# An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis

arXiv: https://arxiv.org/abs/2604.02502 · HTML: https://mlsanity.com/paper/2604.02502/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [CE-Net: Context Encoder Network for 2D Medical Image Segmentation](https://mlsanity.com/paper/1903.02740/) (2019)
- [A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation](https://mlsanity.com/paper/1810.07842/) (2018)
- [Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2106.03180/) (2021)
- [Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning](https://mlsanity.com/paper/2008.12833/) (2020)
- [M-SCAN: A Multistage Framework for Lumbar Spinal Canal Stenosis Grading Using Multi-View Cross Attention](https://mlsanity.com/paper/2503.01634/) (2025)
- [FoundationalECGNet: A Lightweight Foundational Model for ECG-based Multitask Cardiac Analysis](https://mlsanity.com/paper/2509.08961/) (2025)

## Built on by (most cited first, 1 of 1)

- [FedDP-PALD: A Privacy-Preserving Federated Latent Diffusion Framework with Prototype Aggregation for Medical Data Synthesis](https://mlsanity.com/paper/2607.16300/) (2026)

## Abstract (arXiv)

Lumbar Spinal Stenosis (LSS) diagnosis remains a critical clinical challenge, with diagnosis heavily dependent on labor-intensive manual interpretation of multi-view Magnetic Resonance Imaging (MRI), leading to substantial inter-observer variability and diagnostic delays. Existing vision-language models simultaneously fail to address the extreme class imbalance prevalent in clinical segmentation datasets while preserving spatial accuracy, primarily due to global pooling mechanisms that discard crucial anatomical hierarchies. We present an end-to-end Explainable Vision-Language Model framework designed to overcome these limitations, achieved through two principal objectives. We propose a Spatial Patch Cross-Attention module that enables precise, text-directed localization of spinal anomalies with spatial precision. A novel Adaptive PID-Tversky Loss function by integrating control theory principles dynamically further modifies training penalties to specifically address difficult, under-segmented minority instances. By incorporating foundational VLMs alongside an Automated Radiology Report Generation module, our framework demonstrates considerable performance: a diagnostic classification accuracy of 90.69%, a macro-averaged Dice score of 0.9512 for segmentation, and a CIDEr score of 92.80%. Furthermore, the framework shows explainability by converting complex segmentation predictions into radiologist-style clinical reports, thereby establishing a new benchmark for transparent, interpretable AI in clinical medical imaging that keeps essential human supervision while enhancing diagnostic capabilities.