Page 2474

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Machine Learning-Based Multi-Cancer Diagnostic System for Early

Detection and Accurate Classification Across Diverse Cancer Types

Sakshi Singh

, Saurav Kumar

, Yusuf Perwej

, Nikhat Akhtar

Assistant Professor, Department of Computer Science & Engineering, Shri Ramswaroop Memorial

University, Deva Road, Lucknow

Assistant Professor, Department of Computer Science & Engineering, Shri Ramswaroop Memorial

University, Deva Road, Lucknow

Professor, Department of Computer Science & Engineering, Shri Ramswaroop Memorial University,

Deva Road, Lucknow

Professor, Department of Computer Science & Engineering, Goel Institute of Technology &

Management, Lucknow

DOI:

https://doi.org/10.51583/IJLTEMAS.2026.150600180

Received: 01 July 2026; Accepted: 06 July 2026; Published: 20 July 2026

ABSTRACT

Cancer is one of the major causes of death worldwide, mostly owing to late discovery and hence restricted

treatment choices. Existing screening approaches are primarily invasive and often associated with complicated,

long and expensive procedures. In biomedicine and bioinformatics, several research groups have examined the

use of machine learning methods to solve the important challenge of categorizing cancer patients into high- and

low-risk categories. These methodologies have thus been used to mimic the onset and treatment of cancer. The

ability of ML algorithms to detect important characteristics in complex datasets further highlights their

importance. Many of these approaches like as Decision Trees, Logistic Regression (LR), Support Vector

Machines and K-Nearest Neighbours have been widely employed in cancer research to generate prediction

models that aid decision makers to make better and more trustworthy decisions. ML methods are indeed able to

improve our understanding of cancer formation, but need adequate validation to be regarded for application in

ordinary clinical practice. Hence, an ML approach was utilized to simulate the progression of cancer. The

prediction models shown here are based on several ML approaches and a broad variety of input features and

Data Samples. The proposed framework incorporates data preprocessing, feature selection, and advanced

classification algorithms to enhance diagnostic accuracy and facilitate timely clinical decision-making. The

study emphasizes the potential of artificial intelligence in advancing precision oncology and improving

healthcare outcomes.

Keywords: Machine Learning, Kaggle Multi Cancer Dataset, Predictive Models, Cancer Disease, Medical

Images, Classification.

INTRODUCTION

Cancer is one of the leading causes of death worldwide. It is the second largest cause of mortality worldwide

causing 9.7 million deaths in 2022 [1]. Cancer puts a tremendous economic burden on the worldwide population,

impacting individuals, communities, health care systems, and national economies, along with its severe social

and psychological effects on the lives of millions of people and their families [2]. Even with the finest therapeutic

therapy, if the disease is detected only at an advanced stage, the survival rate is reduced by more than half [3].

This shows the significance of early detection, which may drastically improve the odds of survival for patients

and decrease the expenses of therapy [4]. Only 39% of cancers are discovered early [5], according to research

by the American Cancer Society in 2023. Cancer develops from the original location to the metastatic stage

over time, and detection of cancer within this window is crucial to reduce the likelihood of death [7]. Many

Page 2475

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

tumours, for example, may not cause symptoms in the early stages or cause nonspecific, non-specific symptoms,

such as tiredness or weight loss. There is consensus amongst USPSTF, ACS, ASCO (only on maximum and

improved setting), CCA and EG to suggest screening with HPV DNA testing every 5 years for women 30–64

years of age. Cytology every 3 years (USPSTF, ACS, EG) or co-testing every 5 years (USPSTF, ACS) are also

acceptable options. This is based on a study that compared screening strategies in terms of cervical cancer deaths

per 1000 women and concluded that in women >30 years screened with HPV DNA [8] testing at 5-year intervals,

the number of deaths was calculated at 0.29 per 1000 women versus a significantly higher 8.34 in women with

no screening. The analysis of medical pictures plays an important role in the identification of disorders related

to blood, skin, breast, brain, lungs, retina and other organs [9]. Due to the underlying organ dysfunction, tumours

tend to grow fast. Today, 30 to 50 percent of cancers may be avoided by avoiding risk factors and using current

evidence-based preventive strategies [10]. Timely cancer prevention and treatment [11] may also reduce the

burden of the illness on the society. Early diagnosis and therapy are curative for many types of cancer [12,13].

Related Work

Because these markers are released early by tumours, liquid biopsy may identify cancer even in the absence of

symptoms or observable tumours [14]. Liquid biopsy also provides the benefit of real-time tumour information

[15]. Therefore, the development of a single liquid biopsy test, which combines several indicators and may

simultaneously identify many malignancies [16], will address the constraints highlighted in current clinical

practice for cancer diagnosis [17]. The approach is referred to as a multi-cancer early detection (MCED) test and

should be [18] highly sensitive for detection of early-stage cancers, highly specific to [19] avoid false positives,

able to identify the tissue of origin (TOO) of the cancer, and cost effective [20].

This computational approach for autonomous breast cancer disease detection uses multilayer perceptron (MLP)

neural network based on an improved non-dominated sorting genetic algorithm to optimize accuracy and

network structure. The intelligent classification model for breast cancer detection proposed in [21] applies a

genetic algorithm wrapper based on gain-directed simulated annealing to minimize redundant and unneeded

features in the feature space to remove redundant information and reduce training cost. This results in an increase

in classification accuracy and a decrease in computation costs. We test the effectiveness of this approach using

Wisconsin's own breast cancer variations (WBCD and WBC). Researchers in [22] created a CAD for classifying

mammography images, which employs a GA based feature selection strategy to reduce the feature vector and a

semi-supervised support vector machine (SVM) to do classifications. This strategy enhances accuracy. The two

machine learning techniques used in the automated system for breast tissues classification by the analyst of [23],

i.e., a radial basis function network and a feed forward neural network with the back propagation learning

algorithm (BPNN) (RBFN), were discussed. Breast cancer tissues were categorized into six types: adipose,

glandular, glandular-like, connective, and cancer. Data were obtained via electrical impedance spectroscopy

(EIS). The Radial basis function network fared better than the back propagation network in terms of accuracy,

minimum error, maximum epochs and training time for classification of six different breast tissues. As a

consequence, the training time has been reduced and the accuracy has been improved.

Neural network learning may suffer from problems of generalization and can become stuck in local optima. An

SVM-based ensemble learning model for diagnosis of breast cancer is formed by a C-SVM and an SVM with

six different kinds of kernel functions [24]. We offer a Weighted Area Under the Receiver Operating

Characteristic Curve Ensemble (WAUCE) [25] approach for hybridization modelling based on the experience

of several classifiers on diagnostics tasks. The model was evaluated on three datasets the Surveillance,

Epidemiology, and End Results (Surveillance) dataset, the Wisconsin Breast Cancer [26] (WBC) dataset and the

Wisconsin Diagnostic Breast Cancer [27] (WDBC) dataset (SEER). The total accuracy of this method is 98.08%.

[28] described the experimental study and how sensitivity analysis was performed on two categories, Diameter

and Pathological outcome using the multicentre data set. There were three subgroups in diameter; 0-10mm, 10-

20mm, 20-30mm. Sensitivity was 85.7% (95% Cl, 70.8%-100.0%) and specificity was 91.1% (95% Cl, 86.8%-

95.2%) in the 0-10mm group.

Page 2476

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

The 10-20 mm group had a sensitivity of 85.7% (95% Cl, 77.1%-94.3%) and a specificity of 90.1% (95% Cl,

84.8%-95.4%). In the 20-30 mm group, sensitivity was 78.9% (95% Cl, 66.0%-91.8%) and specificity was

91.3% (95% Cl, 83.2%-99.4%) [29].

A machine learning study of MR radiology [30] that helps to improve PI-RADS performance in clinically

significant PCA. This machine learning strategy, a machine aided system for PCA diagnosis, might improve the

functionality of a PIRADS v2 structure design and therefore improve the quality of cancer consultation and

therapy. A deep learning algorithm [32] enables guys to detect prostate cancer [31]. The findings were shown to

be 93.5% accurate and 89% accurate for prostate cancer using 3D MRI images [33]. The [34] technique was

used to identify prostate cancer in men and its findings were 84% accurate compared to semi-deep learning. The

CNN algorithm for prostate cancer diagnosis.

[ 35] [ 36] After replicating the approach, the accuracy for diagnosing prostate cancer was around 86%. For

women who do not have access to pelvic examination or are unwilling to undergo pelvic examination, self-

collected vaginal samples may be utilized for HPV testing [37,38]. Specifically, patients may get specimens

from the vagina by using a tampon, cotton swab, cytobrush, or cervicovaginal lavage, and self-collection can be

conducted under supervision in a clinic setting or at home [39]. However, statistics suggest that the sensitivity

of this approach is much lower than clinician-collected specimens (76% vs. 91%) [40], and EG suggests that this

method should not be favoured over clinician-collected samples.

Cancer Disease

Cancer is a disorder in which the body produces aberrant cells that multiply without control. Everyone is born

with some risk of cancer. No one can get it like a cold or flu. Disruption in the programming of a cell or of a

population of cells may lead to out-of-control proliferation [41]. Age, sex, race, heredity, radioactive substances,

chronic inflammation, cigarettes, smoke and dust may all cause changes to the code. As seen in Figure 1, cancer

may afflict men, women and children, young and old, affluent and poor. You can’t get cancer from someone

else, nor transmit it to someone else.

Now there are new ways of treating cancer and a lot of individuals become well [42]. You may get cancer

anyplace in the body including the bones and the skin depicted in figure1. Of course, many of these are beyond

of our control, but we need to be aware of those we can control. Of all the diseases, cancer is one for which

prevention is a better cure. It's a tough question.

It depends on the stage of cancer and the organs where the disease has appeared. Yes, if cancer is identified in

its early stages, cancer is totally curable for forms like breast cancer. But in general, early identification is very

important in the effective treatment of cancer. The survival rate of the cancer patient is always greater with early

identification, low grade and early stage of cancer. Studies [43] suggest that hormonal, behavioural and

environmental factors may all be involved in an increased risk of breast cancer. But why some women with no

conceivable hazards at all end up with cancer while others with risk factors never do is unclear. Breast cancer is

likely caused by a mix of hereditary and environmental factors.

Research says that India would have roughly 1,70,000 new instances of breast cancer by 2024. It also shows that

1 in 28 women will be diagnosed with the malignancy. The incidence of breast cancer is higher in females, but

men have a 1-2% risk of having the illness [44].

Many men will be diagnosed with prostate cancer throughout the course of their lives. Prostate cancers usually

grow slowly and remain confined, and may not cause any visible symptoms. Some types of prostate cancer grow

slowly and may not need treatment. Other types grow quickly and are far more deadly. The early identification

of prostate cancer enhances [45] the possibility that the illness may be effectively treated if it remains localized

to the gland. Most prostate cancers grow slowly, but others might advance fast [46]. Postmortem studies revealed

that many older men (and some younger men) dying of unrelated causes were in fact afflicted with prostate

cancer.

Page 2477

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Figure 1: The Different Types of Cancer Disease

Cancer occurs in the lung. Inhalation is the introduction of air from the nasal cavity down the trachea into the

lungs, into the bronchi. These cells that line the tubes are where the great majority of lung malignancies begin.

Lung cancer may be split into 2 categories: Non-small cell lung cancer (NSCLC) accounts for around 80% and

small cell lung cancer (SCLC) for 20% [47]. The most prevalent kind of mixed small cell/large cell lung cancer

is when there are both types of lung cancer cells present. Prostate cancer will be diagnosed in a substantial

proportion of males. Prostate cancers frequently grow slowly and remain localised, where they may not cause

any apparent symptoms [48]. Some prostate cancers are slow growing and may not need any treatment, while

others may grow quickly and are far more deadly. Early identification of prostate cancer improves the success

rates of treatment while the illness is still confined to the gland [49]. In most instances, prostate cancer grows

slowly, but sometimes it progresses quickly.

Proposed Framework

The approach used for the extraction of information from the dataset of the patients whether it was benignant or

malignant growth. In this method the datasets are trained and tested with different testing rate and test rate by

different classifiers. We used the classification learner app for this technique which is a machine learning

methodology [50] that assists in the simple prediction of the illnesses. Under Machine Learning, on the Apps

tab, select Classification Learner. Click New Session > From Workspace in the File section of the Classification

Learner tab. In this box click new session, then choose from file, start a new session by importing data from file

and set a validation scheme. Then pick the information to be imported and another window opens, in that window

in upper right corner we have an import selection click on it. Then at this moment another window is launched

with a name new session from file, in that window we obtain the data set variables, validation schemes replies

and predictors for the prediction model [51]. Then click on the start session as shown in figure 2.

After clicking on the start session then at that moment window shown with a scalar plot drawn with malignant

and benignant cancer from the transferred dataset. In that window we have a predictor of the scalar plot on x and

y axis and classifications displaying benignant and malignant malignancy. The produced scalar plot is used to

determine which predictors are utilized to forecast the replies. Now we need to test and train the data using

several classifiers which are present in the model session. All the Machine learning [52] classifiers are present

in the model but we are using four classifiers for testing and training the data. The classifiers employed include

support vector machine, decision tree, Logistic Regression (LR) and k-nearest neighbour classifiers. These

classifiers are evaluated with varied testing and training rates for improved performance assessment. We choose

the classifier that we want to train and test the data and click on the train all button. Then to see the output of the

Page 2478

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

model, pick the model in the model’s pane and check the summary tab [53]. The summary page presents the

training results meretrices, computed on the validation set.

Evaluate the accuracy of the prediction within each class of the selected model. On the Classification Learner

tab, in the Plots section, click the arrow to view the gallery, and then select Confusion Matrix in the Validation

Results group. The matrix provides us the outcomes of the real class and the anticipated class. In the model pane,

we can try to experiment with multiple models to pick the best model, we can add different characteristics for

the model we can reject the features that have poor prediction value [54]. In the model pane click on downward

arrow, in that pick support vector machine classifier and then click on train all. Then the model is trained and

the prediction model is formed according to the characteristics chosen in the next session from the file window.

This window itself we may split the data set into two pieces, one for training and another for evaluating the data.

The training of the model was provided with more data and testing was provided with less data as per the need

to fulfil each point in the prediction model. The model is trained and tested; from this we receive the accuracy

results and confusion matrix. The confusion matrix is used to calculate the values of precision, recall and F-1

score.

Similarly, several classifiers in the model pane were picked such Decision Tree, Logistic Regression (LR) and

K-Nearest Neighbour classifiers are trained and evaluated at varied rates [55]. The prediction model, accuracy

and confusion matrix we achieved from the training and testing the model. The confusion matrix is used to

extract the precision, recall and F-1 score values of the selected classifier. Machine learning enables us to analyse

and apply large datasets faster and more efficiently than previous techniques. For cancer diagnosis a dataset and

a machine learning approach [56] may be used. The dataset is used for developing the supervised machine

learning model for detecting cancer with the help of classification methods. This collection contains features of

malignant and benign tumours. The initial step of the conceptual model considers data purification (filtering)

and data augmentation for processing.

Figure 2: The Proposed Architecture

The suggested conceptual paradigm is built on four pillars: preprocessing, feature extraction, classification, and

performance analysis. From the beginning the conceptual model takes into consideration data augmentation and

data purification (filtering) prior to processing [56]. In the second step, features are extracted. In medical datasets,

this is the process of extracting features and constructing a collection of descriptors. The aim is to identify certain

properties of the sample that may predict consistently whether it is benign or cancerous. The classifiers may be

realized using several machines learning based classification algorithms. A classifier was trained on 3 cancers

like breast cancer, Lung & Colon cancer and Cervical cancer to control samples as a whole model for each

Page 2479

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

sample. Here we have used 3 various classifiers like Decision tree, Logistic Regression (LR), Support Vector

Machines (SVM), KNN and choose the best model whose accuracy is larger and producing better result [57].

Kaggle Multi Cancer Dataset

Images illustrating of different forms of cancer have been accumulated for the sake of study and analysis, and

this collection comprises such photographs. Figure 3 illustrates how the dataset, which consists of 130,000

histopathological pictures representing eight main cancer types and twenty-six subclasses, offers a wealth of

resources for medical image classification and machine learning applications. For the purpose of increasing both

variety and resilience, the dataset was expanded with the use of Keras' Image Data Generator. Subfolders that

are named after the eight primary cancer classes are located at the base of the dataset. Each of these subfolders

[58] includes photos that are grouped into further subclasses. The framework makes it possible for people to

simply browse to the sort of cancer that they are interested in looking at.

Figure 3: Kaggle Multi Cancer Dataset

Outcome

The multi-cancer diagnostic method that was developed and was based on machine learning obtained a high

level of accuracy in identifying and categorizing a wide variety of cancer types, which allowed for earlier

detection and enhanced clinical decision-making [59]. This framework highlighted the promise of AI-driven

precision medicine for scalable, rapid, and accurate cancer detection. It also improved the reliability of

predictions, decreased the number of diagnostic mistakes, supported efficient healthcare delivery, and supported

efficient healthcare delivery. A variety of classifiers, which are shown in tables 1, 2, and 3, are used in the

Page 2480

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

training and testing of the datasets. A prediction model for the classifier is formed by selecting two features

during the feature selection stage [59]. These characteristics are chosen for the creation of the model. As can be

seen in figures 4, 5, and 6, the performance analysis was carried out using a training rate of 80% and a testing

rate of 20% using the Kaggle Multi Cancer Dataset that was used.

Table 1. Performance Metrices of Breast Cancer

Figure 4: The Prediction Breast Cancer Using Four Distinct Models

Table 2. Performance Metrices of Lung & Colon Cancer

Figure 5: The Prediction Lung & Colon Cancer Using Four Distinct Models

Page 2481

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

Table 3. Performance Metrices of Cervical Cancer

Figure 6: The Prediction Cervical Cancer Using Four Distinct Models

CONCLUSION

The research performed binary classification of healthy persons and those with a certain kind of Cancer sickness.

The research highlights the importance of accurate, non-invasive approaches for early cancer diagnosis in

reducing mortality. The suggested Machine Learning-Based Multi-Cancer Diagnostic System illustrates the

potential of artificial intelligence to greatly enhance early detection and accurate categorization of several cancer

kinds. It employs powerful machine learning techniques and extensive clinical or medical images databases to

efficiently discover intricate illness patterns that may be difficult to detect using standard diagnostic methods.

Early and accurate detection of cancer allows prompt clinical intervention, improves treatment planning and

patient outcomes while minimizing diagnostic delays and the expense of health care. The research emphasizes

the significance of suitable data preprocessing, feature selection, and model tuning to get good predictive

performance. Explainable AI and multimodal healthcare data may help improve the reliability and

interpretability. However, there are still obstacles, such as data quality, class imbalance, and clinical validation.

In conclusion, this system offers a viable option for the intelligent, scalable and precision-driven detection of

cancer, eventually leading to improved patient outcomes and healthcare efficiency.

Future Work

Further studies should concentrate on combining multimodal healthcare data, such as medical pictures, genetic

profiles, lab findings and electronic health records, to improve the accuracy and robustness of diagnosis.

Moreover, designing lightweight, real-time and cloud-enabled diagnostic frameworks might encourage practical

deployment in hospitals and distant healthcare settings. Overall, the suggested approach is a promising step

Page 2482

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

towards the construction of intelligent, scalable and reliable multi-cancer detection systems that supports

precision medicine and improves worldwide cancer treatment.

REFERENCES

1. Siegel, R.L.; Miller, K.D.;Wagle, N.S.; Jemal, A. Cancer statistics, 2023. CA Cancer J. Clin. 2023, 73,

17–48.

2. Yabroff, K.R.; Bradley, C.J.; Mariotto, A.B.; Brown, M.L.; Feuer, E.J. Estimates and projections of value

of life lost from cancer deaths in the United States. JAMA Oncol. 2021, 7, 1446–1454.

3. Allemani, C.; Matsuda, T.; Di Carlo, V.; Harewood, R.; Matz, M.; Nikši´c, M.; Bonaventure, A.; Valkov,

M.; Johnson, C.J.; Estève, J.; et al. Global surveillance of trends in cancer survival 2000–14 (CONCORD-

3): Analysis of individual records for 37,513,025 patients diagnosed with one of 18 cancers from 322

population-based registries in 71 countries. Lancet 2018, 391, 1023–1075.

4. Y. Perwej, “The Bidirectional Long-Short-Term Memory Neural Network based Word Retrieval for

Arabic Documents”, Transactions on Machine Learning and Artificial Intelligence (TMLAI), which is

published by Society for Science and Education, United Kingdom (UK), ISSN 2054-7390, Volume 3,

Issue 1, Pages 16 - 27, 2015, DOI: 10.14738/tmlai.31.863

5. Society, A.C.; Facts, C. Cancer Facts & Figures 2023. Available online:

https://www.cancer.org/research/cancer-facts-statistics/ all-cancer-facts-figures.html (accessed on 31

August 2024).

6. Y. Perwej, Firoj Parwej, Nikhat Akhtar, “An Intelligent Cardiac Ailment Prediction Using Efficient ROCK

Algorithm and K- Means & C4.5 Algorithm”, European Journal of Engineering Research and Science

(EJERS), Bruxelles, Belgium, ISSN: 2506-8016 (Online), Vol. 3, No. 12, Pages 126 – 134, 2018, DOI:

10.24018/ejers.2018.3.12.989

7. Y. Perwej, Mohammed Y. Alzahrani, F. A. Mazarbhuiya, Md. Husamuddin, “The State-of-the-Art Cardiac

Illness Prediction Using Novel Data Mining Technique”, International Journal of Engineering Sciences &

Research Technology (IJESRT), ISSN: 2277-9655, Volume 7, Issue 2, Pages 725-739, 2018, DOI:

10.5281/zenodo.1184068

8. Kim, J.J.; Burger, E.A.; Regan, C.; Sy, S. Screening for Cervical Cancer in Primary Care: A Decision

Analysis for the US Preventive Services Task Force. JAMA 2018, 320, 706–714

9. Y. Perwej, Asif Perwej, Firoj Parwej, “An Adaptive Watermarking Technique for the copyright of digital

images and Digital Image Protection”, International journal of Multimedia & Its Applications (IJMA),

which is published by Academy & Industry Research Collaboration Center (AIRCC) , USA , Volume 4,

No.2, Pages 21- 38, April 2012, DOI: 10.5121/ijma.2012.4202

10. Y. Perwej, Firoj Parwej, Asif Perwej, “Copyright Protection of Digital Images Using Robust

Watermarking Based on Joint DLT and DWT”, International Journal of Scientific & Engineering Research

(IJSER), France, ISSN 2229-5518, Volume 3, Issue 6, Pages 1- 9, 2012

11. Meenakshi Rani, Elturabi Osman Ahmed, Yusuf Perwej, S V Anil kumar, Dr.Venkatesan Hariram, “A

Comprehensive Framework for IoT, AI, and Machine Learning in Healthcare Analytics”, Nanotechnology

Perceptions, ISSN 1660-6795, E-ISSN:2235-2074, Collegium Basilea, Switzerland, SCOPUS, Volume

20, S 14, Pages 2118-2131, 4 November 2024, DOI: 10.62441/nano-ntp.vi.3072

12. N. Akhtar, H. Pant, Apoorva Dwivedi, Vivek Jain, Y. Perwej, “A Breast Cancer Diagnosis Framework

Based on Machine Learning”, International Journal of Scientific Research in Science, Engineering and

Technology (IJSRSET), Volume 10, Issue 3, Pages 118-132, May-June-2023, DOI:

10.32628/IJSRSET2310375

13. Smith, R.A.; Andrews, K.S.; Brooks, D.; Fedewa, S.A.; Manassaram-Baptiste, D.; Saslow, D.; Brawley,

O.W.; Wender, R.C. Cancer screening in the United States, 2018: A review of current American Cancer

Society guidelines and current issues in cancer screening. CA Cancer J. Clin. 2018, 68, 297–316

14. Heitzer, E.; Haque, I.S.; Roberts, C.E.S.; Speicher, M.R. Current and future perspectives of liquid biopsies

in genomics-driven oncology. Nat. Rev. Genet. 2019, 20, 71–88.

15. Brito-Rocha, T.; Constâncio, V.; Henrique, R.; Jerónimo, C. Shifting the Cancer Screening Paradigm: The

Rising Potential of Blood-Based Multi-Cancer Early Detection Tests. Cells 2023, 12, 935.

Page 2483

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

16. Wan, J.C.M.; Massie, C.; Garcia-Corbacho, J.; Mouliere, F.; Brenton, J.D.; Caldas, C.; Pacey, S.; Baird,

R.; Rosenfeld, N. Liquid biopsies come of age: Towards implementation of circulating tumour DNA. Nat.

Rev. Cancer 2017, 17, 223–238

17. Shweta Pandey, Rohit Agarwal, Sachin Bhardwaj, Sanjay Kumar Singh, Y. Perwej, Niraj Kumar Singh,

“A Review of Current Perspective and Propensity in Reinforcement Learning (RL) in an Orderly Manner”,

the International Journal of Scientific Research in Computer Science, Engineering and Information

Technology (IJSRCSEIT), Volume 9, Issue 1, Pages 206-227, 2023, DOI: 10.32628/CSEIT2390147

18. Kajal, Kanchan Saini, N. Akhtar, Devendra Agarwal, Ms. Sana Rabbani, Y. Perwej, “Machine Learning

for the Diagnosis and Prognosis of Chronic Illnesses”, International Journal of Scientific Research in

Science, Engineering and Technology (IJSRSET), Print ISSN: 2395- 1990 , Online ISSN : 2394-4099,

Volume 11, Issue 3, Pages 112-122, May-June -2024, DOI: 10.32628/IJSRSET24113100

19. Mohit Gupta, Yusuf Perwej, “The Role of OpenCV in Enhancing Brain Tumor Image Segmentation: A

Review of Recent Developments and Challenges”, International Journal of Creative Research Thoughts

(IJCRT), ISSN: 2320-2882, Volume 12, Issue 6, Pages 347 -353, June 2024

20. Mohit Gupta, Yusuf Perwej, “Brain Tumour Detection Image Segmentation Using OpenCV”,

International Journal of Creative Research Thoughts (IJCRT), ISSN: 2320-2882, Volume 12, Issue 6,

Pages 292 - 301, June 2024

21. Na, L., Qi, E., Xu, M., Bo, G., Gui-Qiu, L.: A novel intelligent classification model for breast cancer

diagnosis. Information Processing and Management, Elsevier, pp. 609-623(2019).

22. Nawel, Z., Nabiha, A., Nilanjan, D., and Mokhtar, S.: Adaptive Semi Supervised Support Vector Machine

Semi Supervised Learning with Features Cooperation for Breast Cancer Classification. Journal of Medical

Imaging and Health Informatics, American scientific publisher, pp. 53-62(2016).

23. Abdulkader, H., John, B. I., Rahib, H.A.: Machine learning

24. techniques for classification of breast tissue. In: 9th International Conference on Theory and Application

of Soft Computing, Computing with Words and Perception, ICSCCW, pp. 402-410. Procedia Computer

Science, Elsevier. Budapest, Hungary (2017).

25. Haifeng, W., Bichen, Z., Sang, W.Y., Hoo, S. K.: A Support Vector Machine-Based Ensemble Algorithm

for Breast Cancer Diagnosis. European Journal of Operational Research, Elsevier, pp. 1-33 (2017)

26. R. Priyadarshini, Naim Shaikh, Rakesh Kumar Godi, Yusuf Perwej, P.K. Dhal, Rajeev Sharma, “IoT-

Based Power Control Systems Framework for Healthcare Applications”, Measurement: Sensors,

ELSEVIER, ScienceDirect, SCIE, Web of Science, SCOPUS, ISSN 2665-9174, Volume 25, Pages 1-6,

January 2023, DOI: 10.1016/j.measen.2022.100660

27. N. Akhtar, Hemlata Pant, Apoorva Dwivedi, Vivek Jain, Y. Perwej, “A Breast Cancer Diagnosis

Framework Based on Machine Learning”, International Journal of Scientific Research in Science,

Engineering and Technology (IJSRSET), Print ISSN: 2395-1990, Volume 10, Issue 3, Pages 118-132,

2023, DOI: 10.32628/IJSRSET2310375

28. Apoorva Dwivedi, Basant Ballabh Dumka, Nikhat Akhtar, Ms Farah Shan, Yusuf Perwej, “Tropical

Convolutional Neural Networks (TCNNs) Based Methods for Breast Cancer Diagnosis”, International

Journal of Scientific Research in Science and Technology (IJSRST), Print ISSN: 2395-6011, Online ISSN:

2395-602X, Volume 10, Issue 3, Pages 1100 -1116, 2023, DOI: 10.32628/IJSRST523103183

29. Chao Zhang,Xing Sun, Kang Dang et all “Toward an Expert Level of Lung Cancer Detection and

Classification Using a Deep Convolutional Neural Network”,The Oncologist,2019

30. N. Akhtar, Nazia Tabassum, Dr. Asif Perwej, Y. Perwej,“ Data Analytics and Visualization Using Tableau

Utilitarian for COVID-19 (Coronavirus)”, Global Journal of Engineering and Technology Advances

(GJETA), Volume 3, Issue 2, Pages 28-50, 2020, DOI: 10.30574/gjeta.2020.3.2.0029

31. J. Wang, C.J. Wu, M.L. Bao, J. Zhang, X.N. Wang, Y.D. Zhang Machine learning-based analysis of MR

radiomics can help to improve the diagnostic performance of PI-RADS v2 in clinically relevant prostate

cancer Eur. Radiol., 27 (10) (2017), pp. 4082-4090

32. S. Liu, H. Zheng, Y. Feng, W. Li Prostate cancer diagnosis using deep learning with 3D multiparametric

MRI Medical Imaging 2017: Computer-Aided Diagnosis, vol. 10134, International Society for Optics and

Photonics (2017), p. 1013428

33. Y. Perwej, “An Optimal Approach to Edge Detection Using Fuzzy Rule and Sobel Method”, International

Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering (IJAREEIE),

Page 2484

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

ISSN (Print) : 2320 – 3765, ISSN (Online): 2278 – 8875, Volume 4, Issue 11, Pages 9161-9179, 2015,

DOI: 10.15662/IJAREEIE.2015.0411054

34. Mahmoud AbouGhaly, Nikhat Akhtar, Elturabi Osman Ahmed, Sunny Kumar, Yusuf Perwej, Ratna

Kumari Tamma, “Internet of Things Based Devices Designed for Pediatric Therapy to Improve Mobility

and Engagement in Children with Cerebral Palsy”, Journal of Neonatal Surgery (JNS), SCOPUS, ISSN:

2226-0439 (Online), Volume 14, Issue S9, Pages 443 - 451, March 2025, DOI: 10.52783/jns.v14.2695

35. X. Wang, W. Yang, J. Weinreb, J. Han, Q. Li, X. Kong, et al. Searching for prostate cancer by fully

automated magnetic resonance imaging classification: deep learning versus non-deep learning Sci. Rep.,

7 (1) (2017), p. 15415

36. Y. Tsehay, N. Lay, X. Wang, J.T. Kwak, B. Turkbey, P. Choyke, et al. Biopsy-guided learning with deep

convolutional neural networks for Prostate Cancer detection on multiparametric MRI 2017 IEEE 14th

International Symposium on Biomedical Imaging (ISBI 2017), IEEE (2017), pp. 642-645

37. Sunny Kumar, Apoorva Dwivedi, Dr. Yusuf Perwej, Moazzam Haidari, Siddharth Singh, Dr. Nagarajan

Gurusamy, “A Smart IoT-Image Processing System for Real-Time Skin Cancer Detection ”, Journal of

Neonatal Surgery (JNS), SCOPUS, ISSN: 2226-0439 (Online), Volume 14, Issue S14, Pages 823-831,

April 2025, DOI: 10.52783/jns.v14.4330

38. Gök, M.; Heideman, D.A.M.; van Kemenade, F.J.; Berkhof, J.; Rozendaal, L.; Spruyt, J.W.M.; Voorhorst,

F.; Beliën, J.A.M.; Babović, M.; Snijders, P.J.F.; et al. HPV testing on self collected cervicovaginal lavage

specimens as screening method for women who do not attend cervical screening: Cohort study. BMJ 2010,

340, c1040

39. Hina Rabbani, Sana Rabbani, Dr. Yusuf Perwej, Saurav Kumar, Dr. Nikhat Akhtar, “AI-Driven

Enhancement of Diabetes Diagnosis Using Deep Learning Techniques”, Journal of Emerging

Technologies and Innovative Research (JETIR), ISSN-2349-5162, Volume 12, Issue 6, Pages 757 - 763,

June 2025, DOI: 10.6084/m9.jetir. JETIR2506297

40. JK Pandey, SK Verma, J Kumar, Y. Perwej, SK Jha, “Ttransformative Role of Advanced Neural

Computation in Clinical Image Diagnostics: A Review of Key Concepts and Applications”, Seminars in

Ultrasound, CT and MRI, Volume 47, Issue 3, 2026, DOI: 10.1053/j.sult.2026.06.010

41. Hina Rabbani, Sana Rabbani, Dr. Yusuf Perwej, Saurav Kumar, Dr. Nikhat Akhtar, “AI-Driven

Enhancement of Diabetes Diagnosis Using Deep Learning Techniques”, Journal of Emerging

Technologies and Innovative Research (JETIR), ISSN-2349-5162, Volume 12, Issue 6, Pages 757 - 763,

June 2025, DOI: 10.6084/m9.jetir. JETIR2506297

42. Farheen Siddiqui, Sarvesh Kumar, Dr. Yusuf Perwej, Ankit Shukla, Dr. Nikhat Akhtar, “AI-Enhanced

Diagnostic System for Reasonable Evaluation Breast Cancer”, International Journal of Scientific Research

in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN: 2456-3307, Volume

11, Issue 3, Pages 816-830, May 2025, DOI: 10.32628/CSEIT25113349

43. Anjali Yadav, Shruti Dwivedi, Anubhav Dwivedi, Ujjwal Thakur, Dr. Nikhat Akhtar, “Intelligent Disease

Diagnosis: A Multi-Disease Prediction Approach Using Machine Learning”, International Journal of

Scientific Research in Science, Engineering and Technology (IJSRSET), Print ISSN: 2395-1990, Online

ISSN: 2394-4099, Volume 12, No. 3, Pages 98 -109, May 2025, DOI: 10.32628/IJSRSET251235

44. Himanshu Srivastava, Drishti Tiwari, Prakhar Tripathi, Ramhit Sharma, Nikhat Akhtar, “A Data-Driven

Approach to Multi-Cancer Detection Using Machines Learning”, Journal of Emerging Technologies and

Innovative Research (JETIR), ISSN-2349-5162, Volume 12, Issue 5, Pages 181 - 189, May 2025, DOI:

10.6084/m9.jetir.JETIR2505617

45. Yusuf Perwej, Prof. Pranati Waghodekar, Mrunal S. Bewoor, Mr. Siddharth Singh, Shubham Jaiswal,

Akansh Garg, “Blockchain for Healthcare Management: Enhancing Data Security and Transparency”,

South Eastern European Journal of Public Health, (SEEJPH), SCOPUS, ISSN: 2197 - 5248, Volume

XXVI, Issue S1, Pages 1173–1184, January 2025, DOI: 10.70135/seejph.vi.3831

46. Yusuf Perwej, Nikhat Akhtar, Devendra Agarwal, “The emerging technologies of Artificial Intelligence

of Things (AIoT) current scenario, challenges, and opportunities”, Book Title“Convergence of Artificial

Intelligence and Internet of Things for Industrial Automation”, SCOPUS,ISBN: 978-1-032-42844-4, CRC

Press, Taylor & Francis Group, 2024

47. Link:https://www.taylorfrancis.com/chapters/edit/10.1201/9781003509240-1/emerging-

technologiesartificial-intelligence-things-aiot-current-scenario-challenges-opportunities-yusuf-perwej-

Page 2485

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

nikhatakhtar-devendra-agarwal?context=ubx&refId=537f1a8f-6a94-4439-b337-3ad3d1ce8845, DOI:

10.1201/9781003509240-1

48. N. Akhtar, Kumar Bibhuti B. Singh, Devendra Agarwal, Y. Perwej, “Improving Quality of Life with

Emerging AI and IoT Based Healthcare Monitoring Systems”, International Journal of Scientific Research

in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN: 2456-3307, Volume

11, Issue 1, Pages 96-107, January 2025, DOI: 10.32628/CSEIT2514551

49. Neha Kulshrestha, N. Akhtar, Y. Perwej, “Deep Learning Models for Object Recognition and Quality

Surveillance”, Accepted International Conference on Emerging Trends in IoT and Computing

Technologies (ICEICT-2022), ISBN 978-10324-852-49, SCOPUS, Routledge, Taylor & Francis, CRC

Press, Chapter 75, pages 508-518, Goel Institute of Technology & Management, 2022, DOI:

10.1201/9781003350057-75

50. Olusola, P.; Banerjee, H.N.; Philley, J.V.; Dasgupta, S. Human Papilloma Virus-Associated Cervical

Cancer and Health Disparities. Cells 2019, 8, 622.

51. Stelzle, D.; Tanaka, L.F.; Lee, K.K.; Ibrahim Khalil, A.; Baussano, I.; Shah, A.S.V.; McAllister, D.A.;

Gottlieb, S.L.; Klug, S.J.; Winkler, A.S.; et al. Estimates of the global burden of cervical cancer associated

with HIV. Lancet Glob. Health 2021, 9, e161–e169

52. N. Akhtar, Saima Rahman, Halima Sadia, Yusuf Perwej, “A Holistic Analysis of Medical Internet of

Things (MIoT)”, Journal of Information and Computational Science (JOICS), ISSN: 1548 - 7741,

SCOPUS, Volume 11, Issue 4, Pages 209 - 222, 2021, DOI: 10.12733/JICS.2021/V11I3.535569.31023

53. Y. Perwej, Shaikh Abdul Hannan, Firoj Parwej, Nikhat Akhtar, “A Posteriori Perusal of Mobile

Computing”, International Journal of Computer Applications Technology and Research (IJCATR), ATS

(Association of Technology and Science), India, ISSN 2319–8656 (Online), Volume 3, Issue 9, Pages 569

- 578, 2014, DOI: 10.7753/IJCATR0309.1008

54. Y. Perwej, “Unsupervised Feature Learning for Text Pattern Analysis with Emotional Data Collection: A

Novel System for Big Data Analytics”, IEEE International Conference on Advanced computing

Technologies & Applications (ICACTA'22), SCOPUS, IEEE No: #54488 ISBN No Xplore: 978-1-6654-

9515-8, Coimbatore, India, 2022, DOI: 10.1109/ICACTA54488.2022.9753501

55. Ankit Shukla, Farheen Siddiqui, Yusuf Perwej, Sarvesh Kumar, Nikhat Akhtar, “An Intelligent

Framework for Emotion Detection from Speech Signals”, Journal of Emerging Technologies and

Innovative Research (JETIR), ISSN-2349-5162, Volume 12, Issue 6, Pages 682 - 688, June 2025, DOI:

10.6084/m9.jetir.JETIR2506069

56. Y. Perwej, “An Evaluation of Deep Learning Miniature Concerning in Soft Computing”, International

Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), ISSN (Online):

2278-1021, ISSN (Print): 2319-5940, Volume 4, Issue 2, Pages 10 - 16, 2015, DOI:

10.17148/IJARCCE.2015.4203

57. Himanshu Srivastava, Drishti Tiwari, Prakhar Tripathi, Ramhit Sharma, Dr. Nikhat Akhtar, “A Data-

Driven Approach to Multi-Cancer Detection Using Machines Learning”, Journal of Emerging

Technologies and Innovative Research (JETIR), ISSN-2349-5162, Volume 12, Issue 5, Pages 181 - 189,

May 2025, DOI: 10.6084/m9.jetir.JETIR2505617

58. Bao, H.; Wang, Z.; Ma, X.; Guo, W.; Zhang, X.; Tang, W.; Chen, X.; Wang, X.; Chen, Y.; Mo, S.; et al.

Letter to the Editor: Anultra-sensitive assay using cell-free DNA fragmentomics for multi-cancer early

detection. Mol. Cancer 2022, 21, 129

59. Saurav Kumar, Sakshi Singh, Yusuf Perwej, Nikhat Akhtar, “A Novel Evolutionary CNN-Driven

Methodology for Detecting Deceptive News Content Across Digital Information Platforms”, Journal of

Emerging Technologies and Innovative Research (JETIR), ISSN-2349-5162, Volume 13, Issue 5, Pages

132 - 143, May 2026, DOI: 10.6084/m9.jetir.JETIR582100

60. Saurav Kumar, Sakshi Singh, Nikhat Akhtar, Yusuf Perwej, “A Data-Driven Machine Learning

Framework for Early Detection and Accurate Diagnosis of Breast Cancer”, International Journal of

Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), Print

ISSN - ISSN : 2456-3307 Online ISSN : 2394-4099, Volume 12, Issue 3, Pages 268-283, May 2026, DOI:

10.32628/CSEIT26123315 https://www.kaggle.com/datasets/obulisainaren/multi-cancer

61. Nicholson, B.D.; Oke, J.; Virdee, P.S.; Harris, D.A.; O‘Doherty, C.; Park, J.E.; Hamady, Z.; Sehgal, V.;

Millar, A.; Medley, L.; et al. Multi-cancer early detection test in symptomatic patients referred for cancer

Page 2486

www.rsisinternational.org

INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,

MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)

ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XV, Issue VI, June 2026

investigation in England and Wales (SYMPLIFY): A large-scale, observational cohort study. Lancet

Oncol. 2023, 24, 733–743

62. Moldovan, N.; van der Pol, Y.; Ende, T.v.D.; Boers, D.; Verkuijlen, S.; Creemers, A.; Ramaker, J.; Vu,

T.; Bootsma, S.; Lenos, K.J.; et al. Multi-modal cell-free DNA genomic and fragmentomic patterns

enhance cancer survival and recurrence analysis. Cell Rep. Med. 2024, 5, 10134