Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging
Background/Aims: Hepatocellular carcinoma (HCC) is a prevalent cancer that significantly contributes to mortality globally, primarily due to its late diagnosis. Early detection is crucial yet challenging. This study leverages the potential of deep learning (DL) technologies, employing the You Only L...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AVES
2025-02-01
|
| Series: | The Turkish Journal of Gastroenterology |
| Online Access: | https://www.turkjgastroenterol.org/en/diagnostic-performance-of-deep-learning-applications-in-hepatocellular-carcinoma-detection-u-computed-tomography-imaging-137310 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823858122528129024 |
|---|---|
| author | Enes Şahin Ozan Can Tatar Mehmet Eşref Ulutaş Sertaç Ata Güler Turgay Şimşek Nihat Zafer Utkan Nuh Zafer Cantürk |
| author_facet | Enes Şahin Ozan Can Tatar Mehmet Eşref Ulutaş Sertaç Ata Güler Turgay Şimşek Nihat Zafer Utkan Nuh Zafer Cantürk |
| author_sort | Enes Şahin |
| collection | DOAJ |
| description | Background/Aims: Hepatocellular carcinoma (HCC) is a prevalent cancer that significantly contributes to mortality globally, primarily due to its late diagnosis. Early detection is crucial yet challenging. This study leverages the potential of deep learning (DL) technologies, employing the You Only Look Once (YOLO) architecture, to enhance the detection of HCC in computed tomography (CT) images, aiming to improve early diagnosis and thereby patient outcomes.
Materials and methods: We used a dataset of 1290 CT images from 122 patients, segmented according to a standard 70:20:10 split for training, validation, and testing phases. The YOLO-based DL model was trained on these images, with subsequent phases for validation and testing to assess the model’s diagnostic capabilities comprehensively.
Results: The model exhibited exceptional diagnostic accuracy, with a precision of 0.97216, recall of 0.919, and an overall accuracy of 95.35%, significantly surpassing traditional diagnostic approaches. It achieved a specificity of 95.83% and a sensitivity of 94.74%, evidencing its effectiveness in clinical settings and its potential to reduce the rate of missed diagnoses and unnecessary interventions.
Conclusion: The implementation of the YOLO architecture for detecting HCC in CT scans has shown substantial promise, indicating that DL models could soon become a standard tool in oncological diagnostics. As artificial intelligence technology continues to evolve, its integration into healthcare systems is expected to advance the accuracy and efficiency of diagnostics in oncology, enhancing early detection and treatment strategies and potentially improving patient survival rates. |
| format | Article |
| id | doaj-art-6a02803a611a49a08f136ebadef3547c |
| institution | Kabale University |
| issn | 2148-5607 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | AVES |
| record_format | Article |
| series | The Turkish Journal of Gastroenterology |
| spelling | doaj-art-6a02803a611a49a08f136ebadef3547c2025-02-11T14:17:31ZengAVESThe Turkish Journal of Gastroenterology2148-56072025-02-0136212413010.5152/tjg.2024.24538Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography ImagingEnes Şahin0https://orcid.org/0000-0003-3777-8468Ozan Can Tatar1https://orcid.org/0000-0002-9046-7362Mehmet Eşref Ulutaş2https://orcid.org/0000-0002-9206-4348Sertaç Ata Güler3https://orcid.org/0000-0003-1616-9436Turgay Şimşek4https://orcid.org/0000-0002-5733-6301Nihat Zafer Utkan5https://orcid.org/0000-0002-2133-3336Nuh Zafer Cantürk6https://orcid.org/0000-0002-0042-9742Department of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, TürkiyeDepartment of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, Türkiye ; Department of Information Systems Engineering, Kocaeli University Faculty of Technology, Kocaeli, TürkiyeUniversity of Health Science, Gaziantep City Hospital, General Surgery, Gaziantep, TürkiyeDepartment of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, TürkiyeDepartment of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, TürkiyeDepartment of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, TürkiyeDepartment of General Surgery, Kocaeli University Faculty of Medicine, Kocaeli, TürkiyeBackground/Aims: Hepatocellular carcinoma (HCC) is a prevalent cancer that significantly contributes to mortality globally, primarily due to its late diagnosis. Early detection is crucial yet challenging. This study leverages the potential of deep learning (DL) technologies, employing the You Only Look Once (YOLO) architecture, to enhance the detection of HCC in computed tomography (CT) images, aiming to improve early diagnosis and thereby patient outcomes. Materials and methods: We used a dataset of 1290 CT images from 122 patients, segmented according to a standard 70:20:10 split for training, validation, and testing phases. The YOLO-based DL model was trained on these images, with subsequent phases for validation and testing to assess the model’s diagnostic capabilities comprehensively. Results: The model exhibited exceptional diagnostic accuracy, with a precision of 0.97216, recall of 0.919, and an overall accuracy of 95.35%, significantly surpassing traditional diagnostic approaches. It achieved a specificity of 95.83% and a sensitivity of 94.74%, evidencing its effectiveness in clinical settings and its potential to reduce the rate of missed diagnoses and unnecessary interventions. Conclusion: The implementation of the YOLO architecture for detecting HCC in CT scans has shown substantial promise, indicating that DL models could soon become a standard tool in oncological diagnostics. As artificial intelligence technology continues to evolve, its integration into healthcare systems is expected to advance the accuracy and efficiency of diagnostics in oncology, enhancing early detection and treatment strategies and potentially improving patient survival rates.https://www.turkjgastroenterol.org/en/diagnostic-performance-of-deep-learning-applications-in-hepatocellular-carcinoma-detection-u-computed-tomography-imaging-137310 |
| spellingShingle | Enes Şahin Ozan Can Tatar Mehmet Eşref Ulutaş Sertaç Ata Güler Turgay Şimşek Nihat Zafer Utkan Nuh Zafer Cantürk Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging The Turkish Journal of Gastroenterology |
| title | Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging |
| title_full | Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging |
| title_fullStr | Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging |
| title_full_unstemmed | Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging |
| title_short | Diagnostic Performance of Deep Learning Applications in Hepatocellular Carcinoma Detection Using Computed Tomography Imaging |
| title_sort | diagnostic performance of deep learning applications in hepatocellular carcinoma detection using computed tomography imaging |
| url | https://www.turkjgastroenterol.org/en/diagnostic-performance-of-deep-learning-applications-in-hepatocellular-carcinoma-detection-u-computed-tomography-imaging-137310 |
| work_keys_str_mv | AT enessahin diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT ozancantatar diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT mehmetesrefulutas diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT sertacataguler diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT turgaysimsek diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT nihatzaferutkan diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging AT nuhzafercanturk diagnosticperformanceofdeeplearningapplicationsinhepatocellularcarcinomadetectionusingcomputedtomographyimaging |