Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology

• URL: http://arxiv.org/abs/2608.15915v1
• Date: Sun, 16 Aug 2026 20:12:13 GMT
• Title: Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology
• Abstract summary: Lung cancer remains the leading cause of cancer-related mortality worldwide.<n>Deep learning has shown considerable potential in computational pathology.<n>This study presents a two-stage deep learning framework for multi-class tissue classification.
• Score: 1.1526546449734862
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lung cancer remains the leading cause of cancer-related mortality worldwide, while histopathological diagnosis is often affected by inter-observer variability and the substantial workload associated with manual slide examination. Although deep learning has shown considerable potential in computational pathology, comprehensive benchmarks that integrate tissue classification and region segmentation within a unified analytical framework remain limited. This study presents a two-stage deep learning framework for multi-class tissue classification and pixel-level histopathological region segmentation, accompanied by a systematic comparison of state-of-the-art architectures at each stage. For tissue classification, six models, a custom convolutional neural network, VGG16, DenseNet, MobileNetV3, a custom Vision Transformer, and YOLO11, are evaluated on a combined dataset of 39,000 images derived from LC25000 and LungHist700. The models distinguish between adenocarcinoma, squamous cell carcinoma, and normal lung tissue. YOLO11 achieves the best classification performance, with an accuracy of 98.38%, a five-fold cross-validation accuracy of 98.21 +/- 0.35%, and a macro F1-score of 0.98. For region segmentation, U-Net, ResNet-encoder U-Net, DeepLabV3+, and YOLO11-seg are evaluated using the GlaS gland segmentation benchmark. DeepLabV3+ obtains the highest Intersection over Union of 0.80 and a Dice score of 0.89, while YOLO11-seg achieves a comparable Intersection over Union of 0.79 using approximately 14x fewer parameters. The best-performing classification and segmentation models are subsequently integrated into an end-to-end framework, providing an accurate, computationally efficient, and reproducible baseline for automated histopathological image analysis.

Related papers

• Multi-cancer detection using a computationally efficient CNN with transfer learning [0.4889686357485836]
  This study introduces a computationally efficient convolutional neural network (CNN) architecture enhanced with transfer learning for multi-cancer detection.<n>We evaluate this approach on three distinct tumor datasets comprising brain magnetic resonance imaging (MRI) and lung and kidney computed tomography (CT) scans.<n>The model achieves test accuracy of 90.85 +- 2.22%, 98.64 +- 2.43% and 99.92 +- 0.08% for brain, lung, and kidney cancer classification, respectively.
  arXiv  Detail & Related papers  (2026-06-21T09:12:44Z)
• Cascade Classification of Dermoscopic Images of Skin Neoplasms with Controllable Sensitivity and External Clinical Validation [36.94429692322632]
  Four architectures were compared in three schemes: binary (malignant/benign), single-stage four-class (benign, MEL, SCC, BCC), and a two-stage cascade (binary triage, then three-class differentiation MEL/ SCC/BCC)<n>All models used ImageNet-pretrained weights and a single augmentation protocol on aggregated open ISIC Archive data.<n>On ISIC MILK10k, direct 11-class classification yields mean-class sensitivity 0.525.
  arXiv  Detail & Related papers  (2026-06-11T09:55:57Z)
• Linking spatial biology and clinical histology via Haiku [35.723756132708026]
  We present Haiku, a tri-modal contrastive learning model trained on multiplexed immunofluorescence (mIF)<n>It comprises 26.7 million spatial patches from 3,218 tissue sections across 1,606 patients spanning 11 organ types.
  arXiv  Detail & Related papers  (2026-04-30T18:53:32Z)
• Diagnostic Performance of Universal-Learning Ultrasound AI Across Multiple Organs and Tasks: the UUSIC25 Challenge [34.86849736082012]
  Current ultrasound AI remains fragmented into single-task tools.<n>General-purpose AI models achieve high accuracy and efficiency across multiple tasks using a single architecture.
  arXiv  Detail & Related papers  (2025-12-19T06:54:30Z)
• HistoART: Histopathology Artifact Detection and Reporting Tool [37.31105955164019]
  Whole Slide Imaging (WSI) is widely used to digitize tissue specimens for detailed, high-resolution examination.<n>WSI remains vulnerable to artifacts introduced during slide preparation and scanning.<n>We propose and compare three robust artifact detection approaches for WSIs.
  arXiv  Detail & Related papers  (2025-06-23T17:22:19Z)
• Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment [3.5408411348831232]
  We present a fully automated, anatomically guided deep learning pipeline for prostate cancer (PCa) risk stratification using routine MRI.<n>The pipeline integrates three key components: an nnU-Net module for segmenting the prostate gland and its zones on axial T2-weighted MRI; a classification module based on the DiceedPT Swin Transformer foundation model, fine-tuned on 3D patches with optional anatomical priors and clinical data; and a VAE-GAN framework for generating counterfactual heatmaps that localize decision-driving image regions.
  arXiv  Detail & Related papers  (2025-05-23T14:40:09Z)
• Deep Learning Enabled Segmentation, Classification and Risk Assessment of Cervical Cancer [0.0]
  Cervical cancer, the fourth leading cause of cancer in women globally, requires early detection through Pap smear tests.<n>In this study, we performed a focused analysis by segmenting the cellular boundaries and drawing bounding boxes to isolate the cancer cells.<n>A novel Deep Learning architecture, the Multi-Resolution Fusion Deep Convolutional Network", was proposed to effectively handle images with varying resolutions and aspect ratios.
  arXiv  Detail & Related papers  (2025-05-21T13:25:27Z)
• A Feature-Level Ensemble Model for COVID-19 Identification in CXR Images using Choquet Integral and Differential Evolution Optimization [0.7510165488300369]
  An effective strategy to mitigate the COVID-19 pandemic involves integrating testing to identify infected individuals.<n>While RT-PCR is considered the gold standard for diagnosing COVID-19, it has some limitations such as the risk of false negatives.<n>This paper introduces a novel Deep Learning Diagnosis System that integrates pre-trained Deep Conal Neural Networks (DCNNs) within an ensemble learning framework.
  arXiv  Detail & Related papers  (2025-01-14T16:28:02Z)
• SALT: Introducing a Framework for Hierarchical Segmentations in Medical Imaging using Softmax for Arbitrary Label Trees [1.004700727815227]
  This study introduces a novel segmentation technique for CT imaging, which leverages conditional probabilities to map the hierarchical structure of anatomical landmarks. The model was developed using the SAROS dataset from The Cancer Imaging Archive (TCIA), comprising 900 body region segmentations from 883 patients. Performance was assessed using the Dice score across various datasets, including SAROS, CT-ORG, FLARE22, LCTSC, LUNA16, and WORD.
  arXiv  Detail & Related papers  (2024-07-11T21:33:08Z)
• Neural Network-Based Histologic Remission Prediction In Ulcerative Colitis [38.150634108667774]
  Histologic remission is a new therapeutic target in ulcerative colitis (UC) Endocytoscopy (EC) is a novel ultra-high magnification endoscopic technique. We propose a neural network model that can assess histological disease activity in EC images.
  arXiv  Detail & Related papers  (2023-08-28T15:54:14Z)
• Comparative analysis of deep learning approaches for AgNOR-stained cytology samples interpretation [52.77024349608834]
  This paper provides a way to analyze argyrophilic nucleolar organizer regions (AgNOR) stained slide using deep learning approaches. Our results show that the semantic segmentation using U-Net with ResNet-18 or ResNet-34 as the backbone have similar results. The best model shows an IoU for nucleus, cluster, and satellites of 0.83, 0.92, and 0.99 respectively.
  arXiv  Detail & Related papers  (2022-10-19T15:15:32Z)
• A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [90.29017019187282]
  " 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset. Analyse of the submitted algorithms using technical and biological metrics was performed. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
  arXiv  Detail & Related papers  (2020-04-26T08:49:17Z)

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.