Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911270538575872 |
|---|---|
| author | Neveditsin, Nikita Lingras, Pawan Patil, Salil Patil, Swarup Mago, Vijay |
| author_facet | Neveditsin, Nikita Lingras, Pawan Patil, Salil Patil, Swarup Mago, Vijay |
| contents | Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13523 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports Neveditsin, Nikita Lingras, Pawan Patil, Salil Patil, Swarup Mago, Vijay Information Retrieval Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization. |
| title | Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2511.13523 |