• Home
  • Search
  • Ensemble voting decreases false positives in AI second-observer reads for detecting colorectal cancer.
  • Cite Icon1
  • https://doi.org/10.1200/jco.2022.40.4_suppl.141Copy DOI Icon

Ensemble voting decreases false positives in AI second-observer reads for detecting colorectal cancer.

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

141 Background: Colorectal cancer (CRC) is the second leading cause of cancer-related deaths, and survival can be improved if early, suspect imaging features on CT of the abdomen and pelvis (CTAP) can be routinely identified. At present, up to 40% of these features are undiagnosed on routine CTAP, but this can be improved with a second observer. In this study, we developed a deep ensemble learning method for detecting CRC on CTAP to determine if increasing agreement between ensemble models can decrease the false positives detected by artificial intelligence (AI) second-observer. Methods: 2D U-Net convolutional neural network (CNN) containing 31 million trainable parameters was trained with 58 CRC CT images from Banner MD Anderson (AZ) and MD Anderson Cancer Center (TX) (51 used for training and 7 for validation) and 59 normal CT scans from Banner MD Anderson Cancer Center. 20 of the 25 CRC cases from public domain data (The Cancer Genome Atlas) were used to evaluate the performance of the models. The CRC was segmented using ITK-SNAP open-source software (v. 3.8). To apply the deep ensemble approach, five CNN models were trained independently with random initialization using the same U-Net architect and the same training data. Given a testing CT scan, each of the five trained CNN models was applied to produce tumor segmentation for the testing CT scan. The tumor segmentation results produced by the trained CNN models were then fused using a simple majority voting rule to produce consensus tumor segmentation results. The segmentation was analyzed by the percentage of correct detection, the number of false positives per case, and the Dice similarity coefficient (DSC). If parts of the CRC were flagged by AI, then it was considered correct. A detection was considered false positive if the marked lesion did not overlap with any CRC; contiguous false positives across different slices of CT image were considered a single false positive. DSC measures the quality of the segmentation by measuring the overlap between the ground-truth and AI detected lesion. Results: Our results showed that increasing the agreement between the 5 models dramatically decreases the number of false positives per CT at the expense of slight decrease in accuracy and DSC. This is described in the table. Conclusions: Our results show that AI-based second observer can potentially detect CRC on routine CTAP. Although the initial result yields high false positives per case, ensemble voting is an effective method for decreasing the false positives with a slight decrease in accuracy. This technique can be further improved for eventual clinical application.[Table: see text]

Similar Papers
  • Research Article

Comparison of segmentation methods to improve throughput in annotating AI-observer for detecting colorectal cancer.

  • Feb 01, 2022
  • Journal of Clinical Oncology
  • Brandon Salinel +14
  • Research Article

Patient body fat and AI ensemble technique and the influence on false-positive rate in AI second observer for colorectal cancer detection.

  • Feb 01, 2025
  • Journal of Clinical Oncology
  • Neal Kucera +13
  • PDF
  • Research Article
  • Citations48

Lossless multi-scale constitutive elastic relations with artificial intelligence

  • Apr 12, 2022
  • npj Computational Materials
  • Jaber Rezaei Mianroodi +4
  • Book Chapter
  • Citations2

Performance Analysis of Various Trained CNN Models on Gujarati Script

  • Oct 30, 2020
  • Parantap Vakharwala +4
  • Research Article
  • Citations6

Development and multicenter validation of deep convolutional neural network-based detection of colorectal cancer on abdominal CT.

  • Feb 01, 2024
  • European radiology
  • Yeo Eun Han +12
  • PDF
  • Research Article

REAL-TIME HAND GESTURE DETECTION AND RECOGNITION USING CONVOLUTIONAL ARTIFICIAL NEURAL NETWORKS

  • Sep 10, 2023
  • METHODIKA Jurnal Teknik Informatika dan Sistem Informasi
  • Gidion Bagas Prananta +2
  • Research Article
  • Citations64

Mineral prospectivity mapping using attention-based convolutional neural network

  • Mar 08, 2023
  • Ore Geology Reviews
  • Quanke Li +2
  • Conference Article
  • Citations13

A Method of Crack Detection Based on Convolutional Neural Networks

  • Sep 28, 2017
  • Xuefeng Zhao +1
  • Conference Article
  • Citations3

Tree-level irrigation inference using UAV thermal imagery and convolutional neural networks

  • Jun 21, 2022
  • Haoyu Niu +2
  • Research Article
  • Citations4

The analysis and optimization of CNN Hyperparameters with fuzzy tree modelfor image classification

  • Mar 01, 2022
  • Turkish Journal of Electrical Engineering and Computer Sciences
  • Kübra Uyar +2
  • PDF
  • Research Article
  • Citations14

Prediction of Machining Condition Using Time Series Imaging and Deep Learning in Slot Milling of Titanium Alloy

  • Nov 16, 2022
  • Journal of Manufacturing and Materials Processing
  • Faramarz Hojati +3
  • Conference Article
  • Citations113

Spectrum Monitoring for Radar Bands Using Deep Convolutional Neural Networks

  • Dec 01, 2017
  • Ahmed Selim +5
  • Research Article
  • Citations7

Reusing Convolutional Neural Network Models through Modularization and Composition

  • Mar 15, 2024
  • ACM Transactions on Software Engineering and Methodology
  • Binhang Qi +3
  • Conference Article
  • Citations1

Use of machine learning approaches to improve non-invasive skin melanoma diagnostic method in spectral range 450 - 950nm

  • Apr 01, 2020
  • Andrey Bondarenko +5
  • Research Article
  • Citations5

A multi-label CNN model for the automatic detection and segmentation of gliomas using [18F]FET PET imaging.

  • Mar 18, 2023
  • European Journal of Nuclear Medicine and Molecular Imaging
  • Masoomeh Rahimpour +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.