Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug;14(4):523-533.
doi: 10.1007/s11571-020-09587-5. Epub 2020 Apr 11.

Detecting prostate cancer using deep learning convolution neural network with transfer learning approach

Adeel Ahmed Abbasi  1 , Lal Hussain  1 , Imtiaz Ahmed Awan  1 , Imran Abbasi  1 , Abdul Majid  1 , Malik Sajjad Ahmed Nadeem  1 , Quratul-Ain Chaudhary  1
Affiliations

Detecting prostate cancer using deep learning convolution neural network with transfer learning approach

Adeel Ahmed Abbasi et al. Cogn Neurodyn. 2020 Aug.

Abstract

Prostate Cancer in men has become one of the most diagnosed cancer and also one of the leading causes of death in United States of America. Radiologists cannot detect prostate cancer properly because of complexity in masses. In recent past, many prostate cancer detection techniques were developed but these could not diagnose cancer efficiently. In this research work, robust deep learning convolutional neural network (CNN) is employed, using transfer learning approach. Results are compared with various machine learning strategies (Decision Tree, SVM different kernels, Bayes). Cancer MRI database are used to train GoogleNet model and to train Machine Learning classifiers, various features such as Morphological, Entropy based, Texture, SIFT (Scale Invariant Feature Transform), and Elliptic Fourier Descriptors are extracted. For the purpose of performance evaluation, various performance measures such as specificity, sensitivity, Positive predictive value, negative predictive value, false positive rate and receive operating curve are calculated. The maximum performance was found with CNN model (GoogleNet), using Transfer learning approach. We have obtained reasonably good results with various Machine Learning Classifiers such as Decision Tree, Support Vector Machine RBF kernel and Bayes, however outstanding results were obtained by using deep learning technique.

Keywords: Convolutional neural network (CNN); Deep learning (DL); GoogleNet; Prostate cancer; Transfer learning.

PubMed Disclaimer

Conflict of interest statement

Conflict of interestThe Authors declares no conflict of interest.

Figures

Fig. 1
Fig. 1
Overview of GoogleNet method by employing transfer learning
Fig. 2
Fig. 2
A simplified architecture of the CNN used in GoogleNet
Fig. 3
Fig. 3
Last layers of the GoogleNet before finetuning
Fig. 4
Fig. 4
Last layers of the GoogleNet after finetuning
Fig. 5
Fig. 5
Confusion matrix for GoogleNet
Fig. 6
Fig. 6
Performance evaluation comparison of ML methods with Deep Learning GoogleNet
Fig. 7
Fig. 7
Performance measure using GoogleNet at different selected iterations
Fig. 8
Fig. 8
Loss at selected iterations using GoogleNet
Fig. 9
Fig. 9
a ROC using ML methods with texture + morphological features and b ROC using GoogleNet Deep Learning method
Fig. 10
Fig. 10
Training progress of GoogleNet
See this image and copyright information in PMC

References

    1. Akin O, Sala E, Moskowitz CS, Kuroiwa K, Ishill NM, Pucar D, Scardino PT, Hricak H. Transition zone prostate cancers: features, detection, localization, and staging at endorectal MR imaging. Radiology. 2006;239:784–792. - PubMed
    1. Asvadi NH, Afshari Mirak S, Mohammadian Bajgiran A, Khoshnoodi P, Wibulpolprasert P, Margolis D, Sisk A, Reiter RE, Raman SS. 3T multiparametric MR imaging, PIRADSv2-based detection of index prostate cancer lesions in the transition zone and the peripheral zone using whole mount histopathology as reference standard. Abdom Radiol. 2018;43:3117–3124. - PMC - PubMed
    1. Bengio Y (2013) Deep learning of representations: looking forward. In: Lecture notes in computer science (including its subseries lecture notes in artificial intelligence and lecture notes in bioinformatics), 7978 LNAI, pp 1–37
    1. Bengio Y, Courville AC, Vincent P (2012) Unsupervised feature learning and deep learning: A review and new perspectives. CoRR. arxiv:1206.5538
    1. Bonzon P. Towards neuro-inspired symbolic models of cognition: linking neural dynamics to behaviors through asynchronous communications. Cogn Neurodyn. 2017;11:327–353. - PMC - PubMed

LinkOut - more resources