Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Boosting Kidney Stone Identification in Endoscopic Images Using Two-Step Transfer Learning

Francisco Lopez-Tiro, Juan Pablo Betancur-Rengifo, Arturo Ruiz-Sanchez, Ivan Reyes-Amezcua, Jonathan El-Beze, Jacques Hubert, Michel Daudon, Gilberto Ochoa-Ruiz, Christian Daul

TL;DR

A two-step transfer learning approach is used to train the kidney stone classifier and shows that learning features from different domains with similar information helps to improve the performance of a model that performs classification in real conditions.

Abstract

Knowing the cause of kidney stone formation is crucial to establish treatments that prevent recurrence. There are currently different approaches for determining the kidney stone type. However, the reference ex-vivo identification procedure can take up to several weeks, while an in-vivo visual recognition requires highly trained specialists. Machine learning models have been developed to provide urologists with an automated classification of kidney stones during an ureteroscopy; however, there is a general lack in terms of quality of the training data and methods. In this work, a two-step transfer learning approach is used to train the kidney stone classifier. The proposed approach transfers knowledge learned on a set of images of kidney stones acquired with a CCD camera (ex-vivo dataset) to a final model that classifies images from endoscopic images (ex-vivo dataset). The results show that learning features from different domains with similar information helps to improve the performance of a model that performs classification in real conditions (for instance, uncontrolled lighting conditions and blur). Finally, in comparison to models that are trained from scratch or by initializing ImageNet weights, the obtained results suggest that the two-step approach extracts features improving the identification of kidney stones in endoscopic images.

Boosting Kidney Stone Identification in Endoscopic Images Using Two-Step Transfer Learning

TL;DR

A two-step transfer learning approach is used to train the kidney stone classifier and shows that learning features from different domains with similar information helps to improve the performance of a model that performs classification in real conditions.

Abstract

Knowing the cause of kidney stone formation is crucial to establish treatments that prevent recurrence. There are currently different approaches for determining the kidney stone type. However, the reference ex-vivo identification procedure can take up to several weeks, while an in-vivo visual recognition requires highly trained specialists. Machine learning models have been developed to provide urologists with an automated classification of kidney stones during an ureteroscopy; however, there is a general lack in terms of quality of the training data and methods. In this work, a two-step transfer learning approach is used to train the kidney stone classifier. The proposed approach transfers knowledge learned on a set of images of kidney stones acquired with a CCD camera (ex-vivo dataset) to a final model that classifies images from endoscopic images (ex-vivo dataset). The results show that learning features from different domains with similar information helps to improve the performance of a model that performs classification in real conditions (for instance, uncontrolled lighting conditions and blur). Finally, in comparison to models that are trained from scratch or by initializing ImageNet weights, the obtained results suggest that the two-step approach extracts features improving the identification of kidney stones in endoscopic images.
Paper Structure (8 sections, 3 figures, 3 tables)

This paper contains 8 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Datasets
  4. Two-step transfer learning
  5. Results and discussion
  6. Two step TL-approach results
  7. Comparison with the state-of-the-art
  8. Conclusion and perspective

Figures (3)

  • Figure 1: Examples of ex-vivo kidney stone images acquired with (a) a CCD camera corrales2021classification and (b) an endoscope el2022evaluation. SEC and SUR stand for section and surface views, respectively. The class types (WW, STR, CYS, etc.) are defined in Table \ref{['tab:dataset']}.
  • Figure 2: Two-step TL workflow. Model A was first initialized with the weights of a ResNet50 network pre-trained with ImageNet, and then fine-tuned with Dataset A. Next, Model B starts with the weights learned from Model A and is finally fine-tuned with Dataset B.
  • Figure 3: UMAP-ICN dimensionality feature reduction mendez2021finding. From left to right: surface, section, and mixed patch sets. The visualizations were generated in the second step of the "HeTL+HoTL" strategy (see Fig. \ref{['fig:method']}).