Jayprakash Upadhyay, Dr. Sudeep Sharma

DOI: https://doi.org/10.5281/zenodo.23733479

Histopathological image classification is challenging due to substantial intra-class variability and similarities between tissue categories. This paper presents a DeepCon⁺ framework for colorectal cancer tissue classification. First, a pretrained Xception network is used to extract deep feature vectors from the images. Principal Component Analysis (PCA) is used to reduce the feature dimensionality while retaining 95% of the original information. Subsequently, class-wise K-means clustering decomposes the eight original tissue classes into 16 subclasses to represent intra-class variations more effectively. A pretrained Xception-based CNN is then fine-tuned using transfer learning to classify the decomposed subclasses. This coarse-learning stage enables the model to learn more discriminative representations of heterogeneous tissue patterns. The overall framework aims to improve feature representation and classification by combining deep feature extraction, dimensionality reduction, class wise clustering, and subclass-level learning. Its effectiveness can be assessed using standard classification metrics, including accuracy, precision, recall, and F1-score. The experimental analysis performed on the colorectal histopathology dataset reveals that the proposed Deep Con⁺ framework markedly surpasses the initial Deep Con model and traditional CNN benchmarks, attaining enhanced classification accuracy and increased F1-score for all tissue categories.

Histopathological Image Classification, DeepCon⁺, Coarse-to-Fine Learning, Class Decomposition, Attention Mechanism, Subclass Learning, Deep Learning.

In this paper DeepCon⁺, model is proposed for colorectal histopathological tissue classification using class decomposition, dimensionality reduction, and refined subclass-to-class mapping. The proposed method achieved 96.00% accuracy and a 96.04% macro F1-score, outperforming the baseline DeepCon model. Improvements were observed in six of eight tissue classes, particularly Complex, Tumor, Stroma, and Lympho. These results demonstrate the potential of DeepCon⁺ to improve tissue classification, although further validation is required to establish its generalizability. Future work will focus on multi-scale feature learning, Vision Transformer hybrid architectures, and improved subclass decomposition. The framework will also be evaluated on independent histopathology datasets to assess its robustness and generalizability.

[1] Y. Xiand P. Xu, ‘‘Global colorectal cancer burden in 2020 and projections to 2040,’’ Translational Oncol., vol. 14, no. 10, Oct. 2021, Art. no. 101174.
[2] D.Hong,B.Zhang,H.Li,Y.Li,J.Yao,C.Li,M.Werner,J.Chanussot,A.Zipf, and X.X.Zhu,‘‘Cross-citymatters: Amultimodalremotesensingbenchmarkdatasetforcross-city semantic segmentation using high resolution domain adaptation networks,’’ Remote Sens. Environ., vol. 299, Dec. 2023, Art. No. 113856.
[3] D.Hong,B.Zhang,X.Li,Y.Li,C.Li,J.Yao,N.Yokoya,H.Li,P.Ghamisi,X.Jia, A. Plaza, P. Gamba, J. A. Benediktsson, and J. Chanussot, ‘‘SpectralGPT: Spectral remote sensing foundation model,’’ IEEE Trans. Pattern Anal. Mach. Intell., early access, Apr. 3, 2024, doi: 10.1109/TPAMI.2024.3362475.
[4] D. Hong, C. Li, B. Zhang, N. Yokoya, J. A. Benediktsson and J. Chanussot, ‘‘Multimodal artificial intelligence foundation models: Unleashing the power of remote sensing big data in Earth observation,’’ Innov. Geosci. vol. 2, no. 1, 2024, Art. no. 100055.
[5] M.Jahanifar,A.Shepard,N.Zamanitajeddin,R.M.S.Bashir,M.Bilal, S.A.Khurram, F. Minhas, and N. Rajpoot, ‘‘Stain-robust mitotic figure detection for the mitosis domain generalization challenge,’’ in Proc. MICCAI, Mar. 2022, pp. 48–52.
[6] N.A.Koohbanani, B.Unnikrishnan, S.A.Khurram, P.Krishnaswamy and N.Rajpoot, ‘‘Self-path: Self supervision for classification of pathology images with limited annotations,’’ IEEE Trans. Med. Imag., vol. 40, no. 10, pp. 2845–2856, Oct. 2021.
[7] F. Ciompi, O. Geessink, B. E.Bejnordi, G. S.deSouza,A. Baidoshvili, G. Litjens, B. van Ginneken, I. Nagtegaal, and J. van der Laak, ‘‘The importance of stain normalization in colorectal tissue classification with convolutional networks,’’ in Proc. IEEE 14th Int. Symp. Biomed. Imag. Apr. 2017, pp. 160–163.
[8] X.Wu,Y.Li,X.Chen,Y.Huang,L.He,K.Zhao,X.Huang, W.Zhang,Y.Huang,Y. Li, M. Dong, J. Huang, T. Xia, C. Liang, and Z. Liu, ‘‘Deep learning features improve the performance of a radiomics signature for predicting Kras status in patients with colorectal cancer,’’ Academic Radiol., vol. 27, no. 11, pp. e254–e262, Nov. 2020.
[9] K.Suzuki, ‘‘Overview of deep learning in medical imaging,’’ Radiological Phys. Technol., vol. 10, no. 3, pp. 257–273, Jul. 2017.
[10] S.Poudel,Y.J.Kim,D.M.Vo,andS.-W.Lee,‘‘Colorectaldiseaseclassificationusing dilation inconvolutional neuralnetwork,’’IEEE Access, vol. 8, pp. 99227–99238, 2020.
[11] efficientlyscaled E.F.Ohata,J.V.S.D.Chagas,G.M.Bezerra,M.M.Hassan,V.H.C.deAlbuquerque, and P. P. R. Filho, ‘‘A novel transfer learning approach for the classification of histological images of colorectal cancer,’’ J. Supercomputer., vol. 77, no. 9, pp. 9494–9519, Feb. 2021.
[12] V. Rachapudi and G. Lavanya Devi, “Improved convolutional neural network-based histopathological image classification,”Evol.Intell.vol.14,no.3,pp.1337–1343,Sep.2021.
[13] T. T. L. Vuong, Q. D. Vu, M. Jahanifar, S. Graham, J. T. Kwak, and N. Rajpoot, ‘‘IMPaSh: A novel domain-shift resistant representation for colorectal cancer tissue classification,’’ in Proc. ECCV, Feb. 2023, pp. 543–555.
[14] J.N.Kather,J.Krisam,P.Charoentong,T.Luedde,E.Herpel,C.-A.Weis,T.Gaiser, A. Marx, N. A. Valous, D. Ferber, L. Jansen, C. C. Reyes-Aldasoro,I. Zörnig, D. Jäger, H. Brenner J. Chang Claude, M. Hoffmeister, and N. Halama, ‘‘Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study,’’ PLOS Med., vol. 16, no. 1, Jan. 2019, Art. no. e1002730.
[15] Z.Gu, W. Li, J. Huo,L. Wang, and Y. GAO, ‘‘LoFGAN: Fusing local representations for few-shot image generation,’’ in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct. 2021, pp. 8443–8451.
[16] A.Kumar, A.K.Bhunia,S.Narayan,H.Cholakkal, R.M.Anwer,J.Laaksonen,and F.S.Khan,‘‘Cross-modulatedfew-shotimagegenerationforcolorectaltissueclassification,’’ in Proc. ICCV, Oct. 2023, pp. 128–137.
[17] M.Nergiz,‘‘Federatedlearning-basedcolorectalcancerclassificationbyconvolutional neural networks and general visual representation learning,’’ Int.J.ImageSyst.Technol., vol. 33, no. 3, pp. 951–964, May 2023.
[18] W. Yu, N. Xu, N. Huang, and H. Chen, ‘‘Bridging the gap: Geometry-centric discriminative manifold distribution alignment for enhanced classification in colorectal cancer imaging,’’ Comput. Biol. Med., vol. 170, Mar. 2024, Art. No. 107998.
[19] Z. Cao et al., "A Novel Colorectal Histopathological Image Classification Method BasedonProgressiveMulti-GranularityFeatureFusionofPatch,"inIEEEAccess,vol.12,pp. 68981-68998, 2024, doi: 10.1109/ACCESS.2024.3401240.
[20] Centers for Disease Control and Prevention.(2022). United States Cancer Statistics: Data Visualizations. [Online]. Available: https://gis.cdc.gov/ Cancer/USCS/#/At A Glance.

Jayprakash Upadhyay, Dr. Sudeep Sharma (2026). DeepCon⁺ based Deep Learning Architecture for Histopathology Image Classification. International Journal of Engineering and Techniques, 12(5), 423–430. ISSN: 2395-1303. DOI: https://doi.org/10.5281/zenodo.23733479