scholarly journals Influence of the Computer-Aided Decision Support System Design on Ultrasound-Based Breast Cancer Classification

Cancers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 277
Author(s):  
Zuzanna Anna Magnuska ◽  
Benjamin Theek ◽  
Milita Darguzyte ◽  
Moritz Palmowski ◽  
Elmar Stickeler ◽  
...  
Keyword(s):  
Breast Lesion ◽  
Characteristic Curve ◽  
Cancer Diagnostics ◽  
Lesion Detection ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
P Value ◽  
Future Design ◽  
Sensitivity Specificity ◽  
Derivatives Of

Automation of medical data analysis is an important topic in modern cancer diagnostics, aiming at robust and reproducible workflows. Therefore, we used a dataset of breast US images (252 malignant and 253 benign cases) to realize and compare different strategies for CAD support in lesion detection and classification. Eight different datasets (including pre-processed and spatially augmented images) were prepared, and machine learning algorithms (i.e., Viola–Jones; YOLOv3) were trained for lesion detection. The radiomics signature (RS) was derived from detection boxes and compared with RS derived from manually obtained segments. Finally, the classification model was established and evaluated concerning accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic curve. After training on a dataset including logarithmic derivatives of US images, we found that YOLOv3 obtains better results in breast lesion detection (IoU: 0.544 ± 0.081; LE: 0.171 ± 0.009) than the Viola–Jones framework (IoU: 0.399 ± 0.054; LE: 0.096 ± 0.016). Interestingly, our findings show that the classification model trained with RS derived from detection boxes and the model based on the RS derived from a gold standard manual segmentation are comparable (p-value = 0.071). Thus, deriving radiomics signatures from the detection box is a promising technique for building a breast lesion classification model, and may reduce the need for the lesion segmentation step in the future design of CAD systems.

scholarly journals A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification

2020 ◽  
Vol 21 (23) ◽  
pp. 9070
Author(s):  
Nguyen Quoc Khanh Le ◽  
Duyen Thi Do ◽  
Truong Nguyen Khanh Hung ◽  
Luu Ho Thanh Lam ◽  
Tuan-Tu Huynh ◽  
...  
Keyword(s):  
Natural Language ◽  
Language Processing ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Essential Genes ◽  
Machine Learning Algorithms ◽  
Computational Framework ◽  
Sequencing Problems ◽  
Sensitivity Specificity ◽  
The Cost

Essential genes contain key information of genomes that could be the key to a comprehensive understanding of life and evolution. Because of their importance, studies of essential genes have been considered a crucial problem in computational biology. Computational methods for identifying essential genes have become increasingly popular to reduce the cost and time-consumption of traditional experiments. A few models have addressed this problem, but performance is still not satisfactory because of high dimensional features and the use of traditional machine learning algorithms. Thus, there is a need to create a novel model to improve the predictive performance of this problem from DNA sequence features. This study took advantage of a natural language processing (NLP) model in learning biological sequences by treating them as natural language words. To learn the NLP features, a supervised learning model was consequentially employed by an ensemble deep neural network. Our proposed method could identify essential genes with sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC), and area under the receiver operating characteristic curve (AUC) values of 60.2%, 84.6%, 76.3%, 0.449, and 0.814, respectively. The overall performance outperformed the single models without ensemble, as well as the state-of-the-art predictors on the same benchmark dataset. This indicated the effectiveness of the proposed method in determining essential genes, in particular, and other sequencing problems, in general.

Evaluation of radiomics as a predictor of tumor hypoxia and response to anti-PD-1 mab treatment (IO) in recurrent/metastatic HNSCC patients (R/M).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 6045-6045
Author(s):  
Dan Paul Zandberg ◽  
Serafettin Zenkin ◽  
Murat AK ◽  
Priyadarshini Mamindla ◽  
Vishal Peddagangireddy ◽  
...  
Keyword(s):  
Tumor Microenvironment ◽  
Cross Validation ◽  
Tumor Hypoxia ◽  
Texture Features ◽  
Classification Model ◽  
P Value ◽  
Patient Cohort ◽  
Volume Of Interest ◽  
Feature Selection Approach ◽  
Sensitivity Specificity

6045 Background: There is a great need for non-invasive predictors of the tumor microenvironment and the efficacy of anti-PD-1 mAb treatment (IO) in R/M HNSCC patients. We previously showed that lower tumor hypoxia was associated with increased efficacy with IO ( Journal of Clinical Oncol. 38, no. 15_suppl (May 20, 2020) 6546) and now we evaluate the predictive value of radiomics in this same patient cohort. Methods: We studied radiomic signatures in a cohort of 36 patients with R/M HNSCC treated with IO. Treatment response was evaluated using RECIST 1.1. Patients were categorized as: Responders (R) ie CR, PR, SD and non-Responders (NR) i.e PD. As per our previous analysis (ref above) hypoxia was evaluated on archival FFPE samples via immunofluorescent imaging and defined by the ratio of percent area (% CAIX) / the mean intensity (Int) of carbonic anhydrase IX in tumor (%CAIX/Int). ImageJ software was used to determine %CAIX and Int. Feature extraction was performed on the pre-immunotherapy baseline CT scans. The lesions were segmented using 3D slicer v4.10.2 to create a volume of interest (VOI) for radiomic texture analysis (TA). A total of 400 features (10 histogram-based and 390 second-order texture features) were calculated from each extracted volume of interest (VOI). Radiomic features were obtained using a feature selection approach based on Least Absolute Shrinkage and Selection Operator (LASSO). Selected features were used to build a classification model, using XGboost, for prediction of tumor response to immunotherapy. Cross-validation was performed using the Leave One Out Cross Validation (LOOCV) approach for the XGBoost method to evaluate the robustness of the estimates and calculated accuracy, sensitivity, specificity and p-value. Results: Our patient cohort had a median age of 59, 69% male, 58% smokers. 61% received IO for platinum failure, 39% frontline. Primary site included 39% OC, 22% OPC (38% HPV positive), 17% Larynx, 5% hypopharynx, and 17% other. Radiomics applied to the primary HNSCC tumor highly predicted tumor hypoxia status with a sensitivity, specificity, and accuracy of 78%, 83%, and 81%, respectively, p = 0.0001. To predict response, we applied radiomics to both the primary HNSCC tumor and pathological lymph nodes; radiomics was also able to predict whether a patient would be a responder (N = 8) versus a non-responder (N = 28) to IO based on the pre-immunotherapy baseline CT scan. The sensitivity, specificity, and accuracy were 93%, 88%, and 92%, respectively, p = 0.02. Conclusions: Even in a small cohort, radiomics could predict response to IO and tumor hypoxia in R/M HNSCC patients. To our knowledge this is the first evaluation of this kind in this patient population. Further evaluation of radiomics as a predictor of efficacy with IO and the tumor microenvironment is warranted.

Evaluation of pre-operative clinical finding and per-operative assessment of carcinoma stomach in tertiary settings of Bangladesh

2020 ◽  
Vol 22 (1) ◽  
pp. 43-46
Author(s):  
Mst Jesmen Nahar ◽  
Md Mahiuddin Matubber ◽  
Md Mahbubur Rahman ◽  
Md Mahbubur Rahman ◽  
Syed Muhammad Baqul Billah ◽  
...  
Keyword(s):  
Lymph Node ◽  
Clinical Picture ◽  
Preoperative Evaluation ◽  
Lymph Node Involvement ◽  
Lesion Detection ◽  
Clinical Feature ◽  
P Value ◽  
Operative Finding ◽  
Node Involvement ◽  
Carcinoma Stomach

Background: Carcinoma stomach, a major killer cancer all over the world, is still presenting late in developing countries due to delay in early diagnosis, lack of awareness, infrastructure etc. Objectives: To establish the importance of preoperative evaluation on operability of carcinoma stomach. Methods: Sixty clinically and histopathologically diagnosed ca stomach cases who underwent surgery in department of Bangabandhu Sheikh Mujib Medical University, Dhaka, and Dhaka Medical College Hospital, Dhaka in 2011 were assessed with clinical picture, investigations, preoperative evaluation and peroperative findings were recorded. Z test for proportion was used to assess clinical decision predictability with a p value of :s;0.05 as significant. Results: Male (73.33%) predominant with 2.75:1 male:female ratio was observed. Mobility, fixity and abdominal lymphadenopathy were not well detected through clinical assessment (p=0.001) while ascites, metastasis and Shelf of Slummer were similar in both clinical and operative finding. The endoscopy of upper GIT finding gave a unique picture as the findings were almost same as were found during operation. USG detected a lesser proportion of the clinical condition compared to peroperative condition whereas CT performed better than the USG except for the lesion detection. Though Computed Tomography (CT) detected higher percentage of lesion, metastasis, ascites and lymph node involvement compared to ultrasonogram (USG), it was significantly higher only for lesion detection (p=0.002) and lymph node involvement (p=<0.001). In the similar manner USG assessment of lesion detection (p=<0.001) and lymph node involvement (p=0.003) was significantly low compared to operative finding. When we looked between CT and operative finding only lesion detection was significantly low (p=0.01) indicating CT to be most effective predictor of clinical picture for operative decision. Preoperative plan were mostly not in accordance with peroperative decision except for total gastrectomy. Conclusion: The study indicates weakness in clinical detection and pre-operative plan compared to per-operative finding. Hence combination of clinical feature and investigation tools especially endoscopy of upper GIT combined with CT is recommended to predict a better operative decision. Journal of Surgical Sciences (2018) Vol. 22 (1): 43-46

The role of serum periostin in the diagnosis of asthma: A meta-analysis

2020 ◽  
Vol 41 (4) ◽  
pp. 240-247
Author(s):  
Lei Yang ◽  
Qingtao Zhao ◽  
Shuyu Wang
Keyword(s):  
Diagnostic Accuracy ◽  
Meta Analysis ◽  
Characteristic Curve ◽  
False Negative ◽  
Summary Receiver Operating Characteristic ◽  
True Negative ◽  
Negative Results ◽  
Noninvasive Biomarker ◽  
Sensitivity Specificity ◽  
Serum Periostin

Background: Serum periostin has been proposed as a noninvasive biomarker for asthma diagnosis and management. However, its accuracy for the diagnosis of asthma in different populations is not completely clear. Methods: This meta-analysis aimed to evaluate the diagnostic accuracy of periostin level in the clinical determination of asthma. Several medical literature data bases were searched for relevant studies through December 1, 2019. The numbers of patients with true-positive, false-positive, false-negative, and true-negative results for the periostin level were extracted from each individual study. We assessed the risk of bias by using Quality Assessment of Diagnostic Accuracy Studies 2. We used the meta-analysis to produce summary estimates of accuracy. Results: In total, nine studies with 1757 subjects met the inclusion criteria. The pooled estimates of sensitivity, specificity, and diagnostic odds ratios for the detection of asthma were 0.58 (95% confidence interval [CI], 0.38‐0.76), 0.86 (95% CI, 0.74‐0.93), and 8.28 (95% CI, 3.67‐18.68), respectively. The area under the summary receiver operating characteristic curve was 0.82 (95% CI, 0.79‐0.85). And significant publication bias was found in this meta‐analysis (p = 0.39). Conclusion: Serum periostin may be used for the diagnosis of asthma, with moderate diagnostic accuracy.

Drug Target Group Prediction with Multiple Drug Networks

2020 ◽  
Vol 23 (4) ◽  
pp. 274-284 ◽  
Author(s):  
Jingang Che ◽  
Lei Chen ◽  
Zi-Han Guo ◽  
Shuaiqun Wang ◽  
Aorigele
Keyword(s):  
Drug Target ◽  
Low Cost ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
Multiple Drug ◽  
Property A ◽  
Multiple Networks ◽  
Proposed Model ◽  
The One

Background: Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments. Methods: In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model. Results and Conclusion: Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

Identify Compounds' Target Against Alzheimer's Disease Based on In-Silico Approach

2019 ◽  
Vol 16 (3) ◽  
pp. 193-208 ◽  
Author(s):  
Yan Hu ◽  
Guangya Zhou ◽  
Chi Zhang ◽  
Mengying Zhang ◽  
Qin Chen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Small Molecule ◽  
Characteristic Curve ◽  
Machine Learning Algorithms ◽  
Learner Model ◽  
Mao B ◽  
Number Of Patients ◽  
Sar Model ◽  
Set Up

Background: Alzheimer's disease swept every corner of the globe and the number of patients worldwide has been rising. At present, there are as many as 30 million people with Alzheimer's disease in the world, and it is expected to exceed 80 million people by 2050. Consequently, the study of Alzheimer’s drugs has become one of the most popular medical topics. Methods: In this study, in order to build a predicting model for Alzheimer’s drugs and targets, the attribute discriminators CfsSubsetEval, ConsistencySubsetEval and FilteredSubsetEval are combined with search methods such as BestFirst, GeneticSearch and Greedystepwise to filter the molecular descriptors. Then the machine learning algorithms such as BayesNet, SVM, KNN and C4.5 are used to construct the 2D-Structure Activity Relationship(2D-SAR) model. Its modeling results are utilized for Receiver Operating Characteristic curve(ROC) analysis. Results: The prediction rates of correctness using Randomforest for AChE, BChE, MAO-B, BACE1, Tau protein and Non-inhibitor are 77.0%, 79.1%, 100.0%, 94.2%, 93.2% and 94.9%, respectively, which are overwhelming as compared to those of BayesNet, BP, SVM, KNN, AdaBoost and C4.5. Conclusion: In this paper, we conclude that Random Forest is the best learner model for the prediction of Alzheimer’s drugs and targets. Besides, we set up an online server to predict whether a small molecule is the inhibitor of Alzheimer's target at http://47.106.158.30:8080/AD/. Furthermore, it can distinguish the target protein of a small molecule.

Discriminating Malignancy in Thyroid Nodules: The Nomogram Versus the Kwak and ACR TI-RADS

2020 ◽  
Vol 163 (6) ◽  
pp. 1156-1165
Author(s):  
Juan Xiao ◽  
Qiang Xiao ◽  
Wei Cong ◽  
Ting Li ◽  
Shouluan Ding ◽  
...  
Keyword(s):  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Diagnostic Study ◽  
Diagnostic Efficiency ◽  
Training Set ◽  
Multivariable Logistic Regression Model ◽  
Predictive Values ◽  
Validation Set ◽  
Sensitivity Specificity

Objective To develop an easy-to-use nomogram for discrimination of malignant thyroid nodules and to compare diagnostic efficiency with the Kwak and American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Study Design Retrospective diagnostic study. Setting The Second Hospital of Shandong University. Subjects and Methods From March 2017 to April 2019, 792 patients with 1940 thyroid nodules were included into the training set; from May 2019 to December 2019, 174 patients with 389 nodules were included into the validation set. Multivariable logistic regression model was used to develop a nomogram for discriminating malignant nodules. To compare the diagnostic performance of the nomogram with the Kwak and ACR TI-RADS, the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values were calculated. Results The nomogram consisted of 7 factors: composition, orientation, echogenicity, border, margin, extrathyroidal extension, and calcification. In the training set, for all nodules, the area under the curve (AUC) for the nomogram was 0.844, which was higher than the Kwak TI-RADS (0.826, P = .008) and the ACR TI-RADS (0.810, P < .001). For the 822 nodules >1 cm, the AUC of the nomogram was 0.891, which was higher than the Kwak TI-RADS (0.852, P < .001) and the ACR TI-RADS (0.853, P < .001). In the validation set, the AUC of the nomogram was also higher than the Kwak and ACR TI-RADS ( P < .05), each in the whole series and separately for nodules >1 or ≤1 cm. Conclusions When compared with the Kwak and ACR TI-RADS, the nomogram had a better performance in discriminating malignant thyroid nodules.

scholarly journals Haemoconcentration as a predictor of severity in acute pancreatitis

2016 ◽  
Vol 4 (1) ◽  
pp. 3-7
Author(s):  
Tanka Prasad Bohara ◽  
Dimindra Karki ◽  
Anuj Parajuli ◽  
Shail Rupakheti ◽  
Mukund Raj Joshi
Keyword(s):  
Acute Pancreatitis ◽  
Pearson Correlation ◽  
Characteristic Curve ◽  
Scoring Systems ◽  
Cost Effective ◽  
Receiver Operator Characteristic Curve ◽  
First Episode ◽  
P Value ◽  
Receiver Operator Characteristic ◽  
Chi Square

Background: Acute pancreatitis is usually a mild and self-limiting disease. About 25 % of patients have severe episode with mortality up to 30%. Early identification of these patients has potential advantages of aggressive treatment at intensive care unit or transfer to higher centre. Several scoring systems are available to predict severity of acute pancreatitis but are cumbersome, take 24 to 48 hours and are dependent on tests that are not universally available. Haematocrit has been used as a predictor of severity of acute pancreatitis but some have doubted its role.Objectives: To study the significance of haematocrit in prediction of severity of acute pancreatitis.Methods: Patients admitted with first episode of acute pancreatitis from February 2014 to July 2014 were included. Haematocrit at admission and 24 hours of admission were compared with severity of acute pancreatitis. Mean, analysis of variance, chi square, pearson correlation and receiver operator characteristic curve were used for statistical analysis.Results: Thirty one patients were included in the study with 16 (51.61%) male and 15 (48.4%) female. Haematocrit at 24 hours of admission was higher in severe acute pancreatitis (P value 0.003). Both haematocrit at admission and at 24 hours had positive correlation with severity of acute pancreatitis (r: 0.387; P value 0.031 and r: 0.584; P value 0.001) respectively.Area under receiver operator characteristic curve for haematocrit at admission and 24 hours were 0.713 (P value 0.175, 95% CI 0.536 - 0.889) and 0.917 (P value 0.008, 95% CI 0.813 – 1.00) respectively.Conclusion: Haematocrit is a simple, cost effective and widely available test and can predict severity of acute pancreatitis.Journal of Kathmandu Medical College, Vol. 4(1) 2015, 3-7

scholarly journals Development of Machine Learning Models to Predict Probabilities and Types of Stroke at Prehospital Stage: the Japan Urgent Stroke Triage Score Using Machine Learning (JUST-ML)

2021 ◽  
Author(s):  
Kazutaka Uchida ◽  
Junichi Kouno ◽  
Shinichi Yoshimura ◽  
Norito Kinjo ◽  
Fumihiro Sakakibara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forests ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Vessel Occlusion ◽  
Predictive Values ◽  
Training Cohort ◽  
Sensitivity Specificity

AbstractIn conjunction with recent advancements in machine learning (ML), such technologies have been applied in various fields owing to their high predictive performance. We tried to develop prehospital stroke scale with ML. We conducted multi-center retrospective and prospective cohort study. The training cohort had eight centers in Japan from June 2015 to March 2018, and the test cohort had 13 centers from April 2019 to March 2020. We use the three different ML algorithms (logistic regression, random forests, XGBoost) to develop models. Main outcomes were large vessel occlusion (LVO), intracranial hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral infarction (CI) other than LVO. The predictive abilities were validated in the test cohort with accuracy, positive predictive value, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F score. The training cohort included 3178 patients with 337 LVO, 487 ICH, 131 SAH, and 676 CI cases, and the test cohort included 3127 patients with 183 LVO, 372 ICH, 90 SAH, and 577 CI cases. The overall accuracies were 0.65, and the positive predictive values, sensitivities, specificities, AUCs, and F scores were stable in the test cohort. The classification abilities were also fair for all ML models. The AUCs for LVO of logistic regression, random forests, and XGBoost were 0.89, 0.89, and 0.88, respectively, in the test cohort, and these values were higher than the previously reported prediction models for LVO. The ML models developed to predict the probability and types of stroke at the prehospital stage had superior predictive abilities.

Sign in / Sign up

Export Citation Format

Share Document