Feasibility study on using house-tree-person drawings for automatic analysis of depression

Zhang, Jie; Yu, Yaoxiang; Barra, Vincent; Ruan, Xiaoming; Yu, Chunshui; Cai, Bo

doi:10.1080/10255842.2023.2231113

Cited by 3 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the sample size of the above experiments is small, only several hundred. Zhang et al [ 21 ] conducted a study where they computed the mean of effective pixel, entropy of effective pixel, and the number of corners in the HTP sketches as features for depression recognition. They employed classifiers such as Support Vector Machines (SVM) and Decision Trees (DT).…”

Section: Related Workmentioning

confidence: 99%

“…(5) the classification head is used to process the feature vector to obtain the classification result. In addition, this paper also uses the traditional CNN, Vision Transformer, and existing works [17,21] for experimental comparison. Our contributions are as follows:…”

Section: Introductionmentioning

confidence: 99%

“…For example, an entire tree being drawn in dark black or incomplete people, or roofs and walls that are separated, may indicate that the test subject has a psychological disorder [ 17 ]. Existing works [ 18 , 19 , 20 ] on manual recognition of depression are based on the above methods, and there are also a number of works [ 17 , 21 ] based on machine learning and deep learning methods. However, the method of manually analyzing drawing features requires extensive training by doctors, resulting in high time costs.…”

Section: Introductionmentioning

confidence: 99%

“…However, the method of manually analyzing drawing features requires extensive training by doctors, resulting in high time costs. On the other hand, the methods proposed by [ 17 , 21 ] are characterized by laborious processing steps. Therefore, we propose a one-stage depression recognition method for HTP sketches, which has few process steps and a higher degree of automation.…”

Section: Introductionmentioning

confidence: 99%

“…(3) Self-Attention and Triplet Attention are used to focus on important features and perform attention fusion; (4) the hybrid attention features are fused with the features of the whole sketch again for feature compensation; (5) the classification head is used to process the feature vector to obtain the classification result. In addition, this paper also uses the traditional CNN, Vision Transformer, and existing works [ 17 , 21 ] for experimental comparison. Our contributions are as follows: A deep learning-based, one-stage depression recognition method (FBANet) for HTP sketches is proposed for the first time.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

FBANet: Transfer Learning for Depression Recognition Using a Feature-Enhanced Bi-Level Attention Network

Wang,

Zhang,

Huang

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

The House-Tree-Person (HTP) sketch test is a psychological analysis technique designed to assess the mental health status of test subjects. Nowadays, there are mature methods for the recognition of depression using the HTP sketch test. However, existing works primarily rely on manual analysis of drawing features, which has the drawbacks of strong subjectivity and low automation. Only a small number of works automatically recognize depression using machine learning and deep learning methods, but their complex data preprocessing pipelines and multi-stage computational processes indicate a relatively low level of automation. To overcome the above issues, we present a novel deep learning-based one-stage approach for depression recognition in HTP sketches, which has a simple data preprocessing pipeline and calculation process with a high accuracy rate. In terms of data, we use a hand-drawn HTP sketch dataset, which contains drawings of normal people and patients with depression. In the model aspect, we design a novel network called Feature-Enhanced Bi-Level Attention Network (FBANet), which contains feature enhancement and bi-level attention modules. Due to the limited size of the collected data, transfer learning is employed, where the model is pre-trained on a large-scale sketch dataset and fine-tuned on the HTP sketch dataset. On the HTP sketch dataset, utilizing cross-validation, FBANet achieves a maximum accuracy of 99.07% on the validation dataset, with an average accuracy of 97.71%, outperforming traditional classification models and previous works. In summary, the proposed FBANet, after pre-training, demonstrates superior performance on the HTP sketch dataset and is expected to be a method for the auxiliary diagnosis of depression.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FBANet: Transfer Learning for Depression Recognition Using a Feature-Enhanced Bi-Level Attention Network

Wang,

Zhang,

Huang

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

A Systematic Review on Multimodal Emotion Recognition: Building Blocks, Current State, Applications, and Challenges

Kalateh,

Estrada-Jimenez,

Nikghadam-Hojjati

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Resting-State Electroencephalogram Depression Diagnosis Based on Traditional Machine Learning and Deep Learning: A Comparative Analysis

Lin,

Fang,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

The global prevalence of Major Depressive Disorder (MDD) is increasing at an alarming rate, underscoring the urgent need for timely and accurate diagnoses to facilitate effective interventions and treatments. Electroencephalography remains a widely used neuroimaging technique in psychiatry, due to its non-invasive nature and cost-effectiveness. With the rise of computational psychiatry, the integration of EEG with artificial intelligence has yielded remarkable results in diagnosing depression. This review offers a comparative analysis of two predominant methodologies in research: traditional machine learning and deep learning methods. Furthermore, this review addresses key challenges in current research and suggests potential solutions. These insights aim to enhance diagnostic accuracy for depression and also foster further development in the area of computational psychiatry.

show abstract

Feasibility study on using house-tree-person drawings for automatic analysis of depression

Cited by 3 publications

References 35 publications

FBANet: Transfer Learning for Depression Recognition Using a Feature-Enhanced Bi-Level Attention Network

FBANet: Transfer Learning for Depression Recognition Using a Feature-Enhanced Bi-Level Attention Network

A Systematic Review on Multimodal Emotion Recognition: Building Blocks, Current State, Applications, and Challenges

Resting-State Electroencephalogram Depression Diagnosis Based on Traditional Machine Learning and Deep Learning: A Comparative Analysis

Contact Info

Product

Resources

About