Deep Learning In Medical Imaging And Drug Design

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Surayya Ado Bala ◽  
Shri Ojha Kant ◽  
Adamu Garba Yakasai
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Drug Design ◽  
Therapy Monitoring ◽  
Surrogate Endpoint ◽  
Cellular Level ◽  
Response To Therapy ◽  
Response To Treatment ◽  
Design Decision ◽  
Medical Diagnostic

Over the last decade, deep learning (DL) methods have been extremely successful and widely used in almost every domain. Researchers are now focusing on the convergence of medical imaging and drug design using deep learning to revolutionize medical diagnostic and improvement in the monitoring from response to therapy. DL a new machine learning paradigm that focuses on learning with deep hierarchical models of data. Medical imaging has transformed healthcare science, it was thought of as a diagnostic tool for disease, but now it is also used in drug design. Advances in medical imaging technology have enabled scientists to detect events at the cellular level. The role of medical imaging in drug design includes identification of likely responders, detection, diagnosis, evaluation, therapy monitoring, and follow-up. A qualitative medical image is transformed into a quantitative biomarker or surrogate endpoint useful in drug design decision-making. For this, a parameter needs to be identified that characterizes the disease baseline and its subsequent response to treatment. The result is a quantifiable improvement in healthcare quality in most therapeutic areas, resulting in improvements in quality and duration of life. This paper provides an overview of recent studies on applying the deep learning method in medical imaging and drug design. We briefly discuss the fields related to the history of deep learning, medical imaging, and drug design.

Improving the Accuracy of Protein-Ligand Binding Affinity Prediction by Deep Learning Models: Benchmark and Model

2019 ◽  
Author(s):  
Mohammad Rezaei ◽  
Yanjun Li ◽  
Xiaolin Li ◽  
Chenglong Li
Keyword(s):  
Deep Learning ◽  
Drug Design ◽  
Binding Affinity ◽  
Benchmark Dataset ◽  
Rational Drug Design ◽  
Learning Models ◽  
Structure Based Drug Design ◽  
Binding Affinity Prediction ◽  
Affinity Prediction ◽  
Rational Drug

<b>Introduction:</b> The ability to discriminate among ligands binding to the same protein target in terms of their relative binding affinity lies at the heart of structure-based drug design. Any improvement in the accuracy and reliability of binding affinity prediction methods decreases the discrepancy between experimental and computational results.<br><b>Objectives:</b> The primary objectives were to find the most relevant features affecting binding affinity prediction, least use of manual feature engineering, and improving the reliability of binding affinity prediction using efficient deep learning models by tuning the model hyperparameters.<br><b>Methods:</b> The binding site of target proteins was represented as a grid box around their bound ligand. Both binary and distance-dependent occupancies were examined for how an atom affects its neighbor voxels in this grid. A combination of different features including ANOLEA, ligand elements, and Arpeggio atom types were used to represent the input. An efficient convolutional neural network (CNN) architecture, DeepAtom, was developed, trained and tested on the PDBbind v2016 dataset. Additionally an extended benchmark dataset was compiled to train and evaluate the models.<br><b>Results: </b>The best DeepAtom model showed an improved accuracy in the binding affinity prediction on PDBbind core subset (Pearson’s R=0.83) and is better than the recent state-of-the-art models in this field. In addition when the DeepAtom model was trained on our proposed benchmark dataset, it yields higher correlation compared to the baseline which confirms the value of our model.<br><b>Conclusions:</b> The promising results for the predicted binding affinities is expected to pave the way for embedding deep learning models in virtual screening and rational drug design fields.

Melanoma: Prognostic Factors and Factors Predictive of Response to Therapy

2020 ◽  
Vol 27 (17) ◽  
pp. 2792-2813
Author(s):  
Martina Strudel ◽  
Lucia Festino ◽  
Vito Vanella ◽  
Massimiliano Beretta ◽  
Francesco M. Marincola ◽  
...  
Keyword(s):  
Prognostic Factors ◽  
Lactate Dehydrogenase ◽  
Checkpoint Inhibitors ◽  
Survival Rates ◽  
Elevated Serum ◽  
Predictive Biomarkers ◽  
Response To Therapy ◽  
Response To Treatment ◽  
Prognostic Features ◽  
Programmed Death

Background: A better understanding of prognostic factors and biomarkers that predict response to treatment is required in order to further improve survival rates in patients with melanoma. Predictive Biomarkers: The most important histopathological factors prognostic of worse outcomes in melanoma are sentinel lymph node involvement, increased tumor thickness, ulceration and higher mitotic rate. Poorer survival may also be related to several clinical factors, including male gender, older age, axial location of the melanoma, elevated serum levels of lactate dehydrogenase and S100B. Predictive Biomarkers: Several biomarkers have been investigated as being predictive of response to melanoma therapies. For anti-Programmed Death-1(PD-1)/Programmed Death-Ligand 1 (PD-L1) checkpoint inhibitors, PD-L1 tumor expression was initially proposed to have a predictive role in response to anti-PD-1/PD-L1 treatment. However, patients without PD-L1 expression also have a survival benefit with anti-PD-1/PD-L1 therapy, meaning it cannot be used alone to select patients for treatment, in order to affirm that it could be considered a correlative, but not a predictive marker. A range of other factors have shown an association with treatment outcomes and offer potential as predictive biomarkers for immunotherapy, including immune infiltration, chemokine signatures, and tumor mutational load. However, none of these have been clinically validated as a factor for patient selection. For combined targeted therapy (BRAF and MEK inhibition), lactate dehydrogenase level and tumor burden seem to have a role in patient outcomes. Conclusions: With increasing knowledge, the understanding of melanoma stage-specific prognostic features should further improve. Moreover, ongoing trials should provide increasing evidence on the best use of biomarkers to help select the most appropriate patients for tailored treatment with immunotherapies and targeted therapies.

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

scholarly journals Deep learning-based solvability of underdetermined inverse problems in medical imaging

2021 ◽  
Vol 69 ◽  
pp. 101967
Author(s):  
Chang Min Hyun ◽  
Seong Hyeon Baek ◽  
Mingyu Lee ◽  
Sung Min Lee ◽  
Jin Keun Seo
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Inverse Problems

scholarly journals Implementing Personalized Medicine in COVID-19 in Andalusia: An Opportunity to Transform the Healthcare System

2021 ◽  
Vol 11 (6) ◽  
pp. 475
Author(s):  
Joaquín Dopazo ◽  
Douglas Maya-Miles ◽  
Federico García ◽  
Nicola Lorusso ◽  
Miguel Ángel Calleja ◽  
...  
Keyword(s):  
Public Health ◽  
Health Care ◽  
Clinical Practice ◽  
Personalized Medicine ◽  
Local Level ◽  
Individual Variability ◽  
Response To Therapy ◽  
Control Measures ◽  
Response To Treatment ◽  
Specific Patient

The COVID-19 pandemic represents an unprecedented opportunity to exploit the advantages of personalized medicine for the prevention, diagnosis, treatment, surveillance and management of a new challenge in public health. COVID-19 infection is highly variable, ranging from asymptomatic infections to severe, life-threatening manifestations. Personalized medicine can play a key role in elucidating individual susceptibility to the infection as well as inter-individual variability in clinical course, prognosis and response to treatment. Integrating personalized medicine into clinical practice can also transform health care by enabling the design of preventive and therapeutic strategies tailored to individual profiles, improving the detection of outbreaks or defining transmission patterns at an increasingly local level. SARS-CoV2 genome sequencing, together with the assessment of specific patient genetic variants, will support clinical decision-makers and ultimately better ways to fight this disease. Additionally, it would facilitate a better stratification and selection of patients for clinical trials, thus increasing the likelihood of obtaining positive results. Lastly, defining a national strategy to implement in clinical practice all available tools of personalized medicine in COVID-19 could be challenging but linked to a positive transformation of the health care system. In this review, we provide an update of the achievements, promises, and challenges of personalized medicine in the fight against COVID-19 from susceptibility to natural history and response to therapy, as well as from surveillance to control measures and vaccination. We also discuss strategies to facilitate the adoption of this new paradigm for medical and public health measures during and after the pandemic in health care systems.

Diagnosing breast cancer tumors using stacked ensemble model

2021 ◽  
pp. 1-9
Author(s):  
Ahmet Haşim Yurttakal ◽  
Hasan Erbay ◽  
Türkan İkizceli ◽  
Seyhan Karaçavuş ◽  
Cenker Biçer
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Medical Imaging ◽  
Early Stage ◽  
False Negative ◽  
Gradient Boosting ◽  
Physical Sign ◽  
Ensemble Model ◽  
Learning Methods ◽  
Dce Mri

Breast cancer is the most common cancer that progresses from cells in the breast tissue among women. Early-stage detection could reduce death rates significantly, and the detection-stage determines the treatment process. Mammography is utilized to discover breast cancer at an early stage prior to any physical sign. However, mammography might return false-negative, in which case, if it is suspected that lesions might have cancer of chance greater than two percent, a biopsy is recommended. About 30 percent of biopsies result in malignancy that means the rate of unnecessary biopsies is high. So to reduce unnecessary biopsies, recently, due to its excellent capability in soft tissue imaging, Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) has been utilized to detect breast cancer. Nowadays, DCE-MRI is a highly recommended method not only to identify breast cancer but also to monitor its development, and to interpret tumorous regions. However, in addition to being a time-consuming process, the accuracy depends on radiologists’ experience. Radiomic data, on the other hand, are used in medical imaging and have the potential to extract disease characteristics that can not be seen by the naked eye. Radiomics are hard-coded features and provide crucial information about the disease where it is imaged. Conversely, deep learning methods like convolutional neural networks(CNNs) learn features automatically from the dataset. Especially in medical imaging, CNNs’ performance is better than compared to hard-coded features-based methods. However, combining the power of these two types of features increases accuracy significantly, which is especially critical in medicine. Herein, a stacked ensemble of gradient boosting and deep learning models were developed to classify breast tumors using DCE-MRI images. The model makes use of radiomics acquired from pixel information in breast DCE-MRI images. Prior to train the model, radiomics had been applied to the factor analysis to refine the feature set and eliminate unuseful features. The performance metrics, as well as the comparisons to some well-known machine learning methods, state the ensemble model outperforms its counterparts. The ensembled model’s accuracy is 94.87% and its AUC value is 0.9728. The recall and precision are 1.0 and 0.9130, respectively, whereas F1-score is 0.9545.

Accelerating De Novo Drug Design against Novel Proteins Using Deep Learning

2021 ◽  
Vol 61 (2) ◽  
pp. 621-630
Author(s):  
Sowmya Ramaswamy Krishnan ◽  
Navneet Bung ◽  
Gopalakrishnan Bulusu ◽  
Arijit Roy
Keyword(s):  
Deep Learning ◽  
Drug Design ◽  
De Novo ◽  
De Novo Drug Design ◽  
Novel Proteins

Pure and Hybrid Deep Learning Models can Predict Pathologic Tumor Response to Neoadjuvant Therapy in Pancreatic Adenocarcinoma: A Pilot Study

2020 ◽  
pp. 000313482098255
Author(s):  
Michael D. Watson ◽  
Maria R. Baimas-George ◽  
Keith J. Murphy ◽  
Ryan C. Pickens ◽  
David A. Iannitti ◽  
...  
Keyword(s):  
Deep Learning ◽  
Neoadjuvant Therapy ◽  
Pancreatic Adenocarcinoma ◽  
Hybrid Model ◽  
Tumor Response ◽  
Tumor Regression ◽  
Area Under The Curve ◽  
Learning Model ◽  
Response To Therapy ◽  
Deep Learning Model

Background Neoadjuvant therapy may improve survival of patients with pancreatic adenocarcinoma; however, determining response to therapy is difficult. Artificial intelligence allows for novel analysis of images. We hypothesized that a deep learning model can predict tumor response to NAC. Methods Patients with pancreatic cancer receiving neoadjuvant therapy prior to pancreatoduodenectomy were identified between November 2009 and January 2018. The College of American Pathologists Tumor Regression Grades 0-2 were defined as pathologic response (PR) and grade 3 as no response (NR). Axial images from preoperative computed tomography scans were used to create a 5-layer convolutional neural network and LeNet deep learning model to predict PRs. The hybrid model incorporated decrease in carbohydrate antigen 19-9 (CA19-9) of 10%. Accuracy was determined by area under the curve. Results A total of 81 patients were included in the study. Patients were divided between PR (333 images) and NR (443 images). The pure model had an area under the curve (AUC) of .738 ( P < .001), whereas the hybrid model had an AUC of .785 ( P < .001). CA19-9 decrease alone was a poor predictor of response with an AUC of .564 ( P = .096). Conclusions A deep learning model can predict pathologic tumor response to neoadjuvant therapy for patients with pancreatic adenocarcinoma and the model is improved with the incorporation of decreases in serum CA19-9. Further model development is needed before clinical application.

scholarly journals Molecular imaging and deep learning analysis of uMUC1 expression in response to chemotherapy in an orthotopic model of ovarian cancer

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hongwei Zhao ◽  
Hasaan Hayat ◽  
Xiaohong Ma ◽  
Daguang Fan ◽  
Ping Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Ovarian Cancer ◽  
Deep Learning ◽  
Cancer Progression ◽  
In Vivo Imaging ◽  
Near Infrared ◽  
Response To Therapy ◽  
Response To Chemotherapy

Abstract Artificial Intelligence (AI) algorithms including deep learning have recently demonstrated remarkable progress in image-recognition tasks. Here, we utilized AI for monitoring the expression of underglycosylated mucin 1 (uMUC1) tumor antigen, a biomarker for ovarian cancer progression and response to therapy, using contrast-enhanced in vivo imaging. This was done using a dual-modal (magnetic resonance and near infrared optical imaging) uMUC1-specific probe (termed MN-EPPT) consisted of iron-oxide magnetic nanoparticles (MN) conjugated to a uMUC1-specific peptide (EPPT) and labeled with a near-infrared fluorescent dye, Cy5.5. In vitro studies performed in uMUC1-expressing human ovarian cancer cell line SKOV3/Luc and control uMUC1low ES-2 cells showed preferential uptake on the probe by the high expressor (n = 3, p < .05). A decrease in MN-EPPT uptake by SKOV3/Luc cells in vitro due to uMUC1 downregulation after docetaxel therapy was paralleled by in vivo imaging studies that showed a reduction in probe accumulation in the docetaxel treated group (n = 5, p < .05). The imaging data were analyzed using deep learning-enabled segmentation and quantification of the tumor region of interest (ROI) from raw input MRI sequences by applying AI algorithms including a blend of Convolutional Neural Networks (CNN) and Fully Connected Neural Networks. We believe that the algorithms used in this study have the potential to improve studying and monitoring cancer progression, amongst other diseases.

Sign in / Sign up

Export Citation Format

Share Document