Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

An explainable machine learning model to solid adnexal masses diagnosis based on clinical data and qualitative ultrasound indicators

Fanizzi, Annarita ; Arezzo, Francesca ; Cormio, Gennaro ; Comes, Maria Colomba ; Cazzato, Gerardo ; Boldrini, Luca ; Bove, Samantha ; Bollino, Michele LU ; Kardhashi, Anila and Silvestris, Erica , et al. (2024) In Cancer Medicine 13(12).
Abstract

Background: Accurate characterization of newly diagnosed a solid adnexal lesion is a key step in defining the most appropriate therapeutic approach. Despite guidance from the International Ovarian Tumor Analyzes Panel, the evaluation of these lesions can be challenging. Recent studies have demonstrated how machine learning techniques can be applied to clinical data to solve this diagnostic problem. However, ML models can often consider as black-boxes due to the difficulty of understanding the decision-making process used by the algorithm to obtain a specific result. Aims: For this purpose, we propose an Explainable Artificial Intelligence model trained on clinical characteristics and qualitative ultrasound indicators to predict solid... (More)

Background: Accurate characterization of newly diagnosed a solid adnexal lesion is a key step in defining the most appropriate therapeutic approach. Despite guidance from the International Ovarian Tumor Analyzes Panel, the evaluation of these lesions can be challenging. Recent studies have demonstrated how machine learning techniques can be applied to clinical data to solve this diagnostic problem. However, ML models can often consider as black-boxes due to the difficulty of understanding the decision-making process used by the algorithm to obtain a specific result. Aims: For this purpose, we propose an Explainable Artificial Intelligence model trained on clinical characteristics and qualitative ultrasound indicators to predict solid adnexal masses diagnosis. Materials & Methods: Since the diagnostic task was a three-class problem (benign tumor, invasive cancer, or ovarian metastasis), we proposed a waterfall classification model: a first model was trained and validated to discriminate benign versus malignant, a second model was trained to distinguish nonmetastatic versus metastatic malignant lesion which occurs when a patient is predicted to be malignant by the first model. Firstly, a stepwise feature selection procedure was implemented. The classification performances were validated on Leave One Out scheme. Results: The accuracy of the three-class model reaches an overall accuracy of 86.36%, and the precision per-class of the benign, nonmetastatic malignant, and metastatic malignant classes were 86.96%, 87.27%, and 77.78%, respectively. Discussion: SHapley Additive exPlanations were performed to visually show how the machine learning model made a specific decision. For each patient, the SHAP values expressed how each characteristic contributed to the classification result. Such information represents an added value for the clinical usability of a diagnostic system. Conclusions: This is the first work that attempts to design an explainable machine-learning tool for the histological diagnosis of solid masses of the ovary.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
gynecological ultrasound, machine learning, ovarian cancer, precision medicine, solid adnexal masses
in
Cancer Medicine
volume
13
issue
12
article number
e7425
publisher
Wiley-Blackwell
external identifiers
  • pmid:38923847
  • scopus:85196739358
ISSN
2045-7634
DOI
10.1002/cam4.7425
language
English
LU publication?
yes
id
51311368-58fd-44df-a62f-9617a7c8f0b2
date added to LUP
2024-08-27 15:47:11
date last changed
2024-10-08 21:59:33
@article{51311368-58fd-44df-a62f-9617a7c8f0b2,
  abstract     = {{<p>Background: Accurate characterization of newly diagnosed a solid adnexal lesion is a key step in defining the most appropriate therapeutic approach. Despite guidance from the International Ovarian Tumor Analyzes Panel, the evaluation of these lesions can be challenging. Recent studies have demonstrated how machine learning techniques can be applied to clinical data to solve this diagnostic problem. However, ML models can often consider as black-boxes due to the difficulty of understanding the decision-making process used by the algorithm to obtain a specific result. Aims: For this purpose, we propose an Explainable Artificial Intelligence model trained on clinical characteristics and qualitative ultrasound indicators to predict solid adnexal masses diagnosis. Materials &amp; Methods: Since the diagnostic task was a three-class problem (benign tumor, invasive cancer, or ovarian metastasis), we proposed a waterfall classification model: a first model was trained and validated to discriminate benign versus malignant, a second model was trained to distinguish nonmetastatic versus metastatic malignant lesion which occurs when a patient is predicted to be malignant by the first model. Firstly, a stepwise feature selection procedure was implemented. The classification performances were validated on Leave One Out scheme. Results: The accuracy of the three-class model reaches an overall accuracy of 86.36%, and the precision per-class of the benign, nonmetastatic malignant, and metastatic malignant classes were 86.96%, 87.27%, and 77.78%, respectively. Discussion: SHapley Additive exPlanations were performed to visually show how the machine learning model made a specific decision. For each patient, the SHAP values expressed how each characteristic contributed to the classification result. Such information represents an added value for the clinical usability of a diagnostic system. Conclusions: This is the first work that attempts to design an explainable machine-learning tool for the histological diagnosis of solid masses of the ovary.</p>}},
  author       = {{Fanizzi, Annarita and Arezzo, Francesca and Cormio, Gennaro and Comes, Maria Colomba and Cazzato, Gerardo and Boldrini, Luca and Bove, Samantha and Bollino, Michele and Kardhashi, Anila and Silvestris, Erica and Quarto, Pietro and Mongelli, Michele and Naglieri, Emanuele and Signorile, Rahel and Loizzi, Vera and Massafra, Raffaella}},
  issn         = {{2045-7634}},
  keywords     = {{gynecological ultrasound; machine learning; ovarian cancer; precision medicine; solid adnexal masses}},
  language     = {{eng}},
  number       = {{12}},
  publisher    = {{Wiley-Blackwell}},
  series       = {{Cancer Medicine}},
  title        = {{An explainable machine learning model to solid adnexal masses diagnosis based on clinical data and qualitative ultrasound indicators}},
  url          = {{http://dx.doi.org/10.1002/cam4.7425}},
  doi          = {{10.1002/cam4.7425}},
  volume       = {{13}},
  year         = {{2024}},
}