“Hepatocellular Carcinoma Detection using

Deep Learning framework”

BY Under the guidance of

HARSHITHA B L (1RR17EC050)
SANJANA N (1RR18EC091)
Dr Vijaya S M
HARSHITHA B (1RR19EC022) Associate Professor
Dept. of ECE.
1
 Project Presentation Outline

 Abstract
 Introduction
 Literature survey
 Existing problems and proposed solution
 Objective
 Block diagram
 Software requirements
 Advantages and Applications
 References

2
 ABSTRACT

• The liver is the largest gland and largest internal organ in the
human body. The abnormal growth of cell in the liver causes
liver cancer which is also known as hepatic cancer .
• Most of the peoples who have liver cancer were died due to
the fact of inaccurate detection. The detection of this is
difficult and mostly found at advanced stage which causes
life-threatening issues.
• So, the principle intention of this project is to detect liver
cancer at earlier stage using image processing technique. This
project presents an automated method of detecting liver cancer
in abdominal CT images and classifying them using the CNN
algorithm.

3
 INTRODUCTION
• Liver cancer is one of the major death factors in the world.
• The most common type of liver cancer is hepatocellular
carcinoma (or hepatoma or HCC). Liver cancer refer to those
abnormal tissue cell that are found in the liver. These can be
identified in a CT scan by a difference in pixel intensity from
other regions of the liver.
• For proper clinical treatment, manual segmentation of this CT
scan is difficult and excessively time-consuming task. Digital
image processing is the technique of using computers to
process the image with the necessary algorithms
• Detection of liver cancer involves three main steps. It includes
pre-processing of image, feature extraction, pattern
recognition and classification.

4
 LITERATURE SURVEY
Sl.No Year Author Title Methodology Disadvantage

1 2022 Piyush AI-Driven Novel Detection of liver The initial

Kumar Approach for cancer in magnetic segmentation was
Shukla, Liver Cancer resonance imaging less successful
Mohammed Screening and of the abdomen because of cancers
Zakariah, Prediction Using pictures by using and other items in
Wesam Atef Cascaded Fully 3D affine invariant the data
Hatamleh Convolutional and shape
Neural Network parameterization
approaches.

2 2020 Bhawana ,Dr. A Review on Using machine The system is

Saroj Liver Cancer learning algorithms impossible to
Hiranwal , Detection such as Decision separate
Manoj Techniques tree, SVM, neural heterogenous
Kumar networks, computer quantities of CT
aided detection. and DW-MRI
from different
scanners.

5
Sl.no Year Author Title Methodology Disadvantage
3 2020 R Aarthi, S Liver Cancer Image It is designed for
Nivetha, P Detection Processing only single mass of
Vikashini, Dr. Using Image tumors
V.T. Processing
Balamurugan

4 2021 Mrs.A.Selvar Liver Cancer Using FCM Poor accuracy of

ani Detection Clustering for the segmentation
M.EE.Babu Using Ml tumour due to overlapping
Sajish2, Classifiers detection of cancer cells
M.Pramod

5 2021 Mohammad Hybrid rider Using HRO The proposed

K Nour, optimization algorithm system does not
Hany with Deep with recurrent classify the deep
Mahgoub, learning neural long instance
Fahad driven Liver short term segmentation
Althukair cancer memory. approaches.
detection and
classification

6
EXISTING PROBLEMS
• Most of the peoples who have liver cancer were died due to
the fact of inaccurate detection.
• For proper clinical treatment, manual segmentation of CT scan
is difficult and excessively time-consuming task.

PROPOSED SOLUTIONS
• In our project we propose the cancer detection using CNN
algorithm. In this we have three phases of detection processing
phase, pre-processing phase and detection phase where the
wavelets are applied to signify the segmentation to classify the
normal and abnormal stages of the tumour Accurate detection
of size and location of tumour plays a vital role in the
diagnosis of tumour
7
 OBJECTIVE OF THE PROJECT

• To propose the Hybridized Fully Convolutional Neural

network for liver cancer detection and segmentation.
• Designing the ensemble segmentation algorithm using a deep
learning system for efficient segmentation and classification of
liver cancer.

8
 BLOCK DIAGRAM

DATA COLLECTION

PRE- PROCESSING

FEATURE EXTRACTION

CLASSIFICATION USING CNN MODEL

9
 METHODOLOGY
The proposed method follows these stages:
 
• Data Set Collection:The dataset for training is obtained.
• Image Segmentation:The segmentation of photographs is the
phase where the visual image is partitioned into several parts.
This normally helps to identify artifacts and boundaries.
• Pre-Processing: In preprocessing stage, the median filter is
used to restore the image under test by minimizing the effects
of the degradations during acquisition.

10
• Feature extraction: The median filter simply replaces each
pixel value with the median value of its neighbors including
itself. Hence, the pixel values which are very different from
their neighbors will be eliminated.
• Convolutional Neural Networks:A CNN is type of a DNN
consists of multiple hidden layers such as convolutional layer,
RELU layer, Pooling layer and fully connected a normalized
layer.

11
 SYSTEM REQUIREMENTS

Software requirements
• Operating system : Windows XP/ Windows 7
• Software Packages : Tensorflow , OpenCv
• Coding Language : Python.
• Toolbox : Image processing toolbox.
• Train and test: CNN
• Framework : FLASK
 

12
 ADVANTAGES AND APPLICATIONS

• Liver cancer detection using CNN Algorithm provides more

accuracy.
• This is the best method for diagnosing liver cancer through
segmentation and helps to diagnose of different types of
cancer.

13
 REFERENCES

1. AI-Driven Novel Approach for Liver Cancer Screening and Prediction Using
Cascaded Fully Convolutional Neural Network by Piyush Kumar Shukla,
Mohammed Zakariah, Wesam Atef Hatamleh,published on 1 February 2022

2. Liver Cancer Detection Using Hybridized Fully Convolutional Neural Network

Based on Deep Learning Framework” on July 24, 2020

3. Lakhani, P., & Sundaram, B. (2016). Deep learning on liver tumor radiography:
Radiology, 284(2), 574-582.

4. Yan, K., Wang& Summers, R. M. (2018). Deep Lesion: automated mining of large-
scale lesion annotations and universal lesion detection with deep learning. Journal
of medical imaging, 5(3), 036501.

14
5. Christ, P. F., Elshaer, M. E. A., Ettlinger, F., Tatavarty, S., Bickel, Bilic, & Sommer,
W. H. (2016, October). Automatic liver and lesion segmentation in CT using SVM
Algorithm and 3D conditional random fields. In International Conference on
Medical Image Computing and Computer-Assisted Intervention (pp. 415-423).
Springer, Cham.

6. Peng, J Liang, P., & Kong, D. (2016). Automatic 3D liver segmentation based on
deep learning and globally optimized surface evolution. Physics in Medicine &
Biology, 61(24), 8676.

15
16