Evaluasi Performa Sistem Kuantifikasi Otomatis Imunohistokimia Berbasis Kecerdasan Buatan Untuk Analisis Ekspresi Tumor Marker
DOI:
https://doi.org/10.32382/jmak.v17i1.2250Kata Kunci:
Imunohistokimia (IHC), Kecerdasan Buatan, Ekspresi Penanda Tumor, Kuantifikasi Otomatis, Analisis Citra Digital, Deep LearningAbstrak
Evaluasi kinerja sistem kuantifikasi otomatis imunohistokimia (IHC) semakin penting untuk menjamin akurasi dan konsistensi dalam analisis ekspresi penanda tumor. Tinjauan sistematis ini bertujuan untuk mengevaluasi kinerja sistem kuantifikasi IHC otomatis berbasis kecerdasan buatan dalam konteks klinis dan penelitian. Penelusuran literatur dilakukan pada basis data PubMed, Scopus, dan ScienceDirect untuk publikasi tahun 2015–2025. Sebanyak 26 studi yang memenuhi kriteria inklusi dianalisis secara kualitatif berdasarkan pedoman PRISMA 2020. Hasil menunjukkan bahwa sistem kuantifikasi IHC berbasis kecerdasan buatan memiliki performa diagnostik tinggi dengan akurasi 90–98%, AUC hingga 0,96, serta korelasi dengan ahli patologi yang melebihi 0,95 pada berbagai biomarker utama seperti HER2, Ki-67, ER, PR, P53, dan PD-L1. Model deep learning seperti convolutional neural networks (CNN), termasuk ResNet dan DenseNet, menunjukkan kemampuan unggul dalam deteksi area tumor dan kuantifikasi ekspresi biomarker secara otomatis. AI juga terbukti meningkatkan reproduksibilitas hasil dengan mengurangi variasi antar-pengamat serta meningkatkan kesesuaian dengan metode referensi, sekaligus menstandarkan interpretasi pada kasus borderline. Perkembangan metode menunjukkan pergeseran dari digital image analysis berbasis aturan menuju deep learning yang lebih adaptif, sehingga meningkatkan akurasi dan generalisasi. Namun, kinerja sistem masih dipengaruhi oleh variasi pra-analitik, termasuk kualitas pewarnaan, heterogenitas data, ukuran dataset, serta kebutuhan supervisi ahli patologi. Secara keseluruhan, meskipun menunjukkan potensi besar dalam meningkatkan objektivitas dan efisiensi diagnostik, implementasi klinis AI dalam kuantifikasi IHC masih memerlukan standardisasi, validasi multisenter, dan evaluasi prospektif lebih lanjut.
Referensi
Bankhead, P., Loughrey, M.B., Fernández, J.A., Dombrowski, Y., McArt, D.G., Dunne, P.D., McQuaid, S., Gray, R.T., Murray, L.J., Coleman, H.G., James, J.A., Salto-Tellez, M. & Hamilton, P.W., 2017, ‘QuPath: Open source software for digital pathology image analysis’, Scientific Reports, 7(1), 16878.
Bencze, J., Szarka, M., Kóti, B., Seo, W., Hortobágyi, T.G., Bencs, V., Módis, L. V. & Hortobágyi, T., 2021, ‘Comparison of Semi-Quantitative Scoring and Artificial Intelligence Aided Digital Image Analysis of Chromogenic Immunohistochemistry’, Biomolecules, 12(1), 19.
Brattoli, B., Mostafavi, M., Lee, T., Jung, W., Ryu, J., Park, S., Park, J., Pereira, S., Shin, S., Choi, S., Kim, H., Yoo, D., Ali, S.M., Paeng, K., Ock, C.-Y., Cho, S.I. & Kim, S., 2024, ‘A universal immunohistochemistry analyzer for generalizing AI-driven assessment of immunohistochemistry across immunostains and cancer types’, npj Precision Oncology, 8(1), 277.
Boyaci, C., Sun, W., Hartman, J. & Ács, B., 2025, ‘Global scoring method of Ki67 immunohistochemistry in breast cancer demonstrates improved concordance using real-world multi-institutional data’, Breast Cancer Research, 27(1), 159.
Casiraghi, E., Huber, Veronica, Frasca, Marco, Cossa, Mara, Tozzi, Matteo, Rivoltini, Licia, Leone, B.E., Villa, A. & Vergani, Barbara, 2018, ‘A novel computational method for automatic segmentation, quantification and comparative analysis of immunohistochemically labeled tissue sections’, BMC Bioinformatics, 19(S10), 357.
Catteau, X., Zindy, E., Bouri, S., Noël, J.-C., Salmon, I. & Decaestecker, C., 2023, ‘Comparison Between Manual and Automated Assessment of Ki-67 in Breast Carcinoma: Test of a Simple Method in Daily Practice’, Technology in Cancer Research & Treatment, 22.
Cheng, J., Han, Y., Yuan, Y., Huang, S., Xiao, B., Kong, Y., Xue, W., Yuan, R., Liu, H., Lan, P., Wu, X., Qian, Y., Ni, D. & Chen, Y., 2025, ‘Automated multi‐regional IHC scoring enhances prognostication in colorectal cancer’, The Journal of Pathology: Clinical Research, 11(5).
Choi, J.E., Kim, K.-H., Lee, Y. & Kang, D.-W., 2024, ‘Digital Validation in Breast Cancer Needle Biopsies: Comparison of Histological Grade and Biomarker Expression Assessment Using Conventional Light Microscopy, Whole Slide Imaging, and Digital Image Analysis’, Journal of Personalized Medicine, 14(3), 312.
Dunenova, G., Kalmataeva, Z., Kaidarova, D., Dauletbaev, N., Semenova, Y., Mansurova, M., Grjibovski, A., Kassymbekova, F., Sarsembayev, A., Semenov, D. & Glushkova, N., 2024, ‘The Performance and Clinical Applicability of HER2 Digital Image Analysis in Breast Cancer: A Systematic Review’, Cancers, 16(15), 2761.
Elie, N., Giffard, F., Blanc-Fournier, C., Morice, P.-M., Brachet, P.-E., Dutoit, S., Plancoulaine, B. & Poulain, L., 2022, ‘Impact of automated methods for quantitative evaluation of immunostaining: Towards digital pathology’, Frontiers in Oncology, 12.
He, Z., Jia, D., Shi, Y., Li, Z., Wu, N. & Zeng, F., 2025, ‘RMD-Net: A Deep Learning Framework for Automated IHC Scoring of Lung Cancer IL-24’, Mathematics, 13(3), 417.
Hou, C., Song, X., Chen, H., Chang, C., Lu, J., Li, C., Qu, H., Guo, R., Xu, J. & Xu, L., 2025, ‘A novel automated IHC staining system for quality control application in ALK immunohistochemistry testing’, Pathology and Oncology Research, 31, 1611964.
Jakobsen, M.R., Teerapakpinyo, C., Shuangshoti, S. & Keelawat, S., 2018, ‘Comparison between digital image analysis and visual assessment of immunohistochemical HER2 expression in breast cancer’, Pathology - Research and Practice, 214(12), 2087–2092.
Kildal, W., Cyll, K., Kalsnes, J., Islam, R., Julbø, F.M., Pradhan, M., Ersvær, E., Shepherd, N., Vlatkovic, L., Tekpli, X., Garred, Ø., Kristensen, G.B., Askautrud, H.A., Hveem, T.S., Danielsen, H.E., Bathen, T.F., Borgen, E., Børresen-Dale, A.-L., Engebråten, O., Fritzman, B., Hartman-Johnsen, O.J., Garred, Ø., Geisler, J., Geitvik, G.A., Hofvind, S., Kåresen, R., Langerød, A., Lingjærde, O.C., Mælandsmo, G.M., Naume, B., Russnes, H.G., Sahlberg, K.K., Sauer, T., Skjerven, H.K., Schlichting, E. & Sørlie, T., 2024, ‘Deep learning for automated scoring of immunohistochemically stained tumour tissue sections – Validation across tumour types based on patient outcomes’, Heliyon, 10(13), e32529.
Krishnamurthy, S., Schnitt, S.J., Vincent-Salomon, A., Canas-Marques, R., Colon, E., Kantekure, K., Maklakovski, M., Finck, W., Thomassin, J., Globerson, Y., Bien, L., Mallel, G., Grinwald, M., Linhart, C., Sandbank, J. & Vecsler, M., 2024, ‘Fully Automated Artificial Intelligence Solution for Human Epidermal Growth Factor Receptor 2 Immunohistochemistry Scoring in Breast Cancer: A Multireader Study’, JCO Precision Oncology, (8).
Liao, C.-H.C., Bakoglu, N., Cesmecioglu, E., Hanna, M., Pareja, F., Wen, H.Y., D’Alfonso, T.M., Brogi, E., Yagi, Y. & Ross, D.S., 2024, ‘Semi-automated analysis of HER2 immunohistochemistry in invasive breast carcinoma using whole slide images: utility for interpretation in clinical practice’, Pathology and Oncology Research, 30, 1611826.
Mahmoud, A.M., Brister, E., David, O., Valyi-Nagy, K., Sverdlov, M., Gann, P.H. & Kim, S.J., 2023, ‘Machine Learning for Digital Scoring of PRMT6 in Immunohistochemical Labeled Lung Cancer’, Cancers, 15(18), 4582.
Moratin, J., Mock, A., Obradovic, S., Metzger, K., Flechtenmacher, C., Zaoui, K., Fröhling, S., Jäger, D., Krauss, J., Hoffmann, J., Freier, K., Horn, D., Hess, J. & Freudlsperger, C., 2021, ‘Digital Pathology Scoring of Immunohistochemical Staining Reliably Identifies Prognostic Markers and Anatomical Associations in a Large Cohort of Oral Cancers’, Frontiers in Oncology, 11(11).
Neagu, A.I., Poalelungi, D.G., Fulga, A., Neagu, M., Fulga, I. & Nechita, A., 2024, ‘Enhanced Immunohistochemistry Interpretation with a Machine Learning-Based Expert System’, Diagnostics, 14(17), 1853.
Niyas, S., Bygari, R., Naik, R., Viswanath, B., Ugwekar, D., Mathew, T., Kavya, J., Kini, J.R. & Rajan, J., 2023, ‘Automated Molecular Subtyping of Breast Carcinoma Using Deep Learning Techniques’, IEEE Journal of Translational Engineering in Health and Medicine, 11, 161–169.
Rizzardi, A.E., Zhang, X., Vogel, R.I., Kolb, S., Geybels, M.S., Leung, Y.-K., Henriksen, J.C., Ho, S.-M., Kwak, J., Stanford, J.L. & Schmechel, S.C., 2016, ‘Quantitative comparison and reproducibility of pathologist scoring and digital image analysis of estrogen receptor β2 immunohistochemistry in prostate cancer’, Diagnostic Pathology, 11(1), 63.
Shu, J., Dolman, G.E., Duan, J., Qiu, G. & Ilyas, M., 2016, ‘Statistical colour models: an automated digital image analysis method for quantification of histological biomarkers’, BioMedical Engineering OnLine, 15(1), 46.
Tewary, S. & Mukhopadhyay, S., 2021, ‘HER2 Molecular Marker Scoring Using Transfer Learning and Decision Level Fusion’, Journal of Digital Imaging, 34(3), 667–677.
Ushakov, E., Naumov, A., Fomberg, V., Vishnyakova, P., Asaturova, A., Badlaeva, A., Tregubova, A., Karpulevich, E., Sukhikh, G. & Fatkhudinov, T., 2023, ‘EndoNet: A Model for the Automatic Calculation of H-Score on Histological Slides’, Informatics, 10(4), 90.
Wang, J., Zhang, S., Li, J., Deng, M., Zeng, Z., Dong, Z., Chen, F., Liu, W., Wu, L. & Yu, H., 2025, ‘Development and clinical validation of deep learning-based immunohistochemistry prediction models for subtyping and staging of gastrointestinal cancers’, BMC Gastroenterology, 25(1), 494.
Wanram, Surasak, Sombatwong, Jakkra, Sakunpong, A., Prasongdee, P., Panomket, Pawana, Wongsena, P., Limpaiboon, T. & Jearanaikoon, Patcharee, 2016, ‘Comparison of Automated and Conventional IHC Visual Scoring Analysis for MHC Class I and Tapasin Expression in Cervical Carcinoma.’, Journal of the Medical Association of Thailand = Chotmaihet thangphaet, 99 Suppl 1(1), S67-75.
Wen, Z., Luo, D., Wang, S., Rong, R., Evers, B.M., Jia, L., Fang, Y., Daoud, E. V., Yang, S., Gu, Z., Arner, E.N., Lewis, C.M., Solis Soto, L.M., Fujimoto, J., Behrens, C., Wistuba, I.I., Yang, D.M., Brekken, R.A., O’Donnell, K.A., Xie, Y. & Xiao, G., 2024, ‘Deep Learning–Based H-Score Quantification of Immunohistochemistry-Stained Images’, Modern Pathology, 37(2), 100398.
Xue, Z.-Z., Li, C., Luo, Z.-M., Wang, S.-S. & Xu, Y.-Y., 2022, ‘Automated classification of protein expression levels in immunohistochemistry images to improve the detection of cancer biomarkers’, BMC Bioinformatics, 23(1), 470.
Horai, Y., Mizukawa, M., Nishina, H., Nishikawa, S., Ono, Y., Takemoto, K. & Baba, N., 2019, ‘Quantification of histopathological findings using a novel image analysis platform’, Journal of Toxicologic Pathology, 32(4), 319–327.
Zhang, J., Guo, Xiaolei, Cai, W., Cao, Y., Ge, W., Huang, P., Hou, D., Zheng, S. & Zhang, G., 2023, ‘Automatic Scoring Method for Tumor IHC Images Based on Deep Learning and Its Application on P53 Protein’, IEEE Access, 11, 64005–64015.
