Acute Myeloid Leukemia (AML) is a rare and rapidly progressing disease characterized by genetic mutations that disrupt the normal development of blood cells. Accurate diagnosis and classification of AML sub-categories are crucial for effective treatment strategies. In this paper, we propose an approach using deep learning classification techniques to automate the differentiation of leukocyte morphology and identify malignant cells. Our study utilizes a large dataset of individual cell images from peripheral blood smears and evaluates various state-of-the-art deep learning architectures through transfer learning and data augmentation techniques. Additionally, we employ a hybrid approach that combines deep learning-based featurization technique with machine learning models applied to the extracted features. Data augmentation techniques are employed to enhance dataset richness, and the featurized dataset is trained using three distinct algorithms: K Nearest Neighbors (KNN), Random Forest, and Multilayer Perceptron (MLP). Using the ConvNextLarge model for featurization with an MLP classifier achieved a leading 95.98% accuracy across 15 categories, surpassing prior algorithms. Our findings contribute to the field of AML diagnosis by providing a computationally efficient and accurate automated system for cytomorphological examination of leukocytes, paving the way for improved personalized treatment strategies,

Explainability/Interpretability in machine learning applications is becoming critical, with legal and industry requirements demanding human understandable machine learning results. We describe the additional complexities that occur when a known interpretability technique (canary models) is applied to a real production scenario. We furthermore argue that reproducibility is a key feature in practical usages of such interpretability techniques in production scenarios. With this motivation, we present a production ML reproducibility solution, namely a comprehensive time ordered event sequence for machine learning applications. We demonstrate how our approach can bring this known common interpretability technique into production viability. We further present the system design and early performance characteristics of our reproducibility solution.

Segmenting objects of interest from 3D data sets is a common problem encountered in biological data. Small field of view and intrinsic biological variability combined with optically subtle changes of intensity, resolution, and low contrast in images make the task of segmentation difficult, especially for microscopy of unstained living or freshly excised thick tissues. Incorporating shape information in addition to the appearance of the object of interest can often help improve segmentation performance. However, the shapes of objects in tissue can be highly variable and design of a flexible shape model that encompasses these variations is challenging. To address such complex segmentation problems, we propose a unified probabilistic framework that can incorporate the uncertainty associated with complex shapes, variable appearance, and unknown locations. The driving application that inspired the development of this framework is a biologically important segmentation problem: the task of automatically detecting and segmenting the dermal-epidermal junction (DEJ) in 3D reflectance confocal microscopy (RCM) images of human skin. RCM imaging allows noninvasive observation of cellular, nuclear, and morphological detail. The DEJ is an important morphological feature as it is where disorder, disease, and cancer usually start. Detecting the DEJ is challenging, because it is a 2D surface in a 3D volume which has strong but highly variable number of irregularly spaced and variably shaped "peaks and valleys." In addition, RCM imaging resolution, contrast, and intensity vary with depth. Thus, a prior model needs to incorporate the intrinsic structure while allowing variability in essentially all its parameters. We propose a model which can incorporate objects of interest with complex shapes and variable appearance in an unsupervised setting by utilizing domain knowledge to build appropriate priors of the model. Our novel strategy to model this structure combines a spatial Poisson process with shape priors and performs inference using Gibbs sampling. Experimental results show that the proposed unsupervised model is able to automatically detect the DEJ with physiologically relevant accuracy in the range 10- 20 μm .

This paper describes the detection of rust defects on highway steel bridges, which are one of the most commonly observed defects on coating surfaces and thus have to be taken care of appropriately since they severely affect the structural integrity of bridges. A rust defect assessment method is presented that automatically detects the percentage of rust in a given digital image of bridge surface taken from a conventional digital camera. A training and detection algorithm is implemented to classify a given block of the image as rust or non-rust. The results of the algorithm are analyzed for its efficiency and possible optimization techniques are suggested.