Publications

2026

1. Under Rev.

   

   Automated PET to Fused PET-CT Mapping Using PCGAN for Lung Cancer Diagnosis

   Md. Abu Sayed, Ashiqur Rahman, Sourav Basak Shuvo, Muhammad Abdul Kadir^†, Md. Ibrahim Al Imran, and 2 more authors

   In 2026 5th IEEE International Conference in Robotics, Automation, Artificial-Intelligence and Internet-of-things (RAAICON), Sep 2026

   Submitted to 2026 5th IEEE International Conference in Robotics, Automation, Artificial-Intelligence and Internet-of-things (RAAICON)

2025

1. arXiv

   

   DL³M: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models

   Md. Najib Hasan, Imran Ahmad, Sourav Basak Shuvo, Md. Mahadi Hasan Ankon, Sunanda Das, and 2 more authors

   arXiv preprint, Dec 2025

   Under review in Medical Image Analysis, Elsevier

   Abs arXiv Bib HTML PDF Code

   Medical image classifiers detect gastrointestinal diseases well, but they do not explain their decisions. Large language models can generate clinical text, yet they struggle with visual reasoning and often produce unstable or incorrect explanations. This leaves a gap between what a model sees and the type of reasoning a clinician expects. We introduce a framework that links image classification with structured clinical reasoning. A new hybrid model, MobileCoAtNet, is designed for endoscopic images and achieves high accuracy across eight stomach-related classes. Its outputs are then used to drive reasoning by several LLMs. To judge this reasoning, we build two expert-verified benchmarks covering causes, symptoms, treatment, lifestyle, and follow-up care. Thirty-two LLMs are evaluated against these gold standards. Strong classification improves the quality of their explanations, but none of the models reach human-level stability. Even the best LLMs change their reasoning when prompts vary. Our study shows that combining DL with LLMs can produce useful clinical narratives, but current LLMs remain unreliable for high-stakes medical decisions. The framework provides a clearer view of their limits and a path for building safer reasoning systems. The complete source code and datasets used in this study are available at https://github.com/souravbasakshuvo/DL3M.

   @article{hasan2025dl3m,
     author = {Hasan, Md. Najib and Ahmad, Imran and Shuvo, Sourav Basak and Ankon, Md. Mahadi Hasan and Das, Sunanda and Siddique, Nazmul and Wang, Hui},
     title = {{DL<sup>3</sup>M}: A Vision-to-Language Framework for Expert-Level Medical Reasoning through Deep Learning and Large Language Models},
     journal = {arXiv preprint},
     year = {2025},
     month = dec,
     note = {Under review in Medical Image Analysis, Elsevier},
   }

2. Res. Eng.

   

   TransfusionNet: Framework for cervical cancer detection using deep learning with multi-level fusion

   Md. Najib Hasan^*, Sourav Basak Shuvo^*, Md Mahadi Hasan Ankon^*, S.M. Taslim Uddin Raju, and Nazmul Siddique^†

   Results in Engineering, Dec 2025

   Abs DOI Bib HTML PDF Code

   This paper presents a hybrid deep learning model, TransfusionNet, comprising VGG19, ResNet50, and ViT with fusion for early detection of cervical cancer. An improved medical image preprocessing technique combining contrast-limited adaptive histogram equalization (CLAHE), Laplacian sharpening, bilateral filtering, and unsharp masking has been applied to enhance image quality. An early-layer feature fusion strategy was used to enhance feature diversity and improve decision-making, unlike conventional methods that fuse only at final layers. The fusion strategy combines features from VGG19, ResNet50, and ViT at multiple stages using concatenation and element-wise addition, allowing integration of detailed and high-level information across different levels. Two separate transition blocks were used to align VGG19 and ResNet50 outputs at different layers. TransfusionNet is trained and tested on the publicly available SIPaKMeD dataset, containing 4,049 images of five classes. TransfusionNet is also verified on Herlev and LCPSI datasets. The five-fold cross-validation was employed to mitigate overfitting and enhance model’s robustness and generalizability. TransfusionNet demonstrates promising results for early cervical cancer detection, achieving state-of-the-art performance on the SIPaKMeD dataset. For batch size 128, TransfusionNet achieved an average accuracy of 99.40%, an F1-score of 99.36%, sensitivity of 99.25%, and Cohen’s Kappa of 99.67% across the five folds.

   @article{hasan2025transfusionnet,
     author = {Hasan, Md. Najib and Shuvo, Sourav Basak and Ankon, Md Mahadi Hasan and Raju, S.M. Taslim Uddin and Siddique, Nazmul},
     title = {TransfusionNet: Framework for cervical cancer detection using deep learning with multi-level fusion},
     journal = {Results in Engineering},
     volume = {28},
     pages = {107174},
     year = {2025},
     month = dec,
     issn = {2590-1230},
     doi = {10.1016/j.rineng.2025.107174},
     url = {https://www.sciencedirect.com/science/article/pii/S2590123025032293},
     publisher = {Elsevier},
   }

3. EICT

   

   Exploring Common Molecular Interactions across Multiple Cancers to Identify Potential Therapeutic Targets and Drug Candidates

   Sourav Basak Shuvo, Sraboni Hossain, Shaira Afra Redhila, and Urmi Bose^†

   In 2025 7th International Conference on Electrical Information and Communication Technology (EICT), Dec 2025

   Abs DOI Bib HTML

   Bioinformatics interprets biological data, especially genomics, to reveal shared genetic and molecular traits across cancers. Background research demonstrates that lung, cervical, liver, and prostate cancers share a significant number of biochemical and genetic traits. To conduct this study, we collected gene expression datasets: GSE19188 (lung cancer), GSE14520 (liver cancer), GSE46602 (prostate cancer), and GSE63514 (cervical cancer) from the Gene Expression Omnibus (GEO) database hosted by NCBI. The GEO2R tool was used for initial preprocessing, filtering, and identification of differentially expressed genes (DEGs). A total of 39 common DEGs shared across all four cancers were identified, from which 10 hub genes (PIK3R1, EZH2, ECT2, KPNA2, CCNB1, AURKA, CLU, TOP2A, BUB1B, ETS2) were selected based on degree centrality within the protein-protein interaction (PPI) network. To understand the biological relevance of these genes, gene ontology (GO), pathway enrichment, and heatmap analysis were performed. Additionally, regulatory and interaction networks were constructed, including the PPI network, TF-gene regulatory network, gene-miRNA interaction network, and protein-chemical interaction network, based on the hub genes. This network-based analysis revealed 15 key miRNAs and 17 transcription factors (TFs) as major regulatory components. Finally, potential therapeutic drug candidates were predicted through drug enrichment analysis using Enrichr, by examining their interactions with the key hub genes. In future, we aim to apply molecular docking and simulation techniques using plant-derived compounds to develop a unified therapeutic strategy targeting all four cancers.

   @inproceedings{shuvo2025molecular,
     author = {Shuvo, Sourav Basak and Hossain, Sraboni and Redhila, Shaira Afra and Bose, Urmi},
     title = {Exploring Common Molecular Interactions across Multiple Cancers to Identify Potential Therapeutic Targets and Drug Candidates},
     booktitle = {2025 7th International Conference on Electrical Information and Communication Technology (EICT)},
     year = {2025},
     pages = {1--6},
     month = dec,
     doi = {10.1109/EICT68394.2025.11355627},
     publisher = {IEEE},
     address = {Khulna, Bangladesh},
     isbn = {979-8-3315-9392-6},
   }

2024

1. ICEEICT

   

   Classification of Gallbladder Cancer Using Average Ensemble Learning

   Sourav Basak Shuvo and Mostafa Zaman Chowdhury^†

   In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT), May 2024

   Abs DOI Bib HTML

   Gallbladder cancer is a highly challenging malignancy within the field of oncology, distinguished by its diagnosis at an advanced stage and its restricted rates of survival. Gallbladder cancer classification from ultrasound images is a very difficult task due to poor image quality and speckle artifact. We suggest employing an ensemble of well-known Convolutional Neural Network models, such as VGG16, VGG19, XceptionNet, and ResNet50, to evaluate their effectiveness in differentiating between normal, benign, and malignant gall bladder conditions. As a result, the ensemble deep learning model significantly enhances the accuracy of classification.

   @inproceedings{shuvo2024gallbladder,
     author = {Shuvo, Sourav Basak and Chowdhury, Mostafa Zaman},
     title = {Classification of Gallbladder Cancer Using Average Ensemble Learning},
     booktitle = {2024 6th International Conference on Electrical Engineering and Information \& Communication Technology (ICEEICT)},
     year = {2024},
     pages = {1450--1455},
     doi = {10.1109/ICEEICT62016.2024.10534480},
     publisher = {IEEE},
     address = {Dhaka, Bangladesh},
     month = may,
     issn = {2769-5700},
   }

1. In Prep.

   NeuroSwin: A Swin Transformer-GRU Model for Parkinson’s Disease Classification and Brain Region Localization from EEG Signals

   Sourav Basak Shuvo, Shaira Afra Redhila, Sraboni Hossain, and Amit Dutta Roy^†

   Manuscript in preparation
2. In Prep.

   CholeNet: A Recurrent-Convolutional Hybrid Ensemble Framework with Quad-Fold Parallel Transfer Learning and Spatio-Sequential Feature Fusion for Gallbladder Cancer Classification

   Sourav Basak Shuvo and Mostafa Zaman Chowdhury^†

   Manuscript in preparation
3. In Prep.

   VRX-UNet: Automated Volumetric Characterization of Intra-tumoral Structures in Gliomas using 3D Segmentation

   Md. Mahadi Hasan Ankon, Sourav Basak Shuvo, Md. Najib Hasan, and Md. Motaleb Hossen Manik^†

   Manuscript in preparation
4. In Prep.

   Advanced image analysis for liver tumor detection and visualization in CT images using automated segmentation

   Md. Abu Sayed, Md. Ashiqur Rahman, Sourav Basak Shuvo, Md. Jahid Hossain, Md. Shafin Alam, and 2 more authors

   Manuscript in preparation
5. Ongoing

   Zero-to-Multi-Shot Benchmarking of Model-Agnostic Meta-Learning (MAML)-Based Domain Adaptation for Multi-Cancer Classification: Comparative Evaluation of LLMs, State-of-the-Art Deep Learning Models, and a Proposed Hybrid Approach

   Md. Najib Hasan, Md. Mahadi Hasan Ankon, Sourav Basak Shuvo, Imran Ahmad, Md. Motaleb Hossen Manik, and 1 more author

   Ongoing Research
6. Ongoing

   Unveiling Overfitting Patterns: Explainable AI-Driven Benchmarking of LLMs, Deep Learning Models, and a Hybrid Framework for Medical Image Classification

   Md. Najib Hasan, Wahid Mahmood Shafin, Md. Mahadi Hasan Ankon, Sourav Basak Shuvo, Taslima Akter Joty, and 1 more author

   Ongoing Research