ColorNephroNet: Kidney tumor malignancy prediction using medical image colorization

Autores

  • Aleksander Obuchowski Gdańsk University of Technology
  • Barbara Klaudel Gdańsk University of Technology
  • Roman Karski Gdańsk University of Technology
  • Bartosz Rydziński Gdańsk University of Technology
  • Mateusz Glembin COPERNICUS, St. Adalbert’s Hospital Gda ́nsk, Department of Urology
  • Paweł Syty
  • Patryk Jasik Gdańsk University of Technology

DOI:

https://doi.org/10.32473/flairs.v35i.130689

Palavras-chave:

Medical Image Classification, Transfer Learning, Colorization, Renal, Tumor, Computer Aided Diagnosis

Resumo

Renal tumor malignancy classification is one of the crucial tasks in urology, being a primary factor included in the decision of whether to perform kidney removal surgery (nephrectomy) or not. Currently, tumor malignancy prediction is determined by the radiological diagnosis based on computed tomography (CT) images. However, it is estimated that up to 16% of nephrectomies could have been avoided because the tumor that had been diagnosed as malignant, was found to be benign in the postoperative histopathological examination. The excess of false-positive diagnoses results in unnecessarily performed nephrectomies that carry the risk of periprocedural complications. In this paper, we present a machine-aided diagnosis system that predicts the tumor malignancy based on a CT image. The prediction is performed after radiological diagnosis and is used to capture false-positive diagnoses. Our solution is able to achieve a 0.84 F1-score in this task. We also propose a novel approach to knowledge transfer in the medical domain in terms of colorization based pre-processing that is able to increase the F1-score by up to 1.8pp.

Downloads

Publicado

2022-05-04

Como Citar

Aleksander Obuchowski, Barbara Klaudel, Roman Karski, Bartosz Rydziński, Mateusz Glembin, Paweł Syty, & Patryk Jasik. (2022). ColorNephroNet: Kidney tumor malignancy prediction using medical image colorization. The International FLAIRS Conference Proceedings, 35. https://doi.org/10.32473/flairs.v35i.130689

Edição

Seção

Special Track: AI in Healthcare Informatics