Deep learning algorithm (YOLOv7) for automated renal mass detection on contrast-enhanced MRI: a 2D and 2.5D evaluation of results

• Published in: Abdominal imaging Vol. 49; no. 4; pp. 1194 - 1201
• Main Authors: Anari, Pouria Yazdian, Lay, Nathan, Zahergivar, Aryan, Firouzabadi, Fatemeh Dehghani, Chaurasia, Aditi, Golagha, Mahshid, Singh, Shiva, Homayounieh, Fatemeh, Obiezu, Fiona, Harmon, Stephanie, Turkbey, Evrim, Merino, Maria, Jones, Elizabeth C., Ball, Mark W., Linehan, W. Marston, Turkbey, Baris, Malayeri, Ashkan A.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2024; Springer Nature B.V
• Subjects: Algorithms; Automation; Benchmarks; Bladder; Carcinoma, Renal Cell - diagnostic imaging; Computer vision; Deep Learning; Gastroenterology; Hepatology; Humans; Imaging; Itk protein; Kidney cancer; Kidney Neoplasms - diagnostic imaging; Kidneys; Machine learning; Magnetic Resonance Imaging; Medicine; Medicine & Public Health; Radiology; Retroperitoneum; Sensitivity; Tumors; Ureters; Deep learning; Computer vision; Renal cell carcinoma; YOLOv7
• ISSN: 2366-0058; 2366-004X; 2366-0058
• DOI: 10.1007/s00261-023-04172-w

Introduction Accurate diagnosis and treatment of kidney tumors greatly benefit from automated solutions for detection and classification on MRI. In this study, we explore the application of a deep learning algorithm, YOLOv7, for detecting kidney tumors on contrast-enhanced MRI. Material and methods We assessed the performance of YOLOv7 tumor detection on excretory phase MRIs in a large institutional cohort of patients with RCC. Tumors were segmented on MRI using ITK-SNAP and converted to bounding boxes. The cohort was randomly divided into ten benchmarks for training and testing the YOLOv7 algorithm. The model was evaluated using both 2-dimensional and a novel in-house developed 2.5-dimensional approach. Performance measures included F1, Positive Predictive Value (PPV), Sensitivity, F1 curve, PPV-Sensitivity curve, Intersection over Union (IoU), and mean average PPV (mAP). Results A total of 326 patients with 1034 tumors with 7 different pathologies were analyzed across ten benchmarks. The average 2D evaluation results were as follows: Positive Predictive Value (PPV) of 0.69 ± 0.05, sensitivity of 0.39 ± 0.02, and F1 score of 0.43 ± 0.03. For the 2.5D evaluation, the average results included a PPV of 0.72 ± 0.06, sensitivity of 0.61 ± 0.06, and F1 score of 0.66 ± 0.04. The best model performance demonstrated a 2.5D PPV of 0.75, sensitivity of 0.69, and F1 score of 0.72. Conclusion Using computer vision for tumor identification is a cutting-edge and rapidly expanding subject. In this work, we showed that YOLOv7 can be utilized in the detection of kidney cancers.