Bayesian Convolutional Neural Networks in Medical Imaging Classification: A Promising Solution for Deep Learning Limits in Data Scarcity Scenarios.
Deep neural networks (DNNs) have already impacted the field of medicine in data analysis, classification, and image processing. Unfortunately, their performance is drastically reduced when datasets are scarce in nature (e.g., rare diseases or early-research data). In such scenarios, DNNs display poo...
| Publicado en: | Journal of Digital Imaging Vol. 36; no. 6; pp. 2567 - 2578 |
|---|---|
| Autores principales: | , , , , , , , , , |
| Formato: | diagnostic images equations & formulas pictorial research tables/charts Journal Article |
| Publicado: |
Springer Nature
Dec2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=173050951&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 173050951 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Dec2023 vid: 36 iid: 6 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 173050951 172751172 173050951 173050951 10.1007/s10278-023-00897-8 173050951 ppf: 2567 ppct: 11 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Bayesian Convolutional Neural Networks in Medical Imaging Classification: A Promising Solution for Deep Learning Limits in Data Scarcity Scenarios. aug: au: Bargagna, Filippo De Santi, Lisa Anita Martini, Nicola Genovesi, Dario Favilli, Brunella Vergaro, Giuseppe Emdin, Michele Giorgetti, Assuero Positano, Vincenzo Santarelli, Maria Filomena affil: https://ror.org/03ad39j10 University of Pisa, Pisa, Italy sug: subj: Convolutional Neural Networks Deep Learning Diagnostic Imaging Trends Models, Statistical Diagnosis, Computer Assisted Human Uncertainty Data Analysis Image Processing, Computer Assisted Amyloidosis, Cardiac Diagnosis Amyloidosis, Cardiac Classification Risk Assessment Validity Descriptive Statistics Funding Source Reliability ab: Deep neural networks (DNNs) have already impacted the field of medicine in data analysis, classification, and image processing. Unfortunately, their performance is drastically reduced when datasets are scarce in nature (e.g., rare diseases or early-research data). In such scenarios, DNNs display poor capacity for generalization and often lead to highly biased estimates and silent failures. Moreover, deterministic systems cannot provide epistemic uncertainty, a key component to asserting the model's reliability. In this work, we developed a probabilistic system for classification as a framework for addressing the aforementioned criticalities. Specifically, we implemented a Bayesian convolutional neural network (BCNN) for the classification of cardiac amyloidosis (CA) subtypes. We prepared four different CNNs: base-deterministic, dropout-deterministic, dropout-Bayesian, and Bayesian. We then trained them on a dataset of 1107 PET images from 47 CA and control patients (data scarcity scenario). The Bayesian model achieved performances (78.28 (1.99) % test accuracy) comparable to the base-deterministic, dropout-deterministic, and dropout-Bayesian ones, while showing strongly increased "Out of Distribution" input detection (validation-test accuracy mismatch reduction). Additionally, both the dropout-Bayesian and the Bayesian models enriched the classification through confidence estimates, while reducing the criticalities of the dropout-deterministic and base-deterministic approaches. This in turn increased the model's reliability, also providing much needed insights into the network's estimates. The obtained results suggest that a Bayesian CNN can be a promising solution for addressing the challenges posed by data scarcity in medical imaging classification tasks. pubtype: Academic Journal doctype: diagnostic images equations & formulas pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|