scholarly journals Comparison of deep learning and conventional machine learning methods for classification of colon polyp types

2021 ◽  
Vol 5 (1) ◽  
pp. 34-42
Author(s):  
Refika Sultan Doğan ◽  
Bülent Yılmaz
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
White Light ◽  
Narrow Band ◽  
Optical Biopsy ◽  
Colon Polyps ◽  
Tissue Biopsy ◽  
Conventional Machine ◽  
White Light Imaging

AbstractDetermination of polyp types requires tissue biopsy during colonoscopy and then histopathological examination of the microscopic images which tremendously time-consuming and costly. The first aim of this study was to design a computer-aided diagnosis system to classify polyp types using colonoscopy images (optical biopsy) without the need for tissue biopsy. For this purpose, two different approaches were designed based on conventional machine learning (ML) and deep learning. Firstly, classification was performed using random forest approach by means of the features obtained from the histogram of gradients descriptor. Secondly, simple convolutional neural networks (CNN) based architecture was built to train with the colonoscopy images containing colon polyps. The performances of these approaches on two (adenoma & serrated vs. hyperplastic) or three (adenoma vs. hyperplastic vs. serrated) category classifications were investigated. Furthermore, the effect of imaging modality on the classification was also examined using white-light and narrow band imaging systems. The performance of these approaches was compared with the results obtained by 3 novice and 4 expert doctors. Two-category classification results showed that conventional ML approach achieved significantly better than the simple CNN based approach did in both narrow band and white-light imaging modalities. The accuracy reached almost 95% for white-light imaging. This performance surpassed the correct classification rate of all 7 doctors. Additionally, the second task (three-category) results indicated that the simple CNN architecture outperformed both conventional ML based approaches and the doctors. This study shows the feasibility of using conventional machine learning or deep learning based approaches in automatic classification of colon types on colonoscopy images.

scholarly journals Automating Visual Blockage Classification of Culverts with Deep Learning

2021 ◽  
Vol 11 (16) ◽  
pp. 7561
Author(s):  
Umair Iqbal ◽  
Johan Barthelemy ◽  
Wanqing Li ◽  
Pascal Perez
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
False Negative ◽  
Hydraulic Modeling ◽  
Machine Learning Algorithms ◽  
Visual Features ◽  
Learning Approaches ◽  
Learning Models ◽  
Conventional Machine

Blockage of culverts by transported debris materials is reported as the salient contributor in originating urban flash floods. Conventional hydraulic modeling approaches had no success in addressing the problem primarily because of the unavailability of peak floods hydraulic data and the highly non-linear behavior of debris at the culvert. This article explores a new dimension to investigate the issue by proposing the use of intelligent video analytics (IVA) algorithms for extracting blockage related information. The presented research aims to automate the process of manual visual blockage classification of culverts from a maintenance perspective by remotely applying deep learning models. The potential of using existing convolutional neural network (CNN) algorithms (i.e., DarkNet53, DenseNet121, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, VGG16, EfficientNetB3, NASNet) is investigated over a dataset from three different sources (i.e., images of culvert openings and blockage (ICOB), visual hydrology-lab dataset (VHD), synthetic images of culverts (SIC)) to predict the blockage in a given image. Models were evaluated based on their performance on the test dataset (i.e., accuracy, loss, precision, recall, F1 score, Jaccard Index, region of convergence (ROC) curve), floating point operations per second (FLOPs) and response times to process a single test instance. Furthermore, the performance of deep learning models was benchmarked against conventional machine learning algorithms (i.e., SVM, RF, xgboost). In addition, the idea of classifying deep visual features extracted by CNN models (i.e., ResNet50, MobileNet) using conventional machine learning approaches was also implemented in this article. From the results, NASNet was reported most efficient in classifying the blockage images with the 5-fold accuracy of 85%; however, MobileNet was recommended for the hardware implementation because of its improved response time with 5-fold accuracy comparable to NASNet (i.e., 78%). Comparable performance to standard CNN models was achieved for the case where deep visual features were classified using conventional machine learning approaches. False negative (FN) instances, false positive (FP) instances and CNN layers activation suggested that background noise and oversimplified labelling criteria were two contributing factors in the degraded performance of existing CNN algorithms. A framework for partial automation of the visual blockage classification process was proposed, given that none of the existing models was able to achieve high enough accuracy to completely automate the manual process. In addition, a detection-classification pipeline with higher blockage classification accuracy (i.e., 94%) has been proposed as a potential future direction for practical implementation.

Transfer learning based convolution neural net for authentication and classification of emotions from natural and stimulated speech signals

2021 ◽  
pp. 1-12
Author(s):  
Mukul Kumar ◽  
Nipun Katyal ◽  
Nersisson Ruban ◽  
Elena Lyakso ◽  
A. Mary Mekala ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Transfer Learning ◽  
Research Work ◽  
Oral Communication ◽  
Neural Net ◽  
Emotion Classification ◽  
Style Transfer ◽  
Conventional Machine ◽  
Neural Network Algorithm

Over the years the need for differentiating various emotions from oral communication plays an important role in emotion based studies. There have been different algorithms to classify the kinds of emotion. Although there is no measure of fidelity of the emotion under consideration, which is primarily due to the reason that most of the readily available datasets that are annotated are produced by actors and not generated in real-world scenarios. Therefore, the predicted emotion lacks an important aspect called authenticity, which is whether an emotion is actual or stimulated. In this research work, we have developed a transfer learning and style transfer based hybrid convolutional neural network algorithm to classify the emotion as well as the fidelity of the emotion. The model is trained on features extracted from a dataset that contains stimulated as well as actual utterances. We have compared the developed algorithm with conventional machine learning and deep learning techniques by few metrics like accuracy, Precision, Recall and F1 score. The developed model performs much better than the conventional machine learning and deep learning models. The research aims to dive deeper into human emotion and make a model that understands it like humans do with precision, recall, F1 score values of 0.994, 0.996, 0.995 for speech authenticity and 0.992, 0.989, 0.99 for speech emotion classification respectively.

scholarly journals Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning

2021 ◽  
Vol 11 (7) ◽  
pp. 3119
Author(s):  
Cristina L. Saratxaga ◽  
Jorge Bote ◽  
Juan F. Ortega-Morán ◽  
Artzai Picón ◽  
Elena Terradillos ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Data Augmentation ◽  
Optical Biopsy ◽  
Colon Polyps ◽  
Optical Coherence ◽  
Colon Lesion ◽  
Patient Prognosis ◽  
B Scan Images

(1) Background: Clinicians demand new tools for early diagnosis and improved detection of colon lesions that are vital for patient prognosis. Optical coherence tomography (OCT) allows microscopical inspection of tissue and might serve as an optical biopsy method that could lead to in-situ diagnosis and treatment decisions; (2) Methods: A database of murine (rat) healthy, hyperplastic and neoplastic colonic samples with more than 94,000 images was acquired. A methodology that includes a data augmentation processing strategy and a deep learning model for automatic classification (benign vs. malignant) of OCT images is presented and validated over this dataset. Comparative evaluation is performed both over individual B-scan images and C-scan volumes; (3) Results: A model was trained and evaluated with the proposed methodology using six different data splits to present statistically significant results. Considering this, 0.9695 (±0.0141) sensitivity and 0.8094 (±0.1524) specificity were obtained when diagnosis was performed over B-scan images. On the other hand, 0.9821 (±0.0197) sensitivity and 0.7865 (±0.205) specificity were achieved when diagnosis was made considering all the images in the whole C-scan volume; (4) Conclusions: The proposed methodology based on deep learning showed great potential for the automatic characterization of colon polyps and future development of the optical biopsy paradigm.

scholarly journals Evaluating Laryngopharyngeal Tumor Extension Using Narrow Band Imaging Versus Conventional White Light Imaging

2021 ◽  
Author(s):  
Manon A. Zwakenberg ◽  
Gyorgy B. Halmos ◽  
Jan Wedman ◽  
Bernard F. A. M. Laan ◽  
Boudewijn E. C. Plaat
Keyword(s):  
White Light ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Tumor Extension ◽  
White Light Imaging

scholarly journals P236 Evaluation of histological inflammation by a novel image enhanced endoscopy technique, dual red imaging, in patients with ulcerative colitis: Preliminary study

2020 ◽  
Vol 14 (Supplement_1) ◽  
pp. S261-S261
Author(s):  
K FUJIMOTO ◽  
K Watanabe ◽  
K Hori ◽  
K Kaku ◽  
N Kinoshita ◽  
...  
Keyword(s):  
Ulcerative Colitis ◽  
White Light ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Topical Steroid ◽  
Treatment Goal ◽  
Practical Approach ◽  
Mayo Score ◽  
White Light Imaging ◽  
Pathological Assessment

Abstract Background Endoscopic remission is the ideal treatment goal for patients with ulcerative colitis (UC) in clinical practice. However, several recent investigations tried to evaluate histological healing as a more optimal treatment goal. The assessment of histological healing, however, is usually inconvenient and time-consuming because of the requirement of a biopsy and pathological assessment. Dual red imaging (DRI; Olympus Corporation, Japan) is a novel image enhanced endoscopy technique that can visualise the inflammation, including that in the surface crypt, and vessel findings of the brownish surface or green-coloured deeper layer of the mucosa in contrast to narrow band imaging. We preliminarily evaluated the utility of DRI in the assessment of histological healing in UC as a practical approach. Methods We enrolled UC patients who provided consent from May 2018 to September 2019 in our hospital, and performed colonoscopy in the entire colon with white-light imaging and DRI, and then endoscopic pictures and biopsy samples were obtained. Central pathological assessment of histological inflammation based on the Nancy index with individual items was performed for each biopsy sample. We also assessed the clinical background, UC activity according to the Mayo score, white-light endoscopic activity according to the Mayo endoscopic subscore (MES), and DRI findings using a 5-point scale. Results We evaluated a total of 90 sets of DRI and pathological findings from 47 UC patients (20 females; median age, 42 [20–84] years; 25 with pancolitis, 17 left-sided colitis, 3 proctitis, and 2 others; median duration of disease, 83 [1–379] months; median Mayo score, 2 [0–11]). Participants were treated with 5-aminosalicylates (38 oral; 7 topical), steroid (4 systemic; 6 topical), immunomodulator (7), anti-TNF agents (5), tofacitinib (3), and tacrolimus (8). Both the MES (r = 0.70) and DRI scale (r = 0.65) correlated well with the Nancy index. Among individual pathological items with respect to inflammation, ulceration (r = 0.69), chronic inflammatory infiltrate (r = 0.66), neutrophils in the lamina propria (r = 0.65), and serrated architectural abnormalities (r = 0.60) correlated well with the Nancy index in contrast to other pathological items. DRI seemed to facilitate the visualisation of histological inflammation in deeper layers of the mucosa compared with white-light imaging or narrow-band imaging. Conclusion The novel DRI technique has potential in the evaluation of histological inflammation without the requirement of a biopsy in patients with UC as a practical approach. A further prospective multicenter study in this regard is needed.

scholarly journals Machine Learning and Deep Learning Techniques, Features and Obstacles in the Cataract Diagnosis

2020 ◽  
Vol 9 (3) ◽  
pp. 87-93
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Literature Review ◽  
Congenital Cataract ◽  
Low Cost ◽  
Current Situation ◽  
Learning Techniques ◽  
Research Questions ◽  
New Research

Cataract is a degenerative condition that, according to estimations, will rise globally. Even though there are various proposals about its diagnosis, there are remaining problems to be solved. This paper aims to identify the current situation of the recent investigations on cataract diagnosis using a framework to conduct the literature review with the intention of answering the following research questions: RQ1) Which are the existing methods for cataract diagnosis? RQ2) Which are the features considered for the diagnosis of cataracts? RQ3) Which is the existing classification when diagnosing cataracts? RQ4) And Which obstacles arise when diagnosing cataracts? Additionally, a cross-analysis of the results was made. The results showed that new research is required in: (1) the classification of “congenital cataract” and, (2) portable solutions, which are necessary to make cataract diagnoses easily and at a low cost.

Sign in / Sign up

Export Citation Format

Share Document