Using explainable deep learning in da Vinci Xi robot for tumor detection

Rohan Ibn Azad; Subhas Mukhopadhyay; Mohsen Asadnia

doi:10.21307/ijssis-2021-017

Using explainable deep learning in da Vinci Xi robot for tumor detection

Rohan Ibn Azad, Subhas Mukhopadhyay, Mohsen Asadnia^*

^*Corresponding author for this work

School of Engineering

Research output: Contribution to journal › Article › peer-review

59 Downloads (Pure)

Abstract

Deep learning has proved successful in computer-aided detection in interpreting ultrasound images, COVID infections, identifying tumors from computed tomography (CT) scans for humans and animals. This paper proposes applications of deep learning in detecting cancerous cells inside patients via laparoscopic camera on da Vinci Xi surgical robots. The paper presents method for detecting tumor via object detection and classification/localizing using GRAD-CAM. Localization means heat map is drawn on the image highlighting the classified class. Analyzing images collected from publicly available partial robotic nephrectomy videos, for object detection, the final mAP was 0.974 and for classification the accuracy was 0.84.

Original language	English
Pages (from-to)	1-16
Number of pages	16
Journal	International Journal on Smart Sensing and Intelligent Systems
Volume	14
Issue number	1
DOIs	https://doi.org/10.21307/ijssis-2021-017
Publication status	Published - Feb 2021

Bibliographical note

Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

Convolutional neural network
Tumor detection
YOLOv4
GRAD-CAM
Live surgery
da Vinci Xi

Access to Document

10.21307/ijssis-2021-017Licence: CC BY-NC-ND

Publisher version (open access)Final published version, 484 KBLicence: CC BY-NC-ND

Cite this

@article{47dbd04496cc4010b9b6595fca37adbf,

title = "Using explainable deep learning in da Vinci Xi robot for tumor detection",

abstract = "Deep learning has proved successful in computer-aided detection in interpreting ultrasound images, COVID infections, identifying tumors from computed tomography (CT) scans for humans and animals. This paper proposes applications of deep learning in detecting cancerous cells inside patients via laparoscopic camera on da Vinci Xi surgical robots. The paper presents method for detecting tumor via object detection and classification/localizing using GRAD-CAM. Localization means heat map is drawn on the image highlighting the classified class. Analyzing images collected from publicly available partial robotic nephrectomy videos, for object detection, the final mAP was 0.974 and for classification the accuracy was 0.84.",

keywords = "Convolutional neural network, Tumor detection, YOLOv4, GRAD-CAM, Live surgery, da Vinci Xi",

author = "Azad, {Rohan Ibn} and Subhas Mukhopadhyay and Mohsen Asadnia",

note = "Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",

year = "2021",

month = feb,

doi = "10.21307/ijssis-2021-017",

language = "English",

volume = "14",

pages = "1--16",

journal = "International Journal on Smart Sensing and Intelligent Systems",

issn = "1178-5608",

publisher = "Massey University",

number = "1",

}

TY - JOUR

T1 - Using explainable deep learning in da Vinci Xi robot for tumor detection

AU - Azad, Rohan Ibn

AU - Mukhopadhyay, Subhas

AU - Asadnia, Mohsen

N1 - Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2021/2

Y1 - 2021/2

N2 - Deep learning has proved successful in computer-aided detection in interpreting ultrasound images, COVID infections, identifying tumors from computed tomography (CT) scans for humans and animals. This paper proposes applications of deep learning in detecting cancerous cells inside patients via laparoscopic camera on da Vinci Xi surgical robots. The paper presents method for detecting tumor via object detection and classification/localizing using GRAD-CAM. Localization means heat map is drawn on the image highlighting the classified class. Analyzing images collected from publicly available partial robotic nephrectomy videos, for object detection, the final mAP was 0.974 and for classification the accuracy was 0.84.

AB - Deep learning has proved successful in computer-aided detection in interpreting ultrasound images, COVID infections, identifying tumors from computed tomography (CT) scans for humans and animals. This paper proposes applications of deep learning in detecting cancerous cells inside patients via laparoscopic camera on da Vinci Xi surgical robots. The paper presents method for detecting tumor via object detection and classification/localizing using GRAD-CAM. Localization means heat map is drawn on the image highlighting the classified class. Analyzing images collected from publicly available partial robotic nephrectomy videos, for object detection, the final mAP was 0.974 and for classification the accuracy was 0.84.

KW - Convolutional neural network

KW - Tumor detection

KW - YOLOv4

KW - GRAD-CAM

KW - Live surgery

KW - da Vinci Xi

UR - http://www.scopus.com/inward/record.url?scp=85122240846&partnerID=8YFLogxK

U2 - 10.21307/ijssis-2021-017

DO - 10.21307/ijssis-2021-017

M3 - Article

AN - SCOPUS:85122240846

SN - 1178-5608

VL - 14

SP - 1

EP - 16

JO - International Journal on Smart Sensing and Intelligent Systems

JF - International Journal on Smart Sensing and Intelligent Systems

IS - 1

ER -

Using explainable deep learning in da Vinci Xi robot for tumor detection

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this