DETECTION OF LUNG CANCER

SL Title of the Authors Journal/ Methodology Pros and Cons

No Paper Year of / Algorithm
publication
1 Exploring Machine Dr.S.S Springer/ MatLab coding Pros: This Absolute Integral
Learning Sumathi, 2024 has been used Based Analysis (AIA)
Techniques in Lung Dr.K to perform AIA machine learning technique
Cancer Detection Sumathi, for the detects accurate cancer
via Absolute Dr.B.Panjav detection of affected parts in the lungs
Integral Based arnam, cancer affected efficiently and it provides
Analysis R.Tamezhen parts or cells in improved accuracy.
eal, the lungs.
A.E.Prabhu Cons: This Absolute Integral
Based Analysis (AIA)
machine learning technique
detects accurate cancer
affected parts in the lungs
efficiently and it provides
improved accuracy.

2 Artificial Nafe Springer / The proposed Pros: This Absolute Integral

intelligence for Muhtasim, 2024 deep learning Based Analysis (AIA)
detection of lung Umma architecture and machine learning technique
cancer using Hany, 7 different detects accurate cancer
transfer learning Tahmina machine affected parts in the lungs
and morphological Islam, learning efficiently and it provides
features Nusrat algorithms are improved accuracy.
Nawreen & applied on the
Abdullah AI preprocessed Cons: It is abserved from
Mamun data & the fivefold cross-validation
extracted results that logistic
features for regression performs with
classification of 99.36% accuracy in 23.71s
lung nodules time using the preprocessed
into three data.
classes:
Malignant,
Benign and
normal.
3 The Use of Artificial Manageme AI in The paper likely Pros: The paper provides a
Intelligence in Lung nt Pranali precision utilized a comprehensive overview
Cancer Pachika, oncology / systematic of
Srijan 2024 literature review AI's potential in revolutionizing
approach to lung cancer management,
Valasapalli,
gather and discussing its applications in
Phuong
analyze existing screening, diagnosis, therapy
Ngo, and selection, prognosis, and
research on the
Goetz surveillance, and highlighting
application of
Kloecker artificial the latest advancements and
intelligence (AI) potential future
in lung cancer advancements in the field.
management, Cons: Despite its thorough
covering various coverage, the paper may face
stages from limitations related to the lack
screening to of standardization in AI usage
treatment. for lung cancer management
and the challenges associated
with integrating AI models into
daily clinical practice, which
could affect their widespread
adoption and effectiveness.

4 A hybrid model C. Springer/ The paper Pros: The hybrid approach

for lung cancer Venkatesh proposes a combining patch
prediction using J. 2023 hybrid model processing, deep learning,
patch processing Chinnabab, for lung cancer and
and deep learning Ajmeera Kir prediction optimization techniques
on CT images an, utilizing patch presents a comprehensive
C. H. Nagar processing and solution for lung cancer
aju, deep learning prediction using CT images,
Manoj on CT images. potentially improving
Kum ar The accuracy and efficiency in
methodology diagnosis.
involves Cons: While the proposed
employing K- model shows promise in
means enhancing segmentation
clustering for accuracy, the integration
image of multiple techniques may
segmentation introduce complexity in
and integrating implementation and require
Particle Swarm careful optimization to achieve
Optimization optimal performance across
(PSO) to diverse datasets and clinical
enhance settings.
segmentation
accuracy.
5 Accurate detection Shuo Hu, Biomarker The study Pros: The study offers a
of early-stage lung Jinsheng Research/ employs promising approach for non
cancer using a Tao, targeted invasive early detection of
2023
panel of circulating Minhua bisulfite lung cancer using cell-free
cell-free DNA Peng, Zhujia sequencing to DNA methylation
methylation Ye, Zhiwei identify DNA biomarkers. It addresses the
biomarkers Chen, methylation need for improved methods
Haisheng biomarkers in of early diagnosis in lung
Chen, lung cancer. cancer, which could
Haifeng Yu, It utilizes a significantly impact
Wang,Jian- prospective- treatment outcomes
Bing Fan, specimen and survival rates.
and Bin Ni collection and
Cons: The study's reliance
retrospective-
on bisulfite sequencing and
blinded-
targeted panels may limit
evaluation trial
the discovery of novel
design with a
biomarkers beyond the
large sample
predetermined regions.
size.
Additionally, the
retrospective-blinded-
evaluation design may
introduce biases in the
interpretation of
results.
6 Artificial Guillaume Springer / The paper Pros: The paper offers a
Intelligence in Chassagnon 2022 employs a thorough analysis of
lung cancer: , Trieu-Nghi systematic artificial intelligence
Current Hoang-Thi, literature review applications in lung cancer
applications and Marie- methodology to care, providing valuable
perspectives Pierre investigate the insights and guidance for
Revel,
current future research and clinical
Philippe
applications of practice.
Soyer
artificial
Cons: It may be limited by
intelligence in
the scope of existing
lung cancer
literature and potential bias
diagnosis,
towards positive findings,
prognosis, and
potentially overlooking
treatment.
recent advancements or
challenges in the field.
7 Artificial Maurizio MDPI / The Pros: The paper offers a
Intelligence in Lung Cè, methodology comprehensive overview of
Cancer Imaging 2022
Giovanni likely involved artificial intelligence
Irmici , Velio a systematic applications in lung cancer
Ascenti , literature review imaging, providing insights
Natallia of existing into early detection,
Khenkina , research on customized treatment
Marco Toto- artificial planning, and prediction of
Brocchi , intelligence patient outcomes, thus
Carlo applications in enhancing clinical decision-
Martinengh lung cancer making.
i, Sergio imaging,
Cons: Potential limitations
Papa and gathering
may arise from the reliance
Gianpaolo relevant studies
on AI models, such as the
Carrafiello from databases
need for robust validation
such as
and integration into clinical
PubMed,
practice, as well as
Scopus, and
considerations regarding
Web of
data privacy and ethical
Science.
implications.

8 Lung Cancer Sharmila Hindavi/ The paper Pros: The paper offers a
Classification and Nageswara 2022 employs comprehensive approach
Prediction Using n,G. machine using machine learning and
Machine Learning Arunkumar, learning & image processing
and Image Anil Kumar image techniques to enhance lung
Processing Bisht, processing cancer detection accuracy,
Shivlal techniques, potentially leading to
Mewada such as improved patient outcomes
, geometric mean and personalized
J.N. V. R. filtering and K- treatment plans.
Swarup means
Cons: Challenges may arise
Kumar, segmentation,
in the practical
Malik for accurate
implementation of these
Jawarneh, lung cancer
techniques, including
and Evans classification
computational resource
Asenso and prediction
requirements, dataset size,
based on
and the need for validation
collected
in real-world clinical
photographs.
settings, which could
affect the scalability and
generalizability of the
proposed methodology.
9 Application Shulin Li , Academic The methodology Pros: The paper provides
analysis of ai Liqiang Journal of used in the paper valuable insights into the
technology Yu,Bo Liu, Science and likely involved potential of AI technology
combined with Qunwei Lin, Technology/ analyzing the combined with spiral CT
spiral CT scanning JiaxinHuang 2021 application of AI
scanning for early lung
in early lung cancer technology
cancer screening, offering
screening combined with
spiral CT scanning
promising avenues for
for early lung improved detection and
cancer screening. diagnosis.
This analysis
Cons: However, limitations
likely included
may arise from the specific
techniques such
as windowing,
techniques employed, such
contrast as windowing and contrast
stretching, and stretching, which could
histogram introduce variability and
modification to potential biases in the
manipulate CT analysis of CT images.
image grayscale
components .

10 Analyzing the Raja Sarath Materials The paper Pros: The utilization of AI
impact of machine Kumar Today: discusses the and ML presents
learning & artificial Boddu a, Proceedings/ potential impact opportunities to enhance the
intelligence and its Partha 2021 of machine diagnosis,
learning and treatment, and care of lung
effect on Karmakar b,
artificial cancer patients,
management of Ankan
intelligence in particularly during a
lung cancer Bhaumik c, pandemic, by
improving lung
detection in covid- Vinay leveraging cutting-edge
cancer detection
19 pandemic Kumar and technologies to
Nassad, management expedite
Vandana e, during the clinical trials, improve research
Sumanta COVID-19 methodologies, and identify
Bhattachary pandemic, novel therapies.
a focusing on the Cons: Despite the promising
use of clinical applications of AI and ML,
and imaging challenges such as data
data combined privacy concerns, algorithm
with machine biases, and the need for
learning validation and regulatory
methods. approval remain significant
hurdles to overcome in the
implementation of these
technologies for lung cancer
management during a
pandemic.
CONCLUSION:
In conclusion, the literature survey reveals a significant advancement in the
early detection of lung cancer through the integration of Artificial Intelligence
(AI) and Machine Learning (ML) techniques. These technologies offer promising
results in improving the accuracy and efficiency of lung cancer detection,
thereby enhancing patient outcomes and survival rates. However, further
research is needed to address challenges such as data standardization, model
interpretability, and clinical validation to ensure the successful implementation
of AI and ML in routine clinical practice for early lung cancer detection.