Detection and Diagnosis of Breast Cancer Using Artificial Intelligence Based assessment of Maximum Intensity Projection Dynamic Contrast-Enhanced Magnetic Resonance Images.

Mio Adachi,Jun Oyama,Tsuyoshi Nakagawa,Yuka Kikuchi,Tomoyuki Fujioka,Goshi Oda,Kazunori Kubota,Koichiro Kimura,Hiroyuki Uetake,Ukihide Tateishi,Wu Xiaotong,Mio Mori

doi:10.3390/diagnostics10050330

Mio Adachi, Jun Oyama + Show 10 more

Open Access

https://doi.org/10.3390/diagnostics10050330

Copy DOI

Abstract

We aimed to evaluate an artificial intelligence (AI) system that can detect and diagnose lesions of maximum intensity projection (MIP) in dynamic contrast-enhanced (DCE) breast magnetic resonance imaging (MRI). We retrospectively gathered MIPs of DCE breast MRI for training and validation data from 30 and 7 normal individuals, 49 and 20 benign cases, and 135 and 45 malignant cases, respectively. Breast lesions were indicated with a bounding box and labeled as benign or malignant by a radiologist, while the AI system was trained to detect and calculate possibilities of malignancy using RetinaNet. The AI system was analyzed using test sets of 13 normal, 20 benign, and 52 malignant cases. Four human readers also scored these test data with and without the assistance of the AI system for the possibility of a malignancy in each breast. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were 0.926, 0.828, and 0.925 for the AI system; 0.847, 0.841, and 0.884 for human readers without AI; and 0.889, 0.823, and 0.899 for human readers with AI using a cutoff value of 2%, respectively. The AI system showed better diagnostic performance compared to the human readers (p = 0.002), and because of the increased performance of human readers with the assistance of the AI system, the AUC of human readers was significantly higher with than without the AI system (p = 0.039). Our AI system showed a high performance ability in detecting and diagnosing lesions in MIPs of DCE breast MRI and increased the diagnostic performance of human readers.

Highlights

Breast cancer is the second most prominent cause of cancer-related death and the most common cancer affecting women [1]
deep learning (DL) is an area of artificial intelligence (AI) in which computers are not not explicitly explicitly programmed programmed but but can can analyze analyze relationships relationships between between existing existing data data and and perform perform tasks tasks based based on these new data on these new data [25]
Our study study is is the the first first report report to to focus focus on on building building an an AI

Summary

Introduction

Breast cancer is the second most prominent cause of cancer-related death and the most common cancer affecting women [1]. The dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI). Modality has the highest sensitivity, so it is widely used for breast cancer detection and diagnosis [2,3,4]. The abbreviated protocol for DCE breast MRI has been reported to provide comparable diagnostic performance to that of the conventional full protocol, increasing access to breast MRI and reducing the cost of existing MRI screening programs [6,7]. Artificial intelligence (AI), especially the deep learning (DL) method with convolutional neural networks (CNNs), has accomplished outstanding performances in medical breast imaging for pattern recognition, object detection, segmentation, and image synthesis [8,9,10,11,12]

Objectives

Methods

Findings

Conclusion