Enhancing Nuclear Medicine Through Innovative AI Models: Integrating Large Language Models and SmoothQuant for Advanced Imaging Precision

References

[1] Kitamura FC, Marques O. Trustworthiness of artificial intelligence models in radiology and the role of explainability. J Am Coll Radiol. 2021;18:1160–2. https://

[2] Mirzaei S, Hustinx R, Prior JO, Ozcan Z, Boubaker A, Farsad M, et al. Improving nuclear medicine practice with UEMS/ EBNM committees. J Nucl Med: Off Publ Soc Nucl Med. 2020;61:18N-20N.

[3] Sokol DK. How good a doctor do you need to be? BMJ Br Med J. 2012;345:e7858. https://

[4] Shelmerdine SC, Martin H, Shirodkar K, Shamshuddin S, Weir -McCall JR, Collaborators F-AS. Can artificial intelligence pass the Fellowship of the Royal College of Radiologists examination? Multi-reader diagnostic accuracy study. BMJ. 2022;379:e072826. https://

[5] Rampton V, Ko A. Robots, radiologists, and results. BMJ. 2022;379:o2853. https://

[6] Dettmers, T., Lewis, M., Belkada, Y., and Zettlemoyer, L. Llm.int8(): 8-bit matrix multiplication for transformers at scale. arXiv preprint https://arXiv:2208.07339, 2022.

[7] Yao, Z., Aminabadi, R. Y., Zhang, M., Wu, X., Li, C., and He, Y. Zeroquant: Efficient and affordable post-training quantization for large- scale transformers, 2022. URL https://arxiv.org/abs/2206.01861.

[8] Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. Language models are few-shot learners. Advances in neural information processing systems, 33: 1877–1901, 2020b.

[9] Rae, J. W., Borgeaud, S., Cai, T., Millican, K., Hoffmann, J., Song, F., Aslanides, J., Henderson, S., Ring, R., Young, S., et al. Scaling language models: Methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446, 2021.

[10] Smith, S., Patwary, M., Norick, B., LeGresley, P., Rajbhandari, S., Casper, J., Liu, Z., Prabhumoye, S., Zerveas, G. Korthikanti, V., et al. Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv preprint arXiv:2201.11990, 2022.

[11] Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X. V., Mihaylov, T., Ott, M., Shleifer, S., Shuster, K., Simig, D., Koura, P. S., Sridhar, A., Wang, T., and Zettlemoyer, L. Opt: Open pre-trained transformer language models, 2022. URL https://arxiv.org/abs/2205.01068

[12] Scao, T. L., Fan, A., Akiki, C., Pavlick, E., Ilic, S., Hesslow, ´ D., Castagné, R., Luccioni, A. S., Yvon, F., Gallé, M., et al. Bloom: A 176b- parameter open-access multilingual language model. arXiv preprint https://arXiv:2211.05100, 2022.

[13] Frantar, E., Ashkboos, S., Hoefler, T., and Alistarh, D. Gptq: Accurate post-training quantization for generative pretrained transformers. arXiv preprint https://arXiv:2210.17323, 2022.

[14] Park, G., Park, B., Kwon, S. J., Kim, B., Lee, Y., and Lee, D. nuqmm: Quantized matmul for efficient inference of large-scale generative language models. arXiv preprint https://arXiv:2206.09557, 2022.

[15] Wei, X., Zhang, Y., Zhang, X., Gong, R., Zhang, S., Zhang, Q., Yu, F., and Liu, X. Outlier suppression: Pushing the limit of low- bit transformer language models, 2022. URL https://arxiv.org/abs/2209.13325.

[16] Devlin, J., Chang, M., Lee, K., and Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT 2019, pp. 4171 – 4186. Association for Computational Linguistics, 2019.

[17] Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., and Zettlemoyer, L. Bart: Denoising sequence-to- sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461, 2019

[18] Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. Quantization and training of neural networks for efficient integerarithmetic-only inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704–2713, 2018.

[19] Bondarenko, Y., Nagel, M., and Blankevoort, T. Understanding and overcoming the challenges of efficient transformer quantization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7947–7969, Online and Punta Cana, Dominican Republic, November 2021. Association for Computational Linguistics. URL https://aclanthology.org/2021. emnlp- main.627

[20] Roemmele, M., Bejan, C. A., and Gordon, A. S. Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In Logical Formalizations of Common-sense Reasoning, Papers from the 2011 AAAI Spring Symposium, Technical Report SS-11-06, Stanford, California, USA, March 21-23, 2011. AAAI, 2011. URL http://www. aaai.org/ocs/index.php/SSS/SSS11/paper/view /2418.

@article{1705251,
      author = {Sanskar Saxena, Vinod Kumar, Jatin Chopra, Pranjal Gupta, Daamini Batra; Bhaumik Tyagi},
      title = {Enhancing Nuclear Medicine Through Innovative AI Models: Integrating Large Language Models and SmoothQuant for Advanced Imaging Precision},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {7},
      number = {6},
      pages = {1-7},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1705251.pdf},
      abstract = {Large language models (LLMs) exhibit superior performance but demand substantial computational and memory resources. Quantization emerges as a viable strategy to alleviate memory requirements and expedite inference. Nonetheless, extant quantization methods encounter challenges in preserving accuracy and ensuring hardware efficiency. This research introduces SmoothQuant, an innovative, training-free, and accuracy-preserving post-training (PTQ) approach, specifically designed to facilitate 8-bit weight and 8-bit activation (W8A8) quantization for LLMs. Leveraging the insight that weights are amenable to quantization while activations pose challenges, SmoothQuant addresses this imbalance by mitigating activation outliers. With the continuous evolution of artificial intelligence (AI) technologies, integrating innovative AI models into the field of nuclear medicine holds immense promise. This research paper explores the synergistic potential of combining Large Language Models (LLMs) and SmoothQuant, a state-of-the-art post-training quantization technique, to achieve advanced imaging precision in nuclear medicine. This is achieved through an offline migration of the quantization complexity from activations to weights, employing a mathematically equivalent transformation. This research presents a turn-key solution that not only optimizes hardware utilization but also contributes to the democratization of LLMs by mitigating associated costs. The study investigates the impact of this integration on data analysis, interpretation, and overall diagnostic accuracy.},
      keywords = {Nuclear Medicine, Artificial Intelligence, Large Language Models, Imaging Precision, Quantization.},
      month = {December},
  }