Automatic, Qualitative Scoring of the Interlocking Pentagon Drawing Test (PDT) Based on U-Net and Mobile Sensor Data

Park, In Gyu; Kim, Yun Joong; Kim, Yeo Jin; Lee, Unjoo

doi:10.3390/s20051283

Cited by 14 publications

(19 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we were able to fine-tune a pre-trained CNN for PCT scoring without any special adjustments just by preparing the teacher data. Contrarily, in the study that evaluated PCTs using object or feature detection, it was necessary to set up a system to detect the features of PCTs that would be scored as correct answers 5 , 6 . The usefulness of fine-tuned CNN to evaluate the clock drawing test and the Rey-Osterrieth complex figure copying test has also been reported 16 , 17 .…”

Section: Discussionmentioning

confidence: 99%

“…Computerized scoring of figure copying tests can be considered reliable because the rater experience does not affect the scoring. A recent study reported the robustness of automated quantitative scoring of PCT has been based on information, such as the number or coordinates of pentagons, obtained from object (or feature) detection 5 , 6 . However, since patients with dementia often redraw figures many times, or sometimes copy in close proximity to a model figure 7 , there is a possibility that detection may not be successful due to many artifacts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep convolutional neural networks for automated scoring of pentagon copying test results

Maruta

Uchida

Kurozumi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

This study aims to investigate the accuracy of a fine-tuned deep convolutional neural network (CNN) for evaluating responses to the pentagon copying test (PCT). To develop a CNN that could classify PCT images, we fine-tuned and compared the pre-trained CNNs (GoogLeNet, VGG-16, ResNet-50, Inception-v3). To collate our training dataset, we collected 1006 correct PCT images and 758 incorrect PCT images drawn on a test sheet by dementia suspected patients at the Osaka City Kosaiin Hospital between April 2009 and December 2012. For a validation dataset, we collected PCT images from consecutive patients treated at the facility in April 2020. We examined the ability of the CNN to detect correct PCT images using a validation dataset. For a validation dataset, we collected PCT images (correct, 41; incorrect, 16) from 57 patients. In the validation testing for an ability to detect correct PCT images, the fine-tuned GoogLeNet CNN achieved an area under the receiver operating characteristic curve of 0.931 (95% confidence interval 0.853–1.000). These findings indicate that our fine-tuned CNN is a useful method for automatically evaluating PCT images. The use of CNN-based automatic scoring of PCT can potentially reduce the burden on assessors in screening for dementia.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep convolutional neural networks for automated scoring of pentagon copying test results

Maruta

Uchida

Kurozumi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…To the aim, visual parameter features such as number of angles, distance/intersection, closure/opening, rotation and closing-in where considered with an Artificial Neural Network classifier [6]. Park et al [75] have recently adopted a mobile device to acquire timestamps, x-y coordinates and touchevents. In this case, raw data were processed by means of U-Net (a convolutional network) to automatically segment angles, distance/intersection between the two drawn figures, closure/opening of the drawn figure contours.…”

Section: Pentagon Testmentioning

confidence: 99%

Online Handwriting, Signature and Touch Dynamics: Tasks and Potential Applications in the Field of Security and Health

2021

View full text Add to dashboard Cite

Background: An advantageous property of behavioural signals (e.g. handwriting), in contrast to morphological ones, such as iris, fingerprint, hand geometry, etc., is the possibility to ask a user for a very rich amount of different tasks.Methods: This article summarises recent findings and applications of different handwriting/drawing tasks in the field of security and health. More specifically, it is focused on on-line handwriting and hand-based interaction, i.e. signals that utilise a digitizing device (specific devoted or general-purpose tablet/smartphone) during the realization of the tasks. Such devices permit the acquisition of onsurface dynamics as well as in-air movements in time, thus providing complex and richer information when compared to the conventional "pen and paper" method.Conclusions: Although the scientific literature reports a wide range of tasks and applications, in this paper, we summarize only those providing competitive results (e.g. in terms of discrimination power) and having a significant impact in the field. KeywordsDrawing • Online handwriting • Signature • Tasks • Touch Dynamics 1 Introduction Signature/handwriting recognition can be split into two categories: off-line and online [2, 24, 90]. In the former case, just the result of the signature/writing (i.e. static

show abstract

“…Motor testing and speech data can distinguish PD cases from controls [223]. Park et al [224] developed a mobile application to automatically evaluate the interlocking pentagon drawing test using a U-Net architecture.…”

Section: Smartphone / Sensor Datamentioning

confidence: 99%

Deep learning for brain disorders: from data processing to disease treatment

Burgos

Bottani

Faouzi

et al. 2020

Briefings in Bioinformatics

View full text Add to dashboard Cite

In order to reach precision medicine and improve patients’ quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

show abstract

Automatic, Qualitative Scoring of the Interlocking Pentagon Drawing Test (PDT) Based on U-Net and Mobile Sensor Data

Cited by 14 publications

References 43 publications

Deep convolutional neural networks for automated scoring of pentagon copying test results

Deep convolutional neural networks for automated scoring of pentagon copying test results

Online Handwriting, Signature and Touch Dynamics: Tasks and Potential Applications in the Field of Security and Health

Deep learning for brain disorders: from data processing to disease treatment

Contact Info

Product

Resources

About