scholarly journals Deep Learning-Based Image Segmentation of Cone-Beam Computed Tomography Images for Oral Lesion Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Xueling Wang ◽  
Xianmin Meng ◽  
Shu Yan
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Oral Lesion ◽  
Cone Beam ◽  
Control Group ◽  
Oral Lesions ◽  
Manual Segmentation ◽  
Blank Group ◽  
And Control ◽  
Experimental Group

This paper aimed to study the adoption of deep learning (DL) algorithm of oral lesions for segmentation of cone-beam computed tomography (CBCT) images. 90 patients with oral lesions were taken as research subjects, and they were grouped into blank, control, and experimental groups, whose images were treated by the manual segmentation method, threshold segmentation algorithm, and full convolutional neural network (FCNN) DL algorithm, respectively. Then, effects of different methods on oral lesion CBCT image recognition and segmentation were analyzed. The results showed that there was no substantial difference in the number of patients with different types of oral lesions among three groups ( P > 0.05 ). The accuracy of lesion segmentation in the experimental group was as high as 98.3%, while those of the blank group and control group were 78.4% and 62.1%, respectively. The accuracy of segmentation of CBCT images in the blank group and control group was considerably inferior to the experimental group ( P < 0.05 ). The segmentation effect on the lesion and the lesion model in the experimental group and control group was evidently superior to the blank group ( P < 0.05 ). In short, the image segmentation accuracy of the FCNN DL method was better than the traditional manual segmentation and threshold segmentation algorithms. Applying the DL segmentation algorithm to CBCT images of oral lesions can accurately identify and segment the lesions.

scholarly journals Application of Deep Learning-Based Integrated Trial-Error + Science, Technology, Reading/Writing, Engineer, Arts, Mathematics Teaching Mode in College Entrepreneurship Education

2021 ◽  
Vol 12 ◽  
Author(s):  
Guangfu Qu ◽  
Wenbo Hu ◽  
Wenxiu Jiao ◽  
Jiangbo Jin
Keyword(s):  
Deep Learning ◽  
Teaching Methods ◽  
Scientific Literacy ◽  
Teaching Method ◽  
Entrepreneurship Education ◽  
Control Group ◽  
Teaching Concept ◽  
Depth Analysis ◽  
And Control ◽  
Experimental Group

The purpose is to achieve a high-quality teaching effect in quality education using the new teaching concept. Firstly, the Deep Learning (DL) theory is introduced to improve the trial-error teaching method, then the trial-error teaching is combined with STREAM education. Afterward, the conical section hyperbola teaching in college entrepreneurship education is specifically studied under experimental analysis using the proposed DL-based integrated trail-error + STREAM teaching methods. The experimental results read: student’s average veracity on the multiple-choice question is 93.4% and 90.1% for the experimental group and control group, respectively; student’s average veracity on short-answer questions is 92.3% and 90.3% for the experimental group and control group, respectively. The results show that the application of DL to the trial-error teaching method can cultivate students’ in-depth analysis and logical thinking ability for mathematical problems. Meanwhile, the DL-based integrated trial-error + STREAM teaching methods stimulate students’ initiative to learn more difficult knowledge, establish integral knowledge systems, and more comprehensively and deeply understand the teaching content. As a result, students’ scientific literacy and humanistic literacy are both improved. Therefore, the proposed DL-based integrated trial-error + STREAM teaching method in college entrepreneurship education has a guiding significance for other disciplines and provides ideas for the expansion and development of STREAM teaching in the future.

scholarly journals Deep Learning-Based Computed Tomography Image Features in the Detection and Diagnosis of Perianal Abscess Tissue

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Song Han ◽  
Jun Yang ◽  
Jihua Xu
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Perianal Abscess ◽  
Ct Images ◽  
Image Features ◽  
Control Group ◽  
Dice Coefficient ◽  
Multislice Spiral Ct ◽  
Detection And Diagnosis ◽  
Experimental Group

The performance characteristics of deep learning fully convolutional neural network (DLFCNN) algorithm-based computed tomography (CT) images were investigated in the detection and diagnosis of perianal abscess tissue. 60 patients who were medically diagnosed as perianal abscesses in the hospital were selected as the experimental group, and 60 healthy volunteers were selected as the control group. In this study, the DLFCNN algorithm based on deep learning was compared with the CNN algorithm and applied to the segmentation training of CT images of patients with perianal abscesses. Then, the segmentation metrics Jaccard, Dice coefficient, precision rate, and recall rate were compared by extracting the region of interest. The results showed that Jaccard (0.7326) calculated by the CNN algorithm was sharply lower than that of the DLFCNN algorithm (0.8525), and the Dice coefficient (0.7264) was also steeply lower than that of the DLFCNN algorithm (0.8434) ( P < 0.05 ). The thickness range of the epidermis and dermis in patients from the experimental group was 4.1–4.9 mm, which was markedly greater than the range of the control group (1.8–3.6 mm) ( P < 0.05 ). Besides, the CT value of the subcutaneous fascia in the experimental group (−95.45 ± 8.26) hugely reduced compared with the control group (−76.34 ± 7.69) ( P < 0.05 ). The accuracy rate of the patients with perianal abscesses was 96.67% by multislice spiral CT (MSCT). Therefore, the DLFCNN algorithm in this study had good stability and good segmentation effect. The skin at the focal site of anal abscess was obviously thickened, and it was simple and accurate to use CT images in the diagnosis of patients with perianal abscesses, which could effectively locate the lesion and clarify the relationship between the lesion and the surrounding structure.

The Effect of Applying POSSE (Predict- Organize-Search-Summarize-Evaluate) on the Students’ Reading Comprehension

2013 ◽  
Vol 2 (1) ◽  
Author(s):  
Eka Rejeki Maha ◽  
Berlin Sibarani
Keyword(s):  
Reading Comprehension ◽  
Experimental Design ◽  
Null Hypothesis ◽  
Alternative Hypothesis ◽  
Choice Test ◽  
Control Group ◽  
Multiple Choice Test ◽  
Level Of Significance ◽  
And Control ◽  
Experimental Group

This study was aimed at finding out The Effect of Applying POSSE (Predict-Organize-Search-Summarize-Evaluate) Strategy on the Students’ Reading Comprehension. This study used the experimental design. The population of this study was the students of SMA Negeri 2 Medan. There were sixty students taken as the sample of the research. This study was conducted with two randomized groups namely experimental and control group. The experimental group was taught by applying POSSE strategy while control group was taught without applying POSSE strategy. The instrument of collecting the data was multiple choice test which consists of 40 items. To obtain the reliability of the test, the researcher used Kuder-Richardson (KR-21). The calculation shows the reliability was 0.81(high). The data were analyzed by using t-test. The calculation shows that t-observed (4.76) is higher than t-table (2.00) at the level of significance (α) 0.05 with the degree of freedom (df) 58. Therefore, the null hypothesis (Ho) is rejected and alternative hypothesis (Ha) is accepted. It means that there was a significant effect of applying POSSE strategy on the students’ reading comprehension. Keywords: POSSE Strategy, Reading Comprehension.

The Effect of Applying Learning Together Method on the Students’ Reading Comprehension

2012 ◽  
Vol 1 (2) ◽  
Author(s):  
Haryato Siregar ◽  
Elia Masa Ginting
Keyword(s):  
Reading Comprehension ◽  
Alternative Hypothesis ◽  
Choice Test ◽  
Control Group ◽  
Teaching Reading ◽  
Multiple Choice Test ◽  
Level Of Significance ◽  
And Control ◽  
Experimental Group ◽  
Learning Together

This study was aimed at finding out the effect of applying Learning Together Method on the students’ reading comprehension. This study used the experimental design. The population of this study was the students of SMP Negeri 1 Muara. There were sixty students of eighth class as the sample of the research. This study was conducted with two randomized groups namely experimental and control group. The experimental group was taught by applying Learning Together Method while control group was taught without applying Learning Together Method. The instrument of collecting the data was multiple choice test which consists of 20 items. To obtain the reliability of the test, the researcher used Kuder-Richardson (KR-21) formula. The calculation shows the reliability was 0.82(high). The data were analyzed by using t-test. The calculation shows that t-observed (4.9) is higher than t-table (2.00) at the level of significance (α) 0.05 with the degree of freedom (df) 58. Therefore, the null hypothesis (Ho) is rejected and alternative hypothesis (Ha) is accepted. It means that teaching reading comprehension by applying Learning Together Method significantly affect reading comprehension. Keywords: Learning Together Method, Reading Comprehension

THE EFFECT OF APPLYING ANIMAL CARTOON PICTURES ON STUDENTS’ ACHIEVEMENT IN WRITING NARRATIVE TEXT

2017 ◽  
Vol 6 (1) ◽  
Author(s):  
Hasanul Arifin Zul And Masitowarni Siregar
Keyword(s):  
T Test ◽  
Narrative Text ◽  
Control Group ◽  
First Year ◽  
Writing Achievement ◽  
Control Groups ◽  
Post Test ◽  
Written Test ◽  
And Control ◽  
Experimental Group

This thesis is focused on the investigation of the effect of applying animal cartoon pictures on students’ achievement in writing narrative text. This study aims to find whether applying animal cartoon pictures significantly affect the students’ writing achievement or not. The data in this study were obtained by administering a written test. The population was the 2015/2016 first year (grade XI) of SMA Swasta Nusantara Lubuk Pakam and 66 students were taken as the sample by using random sampling. The sample was divided into two groups, experimental and control groups. The experimental group was taught by applying animal cartoon pictures while the control group without animal cartoon pictures (x = lecturing). The data were taken the scores from the pre-test and post-test to both experimental and control groups. These data were analyzed by using t-test. The result of computing the t-test obviously showed that t-observed is higher than t-table (5.21 >1,67) with the degree of freedom 64 (df =N-2) at the level significance 0,05 one tail test. It showed that the application of animal cartoon pictures significantly affected the students of SMA Swasta Nusantara Lubuk Pakam achievement in writing narrative text.

THE EFFECT OF PEER REVIEW STRATEGY ON THE STUDENTS’ ACHIEVEMENT IN WRITING DESCRIPTIVE PARAGRAPH

2015 ◽  
Vol 4 (2) ◽  
Author(s):  
Sri Agus Murniasih And I Wayan Dirgeyasa
Keyword(s):  
Peer Review ◽  
Experimental Research ◽  
Research Method ◽  
Alternative Hypothesis ◽  
Control Group ◽  
Post Test ◽  
Class Viii ◽  
And Control ◽  
Essay Test ◽  
Experimental Group

This study was conducted to know the effect of applying Peer Review Strategy on the students’ achievement in writing descriptive paragraph. It was conducted by using experimental research method. This research design was conducted pre-test, post test in experimental and control group. The population of this research was the eight (VIII) grade students of SMP IT IQRA’ Medan. The sample of this research was taken by lottery technique. They were in class VIII-1 by experimental group and the class VIII-2 by control group. The experimental group was taught by using Peer Review Strategy while the control group was given no treatment. The instrument used to collect the data was writing essay test. The data were analyzed by using t-test formula. The result showed that the value of t-observed was higher than the value of t-table. (3,55 > 2,05 (a = 0.05)) with the degree of freedom (df) = 28. It means that there was a significant effect of applying Peer Review Strategy on the students’ achievement in writing descriptive paragraph. So, the alternative hypothesis (Ha) was accepted.

THE EFFECT OF APPLYING DEMONSTRATION METHOD ON STUDENTS’ ACHIEVEMENT IN SPEAKING SKILL AT THE THIRD GRADE OF SMK PAB 3 MEDAN ESTATE

2015 ◽  
Vol 4 (2) ◽  
Author(s):  
Meryanti Napitupulu And Anni Holila Pulungan
Keyword(s):  
High School ◽  
Control Group ◽  
Vocational High School ◽  
Control Groups ◽  
Speaking Test ◽  
The Third ◽  
Speaking Skill ◽  
The Subject ◽  
And Control ◽  
Experimental Group

This study was conducted as an attempt to discover the effect of applying Demonstration Method on students’ achievement in speaking skill. It was an experimental research. The subject was students of Grade XII, Vocational High School (Sekolah Menengah Kejuruan: SMK), which consisted of 79 students. The research was divided into two groups: experimental and control groups. The instrument used to collect the data was speaking test. To obtain the reliability of the test, the writer applied Kuder Richardson 21 formula. The result of the reliability was 0.7, and it was found that the test was reliable. The data were analyzed by using t-test formula. The analysis showed that the scores of the students in the experimental group were significantly higher than the scores of the students in the control group at the level of significant m = 0.05 with the degree of freedom (df) 77, t-observed value 8.9 > t-table value 1.99. The findings indicate that using Demonstration Method significantly affected the students’ achievement in speaking skill. So, English teachers are suggested to use Demonstration Method in order to improve students’ achievement in speaking skill.

THE EFFECT OF RAP (READ, ASK, PARAPHRASE) STRATEGY ON STUDENTS’ READING COMPREHENSION IN READING ANALYTICAL EXPOSITION TEXT

2015 ◽  
Vol 4 (3) ◽  
Author(s):  
Veronika N. And Lince Sihombing
Keyword(s):  
Reading Comprehension ◽  
Experimental Design ◽  
T Test ◽  
Control Group ◽  
Multiple Choice Tests ◽  
Choice Tests ◽  
Second Year ◽  
Level Of Significance ◽  
And Control ◽  
Experimental Group

This study focused on finding out the effect of applying RAP (Read, Ask,Paraphrase) Strategy on students’ reading comprehension in reading analyticalexposition text. This study was conducted in experimental design. The populationof this research was the second year of students in SMA Swasta Katolik BudiMurni 2 Medan. There were seventy students of the second year senior highschool students as the sample of the research. This study was conducted with tworandomized groups namely Experimental Group and Control Group. Theexperimental group was taught by applying RAP Strategy, while the control groupwas taught by applying conventional strategy. The instrument of collecting thedata was multiple choice tests which consisted of 25 items. The data wereanalyzed by using t-test formula. The calculation shown that t-observed (5.36)was higher than t-table (1.994) at the level of significance (α) 0.05 with the degreeof freedom (df) 68. It means that there was a significant effect of applying RAPStrategy on students’ reading comprehension in reading analytical exposition text.

THE EFFECT OF APPLYING SQ3R METHOD ON STUDENTS’ ACHIEVEMENT IN READING COMPREHENSION

2013 ◽  
Vol 2 (2) ◽  
Author(s):  
Pranata Royganda Sihaloho And Masitowarni Siregar
Keyword(s):  
Reading Comprehension ◽  
Research Design ◽  
Conventional Method ◽  
Experimental Research ◽  
T Test ◽  
Control Group ◽  
Multiple Choice Tests ◽  
Choice Tests ◽  
And Control ◽  
Experimental Group

The aim of this study is to discover the effect of applying SQ3R method inreading comprehension. Experimental research design is used as the research method.This research took place at SMA Nasrani 2Medan. There were 2 classes chosen as thesample with 30 students in each class. The classes were divided into two groups namelyexperimental and control group. The experimental group was taught by using SQ3Rmethod and the control group was taught by using conventional method. The instrumentused to collect the data was a set of multiple choice tests, which divided as pre test andpost test. The result of the research was analyzed by using t-test formula. The resultshowed that t-test was higher than t-table (4,23>2,00) at the level of significant 0,05with degree of freedom (df) 58. It means that hypothesis alternative (Ha) is acceptedwhich shows that SQ3R method significantly improves the student’s readingcomprehension.

Using Concept Oriented Reading Instruction (CORI) to Promote Students’ Reading Comprehension

2017 ◽  
Vol 2 (1) ◽  
pp. 42
Author(s):  
Hilma Suryani
Keyword(s):  
Reading Achievement ◽  
Reading Instruction ◽  
Reading Strategies ◽  
Posttest Score ◽  
T Test ◽  
Control Group ◽  
Quasi Experimental ◽  
Effective Reading Strategies ◽  
And Control ◽  
Experimental Group

The problem of this study is “Does Concept Oriented Reading Instruction (CORI) enhance students’ reading achievement?” The design of this study was quasi-experimental. The sample of this study was taken from the population by using purposive sampling. The experimental group consisted of 39 students while the control group consisted of 35 students. The data were collected by using two instruments; test and questionnaire. The test was given twice to each group in order to see whether or not there was significance difference of pretest and posttest either in experimental or control group and whether or not there was significance difference of experimental and control group in terms of their posttest score. To prove the hypothesis, the data from pretest and posttest of experimental and control group were analyzed by applying paired sample t-test and independent sample t-test. The calculation was run by using SPSS computer program. The result of the study shows there was significance difference of students’ reading achievement between experimental and control group. Besides, the use of CORI as reading strategies was proved as effective reading strategies to enhance students’ reading achievement. Keywords: Concept Oriented Reading Instruction; reading strategy; reading achievement

Sign in / Sign up

Export Citation Format

Share Document