Suraj Rajendran

Akshay Bhalla, Suraj Rajendran · gatech

In the modern world, technology is at its peak. Different avenues in programming and technology have been explored for data analysis, automation, and robotics. Machine learning is key to optimize data analysis, make accurate predictions, and hasten/improve existing functions. Thus, presently, the field of machine learning in artificial intelligence is being developed and its uses in varying fields are being explored. One field in which its uses stand out is that of microbial biosynthesis. In this paper, a comprehensive overview of the differing machine learning programs used in biosynthesis is provided, alongside brief descriptions of the fields of machine learning and microbial biosynthesis separately. This information includes past trends, modern developments, future improvements, explanations of processes, and current problems they face. Thus, this paper's main contribution is to distill developments in, and provide a holistic explanation of, 2 key fields and their applicability to improve industry/research. It also highlights challenges and research directions, acting to instigate more research and development in the growing fields. Finally, the paper aims to act as a reference for academics performing research, industry professionals improving their processes, and students looking to understand the concept of machine learning in biosynthesis.

Srivishnu Vusirikala, Suraj Rajendran

We investigate the potential of self-supervision in improving the accuracy of deep learning models trained to classify melanoma patches. Various self-supervision techniques such as rotation prediction, missing patch prediction, and corruption removal were implemented and assessed for their impact on the convolutional neural network's performance. Preliminary results suggest a positive influence of self-supervision methods on the model's accuracy. The study notably demonstrates the efficacy of the corruption removal method in enhancing model performance. Despite observable improvements, we conclude that the self-supervised models have considerable potential for further enhancement, achievable through training over more epochs or expanding the dataset. We suggest exploring other self-supervision methods like Bootstrap Your Own Latent (BYOL) and contrastive learning in future research, emphasizing the cost-benefit trade-off due to their resource-intensive nature. The findings underline the promise of self-supervision in augmenting melanoma detection capabilities of deep learning models.

Pavan Narahari, Suraj Rajendran, Lorena Bori et al.

The success of in vitro fertilization (IVF) at many clinics relies on the accurate morphological assessment of day 5 blastocysts, a process that is often subjective and inconsistent. While artificial intelligence can help standardize this evaluation, models require large, diverse, and balanced datasets, which are often unavailable due to data scarcity, natural class imbalance, and privacy constraints. Existing generative embryo models can mitigate these issues but face several limitations, such as poor image quality, small training datasets, non-robust evaluation, and lack of clinically relevant image generation for effective data augmentation. Here, we present the Diffusion Based Imaging Model for Artificial Blastocysts (DIA) framework, a set of latent diffusion models trained to generate high-fidelity, novel day 5 blastocyst images. Our models provide granular control by conditioning on Gardner-based morphological categories and z-axis focal depth. We rigorously evaluated the models using FID, a memorization metric, an embryologist Turing test, and three downstream classification tasks. Our results show that DIA models generate realistic images that embryologists could not reliably distinguish from real images. Most importantly, we demonstrated clear clinical value. Augmenting an imbalanced dataset with synthetic images significantly improved classification accuracy (p < 0.05). Also, adding synthetic images to an already large, balanced dataset yielded statistically significant performance gains, and synthetic data could replace up to 40% of real data in some cases without a statistically significant loss in accuracy. DIA provides a robust solution for mitigating data scarcity and class imbalance in embryo datasets. By generating novel, high-fidelity, and controllable synthetic images, our models can improve the performance, fairness, and standardization of AI embryo assessment tools.

Suraj Rajendran, Weishen Pan, Mert R. Sabuncu et al.

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows.