Using Machine Learning
بهبود بهره وری گردش کار برای ماموگرافی با استفاده از یادگیری ماشین-2019
Objective: The aim of this study was to determine whether machine learning could reduce the number of mammograms the radiologist must read by using a machine-learning classifier to correctly identify normal mammograms and to select the uncertain and abnormal examinations for radiological interpretation. Methods: Mammograms in a research data set from over 7,000 women who were recalled for assessment at six UK National Health Service Breast Screening Program centers were used. A convolutional neural network in conjunction with multitask learning was used to extract imaging features from mammograms that mimic the radiological assessment provided by a radiologist, the patient’s nonimaging features, and pathology outcomes. A deep neural network was then used to concatenate and fuse multiple mammogram views to predict both a diagnosis and a recommendation of whether or not additional radiological assessment was needed. Results: Ten-fold cross-validation was used on 2,000 randomly selected patients from the data set; the remainder of the data set was used for convolutional neural network training. While maintaining an acceptable negative predictive value of 0.99, the proposed model was able to identify 34% (95% confidence interval, 25%-43%) and 91% (95% confidence interval: 88%-94%) of the negative mammograms for test sets with a cancer prevalence of 15% and 1%, respectively. Conclusion: Machine learning was leveraged to successfully reduce the number of normal mammograms that radiologists need to read without degrading diagnostic accuracy.
Key Words: Breast cancer | deep learning | machine learning | mammography | radiology
Strengths, Weaknesses, Opportunities, and Threats Analysis of Artificial Intelligence and Machine Learning Applications in Radiology
نقاط قوت ، ضعف ، فرصت و تحلیل تهدیدات هوش مصنوعی و برنامه های یادگیری ماشین در رادیولوژی-2019
Currently, the use of artificial intelligence (AI) in radiology, particularly machine learning (ML), has become a reality in clinical practice. Since the end of the last century, several ML algorithms have been introduced for a wide range of common imaging tasks, not only for diagnostic purposes but also for image acquisition and postprocessing. AI is now recognized to be a driving initiative in every aspect of radiology. There is growing evidence of the advantages of AI in radiology creating seamless imaging workflows for radiologists or even replacing radiologists. Most of the current AI methods have some internal and external disadvantages that are impeding their ultimate implementation in the clinical arena. As such, AI can be considered a portion of a business trying to be introduced in the health care market. For this reason, this review analyzes the current status of AI, and specifically ML, applied to radiology from the scope of strengths, weaknesses, opportunities, and threats (SWOT) analysis.
Key Words: Artificial intelligence | deep learning | machine learning | opportunity | radiomics | strength | threat | weakness
تحلیل لبه ای مبتنی بر موجک چند جهته برای تشخیص سطح توسط پروفیلومتری نوری
سال انتشار: 2019 - تعداد صفحات فایل pdf انگلیسی: 10 - تعداد صفحات فایل doc فارسی: 18
دانشمندان، مهندسان و تولید کنندگان نیاز ضروری به تکنیک های بهتر تشخیص و کنترل کیفیت دارند. مترولوژی نوری با استفاده از علوم نور و علوم کامپیوتر به دنبال شبیه سازی، طراحی، محاسبات و بازرسی برای بسیاری از برنامه های کاربردی علمی و صنعتی مانند اپتیک، مکانیک، هواپیما، الکترونیک و … است. آنالیز الگوی fringe روشی برای انجام برخی عملیات در تصاویر نوری و به منظور دریافت نقشه فاز اینترفرومتری و سپس استخراج برخی اطلاعات مفید از آن است. در این مقاله، بهبود محرک الگوریتم دمدولاسیون fringe محلی ارائه شده است، که بر اساس موجک جدید چند جهته است. کارهای عددی و تجربی در مقایسه با سایر الگوریتم های استاندارد، سود جالبی را نشان می دهد. رویکرد ما به سرعت به عنوان فاز روش های بازیابی پرطرفدار اجرا می شود، اما با دقت قابل توجهی دمدولاسیون fringe های نویز را بهبود می دهد. همه این مسائل بدون هیچ پیش پردازش توسط فیلتر کردن مدل ها رخ می دهد.
کليدواژه ها: تصویربرداری نوری | علوم کامپیوتر | پردازش تصویر | موجک چند جهته | فاز بازیابی | طرح ریزی fringe .
|مقاله ترجمه شده|
Medical image classification using synergic deep learning
طبقه بندی تصویر پزشکی با استفاده از یادگیری عمیق هم افزایی-2019
The classification of medical images is an essential task in computer-aided diagnosis, medical image re- trieval and mining. Although deep learning has shown proven advantages over traditional methods that rely on the handcrafted features, it remains challenging due to the significant intra-class variation and inter-class similarity caused by the diversity of imaging modalities and clinical pathologies. In this paper, we propose a synergic deep learning (SDL) model to address this issue by using multiple deep convo- lutional neural networks (DCNNs) simultaneously and enabling them to mutually learn from each other. Each pair of DCNNs has their learned image representation concatenated as the input of a synergic net- work, which has a fully connected structure that predicts whether the pair of input images belong to the same class. Thus, if one DCNN makes a correct classification, a mistake made by the other DCNN leads to a synergic error that serves as an extra force to update the model. This model can be trained end-to-end under the supervision of classification errors from DCNNs and synergic errors from each pair of DCNNs. Our experimental results on the ImageCLEF-2015, ImageCLEF-2016, ISIC-2016, and ISIC-2017 datasets in- dicate that the proposed SDL model achieves the state-of-the-art performance in these medical image classification tasks.
Keywords: Medical image classification | Intra-class variation | Inter-class similarity | Synergic deep learning model
TOP-GAN: Stain-free cancer cell classification using deep learning with a small training set
TOP-GAN: طبقه بندی سلول های سرطانی بدون لکه با استفاده از یادگیری عمیق با یک مجموعه آموزشی کوچک-2019
We propose a new deep learning approach for medical imaging that copes with the problem of a small training set, the main bottleneck of deep learning, and apply it for classification of healthy and cancer cell lines acquired by quantitative phase imaging. The proposed method, called transferring of pre-trained generative adversarial network (TOP-GAN), is hybridization between transfer learning and generative ad- versarial networks (GANs). Healthy cells and cancer cells of different metastatic potential have been im- aged by low-coherence off-axis holography. After the acquisition, the optical path delay maps of the cells are extracted and directly used as inputs to the networks. In order to cope with the small number of clas- sified images, we use GANs to train a large number of unclassified images from another cell type (sperm cells). After this preliminary training, we change the last layers of the network and design automatic classifiers for the correct cell type (healthy/primary cancer/metastatic cancer) with 90–99% accuracies, although small training sets of down to several images are used. These results are better in comparison to other classic methods that aim at coping with the same problem of a small training set. We believe that our approach makes the combination of holographic microscopy and deep learning networks more accessible to the medical field by enabling a rapid, automatic and accurate classification in stain-free imaging flow cytometry. Furthermore, our approach is expected to be applicable to many other medical image classification tasks, suffering from a small training set.
Keywords: Holography | Quantitative phase imaging | Deep learning | Machine learning algorithms | Image classification | Biological cells
Machine Learning Models can Detect Aneurysm Rupture and Identify Clinical Features Associated with Rupture
مدلهای یادگیری ماشینی می توانند پارگی آنوریسم را تشخیص دهند و ویژگیهای بالینی مرتبط با پارگی را شناسایی کنند-2019
- BACKGROUND: Machine learning (ML) has been increasingly used in medicine and neurosurgery. We sought to determine whether ML models can distinguish ruptured from unruptured aneurysms and identify features associated with rupture. - METHODS: We performed a retrospective review of patients with intracranial aneurysms detected on vascular imaging at our institution between 2002 and 2018. The dataset was used to train 3 ML models (random forest, linear support vector machine [SVM], and radial basis function kernel SVM). Relative contributions of individual predictors were derived from the linear SVM model. - RESULTS: Complete data were available for 845 aneurysms in 615 patients. Ruptured aneurysms (n [ 309, 37%) were larger (mean 6.51 mm vs. 5.73 mm; P [ 0.02) and more likely to be in the posterior circulation (20% vs. 11%; P < 0.001) than unruptured aneurysms. Area under the receiver operating curve was 0.77 for the linear SVM, 0.78 for the radial basis function kernel SVM models, and 0.81 for the random forest model. Aneurysm location and size were the 2 features that contributed most significantly to the model. Posterior communicating artery, anterior communicating artery, and posterior inferior cerebellar artery locations were most highly associated with rupture, whereas paraclinoid and middle cerebral artery locations had the strongest association with unruptured status. -CONCLUSIONS: ML models are capable of accurately distinguishing ruptured from unruptured aneurysms and identifying features associated with rupture. Consistent with prior studies, location and size show the strongest association with aneurysm rupture.
Key words : Aneurysm | Aneurysm rupture | Artificial intelligence | Machine learning | Subarachnoid hemorrhage
Application of deep transfer learning for automated brain abnormality classification using MR images
کاربرد یادگیری انتقال عمیق برای طبقه بندی خودکار ناهنجاری مغزی با استفاده از تصاویر MR-2019
Magnetic resonance imaging (MRI) is the most common imaging technique used to detect abnormal brain tumors. Traditionally, MRI images are analyzed manually by radiologists to detect the abnormal conditions in the brain. Manual interpretation of huge volume of images is time consuming and difficult. Hence, computer-based detection helps in accurate and fast diagnosis. In this study, we proposed an approach that uses deep transfer learning to automatically classify normal and abnormal brain MR images. Convolutional neural network (CNN) based ResNet34 model is used as a deep learning model. We have used current deep learning techniques such as data augmentation, optimal learning rate finder and fine-tuning to train the model. The proposed model achieved 5-fold classification accuracy of 100% on 613 MR images. Our developed system is ready to test on huge database and can assist the radiologists in their daily screening of MR images.
Keywords: MRI classification | Abnormal brain images | Deep transfer learning | CNN
Neurobiological divergence of the positive and negative schizophrenia subtypes identified upon a new factor-structure of psychopathology using non-negative factorization: An international machine-learning study
واگرایی عصبی از زیرگروه های اسکیزوفرنی مثبت و منفی مشخص شده بر یک ساختار جدید از روانشناسی با استفاده از فاکتورسازی غیر منفی: یک مطالعه بین المللی یادگیری ماشین-2019
Objective: Disentangling psychopathological heterogeneity in schizophrenia is challenging and previous results remain inconclusive. We employed advanced machine-learning to identify a stable and generalizable factorization of the “Positive and Negative Syndrome Scale (PANSS)”, and used it to identify psychopathological subtypes as well as their neurobiological differentiations. Methods: PANSS data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients, 586 followed up after 1.35±0.70 years) were used for learning the factor-structure by an orthonormal projective non-negative factorization. An international sample, pooled from nine medical centers across Europe, USA, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor-structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional MRI connectivity patterns. Results: A four-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original PANSS subscales and previously proposed factor-models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventro-medial frontal cortex, temporoparietal junction, and precuneus. Conclusions: Machine-learning applied to multi-site data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia
Keywords: non-negative factorization | brain imaging | subtyping | machine learning | multivariate classification | schizophrenia
Combined machine learning and diffusion tensor imaging reveals altered anatomic fiber connectivity of the brain in primary open-angle glaucoma
یادگیری ماشین ترکیبی و تصویربرداری با تانسور انتشار ، ارتباط فیبر آناتومیک مغز را در گلوکوم زاویه باز اولیه تغییر داده است-2019
Parameters derived from diffusion tensor imaging (DTI) have been found to be significantly altered in the optic tracts, optic nerves, and optic radiations in patients with primary open-angle glaucoma (POAG). In this study, DTI-derived parameters were further constructed into fiber connectivity, and we investigated anatomical fiber connectivity changes within and beyond the visual pathway in POAG patients. DTI and T1-weighted magnetic resonance images were acquired in 18 POAG patients and 26 healthy controls (HC). White matter tracts based on the Brodmann atlases (BA) were constructed using the deterministic fiber tracking method. The mean fractional anisotropy (FA), fiber number (FN), and mean fiber length (FL) were measured and then evaluated using twosample t-tests between POAG and HC. The fiber connectivity between regions was taken as the features for classifying HC and POAG using a machine learning method known as naïve Bayesian classification. The mean FA decreased in connections between visual cortex BA17/BA18 and cortex BA23/BA25/BA35/BA36, while it increased in the connections between cortex BA3/BA7/BA9 and BA5/BA6/BA45/BA25 in POAG. Classification using fibers where a significant difference in FN had been identified produced better accuracy (ACC=0.89) than using FA or FL (ACC=0.77 and 0.75, respectively). The FN of individual fiber connections with higher accuracy and significant changes in POAG involved brain regions associated with vision (BA19), depression (BA10/BA46/ BA25), and memory (BA29). These findings strengthen the hypothesis that POAG involves changes in anatomical connectivity within and beyond the visual pathway. Classification using the machine learning method reveals that mean FN has the potential to be used as a biomarker for detecting white matter microstructure changes in POAG.
Keywords: Glaucoma | Anatomic white matter connectivity | Diffusion tensor imaging | Fiber tracking | Machine learning