# Optimization-Incorporated Deep Learning Strategy to Automate L3 Slice Detection and Abdominal Segmentation in Computed Tomography

## TL;DR

This paper presents a deep learning method to automatically detect and segment abdominal tissues in CT scans, improving accuracy for cancer diagnosis.

## Contribution

The novel contribution is an optimization-incorporated deep learning strategy that adjusts augmentation ratios and class weights to handle class imbalance in L3 slice detection and segmentation.

## Key findings

- The optimized models reduced slice detection error to approximately 0.68 ± 1.26 slices.
- The Dice coefficient for abdominal tissue segmentation reached up to 0.987 ± 0.001.
- Balancing class distribution and tuning model parameters significantly enhanced performance.

## Abstract

This study introduces a deep learning-based strategy to automatically detect the L3 slice and segment abdominal tissues from computed tomography (CT) images. Accurate measurement of muscle and fat composition at the L3 level is critical as it can serve as a prognostic biomarker for cancer diagnosis and treatment. However, current manual approaches are time-consuming and prone to class imbalance, since L3 slices constitute only a small fraction of the entire CT dataset. In this study, we propose an optimization-incorporated strategy that integrates augmentation ratio and class weight adjustment as correction design variables within deep learning models. In this retrospective study, the CT dataset was privately collected from 150 prostate cancer and bladder cancer patients at the Department of Urology of Gangneung Asan Hospital. A ResNet50 classifier was used to detect the L3 slice, while standard Unet, Swin-Unet, and SegFormer models were employed to segment abdominal tissues. Bayesian optimization determines optimal augmentation ratios and class weights, mitigating the imbalanced distribution of L3 slices and abdominal tissues. Evaluation of CT data from 150 prostate and bladder cancer patients showed that the optimized models reduced the slice detection error to approximately 0.68 ± 1.26 slices and achieved a Dice coefficient of up to 0.987 ± 0.001 for abdominal tissue segmentation-improvements over the models that did not consider correction design variables. This study confirms that balancing class distribution and properly tuning model parameters enhances performance. The proposed approach may provide reliable and automated biomarkers for early cancer diagnosis and personalized treatment planning.