Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning
ABSTRACT Cancer continues to be a leading cause of mortality worldwide, emphasizing the importance of early detection for effective treatment. Macroscopic methods like X‐ray and CT scans offer limited resolution and pose risks due to ionizing radiation exposure. In contrast, microscopic techniques s...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-04-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.70120 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850191178989830144 |
|---|---|
| author | M. Senthil Pandian S. Deepa Nivethika J. Idhikash Vamsee N. Yashwanth Aishwarya Shaji Prabhakaran Paulraj |
| author_facet | M. Senthil Pandian S. Deepa Nivethika J. Idhikash Vamsee N. Yashwanth Aishwarya Shaji Prabhakaran Paulraj |
| author_sort | M. Senthil Pandian |
| collection | DOAJ |
| description | ABSTRACT Cancer continues to be a leading cause of mortality worldwide, emphasizing the importance of early detection for effective treatment. Macroscopic methods like X‐ray and CT scans offer limited resolution and pose risks due to ionizing radiation exposure. In contrast, microscopic techniques such as histopathology require invasive biopsy samples and lack real‐time diagnostic capabilities. Bridging this gap, THz research offers a promising solution, utilizing nonionizing terahertz radiation to achieve superior resolution. To this end, a proposed microstrip antenna emerges as a cost‐effective and high‐resolution tool for enabling the accurate diagnosis and detection of superficial cancers. This novel approach could revolutionize medical involvement, leading to earlier cancer detection and improved patient outcomes. The THz antenna of size 526 μm × 536 μm designed using Computer Simulation Technology (CST) software radiates at 0.3 THz with a gain of 5 dB. The antenna, when placed in the model replicating human tissue (Phantom model) radiates at 0.88 THz with a return loss of −27 dB and a gain 10 dB. Whereas, the same antenna was designed and simulated with a model replicating human tissue with tumor, radiating at 0.88 THz with a return loss of −38 dB and gain of 9.6 dB. The optimization of the decision was done using the combination of K‐means and logistic regression algorithm to determine 95.06% efficiency. |
| format | Article |
| id | doaj-art-93add6597ee446d4918655e71c86d2a7 |
| institution | OA Journals |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-93add6597ee446d4918655e71c86d2a72025-08-20T02:14:59ZengWileyEngineering Reports2577-81962025-04-0174n/an/a10.1002/eng2.70120Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine LearningM. Senthil Pandian0S. Deepa Nivethika1J. Idhikash2Vamsee N. Yashwanth3Aishwarya Shaji4Prabhakaran Paulraj5School of Civil Engineering VIT University Chennai IndiaSchool of Computer Science and Engineering VIT University Chennai IndiaSchool of Computer Science and Engineering VIT University Chennai IndiaSchool of Computer Science and Engineering VIT University Chennai IndiaSchool of Computer Science and Engineering VIT University Chennai IndiaECE Department St. Joseph University in Tanzania Dar es Salam TanzaniaABSTRACT Cancer continues to be a leading cause of mortality worldwide, emphasizing the importance of early detection for effective treatment. Macroscopic methods like X‐ray and CT scans offer limited resolution and pose risks due to ionizing radiation exposure. In contrast, microscopic techniques such as histopathology require invasive biopsy samples and lack real‐time diagnostic capabilities. Bridging this gap, THz research offers a promising solution, utilizing nonionizing terahertz radiation to achieve superior resolution. To this end, a proposed microstrip antenna emerges as a cost‐effective and high‐resolution tool for enabling the accurate diagnosis and detection of superficial cancers. This novel approach could revolutionize medical involvement, leading to earlier cancer detection and improved patient outcomes. The THz antenna of size 526 μm × 536 μm designed using Computer Simulation Technology (CST) software radiates at 0.3 THz with a gain of 5 dB. The antenna, when placed in the model replicating human tissue (Phantom model) radiates at 0.88 THz with a return loss of −27 dB and a gain 10 dB. Whereas, the same antenna was designed and simulated with a model replicating human tissue with tumor, radiating at 0.88 THz with a return loss of −38 dB and gain of 9.6 dB. The optimization of the decision was done using the combination of K‐means and logistic regression algorithm to determine 95.06% efficiency.https://doi.org/10.1002/eng2.70120cancerdetectionmachine learningoptimizationTHz antennas |
| spellingShingle | M. Senthil Pandian S. Deepa Nivethika J. Idhikash Vamsee N. Yashwanth Aishwarya Shaji Prabhakaran Paulraj Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning Engineering Reports cancer detection machine learning optimization THz antennas |
| title | Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning |
| title_full | Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning |
| title_fullStr | Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning |
| title_full_unstemmed | Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning |
| title_short | Cancer Diagnosis Optimization With a Combination of Flexible THz Antennas and Machine Learning |
| title_sort | cancer diagnosis optimization with a combination of flexible thz antennas and machine learning |
| topic | cancer detection machine learning optimization THz antennas |
| url | https://doi.org/10.1002/eng2.70120 |
| work_keys_str_mv | AT msenthilpandian cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning AT sdeepanivethika cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning AT jidhikash cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning AT vamseenyashwanth cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning AT aishwaryashaji cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning AT prabhakaranpaulraj cancerdiagnosisoptimizationwithacombinationofflexiblethzantennasandmachinelearning |