Head Detection Research Articles

CFNet: Head detection network based on multi‐layer feature fusion and attention mechanism

AbstractRecently, head detection has been widely used in target detection, which has a great application value for improving security prevention and control in public places, as well as enhancing target tracking and identification in national defense, criminal investigation, and other fields. However, detecting small targets accurately at long distances is very difficult, and current methods often lack optimization of multi‐resolution features. Therefore, the authors propose a one‐stage detection network CFNet (cross‐layer feature fusion and fusion weight attention network), in which a fusion weight attention mechanism module (FWAM) is proposed to give different weights to the fused features in order to distinguish the importance of different features. The module increases the weights of features that contain strong information so that the fused features are focused on feature points that are beneficial for optimal head detection. Meanwhile, a cross‐layer feature fusion module is proposed to fuse information from different resolution feature maps to compensate for the decrease in detection accuracy caused by the omission of information features at low resolution, and a connection network for contextual information fusion is constructed, while weight parameter value settings are introduced to optimize the detection effect after fusion of different resolution features. In order to better reflect the effectiveness of the network, the experiments are performed on the SCUT‐HEAD PartA dataset and the Brainwash dataset; the results show that the network the authors proposed is better than the existing comparison methods, which proves the robustness and effectiveness of the network.

HEAD TRACKING AND VOICE RECOGNITION USING OPEN CV IN PYTHON

It is common knowledge that computers are an organization's central nervous system in the modern world. They can store their information on computers and retrieve it whenever required. As a result, having a working grasp of computers is essential. People with impairments cannot perform the tasks that need to be done on the computer. This paper outlines the proposed system for the disabled, which primarily uses the head tracking element utilizing software that mainly consists of head detection and voice recognition. The document also briefly discusses the system's potential benefits for the disabled. Thanks to the head detection feature, they can move the pointer across the screen and operate any software by simply moving their head. Thanks to the implementation of speech recognition technology, they can use their voices to engage with the system. Actual individuals validated the system through testing to ensure it met their needs and effectively provided assistance. These devices are also incredibly inexpensive and disabled individuals who rely on the care and support of others for survival can purchase them.

The performance of 68Ga-FAPI-04 PET/CT in head and neck squamous cell carcinoma: a prospective comparison with 18F-FDG PET/CT.

This study was designed to compare the performance of 68Ga-FAPI-04 and 18F-FDG PET/CT for initial staging and recurrence detection of head and neck squamous cell carcinoma (HNSCC). Prospectively, 77 patients with histologically proven or highly suspected HNSCC underwent paired 18F-FDG and 68Ga-FAPI-04 PET/CT in a week for either initial staging (n = 67) or restaging (n = 10). The diagnostic performance was compared for the two imaging approaches, especially for N staging. SUVmax, SUVmean, and target-to-background ratio (TBR) were assessed for paired positive lesions. Furthermore, change in management by 68Ga-FAPI-04 PET/CT and histopathologic FAP expression of some lesions were explored. 18F-FDG and 68Ga-FAPI-04 PET/CT exhibited a comparable detection efficiency for primary tumor (100%) and recurrence (62.5%). In the twenty-nine patients receiving neck dissection, 68Ga-FAPI-04 PET/CT showed greater specificity and accuracy in evaluating preoperative N staging than 18F-FDG based on patient (p = 0.031 and p = 0.070), neck side (p = 0.002 and p = 0.006), and neck level (p < 0.001 and p < 0.001). As for distant metastasis, 68Ga-FAPI-04 PET/CT detected more positive lesions than 18F-FDG (25 vs 23) and with higher SUVmax (7.99 ± 9.04 vs 3.62 ± 2.68, p = 0.002) by lesion-based analysis. The type of neck dissection in 9 cases (9/33) was altered by 68Ga-FAPI-04. Overall, clinical management was significantly changed in 10 patients (10/61). Three patients had a follow-up 68Ga-FAPI-04 PET/CT post neoadjuvant therapy: One showed complete remission, and the others showed progression. The 68Ga-FAPI-04 uptake intensity was confirmed to be consistent with FAP expression. 68Ga-FAPI-04 outperforms 18F-FDG PET/CT in evaluating preoperative N staging in patients with HNSCC. Furthermore, 68Ga-FAPI-04 PET/CT also shows the potential in clinical management and monitoring response to treatment.

Early detection and prevention of head and neck cancers

Squamous cell carcinoma forms the vast majority of head and neck malignancies, with advanced disease incurring poor long-term survival. Early detection and prompt specialist referral allows the patient a greater chance of cure. Furthermore, basal cell carcinoma is the most common malignancy in humans, with the vast majority presenting in the head and neck region. Dentists have a unique opportunity to assess for cutaneous malignancies during routine visits.Cancer screening should be common practice within dental professionals. In addition to enquiring about common red flag symptoms, a comprehensive and systematic extra- and intra-oral examination should be undertaken at each new and check-up appointment. Urgent referral to an appropriate secondary care provider should be made at the earliest opportunity where concern for cancer exists.

Finding the Least Motion-Blurred Image by Reusing Early Features of Object Detection Network

Taking smartphone-made videos for photogrammetry is a convenient approach because of the easy image collection process for the object being reconstructed. However, the video may contain a lot of relatively similar frames. Additionally, frames may be of different quality. The primary source of quality variation in the same video is varying motion blur. Splitting the sequence of the frames into chunks and choosing the least motion-blurred frame in every chunk would reduce data redundancy and improve image data quality. Such reduction will lead to faster and more accurate reconstruction of the 3D objects. In this research, we investigated image quality evaluation in the case of human 3D head modeling. Suppose a head modeling workflow already uses a convolutional neural network for the head detection task in order to remove non-static background. In that case, features from the neural network may be reused for the quality evaluation of the same image. We proposed a motion blur evaluation method based on the LightGBM ranker model. The method was evaluated and compared with other blind image quality evaluation methods using videos of a mannequin head and real faces. Evaluation results show that the developed method in both cases outperformed sharpness-based, BRISQUE, NIQUE, and PIQUE methods in finding the least motion-blurred image.

Crowd counting using deep learning based head detection

Scale invariance and high miss detection rates for small objects are some of the challenging issues for object detection and often lead to inaccurate results. This research aims to provide an accurate detection model for crowd counting by focusing on human head detection from natural scenes acquired from publicly available datasets of Casablanca, Hollywood-Heads and Scut-head. In this study, we tuned a yolov5, a deep convolutional neural network (CNN) based object detection architecture, and then evaluated the model using mean average precision (mAP) score, precision, and recall. The transfer learning approach is used for fine-tuning the architecture. Training on one dataset and testing the model on another leads to inaccurate results due to different types of heads in different datasets. Another main contribution of our research is combining the three datasets into a single dataset, including every kind of head that is medium, large and small. From the experimental results, it can be seen that this yolov5 architecture showed significant improvements in small head detections in crowded scenes as compared to the other baseline approaches, such as the Faster R-CNN and VGG-16-based SSD MultiBox Detector.

The value of serum p53 antibody as a biomarker in oral and pharyngeal squamous cell carcinoma

Background The development of more sensitive biomarkers for the detection of early-stage head and neck squamous cell carcinoma is needed. Aims/Objectives This study was performed to assess the value of serum p53 antibody (s-p53-Ab) as a biomarker for oral and pharyngeal carcinoma. Material and Methods Pre-treatment serum was collected for 71 patients with oral and pharyngeal carcinoma and 117 healthy volunteers as controls and analyzed s-p53-Ab using enzyme-linked immunosorbent assay (ELISA). Results Using 1.3 U/mL as the cut-off value, 14 of 71 patients (sensitivity 19.7%), and 12 of 117 control cases were positive for s-p53-Ab (specificity 89.7%). Excluding 12 cases of p16-positive oropharyngeal and nasopharyngeal cancer which were all negative for s-p53-Ab, the sensitivity in early-stage 1–2 cases was 30.0%, which was higher than conventional tumor markers. Conclusions and Significance The s-p53-Ab was not detected in any cases of virus-related cancer in which p53 gene mutations were not involved in carcinogenesis. Since the s-p53-Ab sensitivity was high even in early-stage disease, s-p53-Ab measurement may be useful as an early diagnostic biomarker in patients with oral, p16- oropharyngeal, and hypopharyngeal cancer.

Оценка знаний врачей-стоматологов о профилактике и раннем выявлении ассоциированного с вирусом папилломы человека рака головы и шеи

Оценка знаний врачей-стоматологов о профилактике и раннем выявлении ассоциированного с вирусом папилломы человека рака головы и шеи

Evaluation of changes in Salivary Lactate Dehydrogenase Level for detection of Head and Neck Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis Study.

Research has examined the relationship between salivary lactate dehydrogenase (LDH) levels and head and neck squamous cell carcinoma (HNSCC) screening and prognosis. Due to biochemical changes in cancer cells and increased production of lactate products in the body. The present systematic review aims to evaluate the changes in salivary LDH levels in HNSCC patients. The present study is a systematic review and meta-analysis. The data were collected by searching PubMed, Science Direct, Scopus, Web of Science, and Google Scholar from 2000 to 2021. The heterogeneity of the articles was analyzed using I2 and TAU2. After searching the databases, of 988 articles, 665 duplicated articles were excluded by adopting the inclusion and exclusion criteria. So, 25 articles were primarily selected to be reviewed and evaluated for quality. Finally, 19 articles were selected and analyzed according to the Newcastle-Ottawa checklist. A total of 642 HNSCC patients were reviewed. The meta-analysis showed salivary LDH levels in the HNSCC group were higher than the control group (mean difference = 0.675, standard error = 0.058) (P < 0.001). As the research results showed, a significant correlation was observed between salivary LDH levels and HNSCCs. So, LDH can be employed as a valuable and minimally invasive biomarker in head and neck cancer screening and prevention.

CSU-Net: Contour Semantic Segmentation Self-Enhancement for Human Head Detection

The computer vision community has made tremendous progress in solving a variety of semantic image understanding tasks, such as classification and segmentation. With the advancement of imaging technology and hardware, image semantic segmentation, through the use of deep learning, is among the most common topics which have been worked on in the last decade. However, image semantic segmentation suffers from several drawbacks such as insufficient detection of object boundaries. In this study, we present a new convolutional neural network architecture called CSU-Net that aims to self-enhance the results of semantic segmentation. The proposed model consists of two strongly concatenated encoder-decoder blocks. With this design, we reduced requirements on computing power and memory size to decrease costs and increase the training/prediction speed. This study also demonstrates the advantage of the proposed system for small training data sets. The proposed approach has been implemented on our private dataset, as well as on a publicly available dataset. A comparative analysis was carried out with four popular segmentation models and three other recently introduced architectures to show the efficiency of the proposed system. CSU-Net outperformed the other competing neural networks that we considered for the comparative study. As an example, it succeeded in improving the traditional U-Net result by approximately 50% in mean Intersection over Union (mIoU) for both tested datasets. Based on our experience, the CSU-Net can improve results of semantic segmentation in many applications.

Global Wheat Head Detection Challenges: Winning Models and Application for Head Counting.

Data competitions have become a popular approach to crowdsource new data analysis methods for general and specialized data science problems. Data competitions have a rich history in plant phenotyping, and new outdoor field datasets have the potential to embrace solutions across research and commercial applications. We developed the Global Wheat Challenge as a generalization competition in 2020 and 2021 to find more robust solutions for wheat head detection using field images from different regions. We analyze the winning challenge solutions in terms of their robustness when applied to new datasets. We found that the design of the competition had an influence on the selection of winning solutions and provide recommendations for future competitions to encourage the selection of more robust solutions.

Benchmarking Self-Supervised Contrastive Learning Methods for Image-Based Plant Phenotyping.

The rise of self-supervised learning (SSL) methods in recent years presents an opportunity to leverage unlabeled and domain-specific datasets generated by image-based plant phenotyping platforms to accelerate plant breeding programs. Despite the surge of research on SSL, there has been a scarcity of research exploring the applications of SSL to image-based plant phenotyping tasks, particularly detection and counting tasks. We address this gap by benchmarking the performance of 2 SSL methods-momentum contrast (MoCo) v2 and dense contrastive learning (DenseCL)-against the conventional supervised learning method when transferring learned representations to 4 downstream (target) image-based plant phenotyping tasks: wheat head detection, plant instance detection, wheat spikelet counting, and leaf counting. We studied the effects of the domain of the pretraining (source) dataset on the downstream performance and the influence of redundancy in the pretraining dataset on the quality of learned representations. We also analyzed the similarity of the internal representations learned via the different pretraining methods. We find that supervised pretraining generally outperforms self-supervised pretraining and show that MoCo v2 and DenseCL learn different high-level representations compared to the supervised method. We also find that using a diverse source dataset in the same domain as or a similar domain to the target dataset maximizes performance in the downstream task. Finally, our results show that SSL methods may be more sensitive to redundancy in the pretraining dataset than the supervised pretraining method. We hope that this benchmark/evaluation study will guide practitioners in developing better SSL methods for image-based plant phenotyping.

Single-Shot Global and Local Context Refinement Neural Network for Head Detection

Head detection is a fundamental task, and it plays an important role in many head-related problems. The difficulty in creating the local and global context in the face of significant lighting, orientation, and occlusion uncertainty, among other factors, still makes this task a remarkable challenge. To tackle these problems, this paper proposes an effective detector, the Context Refinement Network (CRN), that captures not only the refined global context but also the enhanced local context. We use simplified non-local (SNL) blocks at hierarchical features, which can successfully establish long-range dependencies between heads to improve the capability of building the global context. We suggest a multi-scale dilated convolutional module for the local context surrounding heads that extracts local context from various head characteristics. In comparison to other models, our method outperforms them on the Brainwash and the HollywoodHeads datasets.

Saliva-based cell-free DNA and cell-free mitochondrial DNA in head and neck cancers have promising screening and early detection role.

Cell-free DNA (cfDNA) and cell-free mitochondrial DNA (cf-mtDNA) have been postulated as potential diagnostic and prognostic biomarkers for different human malignancies. Early detection of head and neck malignancies is fundamental for optimal patient management. This study, therefore, aimed to assess the utility of saliva-based liquid biopsy as a noninvasive source of cfDNA and cf-mtDNA for detecting head and neck cancer (HNSCC). One hundred thirty-three patients diagnosed with either oral leukoplakia (OLK) or HNSCC were compared with 137 healthy volunteers. An unstimulated whole saliva sample was collected from each participant. The absolute copy numbers of salivary cf-mtDNA and cfDNA were quantified using Multiplex Quantitative PCR. Two diagnostic indices based on the investigated molecules were assessed for their ability to differentiate between different diagnostic categories. The median scores of cfDNA and cf-mtDNA were statistically significantly higher among HNSCC patients (p < 0.05), revealing area under the curve values of 0.758 and 0.826, respectively. The associated accuracy for this test in discriminating HNSCC from other diagnostic categories was 77.37% for the cfDNA-based index and 80.5% for the cf-mtDNA-based index. The median score of cfDNA was statistically significantly higher for patients with severe epithelial dysplasia (OED) compared to those with epithelial keratosis with no OED and mild OED. However, there was no significant difference between controls and OLK individuals. cfDNA and cf-mtDNA showed potential for use as precision medicine tools to detect HNSCC. Further multi-centre prospective studies are warranted to assess the prognostic utility of these molecules.

HD-YOLO: Using radius-aware loss function for head detection in top-view fisheye images

People detection is commonly used in computer vision systems, particularly for video surveillance and passenger flow statistics. Unlike standard cameras, fisheye cameras offer a large field of view and reduce occlusions when mounted overhead. However, due to the orientation variation of people in fisheye images, head detection models suffer from severe distortion when applied to fisheye images captured by top-view fisheye cameras. This work develops an end-to-end head detection method named HD-YOLO against complex situations in top-view fisheye images. The radius-aware loss function is designed to make HD-YOLO adapt to the impact of fisheye distortion, and the channel attention module is added to the model. We have also created new fisheye-image datasets for evaluation. Experiments showed that HD-YOLO outperforms other baseline methods on public and self-built datasets.

Locating and Counting Heads in Crowds With a Depth Prior.

To simultaneously estimate the number of heads and locate heads with bounding boxes, we resort to detection-based crowd counting by leveraging RGB-D data and design a dual-path guided detection network (DPDNet). Specifically, to improve the performance of detection-based approaches for dense/tiny heads, we propose a density map guided detection module, which leverages density map to improve the head/non-head classification in detection network where the density implies the probability of a pixel being a head, and a depth-adaptive kernel that considers the variances in head sizes is also introduced to generate high-fidelity density map for more robust density map regression. In order to prevent dense heads from being filtered out during post-processing, we utilize such a density map for post-processing of head detection and propose a density map guided NMS strategy. Meanwhile, to improve the ability of detecting small heads, we also propose a depth-guided detection module to generate a dynamic dilated convolution to extract features of heads of different scales, and a depth-aware anchor is further designed for better initialization of anchor sizes in the detection framework. Then we use the bounding boxes whose sizes are generated with depth to train our DPDNet. Considering that existing RGB-D datasets are too small and not suitable for performance evaluation of data-driven based approaches, we collect two large-scale RGB-D crowd counting datasets, which comprise a synthetic dataset and a real-world dataset, respectively. Since the depth value at long-distance positions cannot be obtained in the real-world dataset, we further propose a depth completion method with meta learning, which fully utilizes the synthetic depth data to complete the depth value at long-distance positions. Extensive experiments on our proposed two RGB-D datasets and the MICC RGB-D counting dataset show that our method achieves the best performance for RGB-D crowd counting and localization. Further, our method can be easily extended to RGB image based crowd counting and achieves comparable or even better performance on the RGB datasets for both head counting and localization.

Early detection and prevention of head and neck cancers.

Squamous cell carcinoma forms the vast majority of head and neck malignancies, with advanced disease incurring poor long-term survival. Early detection and prompt specialist referral allows the patient a greater chance of cure. Furthermore, basal cell carcinoma is the most common malignancy in humans, with the vast majority presenting in the head and neck region. Dentists have a unique opportunity to assess for cutaneous malignancies during routine visits.Cancer screening should be common practice within dental professionals. In addition to enquiring about common red flag symptoms, a comprehensive and systematic extra- and intra-oral examination should be undertaken at each new and check-up appointment. Urgent referral to an appropriate secondary care provider should be made at the earliest opportunity where concern for cancer exists.

Advancing Head and Neck Cancer Early Detection Research (NIH)

Advancing Head and Neck Cancer Early Detection Research (NIH)

Head and neck cancer detection by ultrasound: A comparison of referral pathways

Category: Head and neck

JustDeepIt: Software tool with graphical and character user interfaces for deep learning-based object detection and segmentation in image analysis.

Image processing and analysis based on deep learning are becoming mainstream and increasingly accessible for solving various scientific problems in diverse fields. However, it requires advanced computer programming skills and a basic familiarity with character user interfaces (CUIs). Consequently, programming beginners face a considerable technical hurdle. Because potential users of image analysis are experimentalists, who often use graphical user interfaces (GUIs) in their daily work, there is a need to develop GUI-based easy-to-use deep learning software to support their work. Here, we introduce JustDeepIt, a software written in Python, to simplify object detection and instance segmentation using deep learning. JustDeepIt provides both a GUI and a CUI. It contains various functional modules for model building and inference, and it is built upon the popular PyTorch, MMDetection, and Detectron2 libraries. The GUI is implemented using the Python library FastAPI, simplifying model building for various deep learning approaches for beginners. As practical examples of JustDeepIt, we prepared four case studies that cover critical issues in plant science: (1) wheat head detection with Faster R-CNN, YOLOv3, SSD, and RetinaNet; (2) sugar beet and weed segmentation with Mask R-CNN; (3) plant segmentation with U2-Net; and (4) leaf segmentation with U2-Net. The results support the wide applicability of JustDeepIt in plant science applications. In addition, we believe that JustDeepIt has the potential to be applied to deep learning-based image analysis in various fields beyond plant science.