Deep Learning-Based Automated Mole Detection: An Algorithm with Future Implication for Tele-dermatology (Preprint)

2020 ◽  
Author(s):  
Quoc-Viet Tran ◽  
Yen-Po Chin ◽  
Phung-Anh Nguyen ◽  
Ming-Yang Lee ◽  
Hsuan-Chia Yang ◽  
...  
Keyword(s):  
Public Health ◽  
Deep Learning ◽  
Automatic Segmentation ◽  
Confidence Score ◽  
Skin Lesions ◽  
Average Precision ◽  
Health Events ◽  
Bounding Boxes ◽  
Future Implication ◽  
Deep Learning Model

BACKGROUND The automatic segmentation of skin lesions has been reported using the data of dermoscopic images. It is, however, not applicable to real-time detection using a smartphone. OBJECTIVE This study aims to examine a deep learning model for detecting and localizing positions of the mole on the captured images to precisely extract the crop images of the model without any other objects. METHODS The data were collected through public health events in Taiwan between December 2017 and February 2019. All the participants who concerned about the risk of their moles were asked to take the mole-images. Images were then measured and determined the risks by three dermatologists. We labeled the mole position with bounding boxes using the ‘LabelImg’ tool. Two architectures, SSD and Faster-RCNN, have been used to build eight different mole-detection models. The confidence score, intersection over union (IoU), and mean average precision (mAP) with the COCO metrics were used to measure the accuracy of those models. RESULTS 2790-mole images were used for the development and the validation of the models. The Faster-RCNN Inception Resnet model had the highest overall mAP of 0.245, following by 0.234 of the Faster-RCNN Resnet 101, and 0.227 of the Faster-RCNN Resnet 50 model. The SSD Mobilenet v1 model had the lowest mAP of 0.142. The Faster-RCNN Inception Resnet model had a dominant AP of 0.377, 0.236, and 0.129 for the large, medium, and small size of moles. We observed that the Faster RCNN Inception Resnet has shown the best performance with the high confident scores (over 97%) for all kinds of moles. CONCLUSIONS We successfully developed the detection models based on the techniques of SSD and Faster-RCNN. These models might help researchers to localize accurately the position of the moles with its risks as a feasible detection app on the smartphone. We provided the pre-trained models for further studies via GitHub link, https://github.com/vietdaica/Mole_Detection.

scholarly journals USING EDGECONV TO IMPROVE 3D OBJECT DETECTION FROM RGB-D DATA

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 835-839
Author(s):  
W. Lin ◽  
Y. Chen ◽  
C. Wang ◽  
J. Li
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Detection Efficiency ◽  
Point Clouds ◽  
Object Localization ◽  
Average Precision ◽  
Structure Information ◽  
Bounding Boxes ◽  
3D Object Detection ◽  
Deep Learning Model

<p><strong>Abstract.</strong> In this paper, we proposed a novel 3D deep learning model for object localization and object bounding boxes estimation. To increase the detection efficiency of small objects in the large scale scenes, the local neighbourhood geometric structure information of objects has been taken into the Edgeconv model, which can operate the original point clouds. We evaluated the 3D bounding box with high resolution in the RGB-D dataset and acquired stable effectiveness even under the sparse points and the strong occlusion. The experimental results indicate that our method achieved the higher mean average precision and better IOU of bounding boxes in SUN RGB-D dataset and KITTI benchmark.</p>

scholarly journals GLE-Net: A Global and Local Ensemble Network for Aerial Object Detection

2022 ◽  
Vol 15 (1) ◽  
Author(s):  
Jiajia Liao ◽  
Yujun Liu ◽  
Yingchao Piao ◽  
Jinhe Su ◽  
Guorong Cai ◽  
...  
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Aerial Images ◽  
Visual Object ◽  
Detection Algorithms ◽  
Integration Strategy ◽  
Bounding Boxes ◽  
Global And Local ◽  
Deep Learning Model

AbstractRecent advances in camera-equipped drone applications increased the demand for visual object detection algorithms with deep learning for aerial images. There are several limitations in accuracy for a single deep learning model. Inspired by ensemble learning can significantly improve the generalization ability of the model in the machine learning field, we introduce a novel integration strategy to combine the inference results of two different methods without non-maximum suppression. In this paper, a global and local ensemble network (GLE-Net) was proposed to increase the quality of predictions by considering the global weights for different models and adjusting the local weights for bounding boxes. Specifically, the global module assigns different weights to models. In the local module, we group the bounding boxes that corresponding to the same object as a cluster. Each cluster generates a final predict box and assigns the highest score in the cluster as the score of the final predict box. Experiments on benchmarks VisDrone2019 show promising performance of GLE-Net compared with the baseline network.

Smart Street Litter Detection and Classification Based on Faster R-CNN and Edge Computing

2020 ◽  
Vol 30 (04) ◽  
pp. 537-553
Author(s):  
Ping Ping ◽  
Guoyan Xu ◽  
Effendy Kumala ◽  
Jerry Gao
Keyword(s):  
Public Health ◽  
Deep Learning ◽  
Mobile Devices ◽  
Service System ◽  
Environment And Public Health ◽  
City Environment ◽  
Edge Based ◽  
Cleaning Methods ◽  
City Systems ◽  
Deep Learning Model

Cleanliness of city streets has an important impact on city environment and public health. Conventional street cleaning methods involve street sweepers going to many spots and manually confirming if the street needs to be clean. However, this method takes a substantial amount of manual operations for detection and assessment of street’s cleanliness which leads to a high cost for cities. Using pervasive mobile devices and AI technology, it is now possible to develop smart edge-based service system for monitoring and detecting the cleanliness of streets at scale. This paper explores an important aspect of cities — how to automatically analyze street imagery to understand the level of street litter. A vehicle (i.e. trash truck) equipped with smart edge station and cameras is used to collect and process street images in real time. A deep learning model is developed to detect, classify and analyze the diverse types of street litters such as tree branches, leaves, bottles and so on. In addition, two case studies are reported to show its strong potential and effectiveness in smart city systems.

scholarly journals Detection of acne by deep learning object detection

2021 ◽  
Author(s):  
Amandip Sangha ◽  
Mohammad Rizvi
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
State Of The Art ◽  
Average Precision ◽  
Single Class ◽  
Data Set ◽  
Detection Model ◽  
Model Predictions ◽  
Deep Learning Model ◽  
Facial Acne

AbstractImportanceState-of-the art performance is achieved with a deep learning object detection model for acne detection. There is little current research on object detection in dermatology and acne in particular. As such, this work is early in this field and achieves state of the art performance.ObjectiveTrain an object detection model on a publicly available data set of acne photos.Design, Setting, and ParticipantsA deep learning model is trained with cross validation on a data set of facial acne photos.Main Outcomes and MeasuresObject detection models for detecting acne for single-class (acne) and multi-class (four severity levels). We train and evaluate the models using standard metrics such as mean average precision (mAP). Then we manually evaluate the model predictions on the test set, and calculate accuracy in terms of precision, recall, F1, true and false positive and negative detections.ResultsWe achieve state-of-the art mean average precision [email protected] value of 37.97 for the single class acne detection task, and 26.50 for the 4-class acne detection task. Moreover, our manual evaluation shows that the single class detection model performs well on the validation set, achieving true positive 93.59 %, precision 96.45 % and recall 94.73 %.Conclusions and RelevanceWe are able to train a high-accuracy acne detection model using only a small publicly available data set of facial acne. Transfer learning on the pre-trained deep learning model yields good accuracy and high degree of transferability to patient submitted photographs. We also note that the training of standard architecture object detection models has given significantly better accuracy than more intricate and bespoke neural network architectures in the existing research literature.Key PointsQuestionCan deep learning-based acne detection models trained on a small data set of publicly available photos of patients with acne achieve high prediction accuracy?FindingsWe find that it is possible to train a reasonably good object detection model on a small, annotated data set of acne photos using standard deep learning architectures.MeaningDeep learning-based object detection models for acne detection can be a useful decision support tools for dermatologists treating acne patients in a digital clinical practice. It can prove a particularly useful tool for monitoring the time evolution of the acne disease state over prolonged time during follow-ups, as the model predictions give a quantifiable and comparable output for photographs over time. This is particularly helpful in teledermatological consultations, as a prediction model can be integrated in the patient-doctor remote communication.

scholarly journals Deep learning approach for automatic segmentation of ulna and radius in dual-energy X-ray imaging

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Fan Yang ◽  
Xin Weng ◽  
Yuehong Miao ◽  
Yuhui Wu ◽  
Hong Xie ◽  
...  
Keyword(s):  
Deep Learning ◽  
Automatic Segmentation ◽  
Dual Energy ◽  
Learning Approach ◽  
Mineral Density ◽  
X Ray ◽  
X Ray Imaging ◽  
Residual Block ◽  
Deep Learning Model ◽  
Fold Cross Validation

Abstract Background Segmentation of the ulna and radius is a crucial step for the measurement of bone mineral density (BMD) in dual-energy X-ray imaging in patients suspected of having osteoporosis. Purpose This work aimed to propose a deep learning approach for the accurate automatic segmentation of the ulna and radius in dual-energy X-ray imaging. Methods and materials We developed a deep learning model with residual block (Resblock) for the segmentation of the ulna and radius. Three hundred and sixty subjects were included in the study, and five-fold cross-validation was used to evaluate the performance of the proposed network. The Dice coefficient and Jaccard index were calculated to evaluate the results of segmentation in this study. Results The proposed network model had a better segmentation performance than the previous deep learning-based methods with respect to the automatic segmentation of the ulna and radius. The evaluation results suggested that the average Dice coefficients of the ulna and radius were 0.9835 and 0.9874, with average Jaccard indexes of 0.9680 and 0.9751, respectively. Conclusion The deep learning-based method developed in this study improved the segmentation performance of the ulna and radius in dual-energy X-ray imaging.

scholarly journals CT-Based Quantitative Assessment of Coronavirus Disease 2019 Using a Deep Learning-Based Segmentation System: A Longitudinal Study

2021 ◽  
Author(s):  
Jianneng Li ◽  
Wei Zuo ◽  
Qiang Lei ◽  
Guihua Jiang ◽  
Jianhao yan ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Quantitative Analysis ◽  
Automatic Segmentation ◽  
Left Lung ◽  
High Accuracy ◽  
Chest Ct ◽  
The Right ◽  
Deep Learning Model

Abstract BackgroundCoronavirus disease 2019 (COVID-19) is a global catastrophic disease that has severely affected more than 185 countries. The key steps in fighting against COVID-19 involve early detection and tracking of the treatment effects. A large number of studies highlighted computed tomography (CT) as a reliable method for early diagnosis and follow-up monitoring of the disease. However, there are limited data on quantitative analysis of the follow-up images. In this study, we used a deep learning model using a neural network with high accuracy in automatic segmentation and quantification to analyze the infected lesions on chest CT images.MethodsWe used a deep learning model using a neural network with high accuracy in automatic segmentation and quantification to analyze the infected lesions on chest CT images. A total of 14 patients (mean age, 53±14 years; age range, 23–74 years; 42.9% men and 57.1% women) with confirmed mild-type COVID-19 from January 1 to May 7, 2020, were retrospectively reviewed. Initial and follow-up original CT images were collected, and CT quantitative parameters, including percentage of infection (POI) and density variation of pneumonia, were determined.ResultsThe median initial POI was 3.4% (interquartile range, IQR 0.5%–8.4%) for the whole lung, 0.8% (IQR 0.2%–6.7%) for the left lung, and 5.8% (IQR 0.5%–9.7%) for the right lung. The infection was more serious in the right than in the left lung. The infected region mainly involved bilateral lower lobes, more pronounced on the right side. Quantitative CT showed that POI significantly decreased throughout the follow-up period in all 14 patients (p < 0.001). Among them, 50% of the patients had a more significant decrease in POI (51.3%) after a negative nucleic acid test. Moreover, there was a significant decrease in the CT number range of ground-glass opacities (GGO) and consolidation (p < 0.001).ConclusionsThis study demonstrated the quantitative analysis of follow-up CT scans plays an important role in the monitoring of COVID-19 treatment, which could help in treatment planning and standardizing the assessment for discharge.

scholarly journals Development of a Deep Learning-Based Algorithm to Detect the Distal End of a Surgical Instrument

2020 ◽  
Vol 10 (12) ◽  
pp. 4245
Author(s):  
Hiroyuki Sugimori ◽  
Taku Sugiyama ◽  
Naoki Nakayama ◽  
Akemi Yamashita ◽  
Katsuhiko Ogasawara
Keyword(s):  
Deep Learning ◽  
Detection Rate ◽  
Data Augmentation ◽  
Regions Of Interest ◽  
Surgical Instrument ◽  
Average Precision ◽  
Detection Rates ◽  
Video Recordings ◽  
Video Images ◽  
Bounding Boxes

This work aims to develop an algorithm to detect the distal end of a surgical instrument using object detection with deep learning. We employed nine video recordings of carotid endarterectomies for training and testing. We obtained regions of interest (ROI; 32 × 32 pixels), at the end of the surgical instrument on the video images, as supervised data. We applied data augmentation to these ROIs. We employed a You Only Look Once Version 2 (YOLOv2) -based convolutional neural network as the network model for training. The detectors were validated to evaluate average detection precision. The proposed algorithm used the central coordinates of the bounding boxes predicted by YOLOv2. Using the test data, we calculated the detection rate. The average precision (AP) for the ROIs, without data augmentation, was 0.4272 ± 0.108. The AP with data augmentation, of 0.7718 ± 0.0824, was significantly higher than that without data augmentation. The detection rates, including the calculated coordinates of the center points in the centers of 8 × 8 pixels and 16 × 16 pixels, were 0.6100 ± 0.1014 and 0.9653 ± 0.0177, respectively. We expect that the proposed algorithm will be efficient for the analysis of surgical records.

scholarly journals Deep Learning Based Airway Segmentation Using Key Point Prediction

2021 ◽  
Vol 11 (8) ◽  
pp. 3501
Author(s):  
Jinyoung Park ◽  
JaeJoon Hwang ◽  
Jihye Ryu ◽  
Inhye Nam ◽  
Sol-A Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Sagittal Plane ◽  
Automatic Segmentation ◽  
Volume Measurement ◽  
Airway Segmentation ◽  
Fully Automatic ◽  
Deep Learning Model ◽  
Regression Correlation ◽  
Learning Data

The purpose of this study was to investigate the accuracy of the airway volume measurement by a Regression Neural Network-based deep-learning model. A set of manually outlined airway data was set to build the algorithm for fully automatic segmentation of a deep learning process. Manual landmarks of the airway were determined by one examiner using a mid-sagittal plane of cone-beam computed tomography (CBCT) images of 315 patients. Clinical dataset-based training with data augmentation was conducted. Based on the annotated landmarks, the airway passage was measured and segmented. The accuracy of our model was confirmed by measuring the following between the examiner and the program: (1) a difference in volume of nasopharynx, oropharynx, and hypopharynx, and (2) the Euclidean distance. For the agreement analysis, 61 samples were extracted and compared. The correlation test showed a range of good to excellent reliability. A difference between volumes were analyzed using regression analysis. The slope of the two measurements was close to 1 and showed a linear regression correlation (r2 = 0.975, slope = 1.02, p < 0.001). These results indicate that fully automatic segmentation of the airway is possible by training via deep learning of artificial intelligence. Additionally, a high correlation between manual data and deep learning data was estimated.

scholarly journals EspiNet V2: a region based deep learning model for detecting motorcycles in urban scenarios

DYNA ◽  
2019 ◽  
Vol 86 (211) ◽  
pp. 317-326
Author(s):  
Jorge Ernesto Espinosa Oviedo ◽  
Sergio A Velastín ◽  
John William Branch Bedoya
Keyword(s):  
Deep Learning ◽  
Traffic Control ◽  
Learning Model ◽  
Urban Environments ◽  
Average Precision ◽  
Moving Camera ◽  
Model Based ◽  
End To End ◽  
Deep Learning Model

This paper presents “EspiNet V2” a Deep Learning model, based on the region-based detector Faster R-CNN. The model is used for the detection of motorcycles in urban environments, where occlusion is likely. For training, two datasets are used: the Urban Motorbike Dataset (UMD-10K) of 10,000 annotated images, and the new SMMD (Secretaría de Movilidad Motorbike Dataset), of 5,000 images captured from the Traffic Control CCTV System in Medellín (Colombia). Results achieved on the UMD-10K dataset reach 88.8% in average precision (AP) even when 60% motorcycles were occluded, and the images were captured from a low angle and a moving camera. Meanwhile, an AP of 79.5% is reached for SSMD. EspiNet V2 outperforms popular models such as YOLO V3 and Faster R-CNN (VGG16 based) trained end-to-end for those datasets

Sign in / Sign up

Export Citation Format

Share Document