Incremental Learning for Panoramic Radiograph Segmentation

AlQarni, Saeed; Chandrashekar, Geetha; Bumann, Erin E.; Lee, Yugyung

doi:10.1109/embc48229.2022.9871995

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, this procedure is often performed manually, which can be quite time-consuming. The segmentation and numbering are not objective, and there is no guarantee of the accuracy of the results as it relies heavily on the subjective judgment of the dentist [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

Wang,

Liang,

Chang

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Accurate tooth segmentation and numbering are the cornerstones of efficient automatic dental diagnosis and treatment. In this paper, a multitask learning architecture has been proposed for accurate tooth segmentation and numbering in panoramic X-ray images. A graph convolution network was applied for the automatic annotation of the target region, a modified convolutional neural network-based detection subnetwork (DSN) was used for tooth recognition and boundary regression, and an effective region segmentation subnetwork (RSSN) was used for region segmentation. The features extracted using RSSN and DSN were fused to optimize the quality of boundary regression, which provided impressive results for multiple evaluation metrics. Specifically, the proposed framework achieved a top F1 score of 0.9849, a top Dice metric score of 0.9629, and an mAP (IOU = 0.5) score of 0.9810. This framework holds great promise for enhancing the clinical efficiency of dentists in tooth segmentation and numbering tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

Wang,

Liang,

Chang

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…(10)(11)(12)(13)16,19,25,(29)(30)(31)(32) Additionally, many age estimation models have been manually developed, introducing the potential for human error. (4,5,(10)(11)(12)(13)(14)(15)(16)(17)(18)(19)21,22,25,33,34) Addressing this limitation, artificial intelligence (AI) has become a promising approach for creating new age estimation models, as evidenced by previous studies. (6,20,23,35,36) Deep learning, in particular, has gained prominence in age estimation due to its capacity to reduce human workload, enhance accuracy in detection and decision-making, and, in some cases, even classify genders as part of the age estimation process.…”

Section: Introductionmentioning

confidence: 99%

Dental Radiography in Age Determination: Contemporary Methods and Trends

Chulamanee,

Panyarak

2023

Oral Sci Rep

View full text Add to dashboard Cite

The determination of an individual's age assumes paramount significance in forensic and legal contexts, necessitating the utilization of diverse techniques. Dental radiography emerges as a non-invasive approach for determining age-related dental changes. This method grants a comprehensive analysis of various dental features to identify an individual’s precise age, place them within designated age ranges, or define whether they exceed or subordinate to specific age thresholds. This review summarizes age estimation methodologies using dental radiography and conducts the investigations into contemporary trends by reviewing relevant studies published in Pubmed between 2020 and 2023. Age categorization delineates into three distinct phases: pre-natal, neo-natal, and post-natal; childhood and adolescence; and adulthood. Panoramic radiography becomes the predominant radiographic modality, with the Demirjian method is more commonly known for age estimation age in the initial two phases. In contrast, adulthood age estimation relies on anatomical changes. Significantly, artificial intelligence (AI) technology has recently attracted attention for age estimation, yielding promising results. AI demonstrates the potential to enhance the accuracy of conventional methodologies, diminishing human errors and mitigating associated workload burdens, offering inventive ground for future advancements.

show abstract

Incremental Learning for Panoramic Radiograph Segmentation

Cited by 2 publications

References 13 publications

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

STSN-Net: Simultaneous Tooth Segmentation and Numbering Method in Crowded Environments with Deep Learning

Dental Radiography in Age Determination: Contemporary Methods and Trends

Contact Info

Product

Resources

About