Sumotosima: A Framework and Dataset for Classifying and Summarizing Otoscopic Images

• URL: http://arxiv.org/abs/2408.06755v1
• Date: Tue, 13 Aug 2024 09:26:41 GMT
• Title: Sumotosima: A Framework and Dataset for Classifying and Summarizing Otoscopic Images
• Abstract summary: Otoscopy is a diagnostic procedure to examine the ear canal and eardrum using an otoscope. We propose a novel resource efficient deep learning and transformer based framework, Sumotosima. Our framework works on combination of triplet and cross-entropy losses.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Otoscopy is a diagnostic procedure to examine the ear canal and eardrum using an otoscope. It identifies conditions like infections, foreign bodies, ear drum perforations and ear abnormalities. We propose a novel resource efficient deep learning and transformer based framework, Sumotosima (Summarizer for otoscopic images), an end-to-end pipeline for classification followed by summarization. Our framework works on combination of triplet and cross-entropy losses. Additionally, we use Knowledge Enhanced Multimodal BART whose input is fused textual and image embedding. The objective is to provide summaries that are well-suited for patients, ensuring clarity and efficiency in understanding otoscopic images. Given the lack of existing datasets, we have curated our own OCASD (Otoscopic Classification And Summary Dataset), which includes 500 images with 5 unique categories annotated with their class and summaries by Otolaryngologists. Sumotosima achieved a result of 98.03%, which is 7.00%, 3.10%, 3.01% higher than K-Nearest Neighbors, Random Forest and Support Vector Machines, respectively, in classification tasks. For summarization, Sumotosima outperformed GPT-4o and LLaVA by 88.53% and 107.57% in ROUGE scores, respectively. We have made our code and dataset publicly available at https://github.com/anas2908/Sumotosima

Related papers

• OPTED: Open Preprocessed Trachoma Eye Dataset Using Zero-Shot SAM 3 Segmentation [0.0]
  Trachoma remains the leading infectious cause of blindness worldwide, with Sub-Saharan Africa bearing over 85% of the global burden and Ethiopia alone accounting for more than half of all cases.<n>Yet publicly available preprocessed datasets for automated trachoma classification are scarce, and none originate from the most affected region.<n>We present OPTED, an open-source preprocessed trachoma eye dataset constructed using the Segment Anything Model 3 (SAM 3) for automated region-of-interest extraction.
  arXiv  Detail & Related papers  (2026-03-06T21:07:08Z)
• BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification [0.6840587119863303]
  We introduce BRISC, a dataset designed for brain tumor segmentation and classification tasks, featuring high-resolution segmentation masks.<n>The dataset comprises 6,000 contrast-enhanced T1-weighted MRI scans, which were collated from multiple public datasets that lacked segmentation labels.<n>It includes three major tumor types, namely glioma, meningioma, and pituitary, as well as non-tumorous cases.
  arXiv  Detail & Related papers  (2025-06-17T08:56:05Z)
• MRGen: Segmentation Data Engine for Underrepresented MRI Modalities [59.61465292965639]
  Training medical image segmentation models for rare yet clinically important imaging modalities is challenging due to the scarcity of annotated data.<n>This paper investigates leveraging generative models to synthesize data, for training segmentation models for underrepresented modalities.<n>We present MRGen, a data engine for controllable medical image synthesis conditioned on text prompts and segmentation masks.
  arXiv  Detail & Related papers  (2024-12-04T16:34:22Z)
• LSD3K: A Benchmark for Smoke Removal from Laparoscopic Surgery Images [0.7138611948315257]
  Smoke generated by surgical instruments during laparoscopic surgery can obscure the visual field, impairing surgeons' ability to perform operations accurately and safely. Despite laparoscopic image desmoking has attracted the attention of researchers in recent years, the lack of publicly available high-quality benchmark datasets is the main bottleneck to hamper the development progress of this task. We construct a new high-quality dataset for Laparoscopic Surgery image Desmoking, named LSD3K, consisting of 3,000 paired synthetic non-homogeneous smoke images.
  arXiv  Detail & Related papers  (2024-07-18T03:42:16Z)
• WATUNet: A Deep Neural Network for Segmentation of Volumetric Sweep Imaging Ultrasound [1.2903292694072621]
  Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture quality ultrasound images. We present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet) In this model, we incorporate wavelet gates (WGs) and attention gates (AGs) between the encoder and decoder instead of a simple connection to overcome the limitations mentioned.
  arXiv  Detail & Related papers  (2023-11-17T20:32:37Z)
• Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network [63.845552349914186]
  Capturing global contextual information plays a critical role in breast ultrasound (BUS) image classification. Vision Transformers have an improved capability of capturing global contextual information but may distort the local image patterns due to the tokenization operations. In this study, we proposed a hybrid multitask deep neural network called Hybrid-MT-ESTAN, designed to perform BUS tumor classification and segmentation.
  arXiv  Detail & Related papers  (2023-08-04T01:19:32Z)
• A Knowledge Distillation framework for Multi-Organ Segmentation of Medaka Fish in Tomographic Image [5.881800919492064]
  We propose a self-training framework for multi-organ segmentation in tomographic images of Medaka fish. We utilize the pseudo-labeled data from a pretrained model and adopt a Quality Teacher to refine the pseudo-labeled data. The experimental results demonstrate that our method improves mean Intersection over Union (IoU) by 5.9% on the full dataset.
  arXiv  Detail & Related papers  (2023-02-24T10:31:29Z)
• Information Gain Sampling for Active Learning in Medical Image Classification [3.1619162190378787]
  This work presents an information-theoretic active learning framework that guides the optimal selection of images from the unlabelled pool to be labeled. Experiments are performed on two different medical image classification datasets.
  arXiv  Detail & Related papers  (2022-08-01T16:25:53Z)
• Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training [73.60883490436956]
  We propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification. We employ the self-ensemble model with a noisy label filter to efficiently select the clean and noisy samples. We also design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples.
  arXiv  Detail & Related papers  (2022-05-10T07:50:08Z)
• FedMed-ATL: Misaligned Unpaired Brain Image Synthesis via Affine Transform Loss [58.58979566599889]
  We propose a novel self-supervised learning (FedMed) for brain image synthesis. An affine transform loss (ATL) was formulated to make use of severely distorted images without violating privacy legislation. The proposed method demonstrates advanced performance in both the quality of synthesized results under a severely misaligned and unpaired data setting.
  arXiv  Detail & Related papers  (2022-01-29T13:45:39Z)
• Weakly-supervised Generative Adversarial Networks for medical image classification [1.479639149658596]
  We propose a novel medical image classification algorithm called Weakly-Supervised Generative Adversarial Networks (WSGAN) WSGAN only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set. We show that WSGAN can obtain relatively high learning performance by using few labeled and unlabeled data.
  arXiv  Detail & Related papers  (2021-11-29T15:38:48Z)
• Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation [82.61182037130406]
  This work deals with medical image segmentation and in particular with accurate polyp detection and segmentation during colonoscopy examinations. Basic architecture in image segmentation consists of an encoder and a decoder. We compare some variant of the DeepLab architecture obtained by varying the decoder backbone.
  arXiv  Detail & Related papers  (2021-04-02T02:07:37Z)
• Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare [77.99636165307996]
  We classify biomedical images using ensembles of neural networks. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish, Mish, Mexican Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign.
  arXiv  Detail & Related papers  (2020-11-24T01:53:39Z)
• ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Medical Image Segmentation [99.90263375737362]
  We propose ATSO, an asynchronous version of teacher-student optimization. ATSO partitions the unlabeled data into two subsets and alternately uses one subset to fine-tune the model and updates the label on the other subset. We evaluate ATSO on two popular medical image segmentation datasets and show its superior performance in various semi-supervised settings.
  arXiv  Detail & Related papers  (2020-06-24T04:05:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.