Automatic ladybird beetle detection using deep-learning models

Fast and accurate taxonomic identification of invasive trans-located ladybird beetle species is essential to prevent significant impacts on biological communities, ecosystem functions, and agricultural business economics. Therefore, in this work we propose a two-step automatic detector for ladybird beetles in random environment images as the first stage towards an automated classification system. First, an image processing module composed of a saliency map representation, simple linear iterative clustering superpixels segmentation, and active contour methods allowed us to generate bounding boxes with possible ladybird beetles locations within an image. Subsequently, a deep convolutional neural network-based classifier selects only the bounding boxes with ladybird beetles as the final output. This method was validated on a 2, 300 ladybird beetle image data set from Ecuador and Colombia obtained from the iNaturalist project. The proposed approach achieved an accuracy score of 92% and an area under the receiver operating characteristic curve of 0.977 for the bounding box generation and classification tasks. These successful results enable the proposed detector as a valuable tool for helping specialists in the ladybird beetle detection problem.

Download Full-text

Identification of the Facial Features of Patients With Cancer: A Deep Learning–Based Pilot Study

Journal of Medical Internet Research ◽

10.2196/17234 ◽

2020 ◽

Vol 22 (4) ◽

pp. e17234 ◽

Cited By ~ 2

Author(s):

Bin Liang ◽

Na Yang ◽

Guosheng He ◽

Peng Huang ◽

Yong Yang

Keyword(s):

Deep Learning ◽

Characteristic Curve ◽

Age Distribution ◽

Image Data ◽

Face Image ◽

Facial Features ◽

Facial Skin ◽

Data Set ◽

Patients With Cancer ◽

Face Region

Background Cancer has become the second leading cause of death globally. Most cancer cases are due to genetic mutations, which affect metabolism and result in facial changes. Objective In this study, we aimed to identify the facial features of patients with cancer using the deep learning technique. Methods Images of faces of patients with cancer were collected to build the cancer face image data set. A face image data set of people without cancer was built by randomly selecting images from the publicly available MegaAge data set according to the sex and age distribution of the cancer face image data set. Each face image was preprocessed to obtain an upright centered face chip, following which the background was filtered out to exclude the effects of nonrelative factors. A residual neural network was constructed to classify cancer and noncancer cases. Transfer learning, minibatches, few epochs, L2 regulation, and random dropout training strategies were used to prevent overfitting. Moreover, guided gradient-weighted class activation mapping was used to reveal the relevant features. Results A total of 8124 face images of patients with cancer (men: n=3851, 47.4%; women: n=4273, 52.6%) were collected from January 2018 to January 2019. The ages of the patients ranged from 1 year to 70 years (median age 52 years). The average faces of both male and female patients with cancer displayed more obvious facial adiposity than the average faces of people without cancer, which was supported by a landmark comparison. When testing the data set, the training process was terminated after 5 epochs. The area under the receiver operating characteristic curve was 0.94, and the accuracy rate was 0.82. The main relative feature of cancer cases was facial skin, while the relative features of noncancer cases were extracted from the complementary face region. Conclusions In this study, we built a face data set of patients with cancer and constructed a deep learning model to classify the faces of people with and those without cancer. We found that facial skin and adiposity were closely related to the presence of cancer.

Download Full-text

Identification of the Facial Features of Patients With Cancer: A Deep Learning–Based Pilot Study (Preprint)

10.2196/preprints.17234 ◽

2019 ◽

Author(s):

Bin Liang ◽

Na Yang ◽

Guosheng He ◽

Peng Huang ◽

Yong Yang

Keyword(s):

Deep Learning ◽

Characteristic Curve ◽

Age Distribution ◽

Image Data ◽

Face Image ◽

Facial Features ◽

Facial Skin ◽

Data Set ◽

Patients With Cancer ◽

Face Region

BACKGROUND Cancer has become the second leading cause of death globally. Most cancer cases are due to genetic mutations, which affect metabolism and result in facial changes. OBJECTIVE In this study, we aimed to identify the facial features of patients with cancer using the deep learning technique. METHODS Images of faces of patients with cancer were collected to build the cancer face image data set. A face image data set of people without cancer was built by randomly selecting images from the publicly available MegaAge data set according to the sex and age distribution of the cancer face image data set. Each face image was preprocessed to obtain an upright centered face chip, following which the background was filtered out to exclude the effects of nonrelative factors. A residual neural network was constructed to classify cancer and noncancer cases. Transfer learning, minibatches, few epochs, L2 regulation, and random dropout training strategies were used to prevent overfitting. Moreover, guided gradient-weighted class activation mapping was used to reveal the relevant features. RESULTS A total of 8124 face images of patients with cancer (men: n=3851, 47.4%; women: n=4273, 52.6%) were collected from January 2018 to January 2019. The ages of the patients ranged from 1 year to 70 years (median age 52 years). The average faces of both male and female patients with cancer displayed more obvious facial adiposity than the average faces of people without cancer, which was supported by a landmark comparison. When testing the data set, the training process was terminated after 5 epochs. The area under the receiver operating characteristic curve was 0.94, and the accuracy rate was 0.82. The main relative feature of cancer cases was facial skin, while the relative features of noncancer cases were extracted from the complementary face region. CONCLUSIONS In this study, we built a face data set of patients with cancer and constructed a deep learning model to classify the faces of people with and those without cancer. We found that facial skin and adiposity were closely related to the presence of cancer.

Download Full-text

Deep Learning Approaches for Whiteboard Image Quality Enhancement

Color and Imaging Conference ◽

10.2352/j.imagingsci.technol.2019.63.4.040404 ◽

2019 ◽

Vol 2019 (1) ◽

pp. 360-368

Author(s):

Mekides Assefa Abebe ◽

Jon Yngve Hardeberg

Keyword(s):

Deep Learning ◽

Image Quality ◽

Image Data ◽

Quality Enhancement ◽

Network Architectures ◽

Learning Approaches ◽

Data Set ◽

Image Quality Enhancement ◽

Processing Techniques ◽

White Balancing

Different whiteboard image degradations highly reduce the legibility of pen-stroke content as well as the overall quality of the images. Consequently, different researchers addressed the problem through different image enhancement techniques. Most of the state-of-the-art approaches applied common image processing techniques such as background foreground segmentation, text extraction, contrast and color enhancements and white balancing. However, such types of conventional enhancement methods are incapable of recovering severely degraded pen-stroke contents and produce artifacts in the presence of complex pen-stroke illustrations. In order to surmount such problems, the authors have proposed a deep learning based solution. They have contributed a new whiteboard image data set and adopted two deep convolutional neural network architectures for whiteboard image quality enhancement applications. Their different evaluations of the trained models demonstrated their superior performances over the conventional methods.

Download Full-text

Noninvasive patient tracker mask for spinal 3D navigation: does the required large-volume 3D scan involve a considerably increased radiation exposure?

Journal of Neurosurgery Spine ◽

10.3171/2020.5.spine20530 ◽

2020 ◽

Vol 33 (6) ◽

pp. 838-844

Author(s):

Jan-Helge Klingler ◽

Ulrich Hubbe ◽

Christoph Scholz ◽

Florian Volz ◽

Marc Hohenhaus ◽

...

Keyword(s):

Radiation Exposure ◽

Image Data ◽

3D Image ◽

Flat Panel ◽

3D Navigation ◽

Data Set ◽

Dose Area Product ◽

Flat Panel Detector ◽

3D Scan ◽

Area Product

OBJECTIVEIntraoperative 3D imaging and navigation is increasingly used for minimally invasive spine surgery. A novel, noninvasive patient tracker that is adhered as a mask on the skin for 3D navigation necessitates a larger intraoperative 3D image set for appropriate referencing. This enlarged 3D image data set can be acquired by a state-of-the-art 3D C-arm device that is equipped with a large flat-panel detector. However, the presumably associated higher radiation exposure to the patient has essentially not yet been investigated and is therefore the objective of this study.METHODSPatients were retrospectively included if a thoracolumbar 3D scan was performed intraoperatively between 2016 and 2019 using a 3D C-arm with a large 30 × 30–cm flat-panel detector (3D scan volume 4096 cm3) or a 3D C-arm with a smaller 20 × 20–cm flat-panel detector (3D scan volume 2097 cm3), and the dose area product was available for the 3D scan. Additionally, the fluoroscopy time and the number of fluoroscopic images per 3D scan, as well as the BMI of the patients, were recorded.RESULTSThe authors compared 62 intraoperative thoracolumbar 3D scans using the 3D C-arm with a large flat-panel detector and 12 3D scans using the 3D C-arm with a small flat-panel detector. Overall, the 3D C-arm with a large flat-panel detector required more fluoroscopic images per scan (mean 389.0 ± 8.4 vs 117.0 ± 4.6, p < 0.0001), leading to a significantly higher dose area product (mean 1028.6 ± 767.9 vs 457.1 ± 118.9 cGy × cm2, p = 0.0044).CONCLUSIONSThe novel, noninvasive patient tracker mask facilitates intraoperative 3D navigation while eliminating the need for an additional skin incision with detachment of the autochthonous muscles. However, the use of this patient tracker mask requires a larger intraoperative 3D image data set for accurate registration, resulting in a 2.25 times higher radiation exposure to the patient. The use of the patient tracker mask should thus be based on an individual decision, especially taking into considering the radiation exposure and extent of instrumentation.

Download Full-text

Fig Plant Segmentation from Aerial Images Using a Deep Convolutional Encoder-Decoder Network

Remote Sensing ◽

10.3390/rs11101157 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1157 ◽

Cited By ~ 8

Author(s):

Jorge Fuentes-Pacheco ◽

Juan Torres-Olivares ◽

Edgar Roman-Rangel ◽

Salvador Cervantes ◽

Porfirio Juarez-Lopez ◽

...

Keyword(s):

Precision Agriculture ◽

Image Data ◽

Ground Truth ◽

Aerial Images ◽

Aerial Image ◽

Data Set ◽

Visual Appearance ◽

Aerial Robots ◽

Lighting Conditions ◽

Convolutional Encoder

Crop segmentation is an important task in Precision Agriculture, where the use of aerial robots with an on-board camera has contributed to the development of new solution alternatives. We address the problem of fig plant segmentation in top-view RGB (Red-Green-Blue) images of a crop grown under open-field difficult circumstances of complex lighting conditions and non-ideal crop maintenance practices defined by local farmers. We present a Convolutional Neural Network (CNN) with an encoder-decoder architecture that classifies each pixel as crop or non-crop using only raw colour images as input. Our approach achieves a mean accuracy of 93.85% despite the complexity of the background and a highly variable visual appearance of the leaves. We make available our CNN code to the research community, as well as the aerial image data set and a hand-made ground truth segmentation with pixel precision to facilitate the comparison among different algorithms.

Download Full-text

ESR white paper: blockchain and medical imaging

Insights into Imaging ◽

10.1186/s13244-021-01029-y ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

◽

Elmar Kotter ◽

Luis Marti-Bonmati ◽

Adrian P. Brady ◽

Nandita M. Desouza

Keyword(s):

Medical Imaging ◽

Image Data ◽

Distributed Database ◽

Relevant Information ◽

White Paper ◽

Imaging Data ◽

Data Set ◽

Blockchain Technology ◽

Potential Applications ◽

Basic Technology

AbstractBlockchain can be thought of as a distributed database allowing tracing of the origin of data, and who has manipulated a given data set in the past. Medical applications of blockchain technology are emerging. Blockchain has many potential applications in medical imaging, typically making use of the tracking of radiological or clinical data. Clinical applications of blockchain technology include the documentation of the contribution of different “authors” including AI algorithms to multipart reports, the documentation of the use of AI algorithms towards the diagnosis, the possibility to enhance the accessibility of relevant information in electronic medical records, and a better control of users over their personal health records. Applications of blockchain in research include a better traceability of image data within clinical trials, a better traceability of the contributions of image and annotation data for the training of AI algorithms, thus enhancing privacy and fairness, and potentially make imaging data for AI available in larger quantities. Blockchain also allows for dynamic consenting and has the potential to empower patients and giving them a better control who has accessed their health data. There are also many potential applications of blockchain technology for administrative purposes, like keeping track of learning achievements or the surveillance of medical devices. This article gives a brief introduction in the basic technology and terminology of blockchain technology and concentrates on the potential applications of blockchain in medical imaging.

Download Full-text

Application of portrait recognition system for emergency evacuation in mass emergencies

Journal of Intelligent Systems ◽

10.1515/jisys-2021-0052 ◽

2021 ◽

Vol 30 (1) ◽

pp. 893-902

Author(s):

Ke Xu

Keyword(s):

Detection Rate ◽

Characteristic Curve ◽

Recognition Rate ◽

Recognition System ◽

Emergency Evacuation ◽

Shopping Mall ◽

Single Shot ◽

Data Set ◽

Linear Discriminant ◽

Adaboost Algorithm

Abstract A portrait recognition system can play an important role in emergency evacuation in mass emergencies. This paper designed a portrait recognition system, analyzed the overall structure of the system and the method of image preprocessing, and used the Single Shot MultiBox Detector (SSD) algorithm for portrait detection. It also designed an improved algorithm combining principal component analysis (PCA) with linear discriminant analysis (LDA) for portrait recognition and tested the system by applying it in a shopping mall to collect and monitor the portrait and establish a data set. The results showed that the missing detection rate and false detection rate of the SSD algorithm were 0.78 and 2.89%, respectively, which were lower than those of the AdaBoost algorithm. Comparisons with PCA, LDA, and PCA + LDA algorithms demonstrated that the recognition rate of the improved PCA + LDA algorithm was the highest, which was 95.8%, the area under the receiver operating characteristic curve was the largest, and the recognition time was the shortest, which was 465 ms. The experimental results show that the improved PCA + LDA algorithm is reliable in portrait recognition and can be used for emergency evacuation in mass emergencies.

Download Full-text

Clinical implication of psoas muscle mass measurement for predicting death within 3 months in patients with incurable uterine cervical or corpus malignancy

Japanese Journal of Clinical Oncology ◽

10.1093/jjco/hyaa248 ◽

2021 ◽

Author(s):

Hiroyuki Kurosu ◽

Yukiharu Todo ◽

Ryutaro Yamada ◽

Kaoru Minowa ◽

Tomohiko Tsuruta ◽

...

Keyword(s):

Computed Tomography ◽

Muscle Mass ◽

Cancer Cachexia ◽

Mass Measurement ◽

Characteristic Curve ◽

Lumbar Vertebra ◽

Psoas Muscle ◽

Data Set ◽

Cutoff Value ◽

Computed Tomography Images

Abstract Objective The aim of this study was to find a clinical marker for identifying refractory cancer cachexia. Methods We analyzed computed tomography imaging data, which included the third lumbar vertebra, from 94 patients who died of uterine cervix or corpus malignancy. The time between the date of examination and date of death was the most important attribute for this study, and the computed tomography images were classified into >3 months before death and ≤ 3 months before death. Psoas muscle mass index was defined as the left–right sum of the psoas muscle areas (cm2) at the level of third lumbar vertebra, divided by height squared (m2). Results A data set of 94 computed tomography images was obtained at baseline hospital visit, and a data set of 603 images was obtained at other times. One hundred (16.6%) of the 603 non-baseline images were scanned ≤3 months before death. Mean psoas muscle mass index change rates at >3 months before death and ≤3 months before death were −1.3 and −20.1%, respectively (P < 0.001). Receiver operating characteristic curve analysis yielded a cutoff value of −13.0%. The area under the curve reached a moderate accuracy level (0.777, 95% confidence interval 0.715–0.838). When we used the cutoff value to predict death within 3 months, sensitivity and specificity were 74.0 and 82.1%, respectively. Conclusions Measuring change in psoas muscle mass index might be useful for predicting cancer mortality within 3 months. It could become a potential tool for identifying refractory cancer cachexia.

Download Full-text

Geocoding Of A Multi-sensor Image Data Set

10.1109/igarss.1990.688645 ◽

2005 ◽

Author(s):

D. Strobl ◽

J. Raggam

Keyword(s):

Image Data ◽

Data Set

Download Full-text

A new approach to categorising continuous variables in prediction models: Proposal and validation

Statistical Methods in Medical Research ◽

10.1177/0962280215601873 ◽

2015 ◽

Vol 26 (6) ◽

pp. 2586-2602 ◽

Cited By ~ 30

Author(s):

Irantzu Barrio ◽

Inmaculada Arostegui ◽

María-Xosé Rodríguez-Álvarez ◽

José-María Quintana

Keyword(s):

Prediction Models ◽

Characteristic Curve ◽

Prediction Rule ◽

Real Data ◽

Clinical Variable ◽

Chronic Obstructive ◽

Continuous Variables ◽

Discriminative Ability ◽

Data Set ◽

Statistical Point

When developing prediction models for application in clinical practice, health practitioners usually categorise clinical variables that are continuous in nature. Although categorisation is not regarded as advisable from a statistical point of view, due to loss of information and power, it is a common practice in medical research. Consequently, providing researchers with a useful and valid categorisation method could be a relevant issue when developing prediction models. Without recommending categorisation of continuous predictors, our aim is to propose a valid way to do it whenever it is considered necessary by clinical researchers. This paper focuses on categorising a continuous predictor within a logistic regression model, in such a way that the best discriminative ability is obtained in terms of the highest area under the receiver operating characteristic curve (AUC). The proposed methodology is validated when the optimal cut points’ location is known in theory or in practice. In addition, the proposed method is applied to a real data-set of patients with an exacerbation of chronic obstructive pulmonary disease, in the context of the IRYSS-COPD study where a clinical prediction rule for severe evolution was being developed. The clinical variable PCO2 was categorised in a univariable and a multivariable setting.

Download Full-text