Persistent Identifier
|
doi:10.11588/data/YAZWJW |
Publication Date
|
2023-07-07 |
Title
| Implementation of deep learning in liver pathology optimizes diagnosis of benign lesions and adenocarcinoma metastasis [data] |
Author
| Kriegsmann, Mark (Institute of Pathology, Heidelberg University, 69120 Heidelberg, Germany; Pathology Wiesbaden, 65199 Wiesbaden, Germany)
Kriegsmann, Katharina (Department of Hematology, Oncology and Rheumatology, Heidelberg University, 69120 Heidelberg, Germany; Laborarztpraxis Rhein-Main MVZ GbR, 60437 Frankfurt am Main, Germany)
Steinbuss, Georg (Department of Hematology, Oncology and Rheumatology, Heidelberg University, 69120 Heidelberg, Germany)
Zgorzelski, Christiane (Institute of Pathology, Heidelberg University, 69120 Heidelberg, Germany)
Albrecht, Thomas (Institute of Pathology, Heidelberg University, 69120 Heidelberg, Germany)
Heinrich, Stefan (Department of Surgery, University Medical Center Mainz, 55131 Mainz, Germany)
Farkas, Stefan (Department of Surgery, St. Josefs- Hospital, 65189 Wiesbaden, Germany)
Roth, Wilfried (Institute of Pathology, University Medical Center Mainz, JGU-Mainz, 55131 Mainz, Germany)
Hausen, Anne (Institute of Pathology, University Medical Center Mainz, JGU-Mainz, 55131 Mainz, Germany)
Gaida, Matthias M. (Institute of Pathology, University Medical Center Mainz, JGU-Mainz, 55131 Mainz, Germany; TRON, Translational Oncology at the University Medical Center, JGU-Mainz, 55131 Mainz, Germany) |
Point of Contact
|
Use email button above to contact.
Kriegsmann, Mark (Institute of Pathology, Heidelberg University, 69120 Heidelberg, Germany; Pathology Wiesbaden, 65199 Wiesbaden, Germany)
Hausen, Anne (Institute of Pathology, University Medical Center Mainz, JGU-Mainz, 55131 Mainz, Germany) |
Description
| Differentiation of neoplastic and non-neoplastic liver lesions using routine histological tissue sections can be challenging. Correct classification is paramount to forecast prognosis and to select the correct therapy. Deep learning algorithms have recently been suggested to support objective and consistent assessment of digital histopathological images.
In thisstudy, annotation of 7 different classes, namely non-neoplastic bile ducts, benign biliary lesions and liver metastases from colorectal and pancreatic adenocarcinoma, was performed, resulting in a total of 204.159 image patches. The patient cohort was split into three datasets and an EfficientNetV2 and ResNetRS deep learning algorithm to classify the respective categories was trained, optimized, and ultimately tested. Model performance was evaluated on validation and test data using confusion matrices.
In summary, a hereinafter proposed automated classification to identify benign and malignant liver lesions by deep learning methods was described, which performed with high diagnostic accuracy. Furthermore, a huge curated liver dataset was provided. |
Subject
| Medicine, Health and Life Sciences |
Related Publication
| Kriegsmann M, Kriegsmann K, Steinbuss G, et al. Implementation of deep learning in liver pathology optimizes diagnosis of benign lesions and adenocarcinoma metastasis. Clin Transl Med. 2023;00:e1299. doi: 10.1002/ctm2.1299 https://doi.org/10.1002/ctm2.1299 |