Journals / Bozok Tıp Dergisi / 2026 / Cilt: 16 Sayı: 3

PREDICTING CARDIOVASCULAR PATHOLOGY USING MORPHOLOGICAL ANALYSIS OF CARDIAC IMAGES: A DEEP LEARNING-BASED PROSPECTIVE STUDY

Kalp Görüntülerine Dayalı Morfolojik Analiz ile Kardiyovasküler Patoloji Tahmini: Derin Öğrenme Tabanlı Prospektif Çalışma

Sefa Sönmez(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, TIP FAKÜLTESİ)0000-0001-5532-9856
Ömer Faruk Nasip(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, TIP FAKÜLTESİ)0000-0002-8340-1920
Ahmet Depreli(SELÇUK ÜNİVERSİTESİ, TIP FAKÜLTESİ)0000-0001-5941-2358
Merve Nur Özgen Sönmez(TOKAT GAZİOSMANPAŞA ÜNİVERSİTESİ, TIP FAKÜLTESİ)
Bekir Dinçer(SAMSUN ÜNİVERSİTESİ, TIP FAKÜLTESİ)0000-0001-8516-2209
Pages
384–392
Publication Date
2026-09-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

We believe this approach will contribute to forensic reporting processes.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Objective: The aim of this study is to automatically and reliably predict the presence of cardiovascular pathology from heart photographs using deep learning algorithms.
📊
Key Findings & Data:Additionally, it aims to compare the diagnostic performance of different deep learning models.
💡
Conclusion & Impact:We believe this approach will contribute to forensic reporting processes.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Kalp Morfolojisi · Kalp Anatomisi · Adli Tıp

Abstract

Objective: The aim of this study is to automatically and reliably predict the presence of cardiovascular pathology from heart photographs using deep learning algorithms. Additionally, it aims to compare the diagnostic performance of different deep learning models. Material and Methods: This prospective study was conducted with the approval of the Education and Scientific Research Commission of the Council of Forensic Medicine and the Ethics Committee for Non-Interventional Scientific Research at Tokat Gaziosmanpaşa University. A total of 218 cases (110 men, 108 women) whose hearts were removed during autopsy were included in the study. Photographs of the hearts from each case were obtained using a professional camera. Data augmentation techniques were applied for deep learning analysis, generating six variations from each image and resulting in a dataset comprising a total of 1,308 heart photographs. The hearts were examined in detail both macroscopically and microscopically. Cases with identified cardiovascular pathology were classified as the “patient” group, while cases without any cardiovascular pathology were classified as the “control” group. Morphological images of heart tissue were automatically extracted from the heart photographs. The presence of cardiovascular pathology was assessed using deep learning-based models based on these features. Results: The highest classification accuracy (88.38%) for heart images from the patient and control groups was achieved using the DenseNet201 model. Of the 654 images from the patient group, 569 were correctly classified as “patient,” while 85 were incorrectly predicted as belonging to the “control” group. Conclusion: The study demonstrated that cardiovascular pathology can be predicted using deep learning models based on photographs of the heart’s direct morphological structure, without the need for morphometric measurements. We believe this approach will contribute to forensic reporting processes.

Özet

Amaç: Bu çalışmanın amacı, kalp fotoğrafları üzerinden kardiyovasküler patoloji varlığını derin öğrenme algoritmaları ile otomatik ve güvenilir biçimde tahmin etmektir. Ayrıca farklı derin öğrenme modellerinin tanısal performanslarını karşılaştırmaktır. Gereç ve Yöntemler: Bu prospektif çalışma, Adli Tıp Kurumu Eğitim ve Bilimsel Araştırma Komisyonu ve Tokat Gaziosmanpaşa Üniversitesi Girişimsel Olmayan Bilimsel Araştırmalar Etik Kurulu onayı alınarak yürütüldü. Otopsi sırasında kalpleri çıkarılan toplam 218 (110 erkek, 108 kadın) olgu çalışmaya dahil edildi. Her bir olguya ait kalp görüntüleri profesyonel bir kamera kullanılarak elde edildi. Derin öğrenme analizlerinde kullanılmak üzere veri artırma teknikleri uygulanarak her görüntüden altı varyasyon oluşturulmuş ve toplam 1.308 kalp fotoğrafı ile veri seti oluşturuldu. Kalpler makroskobik ve mikroskobik olarak ayrıntılı bir şekilde incelendi. Kardiyovasküler patoloji saptanan olgular “hasta” grubu, herhangi bir kardiyovasküler patolojisi olmayan olgular ise “kontrol” grubu olarak sınıflandırıldı. Kalp fotoğraflarından kalp dokusuna ait morfolojik görüntüler otomatik olarak çıkarıldı. Bu özellikler üzerinden kardiyovasküler patoloji varlığının sınıflandırılması derin öğrenme tabanlı modeller aracılığıyla değerlendirildi. Bulgular: Hasta ve kontrol gruplarına ait kalp fotoğraflarının sınıflandırılmasında en yüksek başarı oranı (%88,38) DenseNet201 modeli ile elde edildi. Hasta grubuna ait 654 fotoğrafın 569’u doğru şekilde “hasta” olarak sınıflandırılırken, 85 fotoğraf yanlış olarak “kontrol” grubunda tahmin edildi. Sonuç: Derin öğrenme modelleri kullanılarak, herhangi bir morfometrik ölçüm gerekmeksizin kalbin doğrudan morfolojik dokusu üzerinden çekilen fotoğraflardan kardiyovasküler patoloji varlığının tahmin edilebildiğini gösterdi. Bu yaklaşımın adli raporlama süreçlerine katkı sağlayacağı kanaatindeyiz.

🔖

Cite This Article

Sönmez, S., Nasip, Ö. F., Depreli, A., Sönmez, M. N. Ö., Dinçer, B. (2026). PREDICTING CARDIOVASCULAR PATHOLOGY USING MORPHOLOGICAL ANALYSIS OF CARDIAC IMAGES: A DEEP LEARNING-BASED PROSPECTIVE STUDY. Bozok Tıp Dergisi, Cilt: 16 Sayı: 3, 384–392. https://doi.org/10.16919/bozoktip.1927334

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (20)

  1. World Health Organization. The top 10 causes of death, 2021. WHO; 2024. Available from: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
  2. İkitimur B. Yaşlılarda koroner arter hastalığına yaklaşım. Türk Kardiyoloji Derneği Arşivi. 2017;45(5):32-4.
  3. Park JH, Na JY, Lee BW, Yang KM, Choi YS. A statistical analysis on forensic autopsies performed in Korea in 2017. Korean J Leg Med. 2018;42(4):111-25.
  4. Hoi KY, Lee SS, Cheong H, Yoo B, Jeon J. Automatic measuring of coronary atherosclerosis from medicolegal autopsy photographs based on deep learning techniques. Forensic Sci Med Pathol. 2025; 21:1664-75
  5. Klüner LV, Chan K, Antoniades C. Using artificial intelligence to study atherosclerosis from computed tomography imaging: a state-of-the-art review of the current literature. Atherosclerosis. 2024;398:117580.
  6. Knecht S, Morandini P, Biehler-Gomez L, Ardagna Y, Perrin M, Cattaneo C, et al. Interpretable machine learning for individualized sex estimation from long bones. Int J Legal Med. 2026;140(2):983-95.
  7. Kuha A, Ackermann J, Junno JA, Oettlé A, Oura P. Deep learning in sex estimation from photographed human mandible using the Human Osteological Research Collection. Leg Med (Tokyo). 2024;70:102476.
  8. Pichetpan K, Singsuwan P, Intasuwan P, Sinthubua A, Palee P, Mahakkanukrauh P. Sex determination using the clavicle by deep learning in a Thai population. Med Sci Law. 2024;64(1):8-14.
  9. Wehbe RM, Katsaggelos AK, Hammond KJ, Hong H, Ahmad FS, Ouyang D, et al. Deep learning for cardiovascular imaging: a review. JAMA Cardiol. 2023;8(11):1089-98.
  10. Chen C, Qin C, Qiu H, Tarroni G, Duan J, Bai W, et al. Deep learning for cardiac image segmentation: a review. Front Cardiovasc Med. 2020;7:508599.
  11. Tsampras T, Karamanidou T, Papanastasiou G, Stavropoulos TG. Deep learning for cardiac imaging: Focus on myocardial diseases, a narrative review. Hell J Cardiol.2025;81:18-24.
  12. Cobo M, Menéndez Fernández-Miranda P, Bastarrika G, Lloret Iglesias L. Enhancing radiomics and Deep Learning systems through the standardization of medical imaging workflows. Sci Data. 2023;10(1):732.
  13. Polidori T, De Santis D, Rucci C, Tremamunno G, Piccinni G, Pugliese L, et al. Radiomics applications in cardiac imaging: a comprehensive review. Radiol Med. 2023;128(8):922-33.
  14. Shang J, Guo Y, Ma Y, Hou Y. Cardiac computed tomography radiomics: a narrative review of current status and future directions. Quant Imaging Med Surg. 2022;12(6):3436.
  15. Pagourelias ED, Mirea O, Vovas G, Duchenne J, Michalski B, Cleemput JV, et al. Relation of regional myocardial structure and function in hypertrophic cardiomyopathy and amyloidois: a combined two-dimensional speckle tracking and cardiovascular magnetic resonance analysis. Eur Heart J Cardiovasc Imaging. 2019;20(4):426-37.
  16. Vigneault DM, Yang E, Jensen PJ, Tee MW, Farhad H, Chu L, et al. Left ventricular strain is abnormal in preclinical and overt hypertrophic cardiomyopathy: cardiac MR feature tracking. Radiology. 2019;290(3):640-8.
  17. Diao K, Liang HQ, Yin HK, Yuan MJ, Gu M, Yu PX, et al. Multi-channel deep learning model-based myocardial spatial-temporal morphology feature on cardiac MRI cine images diagnoses the cause of LVH. Insights into Imaging. 2023;14(1):70. Li Y, Niu C, Wang J, Xu Y, Dai H, Xiong T, et al. A fully automated sex estimation for proximal femur X- ray images through deep learning detection and classification. Leg Med (Tokyo). 2022;57:102056.
  18. Qiu L, Liu A, Dai X, Liu G, Peng Z, Zhan M, et al. Machine learning and deep learning enabled age estimation on medial clavicle CT images. Int J Legal Med. 2024;138(2):487-98.
  19. Fatema K, Montaha S, Rony MAH, Azam S, Hasan MZ, Jonkman M. A robust framework combining image processing and deep learning hybrid model to classify cardiovascular diseases using a limited number of paper-based complex ECG images. Biomedicines. 2022;10(11):2835.
  20. Kaba Ş, Haci H, Isin A, Ilhan A, Conkbayir C. The application of deep learning for the segmentation and classification of coronary arteries. Diagnostics. 2023;13(13):2274.