Annotation-Efficient Task Guidance for Medical Segment Anything

Medical image segmentation is a key task in the imaging workflow, influencing many image-based decisions. Traditional, fully-supervised segmentation models rely on large amounts of labeled training data, typically obtained through manual annotation, which can be an expensive, time-consuming, and error-prone process. This signals a need for accurate, automatic, and annotation-efficient methods of training these models. We propose SAM-Mix, a novel multitask learning framework for medical image segmentation that uses class activation maps produced by an auxiliary classifier to guide the predictions of the semi-supervised segmentation branch, which is based on the SAM framework. Experimental evaluations on the public LiTS dataset confirm the effectiveness of SAM-Mix for simultaneous classification and segmentation of the liver from abdominal computed tomography (CT) scans. When trained for 90% fewer epochs on only 50 labeled 2D slices, representing just 0.04% of the available labeled training data, SAM-Mix achieves a Dice improvement of 5.1% over the best baseline model. The generalization results for SAM-Mix are even more impressive, with the same model configuration yielding a 25.4% Dice improvement on a cross-domain segmentation task. Our code is available at https://github.com/tbwa233/SAM-Mix.

Areas of Improvement for Autonomous Vehicles: A Machine Learning Analysis of Disengagement Reports

Since 2014, the California Department of Motor Vehicles (CDMV) has compiled information from manufacturers of autonomous vehicles (AVs) regarding factors that lead to the disengagement from autonomous driving mode in these vehicles. These disengagement reports (DRs) contain information detailing whether the AV disengaged from autonomous mode due to technology failure, manual override, or other factors during driving tests. This paper presents a machine learning (ML) based analysis of the information from the 2023 DRs. We use a natural language processing (NLP) approach to extract important information from the description of a disengagement, and use the k-Means clustering algorithm to group report entries together. The cluster frequency is then analyzed, and each cluster is manually categorized based on the factors leading to disengagement. We discuss findings from previous years' DRs, and provide our own analysis to identify areas of improvement for AVs.

Implementing the ICE Estimator in Multilayer Perceptron Classifiers

This paper describes the techniques used to implement the ICE estimator for a multilayer perceptron model, and reviews the performance of the resulting models. The ICE estimator is implemented in the Apache Spark MultilayerPerceptronClassifier, and shown in cross-validation to outperform the stock MultilayerPerceptronClassifier that uses unadjusted MLE (cross-entropy) loss. The resulting models have identical runtime performance, and similar fitting performance to the stock MLP implementations. Additionally, this approach requires no hyper-parameters, and is therefore viable as a drop-in replacement for cross-entropy optimizing multilayer perceptron classifiers wherever overfitting may be a concern.

The Information Theoretically Efficient Model (ITEM): A model for computerized analysis of large datasets

This document discusses the Information Theoretically Efficient Model (ITEM), a computerized system to generate an information theoretically efficient multinomial logistic regression from a general dataset. More specifically, this model is designed to succeed even where the logit transform of the dependent variable is not necessarily linear in the independent variables. This research shows that for large datasets, the resulting models can be produced on modern computers in a tractable amount of time. These models are also resistant to overfitting, and as such they tend to produce interpretable models with only a limited number of features, all of which are designed to be well behaved.